aerospace

Article
Advanced UAV Design Optimization Through Deep
Learning-Based Surrogate Models
Hasan Karali * , Gokhan Inalhan * and Antonios Tsourdos

School of Aerospace, Transport and Manufacturing, Cranfield University, Cranfield MK43 0AL, UK;
[email protected]
* Correspondence: [email protected] (H.K.); [email protected] (G.I.)

Abstract: The conceptual design of unmanned aerial vehicles (UAVs) presents significant multidisci-
plinary challenges requiring the optimization of aerodynamic and structural performance, stealth, and
propulsion efficiency. This work addresses these challenges by integrating deep neural networks with
a multiobjective genetic algorithm to optimize UAV configurations. The proposed framework enables
a comprehensive evaluation of design alternatives by estimating key performance metrics required
for different operational requirements. The design process resulted in a significant improvement in
computational time over traditional methods by more than three orders of magnitude. The findings
illustrate the framework’s capability to optimize UAV designs for a variety of mission scenarios,
including specialized tasks such as intelligence, surveillance, and reconnaissance (ISR), combat air
patrol (CAP), and Suppression of Enemy Air Defenses (SEAD). This flexibility and adaptability was
demonstrated through a case study, showcasing the method’s effectiveness in tailoring UAV configu-
rations to meet specific operational requirements while balancing trade-offs between aerodynamic
efficiency, stealth, and structural weight. Additionally, these results underscore the transformative
impact of integrating AI into the early stages of the design process, facilitating rapid prototyping
and innovation in aerospace engineering. Consequently, the current work demonstrates the potential
of AI-driven optimization to revolutionize UAV design by providing a robust and effective tool for
solving complex engineering problems.

Keywords: UAV design; configuration design; machine learning; deep neural networks; data driven;
multidisciplinary design; multiobjective optimization; future engineering
Citation: Karali, H.; Inalhan, G.;
Tsourdos, A. Advanced UAV Design
Optimization Through Deep
Learning-Based Surrogate Models.
Aerospace 2024, 11, 669. https://
1. Introduction
doi.org/10.3390/aerospace11080669 The aircraft design process is a procedure that has evolved over almost a century,
covering gradual phases that are both time- and cost-intensive and result in the production
Academic Editor: Jules Simo
of highly complex products. While witnessing advancements in various facets of the
Received: 2 July 2024 design process, the standardization of the process into a specific framework has been
Revised: 7 August 2024 largely shaped by the developments in computational engineering in recent decades. When
Accepted: 12 August 2024 considering unconventional concepts and operational requirements, especially in the realm
Published: 14 August 2024 of unmanned aerial vehicles, it becomes apparent that the traditional design process
may lack the necessary flexibility and hinder the exploration of the design space. In this
context, machine learning techniques, which have gained popularity in the last decade
due to increased accessibility to high computational power, have the potential to enhance
Copyright: © 2024 by the authors.
creativity in design methodology.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
1.1. Overview of Aircraft Design
distributed under the terms and
conditions of the Creative Commons
A review of the historical evolution of aircraft design processes reveals that the first
Attribution (CC BY) license (https://
vehicles were developed through experimental and trial-and-error approaches. During the
creativecommons.org/licenses/by/ World Wars era, the notable advances in aerospace engineering led to a clear differentiation
4.0/). of subdisciplines within the design process. In parallel with the Jet Age, the evolution

Aerospace 2024, 11, 669. https://doi.org/10.3390/aerospace11080669 https://www.mdpi.com/journal/aerospace

Aerospace 2024, 11, 669 2 of 31

of computers has brought about a revolutionary change in the aircraft design procedure,
notably through the implementation of computer-aided design (CAD) and computational
analysis methods. These technologies have enabled engineers to develop intricate and
precise digital models, conduct sophisticated simulations, and perform analyses with
enhanced accuracy and efficiency. In this way, the dependence on the wind tunnel was
reduced, opening the way for easier and faster iterative design [1]. At the same time,
developments in these tools and differences in fidelity in analysis methodologies have led
to a more systematic approach to the design process. The design process was structured
into three fundamental phases, spanning from initial requirements to the prototyping and
manufacturing stage: conceptual design, preliminary design, and detailed design.
The first and crucial stage of the design process is the conceptual design phase, where
the aircraft is defined at the system level. During this phase, multiple concepts are analyzed,
and the selected design is the one that most effectively meets the mission requirements.
The complications involved in the aircraft design process require a systematic approach
that involves decomposition using a hierarchical structure of various levels. As the design
process progresses from one phase to the next, there is a significant increase in the fidelity
of the product, the complexity of the model, and the time required for completion. The
conceptual design stage is highly critical, with many decisions made under significant
uncertainty, and actual costs are revealed much later in the process [2]. However, the level of
human interaction in this process is quite intensive. As seen in Figure 1, changes are easier
to implement in the early stages of design, while the commitment to the configuration is at
its lowest. As the process progresses, these two phenomena change in opposite proportions.
However, the most critical point here is that the change in design can result in very high
costs in the later stages. Therefore, it is important to determine the correct configuration
by minimizing human interaction in the early stages. In the classical approach, fast but
low-level approaches, such as historical data, semi-empirical methods, and figure of merit
(FoM), are preferred to aid configuration selection [3–5]. The potential for innovation is
highest in the early design process, making it imperative to increase fidelity during the
initial design stages to minimize uncertainty [6]. This poses a problem in the design of
complex, innovative, and unconventional vehicles.

Level

Commitment to
configuration
Ease of
change

Product
knowledge
Cost of
change

Conceptual Preliminary Detail Design Development Design

Design Design Phase Phase

Figure 1. Change in design phenomena in the design phases.

By its very nature, aircraft design is an iterative process. When aircraft design pro-
cedures are examined, various flowcharts on this subject can be found [7]. However, the
primary issue here is that this process is highly human-centric in nature at present. This
issue particularly comes to the fore in the initial layout/concept sketch phase. Upon analy-
sis of the design processes during the conceptual and early preliminary design stages, it
becomes apparent that the conceptual phase drives configuration design, while the prelim-
inary design phase focuses on component design and sizing. Methods such as topology
optimization that will provide these two simultaneously are quite difficult for aircraft
geometries, as the limited design points are insufficient to represent the entire geometry [8].
Therefore, a new approach is needed that incorporates primarily the sizing of components
and the selection of configurations.
Aerospace 2024, 11, 669 3 of 31

1.2. Design from the Perspective of Unmanned Aerial Vehicles

The design procedure, particularly in the case of unmanned aerial vehicles, involves
certain differences. Specifically, when concepts of unmanned aerial vehicles are addressed,
all considerations and constraints related to pilots and crew are removed. In today’s
context, the autonomous control systems, material technologies, and new production
techniques used in these vehicles drive the design process to move in a different direction. If
operational requirements are taken into account, the situation becomes even more complex.
This complexity arises from the need to maximize operational efficiency, minimize risks,
and meet diverse mission requirements while adapting to advances in technology and
market demands. In this sense, systems that utilize common components and enable rapid
and cost-effective production are at the forefront.
Especially when considering an autonomous system, it is no longer possible to ap-
proach these vehicles as conventional aerial vehicles as they are increasingly viewed as
high-tech systems/robots. The concept that technological tools can be shaped according
to humanity’s interests and thus possess disposable features has been explored in various
science-fiction works [9]. The aforementioned systems, which can be compared to the
swarms of robotic machines depicted as off-world technology in twentieth-century works,
have quickly become an inevitable reality in today’s complex tactical environment [10].
Such systems, which are mass-produced in large numbers, are considered attritable because
of their low life-cycle cost (LCC) expectancy. This compels the design process to move
towards cost-effectiveness as much as possible. Figure 2 illustrates various prototypes and
concepts of “attritable/reusable” and “loyal/robotic wingman” UAVs developed within
the manned–unmanned teaming (MUM-T) framework. These vehicles stand out from
existing tactical UAV systems due to their high subsonic cruise speeds, high maneuver-
ability, and limited stealth capabilities. Additionally, unlike blended wing body concept
stealth UAVs, which have much higher maximum takeoff weights (MTOWs) and costs,
these prototypes offer limited payload capacities but affordable life-cycle costs. A key chal-
lenge lies in developing design approaches that incorporate nonconventional perspectives,
particularly in the next-generation design of “plug and play” configurations across a fleet
of unmanned combat aerial vehicles (UCAVs) [11–13]. These vehicles are expected to fulfill
a variety of different mission requirements while minimizing entire life-cycle costs [14–19].
For instance, an ISR (intelligence, surveillance, and reconnaissance) mission requires high
endurance and various payloads for observation, while an EW (electronic warfare) mission
demands high range and cruising speed. A SEAD (Suppression of Enemy Air Defenses)
mission additionally requires high maneuverability and a low radar cross section (RCS).
All of these operations can be performed by changing the modular lifting surfaces (wing,
tail, or canard) and/or fuselage components of a single configuration. Selecting the most
appropriate components for each mission scenario requires navigating through numerous
optimal points within a huge design space.

(a) EADS Barracuda (2006). (b) Kratos XQ-58 (2019). (c) Boeing MQ-28 (2021). (d) Baykar Kızılelma (2022).

(e) GA XQ-67A (2024). (f) Qinetiq Jackdaw. (g) BAE Systems UAS. (h) Anduril Fury.

Figure 2. Next-generation high-performance UAV prototypes (with their first flight) and concepts in
development [20–27].
Aerospace 2024, 11, 669 4 of 31

As in the case mentioned, the design process often requires the integration of multi-
ple engineering disciplines. The multidisciplinary design optimization (MDO) approach
consolidates all disciplines into a unified framework. MDO refers to the design of com-
plex engineering systems comprising interactive subsystems influenced by interdependent
physical phenomena [28]. In aircraft design studies, typical disciplines within MDO include
aerodynamics, structures, weight and balance, and propulsion. As indicated in [29], aircraft
design optimization has historically utilized semi-empirical equations to rapidly analyze
conventional fixed-wing aircraft. However, applying these low-fidelity models to UAVs
can pose challenges due to their reliance on traditional fixed-wing regression data. In
general, the data in semi-empirical approaches are not very accurate, especially in terms of
aerodynamic performance, as stated in [30], since they do not cover the dimensions and
flight conditions of UAVs. Therefore, more complex approaches, such as numerical meth-
ods, should enter the design process earlier. However, performing optimization through
high-fidelity tools, which require many evaluations of the mathematical model to compute
the performance of the system at each iteration loop, can be computationally expensive
and time-consuming [31]. At this point, machine learning-based solutions come to the fore
in the literature as an alternative approach to this problem.

1.3. Design Solutions Using Machine Learning

Machine learning is a computational approach that enables systems to learn and
improve from experience without explicitly programming them, with a primary focus
on exploiting data to improve performance and make informed decisions. The field of
aerospace engineering, which is packed with data and already constructed on a limited
multiobjective optimization framework that is perfectly suited for contemporary machine
learning approaches, is perhaps the best example of the potential for data-driven advance-
ment [32]. In particular, in terms of design optimization and upgrade analysis, performance
validation and optimization, and product improvement and calibration, machine learning-
based digital twins offer significant advantages [33].
In the literature, various studies have been conducted that utilize machine learning to
address the design problems of aerial vehicles. In [34], the research explores the selection
of configurations using a database of existing UAVs through the application of decision
tree classifiers. Sharma and Hosder [35] investigated the feasibility of using neural network
models to predict the maximum take-off weight, fuselage length, thrust, and aspect ratio of
airliner configurations. In terms of the design point, Oroumieh et al. [36] introduced an
approach using fuzzy logic and neural networks to determine the wing area and engine
thrust and validated this approach through an application to a specific class of light business
jets. In the study conducted by Boutemedjet et al. [37] for the design of small UAVs, the
design parameters were statistically derived from historical trends of existing UAVs, and
the wing planform was optimized using a neural network-based aerodynamic model.
In [38], a meta-model of the multidisciplinary design and analysis module with neural
networks was developed and used to obtain the handling qualities of a small UAV.
In addition, machine learning algorithms have become widely used in aerodynamic
design and design optimization as surrogate models. Bekemeyer et al. [39] developed a
surrogate modeling toolbox utilizing data-driven techniques such as deep learning, data
fusion, and reduced-order modeling to meet the comprehensive requirements of aerody-
namic data for design and certification processes. In [40], Sharma and Hosder examine
the feasibility of using machine learning models, specifically artificial neural networks, to
predict aircraft configuration design variables from mission-informed performance data
for blended wing body aircraft, showing that such models significantly improve prediction
accuracy and computational efficiency. Wu et al. [41], addressing the missile design opti-
mization problem, developed an algorithm that utilizes a convolutional neural network
(CNN) for feature extraction from design drawings and a multitask learning-based neural
network model to predict aerodynamic parameters such as axial force, normal force, pitch-
ing moment, and pressure center, thereby accelerating the design process. Yan et al. [42]
Aerospace 2024, 11, 669 5 of 31

developed an algorithm for aerodynamic shape optimization of missile control surfaces, em-
ploying reinforcement learning for extracting optimization experience from DATCOM and
transfer learning for CFD-based optimization, significantly reducing computational costs
and accelerating the design process by over 62.5%. Furthermore, Li et al. [43] provided
a comprehensive review of machine learning applications in aerodynamic shape opti-
mization and summarized some of the successful algorithms and applications in compact
geometric design space, fast aerodynamic analysis, and efficient optimization architecture.
In [44–51], artificial neural networks and convolutional neural network algorithms were
used to predict the aerodynamic performance of various components of the aircraft, such
as the airfoil, the nacelle of the engine, and the wing. Furthermore, comparisons between
models based on artificial intelligence and classical methods have demonstrated signifi-
cant advantages for AI as data sets expand [52]. Traditional methods reliant on statistical
approaches tend to become redundant, overshadowed by the substantial reductions in
computation time offered by AI techniques, which often show order-of-magnitude im-
provements. Furthermore, the authors have discovered that machine learning techniques,
in particular neural networks, have great potential in these areas. In [30], we developed
deep learning-based surrogate models to capture the nonlinear aerodynamic performance
of conventional small UAV configurations. In [53], we developed a neural network-based
deep transfer learning model with a multifidelity approach to predict the aerodynamic
performance of next-generation low-cost modular UCAVs. These AI models leverage
advanced machine learning algorithms to process and analyze large volumes of data more
efficiently than classical methods. Consequently, AI-driven optimizations in fields like
aerospace and engineering are not only faster but also promise to deliver more innovative
and effective solutions. The scalability of AI methods enables them to handle complex, mul-
tivariable problems with greater precision, retaining the potential to significantly accelerate
the development cycles of new technologies.
The remainder of this paper is organized as follows. Section 2 outlines the conceptual
framework and highlights the novelty of the developed algorithm, which integrates mission
requirements with geometry design through multidisciplinary approaches and AI-driven
models. Section 3 details the methodology, starting with the initial sizing algorithm that
employs fundamental flight performance equations to establish baseline dimensions and
metrics for the UAV. Following, the aircraft model is explained in detail under the topics of
aerodynamics, radar cross section, structures, propulsion, and weights. In the rest of the
section, mathematical and physical information about artificial neural network modeling
and multiobjective genetic algorithms is given. Section 4 discussed the application of
the model in an example case, demonstrating its practical utility. In Section 5, the results
derived from the application scenario are presented, leading to Section 6, where conclusions
are drawn from the findings and potential avenues for future research are suggested.

2. Conceptual Framework
In light of all this information, there has been an observed need to automate the current
design process to incorporate more information at the early stages of design. The idea of
developing a trustworthy intelligent algorithm that will link geometry design with mission
requirements has emerged. In [54], we introduced a basic AI-driven framework that utilizes
machine learning to enhance the configuration selection process in aircraft design. This
algorithm, which initially considers only aerodynamics and structural performance param-
eters as part of the vehicle model, features an AI-supported optimization methodology.
It identifies the best configuration from predefined concepts (conventional, lambda, and
delta) based on specific mission criteria and establishes the initial layout. In [55], we ex-
plored a multidisciplinary conceptual design framework for UAVs that employs AI-driven
surrogate models. This approach significantly improves the initial design stage, enabling
the initial sizing of critical components and selection of the optimal configuration based on
aerodynamics, structural mass, and radar cross-section predictions. These frameworks aim
Aerospace 2024, 11, 669 6 of 31

to streamline the design process, reduce costs, and enhance time efficiency by integrating
multiple engineering disciplines and leveraging machine learning technologies.
In this work, a comprehensive structure is proposed based on previous experiences.
The main goal is to establish an intelligent design algorithm that will match the given task
with the optimum point in the design space. For this purpose, multipurpose, hierarchi-
cal, mixed-variable design spaces are efficiently explored with multidisciplinary design
optimization located at the core, as given in Figure 3. Mission-level planning at the top of
this structure defines operational standards and reduces mission-specific requirements to
mission performance parameters. These parameters are used as objective functions and
equality/inequality constraints in the optimization definition. At the base of the structure
are surrogate models/digital twins to reduce the need for high-quality simulations across
various disciplines. This layer, containing aerodynamics, structural, radar cross-section,
weights, and propulsion models that may be required for an early-stage aircraft, allows
instant estimation of performance parameters related to the vehicle at each point in the
design space in the optimization cycle. To achieve this, in this work, a state-of-the-art
physics-informed feature engineering approach is also developed. This study offers several
key contributions to the field of UAV design optimization, which can be summarized
as follows:
• Combines DNNs with multiobjective genetic algorithms for rapid UAV design opti-
mization, speeding up the process by over three orders of magnitude.
• Develops a multidisciplinary framework integrating aerodynamics, structural analysis,
radar cross section, and propulsion for comprehensive UAV evaluation.
• Utilizes physics-informed feature engineering for accurate surrogate models, predict-
ing key UAV metrics with high precision.
• Optimizes UAV designs for specific missions by addressing distinct operational needs.

Mission performance
Operational standards and mission parameters
specific requirements Mission
Level
Planning

Optimization requirements:
cruise speed, range, endurance,
Explore of multiobjective, Multidisciplinary RCS, payload weight
hierarchical, mixed variable Design Optimization
design spaces efficiently of Aerial Vehicle
Multidisciplinary solvers:
CL, CD, Weight, RCS, Thrust

To reduce the need

for high-fidelity Aerodynamics
simulations in Surrogate Models / Digital Twins Structural Weights Surrogate aerodynamics,
various disciplines structural, weights, RCS,
propulsion models

RCS Propulsion

Figure 3. Proposed approach to develop trustworthy autonomous systems.

3. Methodology
This section presents a robust framework that employs a combination of mathematical
modeling and computational simulations to optimize the design of unmanned aerial
vehicles. The methodology starts with the design/mission requirements inputs, as shown
in the flowchart in Figure 4, and is completed with the design of the optimum aerial vehicle
configuration in accordance with these requirements.
The requirements given in the first stage are turned into design parameters with
the initial sizing algorithm based on flight performance and design point calculations.
Afterward, the most suitable design point is searched via multiobjective optimization
within this determined design space. In this part, the design space is effectively searched
by using AI-based vehicle models. These models are obtained by combining various
disciplines with a framework that includes analysis, data generation, and training. The
Aerospace 2024, 11, 669 7 of 31

following sections detail the specific algorithms and computational models used and
summarize their contribution to the design process.

Figure 4. General framework for UAV design process.

3.1. Initial Sizing Algorithm

The initial sizing algorithm transforms the design requirements into design parameters.
These requirements are provided as a list or mission profile. In a typical mission profile,
as illustrated in Figure 5, there may be various targeted performance parameters and
configurations for each flight phase. Therefore, it is crucial to identify a feasible design
point area that simultaneously satisfies all these requirements.

Figure 5. Typical mission profile of a UAV.

In the calculation of design points, performance requirements such as stall speed (Vs ),
maximum speed (Vmax ), maximum rate of climb (ROCmax ), take-off run (STO ), and ceiling
(hc ) are employed to determine a feasible design space in terms of wing loading (W/S)
Aerospace 2024, 11, 669 8 of 31

and thrust loading (T/W). Each of these parameters plays a crucial role in defining the
design space and ensuring the UAV meets its intended operational capabilities:
• Stall speed (Vs ): minimum speed for maintaining level flight.
• Maximum speed (Vmax ): highest achievable speed in level flight.
• Rate of climb (ROCmax ): defines how quickly an aircraft gains height.
• Take-off run distance (STO ): distance required for take-off.
• Ceiling altitude (hc ): maximum altitude for sustained level flight.
In order to identify the optimal selection, the flight performance equations are solved
based on wing loading and thrust loading, and inequality constraints are generated accord-
ingly. This method is entirely based on aircraft performance requirements and employs
flight mechanics theory. Consequently, the procedure is analytical and yields highly reli-
able results.
The wing loading based on the stall speed requirements is shown as
 
W 1
= ρVs2 CLmax (1)
S Vs 2
where ρ denotes the air density and CLmax is the maximum lift coefficient. The following
relation is used for the maximum speed requirement:
   
TSL 2 1 2K W
= ρo Vmax CDo   + 2
(2)
W Vmax 2 SW ρσVmax S

where ρo is the sea-level air density, CDo is the zero-lift drag coefficient, and K is referred to
as the induced drag factor.
CDG
 h  i
1
 
T µ − µ + C LR exp 0.6ρgC DG
S TO W/S
=   (3)
W STO 1 − exp 0.6ρgCDG STO W/S 1

where µ is the friction coefficient of the runway surface and is generally taken as 0.05 for
concrete/asphalt surfaces. CLR represents the aircraft lift coefficient in take-off rotation.
It can be obtained by solving the lift equation inversely using take-off rotation speed
(1.1 − 1.2Vs ). CDG indicates the drag coefficient, accounting for ground effects during
takeoff. The wing and engine sizing based on rate of climb requirements can be defined
as follows:
 
T ROC 1
= s  + (4)
W ROC r2 W ( L/D )max
CD S
ρ 0
K

The ceiling is defined as the highest altitude at which an aircraft maintains its level
flight. The ceiling is not a critical requirement for many aircraft, but it is critical for some
missions, such as ISR (intelligence, surveillance, and reconnaissance). Similarly, as a
function of wing and thrust loading, the performance equation can be stated as follows:
 
T ROCC 1
= s   + σ ( L/D ) (5)
W hC 2 W C max
σC q
C S
Do
ρC K

where σC is the relative air density and ρc is the air density, both at the ceiling altitude. The
relevant equations can be found in aircraft design or flight performance textbooks [5,56]. In the
initial design iteration, table-based aerodynamic and geometric data are used for unknown
parameters. However, during subsequent design iterations, this information is directly
derived from the aerodynamic performance and geometry of the previous configuration.
Aerospace 2024, 11, 669 9 of 31

In the initial sizing phase, the fundamental dimensions of the aircraft are established
based on the design point output and specific requirements. The wing area is derived by
dividing the maximum take-off weight by the wing loading. Likewise, engine thrust is
determined by multiplying the maximum take-off weight by the thrust loading. Through
this process, the necessary wing area and engine thrust are calculated as follows:
   
W T
S = Wmtow / , T = Wmtow · (6)
S W
The selection of an engine is typically made from among existing engines, as develop-
ing a UAV-specific engine is not usually the first choice due to the constraints of cost and
time. In addition to numerical evaluations, the selection of an engine is also influenced by
factors such as the manufacturing country, production maintenance competence, usage
permit, etc. Furthermore, the selection of an engine may also take into account factors such
as specific fuel consumption and cost. Consequently, the current algorithm enables the user
to select an engine that meets the required thrust level. Table 1 lists some of the available
turbofan engines that are suitable for high subsonic UAVs.

Table 1. Sample engine table for high subsonic UAV case [57–66].

Length Diameter Dry Weight Maximum Thrust

Engine
(mm) (mm) (kg) (kN)
Pratt Whitney Canada PW610F 1153 704 115.7 4.22
Pratt Whitney Canada PW615F 1258 750 140 6.49
Williams FJ33 976 466 140 8.21
Pratt Whitney Canada PW617 1360 750 172 8.41
GE Honda HF120 1510 660 211.3 9.10
Pratt Whitney Canada JT15D 1531 685.8 285.7 13.57
Honeywell TFE731-2 1844 1041 184 15.57
Williams FJ44-4 1340 640 298 16.00
Ivchenko AI-25TL 1494 611.6 350 16.90
Pratt Whitney Canada 545B 1742 693.4 376.5 17.58

As illustrated in Figure 6, the fuselage is divided into three sections to determine

the basic dimensions. In the case of the fore body, the sensor and avionics systems act as
constraints. The dimensions of the mid-body are calculated based on the internal payload
requirements. The length and diameter resulting from the selection of the engine are
employed for the sizing of the aft body. All of these data are then utilized to determine a
representative body length and hydraulic diameter.

Fore-body Mid-body Aft-body

Figure 6. MQ-28 UAV representative fuselage sections: fore body, mid-body, and aft body.
Aerospace 2024, 11, 669 10 of 31

3.2. Aircraft Model

This section provides a comprehensive review of the aircraft model and includes
details on integrated disciplines. All these disciplines are created with mathematical and
physical algorithms that allow for analysis of the aircraft from various aspects. First, the
aerodynamic model analyzes airflow interactions and their impact on aircraft performance
and calculates aerodynamic forces using computational aerodynamics methods. Following
this, the radar cross section is assessed, focusing on the UAV’s detectability by radar
through simulations that consider the shape of the aircraft. The structure model addresses
the structural integrity and weight optimization of the UAV, utilizing finite element analysis
(FEA) to ensure durability under aerodynamic loads. The propulsion model performs
calculations related to the engine performance. Lastly, the weights model methodically
calculates the distribution of weights, taking into account all the contributions of the
previous subsystems.

3.2.1. Aerodynamics
An understanding of the aerodynamics of UAVs is of paramount importance to achieve
optimal performance, efficiency, and mission success. It is crucial to determine the basic
aerodynamic characteristics in the conceptual and preliminary design stages to ensure the
successful development of UAVs. The initial stages of the development process involve
pivotal decisions that have a significant impact on the entire process. By conducting an
early assessment of aerodynamic characteristics, designers can make informed decisions
about wing configurations, airfoil selections, and the overall vehicle layout.
In light of the necessity to analyze diverse geometries under specific flow conditions
during the design stages, the deployment of rapid and precise aerodynamic solvers is of
vital importance. Computational aerodynamic tools are typically classified into two cate-
gories: low- and high-fidelity methods. Low-fidelity methods, which simplify assumptions
about flow equations, can calculate the forces and moments of basic components of aerial
vehicles in seconds on a simple personal computer [67]. Examples of these methods include
semi-empirical and potential theory-based approaches. In contrast, high-fidelity methods
refer to CFD techniques that solve the complete Navier–Stokes equations for complex and
detailed geometries. Table 2 compares different computational aerodynamic methods and
notes their accuracy values as reported by [1].
Among low-order methods, potential flow-based panel methods offer more complex
geometry modeling and solutions than semi-empirical methods and vortex lattice methods
(VLM). However, panel methods remain less comprehensive than CFD solutions. Because
panel methods use simplified forms derived from the Navier–Stokes equations, they ignore
viscous effects and heat transfer, which means that they cannot compute skin friction drag,
separation, or transonic shocks [68]. Despite this, panel methods have advantages over
VLM, as they can model blunt geometries and apply boundary conditions on the actual
surface rather than an average mean surface.

Table 2. Comparison of computational aerodynamic methods [69].

Approach Primary Use Accuracy (Average) Computation Time Examples

Semi-empirical DATCOM, ESDU,
Conceptual design ±15% Seconds on a PC
methods AAA, RDS, etc.
Seconds/minutes on VSPAero, PANAir,
Potential flow methods Preliminary design ±10%
a PC AVL, XFOIL, etc.
Hours/days/weeks on SU2, Fluent, USM3D,
CFD methods Detailed design ±5%
a WS/HPC OpenFOAM, etc.

Panel methods can be briefly described as numerical schemes used to solve the linear,
inviscid, irrotational flow equation at subsonic or supersonic free-stream Mach numbers.
Aerospace 2024, 11, 669 11 of 31

The name of the equation that the panel codes solve is the Prandtl–Glauert equation. For
steady subsonic flow, this equation can usually be defined as
 
˜ 2 ϕ = 1 − M∞
∇ 2
ϕxx + ϕyy + ϕzz = 0 (7)

For subsonic flows, Equation (7) is elliptical. This type of equation allows any distur-
bance to be felt everywhere in the flow field, although the effect usually disappears with
distance. To model the effect of geometry on flow, the singularities are distributed over
the entire geometry and their strengths are calculated over the surface velocity boundary
conditions. The velocities induced by each ring vortex at a specified control point are
calculated using the Biot–Savart law. The contribution of each vortex loop and trailing
wake at a given i control point is calculated as follows:
Loops h i Wakes h i
⃗i =
V ∑ ⃗ loop
V
j
+ ∑ ⃗ wake
V
j
(8)
j j

Then the free-stream velocity component is added to the induced velocity and tangency
boundary condition, applied as
h i
⃗∞ + V
V ⃗ i · n̂i = 0 (9)

In the panel method model, shade wakes are represented as vortex filaments that
leave sharp trailing edges of wings and possibly bodies. The strength of these filaments is
determined by the Kutta condition, which allows the flow to leave the trailing edge properly.
Furthermore, in VSPAERO, the location of these vortex filaments is solved iteratively in the
overall flow field solution. Further details of the panel method algorithm can be found in
the literature [67]. At the end of the process, the whole problem is reduced to the solution
of a set of linear equations:

A⃗x = ⃗b (10)
where ⃗x represents the unknown circulation strengths. To reduce computational cost,
VSPAERO uses an iterative method, the generalized minimal residual method (GMRES),
for the numerical solution of this system of linear equations.

⃗Ri = ⃗b − A⃗xi (11)

−
→
where ⃗Ri → 0 as i → ∞. Using the preconditioned GMRES algorithm, a matrix-free
evaluation of the residual is obtained. In this application, the precondition matrix was
selected as an approximate LU decomposition of A. After calculating the strength of the
singularities, the aerodynamic forces and moments affecting the geometry are obtained.
Using Bernoulli’s equation, the pressure coefficient C p is computed as follows:
 2
V
Cp = 1 − (12)
V∞
where V is the local velocity in the panel and V∞ is the free-stream velocity. The aero-
dynamic forces are obtained by integrating the pressure distribution over the surface
as follows:
Z
F= pn dS (13)
S
where p is the pressure on the surface and n is the surface normal. The aerodynamic
moments are calculated as follows:
Z
M= (r × pn) dS (14)
S
Aerospace 2024, 11, 669 12 of 31

where r is the position vector. A variety of correction factors are employed to account for
the local compressibility effects that are particularly common in the high-speed subsonic
regime. The most popular of these is the Prandtl–Glauert rule, although a superior model,
the Kármán–Tsien rule, is employed in this work. In this model, the free-stream Mach
number is utilized to correct the pressure coefficient (C p ). It is defined as follows:

Cp
Cp = p h 0 p i (15)
2 + M2 / 1 +
1 − M∞ 1 − M 2 C p 0 /2
∞ ∞

where M∞ is the free-stream Mach number and C p 0 is the potential flow coefficient of
the pressure. The inviscid solution provided by the panel method necessitates a distinct
approach to calculate parasite drag values. Estimation of parasite drag is achieved through
the calculation of skin friction drag using laminar and turbulent flow correlations, form
drag based on component shape, and interference drag resulting from the interaction
between components as follows:
CD,parasite = CD,skin friction + CD,form + CD,interference (16)

Consequently, the calculation of the aerodynamic parameters that are pivotal for the
preliminary design phase is feasible through the utilization of this model.

3.2.2. Radar Cross Section

The radar cross section (RCS) is a measure of an object’s detectability by radar systems.
It represents the effective area of an object that presents itself as an incident radar signal,
reflecting the proportion of the signal that is scattered back to the radar receiver. The
radar cross section is influenced by several parameters, which can be broadly categorized
as follows: the target’s geometry, the materials it comprises, the frequency of the inci-
dent radar signal, the radar’s polarization, and the positions of antennas relative to the
target [70]. The definition of RCS is typically expressed in terms of electric fields, with
the range R approaching infinity to ensure that the definition is solely dependent on the
target’s characteristics.
!
r 2
2 |E |
σ = 4π lim R (17)
R→∞ | E t |2
2
where sigma is the RCS, R is the range, and |Er | and Et are the backscattered and incident
electric field squared magnitudes, respectively.
RCS is expressed in m2 in physical scale and decibels referenced to a square meter
(dBsm) in dB scale. The conversion between these two units is expressed as follows:
h i
σ [dBsm] = 10 log(σ ) m2 (18)

RCS values in military aircraft generally vary between −20 dBsm and 20 dBsm [71]. It
is speculated that the front sector X-band RCS of the well-known sophisticated RF stealth
fighter F-22 is less than −20 dBsm. On the other hand, in a study conducted on the UAV
class discussed in this article, the mean RCS value was observed to vary between −10 dBsm
and 10 dBsm [72].
Characterizing a radar target solely through a constant RCS value is challenging due
to the variable nature of RCS, influenced by factors such as radar look angles, frequency,
polarization, and target materials [73]. In the literature, a single RCS value, often denoted
as the mean RCS value (σ), is provided for the target vehicles [74]. This mean value is
typically calculated using a specific methodology. In the current model, the average value
is calculated as follows:
N
1
σ=
N ∑ σ ( θi ) (19)
i =1
Aerospace 2024, 11, 669 13 of 31

Numerical simulation methods for RCS problems are divided into two categories: full-
wave and asymptotic. Full-wave methods, such as the finite element and finite-difference
time-domain methods, provide accurate results but are computationally quite expensive.
Especially considering the wavelength values in the current work, it is impractical to use
full-wave methods. Asymptotic methods, such as physical optics (PO) and ray tracing, are
computationally efficient and successful in backscattering RCS simulations for electrically
large targets. PO is efficient and accurate for convex targets, while ray tracing solves
multiscattering problems, making it suitable for concave geometries [75]. The algorithm
implemented in this work uses the physical optics (PO) approximation combined with ray
tracing to generate the RCS of the aerial vehicle based on its three-dimensional surface
model [76].

3.2.3. Structures
Structural models are another critical component of the aircraft design process. Sta-
tistical or basic analysis-based methodologies allow the rapid and flexible evaluation of
different structural design alternatives at an early stage without the need for complex
calculations. These approaches are crucial at the beginning of the aircraft design process for
estimating structural weight and using this information to develop more efficient designs.
In this work, two distinct structural models are used, each specifically tailored to
the components of the aircraft. A simplified shell model is used for the structural model
of the fuselage. This model allows calculations based on the geometric dimensions of
the fuselage. For lifting surfaces, which constitute the main structural weight, a more
complex methodology, the finite element method (FEM) with spatial beam elements [77], is
used. This model particularly utilizes a combination of truss, beam, and torsion elements,
which are designed to carry axial, bending, and torsional loads. Each spatial beam element
possesses six degrees of freedom at each end, comprising three translational displacements
(in x, y, z directions) and three rotational degrees of freedom (around the x, y, z axes),
totaling twelve degrees of freedom per element. These beam elements are connected end-to-
end to represent the wing structural spar. The nodal displacements and rotations based on
the forces and moments acting on the structure are calculated, and using this information,
a global stiffness matrix is constructed. Basically, the algorithm solves the following set of
linear equations:

K⃗u = ⃗f (20)
where K is the global stiffness matrix, ⃗u is the vector of displacements and rotations at the
nodes, and ⃗f are the forces and moments acting at the nodes. The stiffness characteristics
of a beam element in finite element analysis are determined by its axial, bending, and
torsional properties. The axial stiffness, which resists deformation due to axial forces, is
represented by the matrix
 
AE 1 −1
k axial = (21)
L −1 1
where A denotes the cross-sectional area, E is the Young’s modulus, and L is the length of
the beam element. Bending stiffness, which resists deformation due to bending moments,
is a property that is influenced by both the y axis and the z axis. The bending stiffness
matrix for the y axis is given by

−12 6L
 
12 6L
EIy  6L 4L2 −6L 2L2 
k bending,y = 3  (22)
L −12 −6L 12 −6L
6L 2L2 −6L 4L2
and for the z axis by
Aerospace 2024, 11, 669 14 of 31

−6L −12 −6L

 
12
EIz  − 6L 4L2 6L 2L2 
k bending,z = 3  (23)
L  − 12 6L 12 6L 
−6L 2L2 6L 4L2
where Iy and Iz are the moments of inertia on the y axis and the z axis, respectively. The
torsional stiffness, which resists deformation due to torsional moments, is described by
the matrix
 
GJ 1 −1
k torsional = (24)
L −1 1
where G is the shear modulus and J is the polar moment of inertia.
The presented approach transfers the loads acquired from the aerodynamics module
(compressible three-dimensional panel method) to the structural model and performs
internal optimization to find the lightest structure while adhering to failure restrictions.
Thus, the structural weight of a vehicle with a predefined geometry can be calculated with
considerably greater reliability than with statistical methods.

3.2.4. Propulsion
The propulsion system module is designed for jet engines, as the proposed air vehicle
will conduct its operations in the high subsonic flight regime. This module incorporates an
approach where the fuel weight is calculated based on the propulsion system performance.
The total fuel weight required for a flight depends on the mission, aircraft aerodynamics,
and engine-specific fuel consumption (SFC). The SFC is a parameter for a turbofan or
turbojet engine that measures how efficiently it burns fuel and converts it to thrust. The
SFC for jet engines is defined as the mass of fuel required to deliver a particular thrust for a
given period:

ṁ f uel
SFC = (25)
T
Returning to the fuel weight calculation, the requirements related to the mission are
known at the beginning of the design process, and the aerodynamic performance data are
calculated through the aerodynamics module. The SFC value is obtained with the selected
engine in the initial size step. Using all this information, it is possible to calculate the fuel
required for the flight segments. In a typical mission where there is no payload release,
the fuel weight can be considered equal to the difference between the take-off and landing
weight of the vehicle.

Wfuel = Wtake−off − Wlanding (26)

Using this approach, the vehicle weight ratio throughout the flight segments is multi-
plied in a chain manner to find the final take-off and landing weight ratio.

Wfuel Wlanding
= 1− (27)
Wtake−off Wtake−o f f
In this calculation, the typical weight ratios in the take-off, climb, descent, and landing
phases vary between 0.97 and 0.99. The critical flight segment in terms of fuel weight is
the cruise or loiter phase. According to the flight mission profile, the weight ratio for a
range-oriented mission is calculated as follows:

V( L/D)max L
   
Wstart
Rmax = ln
SFC D max Wend
(28)
Wend − R · SFC
= e V( L/D)max
Wstart
Aerospace 2024, 11, 669 15 of 31

In the context of an endurance-oriented task requirement, the weight ratio is as follows:

 
( L/D )max Wstart
Emax = ln
SFC Wend
(29)
Wend − E · SFC
=e ( L/D ) max
Wstart
The sets of equations mentioned above enables the calculation of the fuel weight
required to execute missions with varying requirements.

3.2.5. Weight
The weight calculation is crucial in aircraft design, serving as a fundamental factor that
significantly influences various design aspects and performance parameters. The precise
determination of an aircraft’s weight directly impacts its structural integrity, aerodynamic
characteristics, fuel capacity, payload limits, and overall operational capabilities. Although
a target maximum take-off weight (MTOW) is established at the outset of the design
phase, the distribution of this weight among other components is equally critical. In the
present work, the weight module incorporates data from both the structural and propulsion
modules. This integration enables the realistic calculation of weight components, such as
the UAV’s payload capacity.
A UAV’s maximum take-off weight is made up of three major weight groups: empty
weight, payload weight, and fuel weight. The total weight of the UAV is the sum of the
following three components:

WMTOW = Wempty + Wpayload + Wfuel (30)

where Wpayload can be obtained by the requirements and Wfuel can be computed using the
propulsion module. The empty weight encompasses the weight of the UAV’s airframe,
propulsion system, avionics, and other miscellaneous equipment. In order to calculate
Wempty , its components must be examined:

Wempty = Wstructure + Wengine + Wsystems (31)

where Wengine obtained by propulsion module. Wsystems , which includes all avionics and
other fixed equipment, is calculated from the table-based approach. Wstructure is calculated
from the structural module in four components.

Wstructure = Wwing + Wtail + Wfuselage + Wgear (32)

The weight module is of critical importance, especially in terms of calculating the
weight components. In the following stages, using the output of this module makes it
possible to make optimizations regarding the operational requirements of the vehicle
through the maximum weight or payload/fuel weight.

3.3. Artificial Neural Network Modeling

The section on artificial neural network modeling examines the integration of data-
driven models into the optimization cycle, utilizing information from various disciplines.
This approach focuses on developing reduced-order models (ROMs) to enhance the ef-
ficiency of the design process by replacing complex systems. By leveraging data from
aerodynamics, radar cross-section, structure, and weight models, a comprehensive design
space is generated. Neural networks are employed as surrogate models to generate reli-
able performance predictions, which are crucial to optimizing UAV configurations. The
methodology is based on a systematic approach, which is explained in more detail below.

3.3.1. Data Generation and Sampling

The methodology employed in this work for data generation and sampling integrates
various disciplines within a comprehensive aircraft design and analysis framework. This
Aerospace 2024, 11, 669 16 of 31

framework enabled the automatic generation of a design space that encompasses hundreds
of configurations and their respective performance parameters. In order to ensure a
comprehensive and representative sampling of the design space, the Latin hypercube
sampling (LHS) method was incorporated into the algorithm. LHS is a statistical method
employed to generate a quasi-random sample of plausible collections of parameter values
from a multidimensional distribution [78]. This ensures that each parameter is uniformly
sampled throughout its range. In Figure 7, it is possible to examine the visualization of the
LHS distribution of the four parameters (wing area, aspect ratio, taper ratio, and sweep
angle) required to define a wing component. This technique is particularly effective in
reducing the number of samples required for accurate statistical representation compared
to simple random sampling.

Figure 7. Visualization of Latin hypercube sampling for wing component.

A Python script was developed to implement the algorithm, integrating the NASA
open-source parametric model (OpenVSP) API, which allows parametric modeling of the
configurations [79,80]. This approach facilitated the parametric setting of vehicle compo-
nents, enabling detailed and flexible modeling. Furthermore, analysis tools from various
disciplines were integrated into the framework, enabling a comprehensive evaluation of
different configurations. The developed Python modules integrated the performance pa-
rameters obtained from aerodynamic, structural, RCS, and weight models into a single data
set. The systematic approach to data generation and sampling was a critical element in de-
veloping a reliable artificial neural network model capable of making accurate predictions
across a broad spectrum of conditions.
The design space generation algorithm detailed in Algorithm 1 begins by taking the
number of configurations (nconfig ) and the parameter limits (Xlimits ) as input to produce
the final design space dataframe (DF). First, the VSP API is initialized, and physical and
environmental parameters are defined. The Latin hypercube sampling (LHS) methodology
is then employed to generate a quasi-random sampling distribution (S) within the given
parameter limits, resulting in a set of configuration vectors (Vconfig ). For each configuration
vector (−
→
vi ) in the set, the wing, tail, and fuselage geometries are defined using specific geo-
metric parameters. These geometries are then set in the VSP model, which is subsequently
updated.
Aerospace 2024, 11, 669 17 of 31

Algorithm 1 Design space generation algorithm.

Input: nconfig , Xlimits
Output: DF
1: procedure D ESIGN S PACE (nconfig , Xlimits )
2: Initialize VSP API
3: Define physical and environmental parameters
4: S ← initialize LHS with Xlimits
5: Vconfig ← S(nconfig )
6: for i ← 1 to nconfig do
7:
−
→
vi ← − →vi ∈ Vconfig
8: Define wing geometry using ⃗vi = { ARwing , λwing , Λwing , Γwing , Awing }
9: Define tail geometry using ⃗vi = { ARtail , λtail , Λtail , Γtail , Atail }
10: Define fuselage geometry using ⃗vi = {l f ore , lmid , la f t , dh }
11: Set geometry using wing, tail, fuselage
12: Update VSP model
13: M aero ← mesh − →
vi
14: c L , c D , c M , Q aero ← A ERODYNAMICS P ERFORMANCE (M aero )
15: Mstructural ← mesh − →
vi
16: Wstructure ← S TRUCTURAL P ERFORMANCE (Mstructural , Q aero )
17: M RCS ← mesh − →
vi
18: σdBsm ← R ADAR C ROSS S ECTION P ERFORMANCE (M RCS )
19: Wempty ← W EIGHTS (⃗vi , Wstructure , c L , c D )
−→ −→
20: DFi ← DFi = {⃗vi , c L , c D , c M , σdBsm , Wstructure , Wempty }
21: end for
−→
22: DF i,j ← DFi concat for i = {1, 2, 3, ..., nconfig }
23: return DF }
24: end procedure

25: procedure A ERODYNAMICS P ERFORMANCE(M aero )

26: Re, M, ν, µ, α ← Set flow conditions
27: Run aerodynamics analysis
28: return {c L , c D , c M }
29: end procedure

30: procedure S TRUCTURAL P ERFORMANCE(Mstructural , Q aero )

31: if component = wing or tail then
32: E, G, σS ← Set analysis parameters
33: Run structural analysis
34: Optimize Wstructure
35: else
36: Calculate Wstructure
37: end if
38: Wstructure ← Wstructure = Wwing + Wtail + W f us
39: return Wstructure
40: end procedure
41: procedure R ADAR C ROSS S ECTION P ERFORMANCE(M RCS )
42: θ, ϕ ← Set analysis parameters
43: Run RCS analysis
44: return σdBsm
45: end procedure

46: procedure W EIGHTS(⃗vi , Wstructure , c L , c D )

47: Run weights analysis
48: return Wempty
49: end procedure
Aerospace 2024, 11, 669 18 of 31

The algorithm proceeds by performing aerodynamic, structural, radar cross-section

(RCS), and weight analyses on each configuration. Aerodynamic performance (coefficients
c L , c D , c M , and aerodynamic loads Q aero ) is evaluated by meshing the geometry (M aero )
and performing the three-dimensional compressible panel method analysis. Structural
performance (Wstructure ) is determined by meshing the geometry (Mstructural ), performing
the one-dimensional finite element method analysis, and optimizing the structural weight
based on aerodynamic loads. The RCS analysis is conducted by meshing the geometry
(M RCS ) and running the physical optics (PO) approximation combined with ray tracing.
The empty weight (Wempty ) of the configuration is then calculated using the geometric
parameters, structural weight, and aerodynamic coefficients.
−→
The results of each analysis ( DFi ), comprising geometric parameters, aerodynamic
coefficients, RCS, structural weight, and empty weight, are concatenated to form the
design space dataframe (DF). The subprocedures “Aerodynamic Performance”, “Structural
Performance”, “Radar Cross Section Performance” and “Weights” include specific analysis
and provide a modular and systematic approach to evaluate the performance of each
configuration within the design space by running relevant tools.

3.3.2. Physics-Informed Feature Engineering

Feature engineering represents a pivotal aspect in enhancing the efficacy of neu-
ral network models used for UAV analysis. The process begins with data analysis and
the selection of the most relevant features that serve as input to neural networks. Pear-
son’s correlation analysis is performed to understand the relationships between different
characteristics, ensuring that only those with significant impact are retained [81,82]. The
correlation coefficient for each future is calculated as follows:

∑( xi − x̄ )(yi − ȳ)
r= p (33)
∑( xi − x̄ )2 ∑(yi − ȳ)2
where r is the correlation coefficient, xi and yi represent the values of the variables in a
sample, and x̄ and ȳ are the mean values of the variables. Calculated correlations are of great
significance in the context of feature selection in data-driven modeling. The identification
of variables exhibiting a strong correlation (either positive or negative) facilitates the
selection of the most crucial parameters influencing the model’s output, thereby enabling
the generation of a more efficient and accurate prediction model.
Figure 8 presents a scatter plot matrix that illustrates the relationships between the
target parameters and example future sets of a wing. Each row represents a different
target variable: lift coefficient (CL ), drag coefficient (CD ), radar cross section, and empty
weight. Each column represents parameters of geometry and flow conditions. The plots
demonstrate that CL and CD increase with the angle of attack, in accordance with typical
aerodynamic behavior. However, they also exhibit some variation with other parameters,
although the trends are less obvious. The RCS exhibits a scattered distribution across all
parameters, indicating a complex relationship influenced by multiple factors. The weight
appears to vary significantly with geometric parameters such as aspect ratio, reference
span, and chord length.
Upon training the model using feature sets related to flow and geometry as previ-
ously described, it was observed that the model exhibited limited generalization ability,
particularly in aerodynamic performance parameters. This issue was addressed by adding
physical information to the algorithm. Incorporating physical information into neural
networks can significantly enhance prediction accuracy and reliability, particularly in com-
plex engineering applications such as UAV design. One approach for the artificial neural
network to obtain physical information is to include physical constraints directly in the
cost function. Formulating the cost function to include terms that penalize deviations
from known physical laws directs the neural network to produce physically plausible
output. Another method involves augmenting the training data with additional physical
information. This can be achieved by creating synthetic data points that satisfy physical
Aerospace 2024, 11, 669 19 of 31

equations and adding them to the training data set. For example, combining data points
derived from an aerodynamics equation ensures that the neural network is exposed to
a wide range of physically correct scenarios during training. This approach enables the
neural network to learn the underlying physical relationships more effectively.

Figure 8. Scatter-plot matrix of target parameters and geometry/flow features.

In this work, an empirical lift-curve slope was calculated using other geometric fea-
tures and provided to the algorithm with the objective of enhancing the generalizability
of the lift coefficient. In order to achieve this objective, the compressible form of the
Helmbold–Diederich equation, which was developed for a thin-section swept planform,
was employed [83,84]. The general form of this equation is as follows:

2π AR
a= q (34)
2+ ( β · AR)2 + ( AR · tan Λ1/2 )2 + 4
√
where β = 1 − M2 is the Prandtl–Glauert compressibility factor. In the application of this
equation, the quarter-chord sweep angle (Λ1/4 ) is commonly used due to its consistency and
historical validation in calculating aerodynamic coefficients such as lift-curve slopes [85].
However, the half-chord sweep angle (Λ1/2 ) can provide a better correlation with the lifting
surface theory, particularly in scenarios with significant wing taper, as it helps reduce
scatter and improve accuracy by effectively accounting for the impact of the taper on
aerodynamic properties [86]. ESDU TM 169 indicates that the use of the half-chord sweep
angle (Λ1/2 ) improves the correlation of lift-curve slope data with theoretical predictions,
rendering it advantageous for complex wing geometries [87]. It is also important to note
that this approach is valid for a sweep angle of up to 60 degrees.

3.3.3. Multilayer Perceptron-Based Network Architecture

Neural network algorithms were employed to train the black-box model using a
multilayer perceptron (MLP) structure to regress the performance data Y based on the
input features X. A fully connected network with L hidden layers is described by modeling
equations that relate the input features x to their target predictions y. The neural network
consists of M input features and N layers, with each layer composed of neurons performing
a series of mathematical operations followed by nonlinear activation functions.
The model parameters ξ are defined as ξ = {W, b}, where W = {wi }iN=1 and b =
N
{bi }i=1 . The output of the l-th layer is given by
Aerospace 2024, 11, 669 20 of 31

!
Nl  
f ( x, ξ l ) = f wl ,bl ( x ) = zl ∑ wlj x j + bl = Zl wlT xl + bl (l = 1, . . . , N ) (35)
j =1

In this equation, Nl is the number of neurons in the l-th layer, Zl is the nonlinear
activation function of the l-th layer, and xl is the input to the l-th layer, which is also the
output of the (l − 1)-th layer. The parameters wl and bl are the learnable weights and biases
of the l-th layer, respectively.
The final output of the neural network, ŷ( x ), is the result of a complex and composite
mapping defined as
 
ŷ( x ) := f w N ,bN ◦ f w N −1 ,bN −1 ◦ · · · ◦ f w1 ,b1 ( x ) (36)

In the implemented neural network architecture, the input layer accepts features with
shape (n_ f eatures). The first hidden layer, L1, consists of 512 neurons with a sigmoid
activation function and weights initialized using the “the normal” method:

L1 = σ (W1 x + b1 ) (37)
where σ denotes the sigmoid activation function, W1 is the weight matrix, and b1 is the bias
vector for the first layer. The sigmoid activation function is defined as

1
σ(z) = (38)
1 + e−z
The subsequent layers follow a similar structure:

L2 =σ (W2 L1 + b2 )
.. (39)
.
Ln−1 =σ (Wn−1 Ln−2 + bn−1 )
The output layer consists of a single neuron with a linear activation function, resulting
in the final prediction:

ŷ = Wn Ln−1 + bn (40)
The model is compiled using the Yogi optimizer with parameters β 1 = 0.9 and
β 2 = 0.999, and it optimizes the mean absolute error (MAE) loss function [88]. The Yogi
optimizer updates the model parameters as follows:

m t = β 1 m t −1 + (1 − β 1 ) g t (41)

vt = vt−1 − (1 − β 2 )sign(vt−1 − gt2 ) gt2 (42)

mt vt
m̂t = , v̂t = (43)
1 − βt1 1 − βt2
η
θ t +1 = θ t − √ m̂t (44)
v̂t + ϵ
where mt and vt are the first- and second-moment estimates, respectively, β 1 and β 2 are
the exponential decay rates for these estimates, gt is the gradient at the time step t, η is the
learning rate, and ϵ is a small constant to prevent division by zero. The mean absolute error
(MAE) is defined as
Aerospace 2024, 11, 669 21 of 31

n
1
MAE =
n ∑ |yi − ŷi | (45)
i =1

The Yogi optimizer ensures the efficient and stable convergence of the neural network
model parameters. This approach ensures that the architectural network is able to identify
and capture complex relationships within the data, allowing accurate predictions of the
performance metric Y. The training results of the neural networks developed are presented
in the following sections, along with an example of a UAV performance analysis application.

3.4. Multiobjective Genetic Algorithm

In this work, a multiobjective genetic algorithm (MOGA) was employed to optimize
the design parameters. Genetic algorithms are robust optimization techniques inspired by
the principles of natural selection and genetics. They are particularly effective for solving
complex, multiobjective optimization problems where multiple conflicting objectives need
to be simultaneously satisfied.
The optimization algorithm utilized in this research comprises a series of essential
steps, as illustrated in Figure 9. First, a population of potential solutions is randomly
generated within the defined parameter space. Each solution, also known as an individual,
is represented by a chromosome that encodes the design variables. Subsequently, each indi-
vidual within the population is evaluated based on a number of objective functions. These
functions assess the performance of the design with regard to criteria such as aerodynamic
efficiency, radar cross section (RCS), and structural weight. Individuals are selected for
reproduction based on their fitness, with a preference given to those with higher fitness
scores. This ensures that high-quality solutions are propagated through successive gen-
erations. Pairs of selected individuals undergo a crossover, exchanging portions of their
chromosomes to produce offspring. This process introduces novel genetic combinations
and expands the search space for potential solutions. Additionally, the offspring are sub-
jected to random mutations, whereby minor alterations are made to their chromosomes.
Mutation serves to maintain genetic diversity within the population, thereby preventing
premature convergence to local optima. The population is sorted into distinct fronts based
on the principle of Pareto dominance. The crowding distance is calculated in order to
maintain diversity among solutions on the same front. Individuals with superior ranks
and elevated crowding distances are selected for the subsequent generation. The current
population is replaced by the new generation of individuals, and the process iterates until
a termination criterion is met, such as a maximum number of generations or convergence
of the Pareto front.

Evaluate fitness Select ranked

Start Initialize population Selection
function individiual

Crossover

Mutation

Offspring
evaluation

Population
reached? No

No Yes

Yes Generation Rank parents and

End
reached? offsprings

Figure 9. Flowchart of the Nondominated Sorting Genetic Algorithm (NSGA-II) process: initialization,
evaluation, selection, crossover, mutation, and ranking.
Aerospace 2024, 11, 669 22 of 31

The specific implementation of the MOGA in this work used the Nondominated
Sorting Genetic Algorithm II (NSGA-II), which is well-known for its efficiency in handling
multiobjective optimization problems [89]. The algorithm was implemented using a versa-
tile optimization library in Python [90]. The application of NSGA-II resulted in a diverse
set of optimized design configurations. The Pareto front obtained demonstrates the trade-
offs between conflicting objectives, providing valuable insights for decision makers. Key
performance indicators such as aerodynamic lift-to-drag ratio, structural weight efficiency,
and radar cross section were significantly improved through the optimization process.

4. Application of the Model

An example design problem was discussed to implement the model. The application
focused on the previously mentioned high-performance UAVs. A list of requirements was
determined for a generic design capable of long-range flight, operating at high subsonic
speeds, and mounting various internal payload systems.
The requirements for the proposed aerial system are listed as follows:
• Maximum take-off weight: 3000 kg
• Payload weight: 500 kg
• Cruise speed: 0.7 Mach
• Endurance: 5 hours
• Range: 3000 NM
• Maximum altitude: 45,000 ft
The requirements were used as input to the initial design algorithm to make the
preliminary estimates necessary for the initial sizing of the aircraft. In order to create the
design space, the maximum and minimum ranges of the design variables are determined
and provided as input to the neural network algorithm. Table 3 shows the ranges of
design variables identified for concept design space exploration. These parameters are
grouped into four main categories: wing, fuselage, engine thrust, and flow conditions.
The design space is constrained so that the solution point of the wing area obtained from
the initial design algorithm covers the perimeter of the prediction. It is possible to model
any one-piece wing with aspect ratio, taper, and sweep. The hydraulic diameter and the
fineness ratio were considered for the fuselage modeling. The maximum thrust value
for the engine was obtained from the initial design algorithm, similar to the wing area.
Flow conditions were determined to cover the target flight regime at cruising altitude. As
a result, performance models were obtained following the data generation and artificial
neural network training described in the previous sections.
The results of the performance evaluation of neural network models in predicting
aerodynamic coefficients, radar cross-section, and weight characteristics are presented
in Figure 10, which contains several key subfigures. Figure 10a illustrates the predicted
versus actual lift coefficient (CL ) values, showcasing an exceptional fit with an R2 value of
0.9971. The residuals plot reveals a minimal deviation from the actual values, with residuals
clustering closely around the zero-error line and a maximum residual of approximately
±0.075. The histogram of residuals displays a symmetric distribution centered around
zero, indicating that the majority of predictions are highly accurate and demonstrating
the model’s robustness in predicting lift coefficients. Figure 10b presents the predicted
versus actual drag coefficient (CD ) values, indicating a strong correlation with an R2 value
of 0.9939. The residuals plot exhibits a tight distribution around the zero-error line, with a
maximum residual of approximately ±0.003. The residual histogram further confirms the
accuracy of the model, with most residuals clustering near zero. Figure 10c evaluates the
predicted versus actual radar cross-section (RCS) values. An R2 value of 0.9956 suggests
robust model performance. The residual plot and the corresponding histogram show
that most predictions are accurate, with residuals closely aligned with the zero-error line
and a maximum residual of approximately ±0.15. The narrow spread of residuals in the
histogram signifies the model’s consistent reliability in predicting RCS values. Lastly, Figure
10d compares the predicted versus actual empty weight values, giving an R2 value of 0.9929.
Aerospace 2024, 11, 669 23 of 31

The residual plot demonstrates that the predictions are generally accurate, with minor
deviations from the actual values and a maximum residual of around ±20 kg. The residual
histogram supports this observation, showing a concentration of residuals around zero.

Table 3. Design variable ranges for conceptual design space exploration.

Parameter Symbol Units Minimum Maximum

Wing area A m2 15 25
Aspect ratio AR − 2 8
Wing
Taper ratio λ − 0.2 0.6
Sweep Λ ◦ 15 40
Length l m 5 15
Hydraulic diameter dh m 1 2
Fuselage Fineness ratio f − 2.5 15
Engine Thrust T kN 5 20
Angle of attack α ◦ 0 4
Mach number M − 0.6 0.8
Flow condition Reynolds number Re − 6 · 106 18 · 106

The collective results demonstrate the effectiveness of neural network models in accu-
rately predicting critical aerodynamics, radar cross-section, and weight parameters. The
current margins of error are below acceptable levels in the early design stages. The high
values of the correlation coefficient, R2 , and the narrow distributions of residuals in all
models demonstrate the robust precision of the neural network approach utilized in this
investigation. Once the data-driven models have been obtained, the subsequent step is
to define the objective functions and constraints that are necessary for the execution of
the multiobjective genetic algorithm. The optimization process focuses on improving the
design of a high-performance UAV by simultaneously addressing multiple conflicting objec-
tives. The optimization problem identified for this specific application can be summarized
as follows:

minimize F = { f 1 ( x, y), f 2 ( x ), f 3 ( x, y)}

⃗ ={λ,AR,Λ,...}
x ∈V
⃗ ={α,M,Re,...}
y ∈U

CL
where f 1 ( x, y) = −
CD
f 2 ( x ) = RCS
f 3 ( x, y) = Wempty (46)

subject to 0.2 ≤ λ ≤ 0.6

4 ≤ AR ≤ 8
15◦ ≤ Γ ≤ 40◦
0◦ ≤ α ≤ 2◦
where the objective functions include maximizing the lift-to-drag ratio, minimizing the
radar cross section, and minimizing the empty weight of the UAV. These objectives are
essential to improve aerodynamic efficiency, stealth capabilities, and overall performance.
While a wing structure with a high span ratio is required to increase aerodynamic efficiency,
a wing with a lower span ratio and angle of attack is required to minimize structural
weight. While stealth performance increases with the sweep angle, it also changes with the
overall shape of the vehicle. It is possible to search for wing configurations with different
planforms such as tapered, sweptback, and delta in the current design space. Optimization
Aerospace 2024, 11, 669 24 of 31

variables such as the taper ratio, the aspect ratio, the sweep angle, and the angle of attack
are constrained within certain ranges to ensure realistic and feasible design solutions.

(a) Performance metrics for the aerodynamic model (CL ).

(b) Performance metrics for the aerodynamic model (CD ).

(c) Performance metrics for the RCS model.

(d) Performance metrics for the weight model (Wempty ).

Figure 10. Performance visualization of neural networks models.

5. Results
The problem is solved using a multiobjective genetic algorithm, which efficiently
explores the design space and finds a diverse set of optimal solutions along the Pareto
front. This approach provides valuable insight into the trade-offs between different design
Aerospace 2024, 11, 669 25 of 31

objectives, allowing the selection of the most balanced and effective UAV configurations.
The optimization process is performed using the Nondominated Sorting Genetic Algorithm
II (NSGA-II) with a population size of 50 and an iteration criterion of 200 generations.
As a result of the optimization, the Pareto front surface shown in Figure 11 was
obtained. The given three-dimensional surface plots illustrate the trade-offs between three
key objectives: maximizing the lift-to-drag ratio (CL/CD), minimizing the radar cross
section (RCS), and minimizing the empty weight. The color gradient from blue to yellow
represents different levels of the third objective (empty weight). The smooth and continuous
surface of the Pareto front indicates a well-defined and consistent set of optimal solutions
generated by the NSGA-II algorithm.
Three configurations maximizing each objective from the Pareto front solution were consid-
ered and compared based on the performance metrics determined. These performance metrics
are defined as endurance, range, speed, maneuverability, stealth, and payload. Representative
models of the configurations and the radar plot are shown in Figure 12. In the figure, the
configuration numbers are presented in a sorted order according to the objective. The
optimal configuration for aerodynamic efficiency is Configuration 1, while Configuration
2 is the most effective in minimizing the radar cross section (RCS) and Configuration 3
is the lowest in empty weight. Configuration 1 (shown in blue) exhibits a remarkable
degree of success in endurance and range measurements, performing approximately 43%
better in aerodynamic efficiency. It can be observed that this concept is more suitable
for mission profiles such as ISR. Additionally, stealth and payload are sufficient to carry
surveillance equipment while avoiding detection. Configuration 2 (in yellow) demonstrates
the overall performance in other metrics while exhibiting superior stealth performance
with −8.69dBsm ≈ 0.1357m2 RCS. The high scores in stealth, speed, and maneuverability
make Configuration 2 an optimal choice for SEAD and tactical strike missions where rapid
maneuvers and low detectability are paramount. Configuration 3 (red) scores high both in
speed and maneuverability with an empty weight of approximately 1350 kg, indicating
a design optimized for agile and fast operations. However, this design compromises on
endurance and range. The configuration exhibits the highest performance in speed and
maneuverability, accompanied by a high payload, making it suitable for combat air patrol
(CAP) missions where agility and rapid response are paramount.
The design process, which leveraged advanced AI models, was remarkably efficient,
requiring a total of just 4–5 s to complete. This rapid optimization was accomplished
through the utilization of a personal laptop, equipped with an Intel Core i7-11800H pro-
cessor and 32 GB of RAM. The deployment of AI-driven models markedly accelerated the
assessment of design solutions, facilitating quick navigation through the intricate design
space. In contrast, had traditional methodologies been employed, the optimization pro-
cess would have taken 4–5 h to achieve comparable results with the same computational
environment.

Figure 11. Pareto front visualization of UAV design optimization.

Aerospace 2024, 11, 669 26 of 31

Figure 12. Comparative analysis of UAV configurations.

6. Conclusions
In this work, we demonstrated the application of advanced deep neural networks
to the multidisciplinary conceptual design of UAVs. The goal was to enhance the design
process by leveraging AI to optimize various performance metrics, including aerodynamic
efficiency, stealth capabilities, and structural weight. By employing a multiobjective genetic
algorithm integrated with AI-driven models, we efficiently explored the design space
and identified a set of optimal UAV configurations. The proposed design process was
completed in just a couple of seconds. This represents an improvement of more than
three orders of magnitude compared to traditional methods, which would have required
computational times of the order of hours to achieve comparable results. A state-of-the-art
physics-informed feature engineering approach was employed to develop precise surrogate
models, which accurately predict critical UAV performance metrics such as aerodynamic
efficiency, stealth capabilities, and structural integrity. The results show significant advan-
tages of this AI-based approach. The AI models enabled a rapid and precise evaluation
of design solutions, facilitating a comprehensive understanding of the trade-offs between
different design objectives. The Pareto front generated from the optimization process
provided valuable insights into the optimal balance between lift-to-drag ratio, radar cross
section, and structural weight. Furthermore, the research tailors UAV designs to specific
mission profiles by addressing unique operational requirements, ensuring each config-
uration excels in its intended application, such as ISR, SEAD, or CAP missions. In the
example application, three UAV configurations were identified and analyzed based on their
performance in six key parameters: endurance, range, speed, maneuverability, stealth, and
payload. Configuration 1, with its high endurance and range, is well suited for intelligence,
surveillance, and reconnaissance (ISR) missions. Configuration 2, which excels in stealth,
speed, and maneuverability, is ideal for Suppression of Enemy Air Defenses (SEAD) and
tactical strike missions. Configuration 3, optimized for speed and maneuverability, is best
suited for combat air patrol (CAP) missions.
The integration of AI in the UAV design process offers substantial benefits, including
significant reductions in computational time and enhanced flexibility to explore complex
design spaces. This approach not only facilitates rapid prototyping and iterative design but
also paves the way for more efficient and effective engineering solutions in the aerospace
industry. The potential for AI-driven optimization to revolutionize UAV design and address
other multidisciplinary engineering challenges is considerable and continues to evolve.

Author Contributions: Conceptualization, H.K. and G.I.; methodology, H.K. and G.I.; software, H.K.
and G.I.; validation, H.K. and G.I.; formal analysis, H.K. and G.I.; investigation, H.K. and G.I.; re-
sources, H.K. and G.I.; data curation, H.K.; writing—original draft preparation, H.K.; writing—review
and editing, G.I. and A.T.; visualization, H.K.; supervision, G.I. and A.T.; project administration, G.I.;
funding acquisition, G.I. All authors have read and agreed to the published version of the manuscript.
Aerospace 2024, 11, 669 27 of 31

Funding: Hasan Karali is co-funded by the UKRI EPSRC and the BAE Systems under 210085
numbered Industrial CASE award: Towards Trustworthy AI-driven Autonomous Systems: Multi-
Disciplinary Design Optimisation.
Data Availability Statement: The raw data supporting the conclusions of this article will be made
available by the authors on request.
Acknowledgments: AI has been utilized to enhance the overall language proficiency and clarity of
the article. It is important to note that the conceptualization, formulation of equations, innovative
contributions, and development of codes and figures were independently accomplished without
AI assistance.
Conflicts of Interest: The authors declare no conflicts of interest.

Abbreviations
CAD Computer-aided design
CAP Combat air patrol
CFD Computational fluid dynamics
EW Electronic warfare
FEM Finite element method
FoM Figure of merit
DNN Deep neural network
ISR Intelligence, surveillance and reconnaissance
LCC Life-cycle costing
LHS Latin hypercube sampling
MDO Multidisciplinary design optimization
MTOW Maximum take-off weight
PM Panel method
PO Physical optics
RCS Radar cross section
RF Radio frequency
ROM Reduced order model
SEAD Suppression of Enemy Air Defenses
SFC Specific fuel consumption
UAS Unmanned aerial system
UAV Unmanned aerial vehicle
UCAV Unmanned combat aerial vehicle
VLM Vortex lattice method

Nomenclature
α Angle of attack
Λ Sweep angle
AR Aspect ratio
bre f Reference span
λ Taper ratio
CL Lift coefficient
CD Drag coefficient
CM Moment coefficient
M Mach number
Re Reynolds number
Sre f Reference wing area
ρ Air density
µ Dynamic viscosity
Vin f Free stream velocity
dh Hydraulic diameter
f Fineness ratio
T Thrust
Aerospace 2024, 11, 669 28 of 31

RCS Radar cross section

Wempty Empty weight
Croot Root chord length
Ctip Tip chord length
Q aero Aerodynamic loads
Nl Number of neurons in the l-th layer
Zl Nonlinear activation function of the l-th layer
xl Input to the l-th layer
wl Weights of the l-th layer
bl Biases of the l-th layer
f ( x, ξ l ) Output of the l-th layer
ξ Model parameters (weights and biases)
σ Sigmoid activation function
η Learning rate
N Number of layers

References
1. Cummings, R.M.; Mason, W.H.; Morton, S.A.; McDaniel, D.R. Applied Computational Aerodynamics: A Modern Engineering Approach;
Cambridge Aerospace Series; Cambridge University Press: Cambridge, UK, 2015. [CrossRef]
2. Jungo, A.; Zhang, M.; Vos, J.B.; Rizzi, A. Benchmarking New CEASIOM with CPACS adoption for aerodynamic analysis and
flight simulation. Aircr. Eng. Aerosp. Technol. 2018, 90, 613–626. [CrossRef]
3. Roskam, J. Airplane Design; DARcorporation: St. Lawrence, KS, USA, 1985.
4. Raymer, D. Aircraft Design: A Conceptual Approach; American Institute of Aeronautics and Astronautics Inc.: Las Vegas, NV,
USA, 2012.
5. Sadraey, M.H. Aircraft Design: A Systems Engineering Approach; Aerospace Series; John Wiley and Sons: Chichester, UK, 2013.
[CrossRef]
6. de Weck, O.; Willcox, K. Multidisciplinary System Design Optimization. 2003. Available online: https://ocw.mit.edu/courses/
ids-338j-multidisciplinary-system-design-optimization-spring-2010/ (accessed on 10 June 2022).
7. Roth, G.L.; Altman, A. Re-imagining Engineering Conceptual Design for Aerospace. In Proceedings of the AIAA AVIATION
2022 Forum, Chicago, IL, USA, 27 June–1 July 2022; p. 3880.
8. Liao, P.; Song, W.; Du, P.; Feng, F.; Zhang, Y. Aerodynamic Intelligent Topology Design (AITD)-A Future Technology for Exploring
the New Concept Configuration of Aircraft. Aerospace 2023, 10, 46. [CrossRef]
9. Asimov, I. I, Robot; Doubleday: New York, NY, USA, 1950.
10. Stanisław, L. The Invincible; Seabury Press: New York, NY, USA, 1973.
11. Humphreys, C.; Cobb, R.; Jacques, D.; Reeger, J. Optimal Mission Path for the Uninhabited Loyal Wingman. In Proceedings of
the 16th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference, Dallas, TX, USA, 22–26 June 2015; p. 2792.
12. Stensrud, R.; Mikkelsen, B.; Betten, S.; Valaker, S. A proposal for a simple evaluation method in support of the initial concept
phase assessing a future unmanned Loyal Wingman for Royal Norwegian Air Force (RNoAF). In Proceedings of the 38th
International Symposium on Military Operational Research (38 ISMOR), Online, 20–21 July 2021.
13. Harper, J. The Rise of Skyborg: Air Force Betting on New Robotic Wingman. Natl. Def. 2020. Available on-
line: https://www.nationaldefensemagazine.org/articles/2020/9/25/air-force-betting-on-new-robotic-wingman#:~:
text=The%20Rise%20of%20Skyborg%3A%20Air%20Force%20Betting%20on%20New%20Robotic%20Wingman&text=The%20
next%20year%20will%20be,will%20soon%20undergo%20operational%20experimentation (accessed on 11 August 2024).
14. Gunzinger, M.; Autenried, L. Understanding the Promise of Skyborg and Low-Cost Attritable Unmanned Aerial Vehicles.
Mitchell Inst. Policy Pap. 2020, 24. Available online: https://mitchellaerospacepower.org/understanding-the-promise-of-skyborg-
and-low-cost-attritable-unmanned-aerial-vehicles/ (accessed on 11 August 2024).
15. Reim, G. Analysis: US Air Force eyes adoption of ‘Loyal Wingman’ UAVs. Flight Glob. 2018. Available online: https:
//www.flightglobal.com/analysis/analysis-us-air-force-eyes-adoption-of-loyal-wingman-uavs/129330.article (accessed on 11
August 2024).
16. Smith, A.; Rogers, M. F-35 Sustainment: DOD Needs to Cut Billions in Estimated Costs to Achieve Affordability; U.S. Government
Accountability Office: Washington, DC, USA, 2021.
17. Colombi, J.; Bentz, B.; Recker, R.; Lucas, B.; Freels, J. Attritable design trades: Reliability and cost implications for unmanned
aircraft. In Proceedings of the 2017 Annual IEEE International Systems Conference (SysCon), Montreal, QC, Canada, 24–27 April
2017; IEEE: New York, NY, USA, 2017; pp. 1–8.
18. Pittaway, N. Boeing details MQ-28A payload ground test phase. Aust. Def. Mag. 2022. Available online: https:
//www.australiandefence.com.au/defence/air/boeing-details-mq-28a-payload-ground-test-phase#:~:text=A%20variety%20
of%20payloads%20will,of%20the%20aircraft%27s%20removable%20nose (accessed on 11 August 2024).
Aerospace 2024, 11, 669 29 of 31

19. Newdick, T. The United Kingdom Has Chosen Who Will Build Its First Prototype Loyal Wingman Combat Drone. Drive Warzone
2021. Available online: https://www.thedrive.com/the-war-zone/42134/the-united-kingdom-has-chosen-who-will-build-its-
first-prototype-loyal-wingman-combat-drone (accessed on 11 August 2024).
20. Aviation Week. EADS Barracuda. Available online: https://aviationweek.com/defense-space/eads-cassidian-eyes-further-
barracuda-uav-flights (accessed on 26 May 2024).
21. 96th Test Wing, 40th Flight Test Squadron. Kratos XQ-58. Photo by Master Sgt. Tristan McIntire. Available online: https:
//www.flightglobal.com/military-uavs/usmc-completes-first-test-flight-with-autonomous-xq-58/155257.article (accessed on 26
May 2024).
22. Australian Defense Department. MQ-28 Loyal Wingman. Available online: https://aviationweek.com/shownews/farnborough-
airshow/boeings-phantom-works-wants-untethered-loyal-wingman (accessed on 26 May 2024).
23. Anadolu Images. Baykar Kizilelma. Available online: https://www.aa.com.tr/tr/bilim-teknoloji/bayraktar-kizilelma-ilk-
ucusunu-gerceklestirdi/2763872 (accessed on 26 May 2024).
24. General Atomics. XQ-67A Off Board Sensing Station Maiden Flight over Palmdale, California. Available online: https:
//www.dvidshub.net/image/8275788/afrls-xq-67a-makes-1st-successful-flight(accessed on 26 May 2024).
25. Qinetiq. Qinetiq Derives Collaborative UAS from Banshee Target. Credit: Qinetiq. Available online: https://aviationweek.com/
defense-space/aircraft-propulsion/qinetiq-derives-collaborative-uas-banshee-target (accessed on 26 May 2024).
26. BAE Systems. UAS Concepts. 2023. Available online: https://www.baesystems.com/en/product/uas-concepts (accessed on 26
May 2024).
27. Air & Space Forces Magazine. Anduril and General Atomics to Develop New Collaborative Combat Aircraft for Air Force. The
Anduril “Fury” Autonomous Aircraft on April 24. Courtesy Photo. Available online: https://www.airandspaceforces.com/cca-
contract-winners-to-be-announced-imminently/ (accessed on 11 August 2024).
28. Sobieszczanski-Sobieski, J. Multidisciplinary design optimization: An emerging new engineering discipline. In Advances in
Structural Optimization; Springer: Berlin/Heidelberg, Germany, 1995; pp. 483–496.
29. Nguyen, N.V.; Choi, S.M.; Kim, W.S.; Lee, J.W.; Kim, S.; Neufeld, D.; Byun, Y.H. Multidisciplinary unmanned combat air vehicle
system design using multi-fidelity model. Aerosp. Sci. Technol. 2013, 26, 200–210. [CrossRef]
30. Karali, H.; Inalhan, G.; Umut Demirezen, M.; Adil Yukselen, M. A new nonlinear lifting line method for aerodynamic analysis
and deep learning modeling of small unmanned aerial vehicles. Int. J. Micro Air Veh. 2021, 13, 17568293211016817. [CrossRef]
31. Ng, L.W.; Willcox, K.E. Multifidelity approaches for optimization under uncertainty. Int. J. Numer. Methods Eng. 2014, 100, 746–772.
[CrossRef]
32. Brunton, S.L.; Nathan Kutz, J.; Manohar, K.; Aravkin, A.Y.; Morgansen, K.; Klemisch, J.; Goebel, N.; Buttrick, J.; Poskin, J.;
Blom-Schieber, A.W.; et al. Data-driven aerospace engineering: Reframing the industry with machine learning. AIAA J. 2021,
59, 2820–2847. [CrossRef]
33. AIAA Digital Engineering Integration Committee. Digital Twin: Definition & Value—An AIAA and AIA Position Paper; AIAA:
Reston, VA, USA, 2020.
34. Dantas de Jesus Ferreira, J.A.; Secco, N.R. Decision tree classifiers for unmanned aircraft configuration selection. Aircr. Eng.
Aerosp. Technol. 2021, 93, 1122–1132. [CrossRef]
35. Sharma, R.S.; Hosder, S. Investigation of aircraft design space exploration with machine learning. In Proceedings of the AIAA
Scitech 2021 Forum, Virtual, 11–15 & 19–21 January 2021; p. 0114.
36. Oroumieh, M.A.A.; Malaek, S.M.B.; Ashrafizaadeh, M.; Taheri, S.M. Aircraft design cycle time reduction using artificial
intelligence. Aerosp. Sci. Technol. 2013, 26, 244–258. [CrossRef]
37. Boutemedjet, A.; Samardžić, M.; Rebhi, L.; Rajić, Z.; Mouada, T. UAV aerodynamic design involving genetic algorithm and
artificial neural network for wing preliminary computation. Aerosp. Sci. Technol. 2019, 84, 464–483. [CrossRef]
38. Setayandeh, M.R. Surrogate model–based robust multidisciplinary design optimization of an unmanned aerial vehicle. J. Aerosp.
Eng. 2021, 34, 04021029. [CrossRef]
39. Bekemeyer, P.; Bertram, A.; Hines Chaves, D.A.; Dias Ribeiro, M.; Garbo, A.; Kiener, A.; Sabater, C.; Stradtner, M.; Wassing, S.;
Widhalm, M.; et al. Data-driven aerodynamic modeling using the DLR SMARTy toolbox. In Proceedings of the AIAA Aviation
2022 Forum, Chicago, IL, USA, 27 June–1 July 2022; p. 3899.
40. Sharma, R.S.; Hosder, S. Mission-Driven Inverse Design of Blended Wing Body Aircraft with Machine Learning. Aerospace 2024,
11, 137. [CrossRef]
41. Wu, P.; Yuan, W.; Ji, L.; Zhou, L.; Zhou, Z.; Feng, W.; Guo, Y. Missile aerodynamic shape optimization design using deep neural
networks. Aerosp. Sci. Technol. 2022, 126, 107640. [CrossRef]
42. Yan, X.; Zhu, J.; Kuang, M.; Wang, X. Aerodynamic shape optimization using a novel optimizer based on machine learning
techniques. Aerosp. Sci. Technol. 2019, 86, 826–835. [CrossRef]
43. Li, J.; Du, X.; Martins, J.R. Machine learning in aerodynamic shape optimization. Prog. Aerosp. Sci. 2022, 134, 100849. [CrossRef]
44. Bouhlel, M.A.; He, S.; Martins, J.R. Scalable gradient–enhanced artificial neural networks for airfoil shape design in the subsonic
and transonic regimes. Struct. Multidiscip. Optim. 2020, 61, 1363–1376. [CrossRef]
45. Du, X.; He, P.; Martins, J.R. A B-spline-based generative adversarial network model for fast interactive airfoil aerodynamic
optimization. In Proceedings of the AIAA Scitech 2020 Forum, Orlando, FL, USA, 6–10 January 2020; p. 2128.
46. Li, J.; Zhang, M. Data-based approach for wing shape design optimization. Aerosp. Sci. Technol. 2021, 112, 106639. [CrossRef]
Aerospace 2024, 11, 669 30 of 31

47. Barnhart, S.A.; Narayanan, B.; Gunasekaran, S. Blown wing aerodynamic coefficient predictions using traditional machine
learning and data science approaches. In Proceedings of the AIAA Scitech 2021 Forum, Virtual, 11–15 & 19–21 January 2021;
p. 0616.
48. Yuan, Y.; Dongli, M.; Muqing, Y.; Zhang, L.; Yang, G. Adaptive-surrogate-based robust optimization of transonic natural laminar
flow nacelle. Chin. J. Aeronaut. 2021, 34, 36–52.
49. Yu, B.; Xie, L.; Wang, F. An improved deep convolutional neural network to predict airfoil lift coefficient. In Proceedings of the
International Conference on Aerospace System Science and Engineering; Springer: Berlin/Heidelberg, Germany, 2019; pp. 275–286.
50. Zhang, Y.; Sung, W.J.; Mavris, D.N. Application of convolutional neural network to predict airfoil lift coefficient. In Proceedings
of the 2018 AIAA/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference, Kissimmee, FL, USA, 8–12
January 2018; p. 1903.
51. Wu, M.Y.; Yuan, X.Y.; Chen, Z.H.; Wu, W.T.; Hua, Y.; Aubry, N. Airfoil shape optimization using genetic algorithm coupled deep
neural networks. Phys. Fluids 2023, 35, 085140. [CrossRef]
52. Keane, A.J.; Voutchkov, I.I. Surrogate approaches for aerodynamic section performance modeling. AIAA J. 2020, 58, 16–24.
[CrossRef]
53. Karali, H.; Inalhan, G.; Tsourdos, A. AI-Based Multifidelity Surrogate Models to Develop Next Generation Modular UCAVs. In
Proceedings of the AIAA Scitech 2023 Forum, National Harbor, MD, USA, 23–27 January 2023. [CrossRef]
54. Karali, H.; Inalhan, G.; Tsourdos, A. AI-driven Unmanned Aerial System Conceptual Design with Configuration Selection. In
Proceedings of the 2023 IEEE Conference on Artificial Intelligence (CAI), Santa Clara, CA, USA, 5–6 June 2023; IEEE: New York,
NY, USA, 2023; pp. 83–84. [CrossRef]
55. Karali, H.; Inalhan, G.; Tsourdos, A. AI-Driven Multidisciplinary Conceptual Design of Unmanned Aerial Vehicles. In Proceedings
of the AIAA SCITECH 2024 Forum, Orlando, FL, USA, 8–12 January 2024; p. 1708. [CrossRef]
56. Roskam, J.; Lan, C.T.E. Airplane Aerodynamics and Performance; DARcorporation: St. Lawrence, KS, USA, 1997.
57. Pratt & Whitney Canada. JT15D Turbofan Engine. Available online: https://airandspace.si.edu/collection-objects/pratt-
whitney-canada-jt15d-1turbofan-engine-cutaway/nasm_A19780210000 (accessed on 7 August 2024).
58. Pratt & Whitney Canada. PW617 Turbofan Engine. Available online: https://www.prattwhitney.com/en/products/business-
aviation-engines/pw600 (accessed on 7 August 2024).
59. Pratt & Whitney Canada. PW545B Turbofan Engine. Available online: https://www.prattwhitney.com/en/products/business-
aviation-engines/pw500 (accessed on 7 August 2024).
60. Pratt & Whitney Canada. PW610F Turbofan Engine. Available online: https://www.prattwhitney.com/en/products/business-
aviation-engines/pw600 (accessed on 7 August 2024).
61. Pratt & Whitney Canada. PW615F Turbofan Engine. Available online: https://www.prattwhitney.com/en/products/business-
aviation-engines/pw600 (accessed on 7 August 2024).
62. GE Honda. GE Honda HF120 Turbofan Engine. Available online: https://www.geaviation.com (accessed on 7 August 2024).
63. Ivchenko Progress. AI-25TL Turbofan Engine. Available online: http://uecrus.com (accessed on 7 August 2024).
64. Williams International. FJ33 Turbofan Engine. Available online: https://www.williams-int.com/products/ (accessed on 7
August 2024).
65. Williams International. FJ44-4 Turbofan Engine. Available online: https://www.williams-int.com/products/ (accessed on 7
August 2024).
66. Honeywell Aerospace. TFE731-2 Turbofan Engine. Available online: https://aerospace.honeywell.com/us/en/products-and-
services/product/hardware-and-systems/engines/tfe731 (accessed on 7 August 2024).
67. Katz, J.; Plotkin, A. Low-Speed Aerodynamics, 2nd ed.; Cambridge Aerospace Series; Cambridge University Press: Cambridge, UK,
2001. [CrossRef]
68. Erickson, L.L. Panel Methods: An Introduction; Technical Publication NASA-TP-2995, NASA Technical Paper 2995 December 1990;
NASA Ames Research Center: Moffett Field, CA, USA, 1990.
69. Karali, H.; Demirezen, U.M.; Yukselen, M.A.; Inalhan, G. A novel physics informed deep learning method for simulation-based
modelling. In Proceedings of the AIAA Scitech 2021 Forum, Virtual, 11–15 & 19–21 January 2021; p. 0177. [CrossRef]
70. Karakoc, A.; Kaya, H. A multi-objective multi-disciplinary optimization approach for NATO AVT 251 UCAV–MULDICON. In
Proceedings of the 2018 Applied Aerodynamics Conference, Atlanta, GA, USA, 25–29 June 2018; p. 3001.
71. Fourikis, N. Advanced Array Systems, Applications and RF Technologies; Academic Press: Cambridge, MA, USA, 2000.
72. Chung, S.S.M.; Tuan, S.C. Radar Cross Section Simulation of XQ-58 Valkyrie Like CAD Model. In Proceedings of the 2020
International Workshop on Electromagnetics: Applications and Student Innovation Competition (iWEM), Makung, Taiwan, 26–28
August 2020; IEEE: New York, NY, USA, 2020; pp. 1–2.
73. Leung, S.; Liang, C.p.; Tao, X.f.; Li, F.f.; Poo, Y.; Wu, R.x. Broadband radar cross section reduction by an absorptive metasurface
based on a magnetic absorbing material. Opt. Express 2021, 29, 33536–33547. [CrossRef] [PubMed]
74. Kapoulas, I.K.; Hatziefremidis, A.; Baldoukas, A.; Valamontes, E.S.; Statharas, J. Small Fixed-Wing UAV Radar Cross-Section
Signature Investigation and Detection and Classification of Distance Estimation Using Realistic Parameters of a Commercial
Anti-Drone System. Drones 2023, 7, 39. [CrossRef]
75. Peng, Z.; Li, C.; Uysal, F. Modern Radar for Automotive Applications; Institution of Engineering and Technology: Stevenage, UK,
2022.
Aerospace 2024, 11, 669 31 of 31

76. Peng, Z. Rookiepeng/Radarsimpy. 2022. Available online: https://zenodo.org/records/6792269 (accessed on 11 August 2024).
77. Jasa, J.P.; Hwang, J.T.; Martins, J.R. Open-source coupled aerostructural optimization using Python. Struct. Multidiscip. Optim.
2018, 57, 1815–1827. [CrossRef]
78. Bouhlel, M.A.; Hwang, J.T.; Bartoli, N.; Lafage, R.; Morlier, J.; Martins, J.R.R.A. A Python surrogate modeling framework with
derivatives. Adv. Eng. Softw. 2019, 135, 102662. [CrossRef]
79. McDonald, R.A. Advanced modeling in OpenVSP. In Proceedings of the 16th AIAA Aviation Technology, Integration, and
Operations Conference, Washington, DC, USA, 13–17 June 2016; p. 3282.
80. McDonald, R.A.; Gloudemans, J.R. Open Vehicle Sketch Pad: An Open Source Parametric Geometry and Analysis Tool for
Conceptual Aircraft Design. In Proceedings of the AIAA SCITECH 2022 Forum, San Diego, CA, USA, 3–7 January 2022; p. 0004.
81. Freedman, D.; Pisani, R.; Purves, R. Statistics (International Student Edition); WW Norton & Company: New York, NY, USA, 2007.
82. Benesty, J.; Chen, J.; Huang, Y.; Cohen, I. Pearson Correlation Coefficient; Springer: Berlin/Heidelberg, Germany, 2009; pp. 1–4.
83. Engineering Sciences Data Unit. Lift-Curve Slope and Aerodynamic Centre Position of Wings in Inviscid Subsonic Flow; Technical
Report ESDU 70011; As at Amendment I; ESDU International: London, UK, 1970.
84. Engineering Sciences Data Unit. Wing Angle of Attack for Zero Lift at Subcritical Mach Numbers; Technical Report ESDU 87031; As
at Amendment A; ESDU International: London, UK, 1987.
85. ESDU International. Lift-Curve Slope of Swept and Tapered Wings; Technical Memorandum ESDU AERO W.01.01.01, Issued March
1953, with Amendments A to D, October 1989; ESDU International: London, UK, 2001.
86. Lowry, J.; Polhamus, E. A Method for Predicting Lift Increments Due to Flap Deflections at Low Angles of Attack in Incompressible
Flow. Technical Note Technical NACA-TN-3911, 1 August 1957.
87. ESDU International. Wing Lift-Curve Slope in Inviscid Subsonic Flow: Improvements to the Helmbold-Diederich Equation and Comparison
with Data from ESDU 70011; Technical Memorandum TM 169; ESDU International: London, UK, 2012.
88. Zaheer, M.; Reddi, S.J.; Sachan, D.; Kale, S.; Kumar, S. Adaptive Methods for Nonconvex Optimization. In Proceedings of the
Advances in Neural Information Processing Systems, Montreal, QC, Canada, 3–8 December 2018; Volume 31.
89. Deb, K.; Pratap, A.; Agarwal, S.; Meyarivan, T. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol.
Comput. 2002, 6, 182–197. [CrossRef]
90. Blank, J.; Deb, K. pymoo: Multi-objective Optimization in Python. IEEE Access 2020, 8, 89497–89509. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.