Journal of Physics: Conference

Series

PAPER • OPEN ACCESS You may also like

- Discussion on the Innovation and
Intelligent manufacturing in the context of industry Transformation of IMM and Processing
Mode
4.0: A case study of siemens industry Miao He

- Design of the Intelligent Manufacturing

Demonstration System based on IoT in the
To cite this article: V Kishorre Annanth et al 2021 J. Phys.: Conf. Ser. 1969 012019 Context of Industry 4.0
Yiyang Liu, Zenghui Li, Zhining Wang et
al.

- Application and Prospect of Intelligent

Manufacturing in Practice
View the article online for updates and enhancements. Runyan Zhang, Yan Yuan and Limin Chen

This content was downloaded from IP address 42.112.181.50 on 15/06/2024 at 10:51

IRMAS 2021 IOP Publishing
Journal of Physics: Conference Series 1969 (2021) 012019 doi:10.1088/1742-6596/1969/1/012019

Intelligent manufacturing in the context of industry 4.0: A

case study of siemens industry

V Kishorre Annanth, M Abinash and Lokavarapu Bhaskara Rao*

School of Mechanical Engineering, Vellore Institute of Technology, Vandalur-
Kelambakkam Road, Rajan Nagar, Chennai-600127, Tamil Nadu, India

*
E-mail: [email protected]

Abstract. At present, the methods by which products are designed and manufactured are
advancing at a rapid pace just before our eyes. The contemporary period known as Industry 4.0
is realizing an evolution from manual to digital operations and it has great importance to
manufacturers throughout the world. In the context of Industry 4.0, intelligent manufacturing is
a paradigm enabled for the integration of smart sensors and controls. Traditional manufacturers
are exploring intelligent manufacturing approaches (Machine Learning/Artificial Intelligence,
Internet of Things, Digital Twin, etc.) to improve their competitiveness, but lack in implementing
them. This paper reviews the intelligent manufacturing approaches and extends a study on how
a manufacturing production plant applies its intelligence in executing these approaches to
transform from discrete manufacturing to intelligent manufacturing. The case study initiates the
implementation of Siemens manufacturing production plant into a model based on intelligent
manufacturing, thereby transforming the whole into an intelligent manufacturing industry. A
broadened path about the implementation of intelligent manufacturing in this industry is
outlined. In the operation of selecting these approaches, the manufacturing plant continuously
mechanizes its products, informatizes its management, and digitizes its operation.

1. Introduction
In today’s world, a very popular strategic topic known as Industry 4.0 initiated by the Germans has a
great influence on designing intelligent factories where the automation of manufacturing systems are
improvised and transformed by the Internet of Things (IoT), cloud computing, and cyber-physical
systems [1,2]. Industry 4.0 qualifies companies to compute the performance of their plants and machines
by making clever decisions via real-time communication with humans and machines to endlessly
advance their productivity [3]. Industry 4.0 fuses intelligent production procedures and automation of
production systems to open the way for a new era that will essentially alter the production and industry
supply chains, and line frameworks.
Within the aspects of the fourth industrial revolution, the present-day challenge is to expand
reconfigurable and collaborative manufacturing systems that control and support effectively few
batches, high quality and low costs, and product diversity by initiating different features of adaptation,
modularization, and agility [4]. Intelligent Manufacturing Systems (IMS) provides not only
reconfigurability and flexibility but also this abstraction brings more than a few ideas of software
intelligence definitions, which inspected attributes such as decentralization, autonomy, reliability,
flexibility, learning, efficiency, and self-regeneration [5,6]. IMS can yield the best results compared to
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution
of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
Published under licence by IOP Publishing Ltd 1
IRMAS 2021 IOP Publishing
Journal of Physics: Conference Series 1969 (2021) 012019 doi:10.1088/1742-6596/1969/1/012019

conventional manufacturing systems as they are effective in self-learning, analyzing, and detaining
complexities, which are also able to analyze and store huge amounts of data to obtain an escalated grade
of the product to minimize the cost of production while reducing the time-to-market.
Intelligent manufacturing (IM), one of its solving approaches is the development of big data analytics
which granted an opportunity in semiconductor manufacturing factories to improve Fault Detection &
Classification (FDC) system potentialities that lessen the missed and false alarms [7, 8]. Another solving
approach where IM is implemented is the Cyber-Physical Logistics Systems (CPLS) for gear
manufacturing factories that have organized their procedures following the flexible production
principles via this approach. The goal of the CPLS is to elevate flexible behavior through independent
decisions and authorize depletion of inventories due to the self-governing solving of errors
instantaneously. From research on computer simulation based on the current space of an electric train,
it has been observed that the number of cycles and number of loops driven in the cycle can be reduced
by 68% and 27% respectively [9]. One of the best application scenarios where IM is implemented is the
symbiotic human-robot collaboration [10,11] which is specified for a fenceless environment in which
profitability and effective utilization of resources can be upgraded by blending the accuracy of machines
and the flexibility of humans. Some human-robot coordination, where it holds the properties of dynamic
task planning, active collision advance, and adaptive robot control can be qualified by using Robotic
Cyber-Physical Systems (CPS). The method is to disclose safe halfway Human-Robot Collaboration
(HRC) without any fencing. Another application scenario where IM is implemented is a case company
that is a seller for the flight sector, which provides completely integrated solutions for inspection
systems. Starting from trading their video monitoring solutions to providing video storage and analysis
storage would be the most pivotal change for a company. To create an innovative solution, utmost
importance is given to check if services are being received by the market and its neighboring districts.
To achieve IM, the goal of an industry is to combine distributed manufacturing services to finish
complex tasks. Nevertheless, conventional manufacturers are investigating methods to build on their
competitiveness. IM key techniques appear to be the quick fix to accomplish their objectives but the
absence of guidance or instructions made them difficult to execute these techniques. For that reason,
this paper evaluates IM's key approaches by introducing a case study on Siemens manufacturing plant
which applies its intelligence in executing these approaches thus transforming the plant into an
intelligent manufacturer. The extending track of IM in the Siemens manufacturing plant is also outlined.

2. Key technologies and research areas of intelligent manufacturing

This segment evaluates a few essential techniques and their applications implemented in IM, considering
the Industrial Internet of Things (IIoT), Artificial Intelligence & Machine Learning (AI & ML), Big
Data Analytics, Digital Twin, and Cloud Computing as depicted in table 1.

2.1. Industrial Internet of Things (IIoT)

IoT is referred to as the use of smart or digital technologies in industries that help in analyzing various
system architectures, information processing, location, and other security problems with ease, which
requires minimal human interaction and broader connectivity and computing ability with various
devices [12-15]. Over the years it had witnessed a clear integration with Industry 4.0 where they had
differentiated computers, machines, Internet of Things on one side, and people who do intelligent
industrial operations with the help of data analytics for transforming individual and business outcomes
on the other side, which in whole together contributes to the IIoT [16]. So, in short, we could say that
whenever there is an involvement of IoT under the manufacturing process or being used for industrial
application, the term IIoT would be derived [17,18]. These are used in associating various industrial
activities/products such as power grids, connecting to clouds from a sensor by using a network, and
engines [19,20]. This finally focuses on optimizing the product, starting right from boosting its
productivity, being more efficient, reducing overall costs to moving forward, and adapting to various
changes in the present world.

2
IRMAS 2021 IOP Publishing
Journal of Physics: Conference Series 1969 (2021) 012019 doi:10.1088/1742-6596/1969/1/012019

2.2. Artificial Intelligence & Machine Learning (AI & ML)

AI is an approach where human intelligence is imitated, strengthened, or even replaced with the help of
computers by applying logic, decision trees, and ML. Autonomous intelligence systems have been found
out to be a vital development as there have been innovations and advancements in unmanned combat
vehicles, which easily excels the advanced technologies in robotics [21,22]. To improve a particular task
with time, few statistical techniques are applied, this is when ML comes into act making it a subset to
AI [23]. Deep learning comes in handy which would ease the investigating and processing of large
manufacturing data by providing enormous data analytic tools and focusing on the future requirements
for efficient and sustainable production. To check computer communication various tests were
considered and one such is the Turing test, which would tell up to what level machines could think,
involving a computer, examiner, and a machine placed at unique locations. Automation is always a key
factor that brings a change in manufacturing, which further contributes to intelligent technologies from
design to shipment [24-26]. Nowadays, there are various openings integrated with AI such as the internet
of things, cloud computing, to the latest 5G technology, which would promote decision making,
additional knowledge techniques, and concentrating on real-world problems thus contributing a lot to
intelligent manufacturing [27]. So, these intelligent behaviors with the help of AI and ML are integrated
into the conventional manufacturing systems ranging from determining the quality of product, process,
and product planning to delivery and also ensuring their competitiveness level with the present market.

2.3. Big Data Analytics (BDA)

Nowadays, with extreme growth over the internet and IoT data has become easily accessible and at the
same time, it's made available everywhere in various industries which led to the crises of big data [28].
Big data derives from devices, sensors, and also including social media feeds. Since the data
requirements were large, there arose a huge question if IoT could process the right data at the right time
despite growing advancement in IoT, this is where Big Data Analytics comes into play which involved
advanced analytic techniques to process large operations and data, especially in the manufacturing sector
[29-31]. The Centre for Intelligence Maintenance Systems has developed predictive analytics known as
the Watchdog Agent which has made sure that each processing of big data to be transformed into useful
information [32,33]. Even the cyber-physical system integrates with knowledge from data-driven
analytic algorithms and at the same time with a piece of practical knowledge, to simulate the conditions
of the machine with a 5S approach that comprises Synchronization, Sensing, Synthesis, Service, and
Storage. The big data analytics path is selected based on computational speed, operational-easy, cost of
investment, and other various updates [34]. These analytic techniques along with cyber-physical systems
are introduced, such that the manufactures would remain competitive in this predictive manufacturing
process by keeping up with the emerging technologies and products more efficiently and productively.

2.4. Digital Twin (DT)

A combined system that could compute, monitor, simulate, and also check system status and control
processes is termed Digital Twin (DT) [35-39]. Manufacturing systems can detect material processes,
create a DT in the everyday life [40], accept real-time information from the real world for analysis in a
computer simulation, and construct enlightened decisions through everyday communication and
collaboration with human beings. Zheng et al. [41] strongly believed that various trends can be obtained,
making it a vital analysis in the direction of IM, through drastic growth which can be seen in the field
of virtual technology and data acquisition. An IM structure by Zhou et al. [42] was drafted for building
up a conceptual DT manufacturing cell, through which it connects with prediction, optimization,
intelligent simulation, control, and various other perceptions. DT is a real-time digital representation of
a physical organization that not only ideally plots physical objects but also adjusts material objects based
on the design paradigm.

2.5. Cloud Computing (CC)

3
 IRMAS 2021 IOP Publishing
Journal of Physics: Conference Series 1969 (2021) 012019 doi:10.1088/1742-6596/1969/1/012019

Cloud computing is the delivery of accessible, computing power and data storage, which is acquired
remotely by the user through a system [43-47]. Through this, cloud manufacturing was introduced,
where a system-oriented manufacturing prototype was set up to reduce resource consumption along with
possible utilization to the extent [48,49]. Various cloud computing implementations in IM were studied
by Zhong et al. [50], along with Zhou et al. [51], from which cloud computing was selected to be the
most vital and prepared technology for IM. Everything from processing software to adjusted business
programs mapped out and expanded for an organization can probably achieve on a cloud system. Cloud
computing has been accepted with escalating competitiveness through higher flexibility, elasticity, cost
reduction, and proper resource utilization.

Table 1. Typical applications of key technologies.

Industries/
Key technologies companies Aims Improvements References
Industrial Internet of IIoT–enabled Combining Enhanced interpretation [20]
Things (IIoT) manufacturing domains and from users and improved
measurement, easing the performance
France interpretation of
sensor data.

Artificial Transportation, Formulating a new Solving the railway container [26]

Intelligence (AI) and China entropy-AI and ML station reselection problem
Machine Learning cloud-based approach
(ML)

Big Data Analytics Tata Motor, Driving quality and Analytics of CRM system data [31]
(BDA) India reducing cost in and utilizes process excellence
the manufacturing and six sigma principles
process

Digital Twin (DT) Transportation, Maximize the product Capacities of self-thinking, [42]
China quality and throughput decision-making and execution

Cloud Computing Manufacturing, Proposing a service- Adopting LAMMOD platform for [49]
(CC) Iran oriented approach distributed manufacturing agents

3. Case study

3.1. Background
From a small garage in a back cortile in Berlin to a global corporation. Siemens AG, a German company,
which was founded in 1966 is a global technology dominant for more than 170 years, which had excelled

4
IRMAS 2021 IOP Publishing
Journal of Physics: Conference Series 1969 (2021) 012019 doi:10.1088/1742-6596/1969/1/012019

in various fields like innovation, engineering, reliability, quality, and internationality. It had further
progressed to become the largest industrial manufacturing company in Europe with its branch offices
located abroad. Around the globe, Siemens turned out to be playing a vital role and showed active
involvement by focusing on areas ranging from intelligent infrastructure for buildings and distributed
energy systems; to automation and digitalization and manufacturing industries.
The integration capability and operational agility of industrial control, improving feasibility, strong
information modeling, execution systems, and associated processes by combining proven and affordable
system and software technology, and finally, the engineering paradigms which were all considered to
be the most important objectives or goal of Siemens AG.
From mobile telephones, diagnostic imaging systems, and hearing aids to numerous other products
such as ground movement radar for airfields, mass transit systems, and power generating equipment
were all witnessed as the company’s development during the early 21st century. Pumps and compressors,
drives for conveyor belts and rolling steel mills, heavy-duty motors, various automation equipment, and
gears for the wind turbine, were some of the automation and industrial plant-associated products that
Siemens had later focused on, but not limited to production machinery and raw material processing.
Along with these products, Siemens was sanctioned with various projects around the world starting from
its construction of 17 nuclear power plants in Germany to winning a $966.8 million contract from an oil
firm situated in Saudi Aramco, being the largest tender ever received by Siemens from any company
situated in Saudi for power plant components. Siemens Healthineers AG had also reported that acquiring
U.S. cancer devices and also software company Varian Medical Systems with complete stock estimated
at $16.4 billion was one of their major plans in August 2020.

3.2. IIoT – A framework of IoT in manufacturing

Figure 1. IIOT – An industry sector classification (Boyes H., 2018, p.12).

The business to business (B2B) approach being used in the current digital platforms is known as the
IIoT platforms forming a flexible and open network based on the industry sector classification depicted
in figure 1, keeping in mind the main objective of ease of integration over the generation of platform-
based advancement. Over the years, Mindsphere has obtained a leading industrial IoT position as facility
or service solutions. Ranging from edge to cloud with data collected over connected products, systems,
and plants to generate better quality products, for optimization purposes as well as to innovate new

5
IRMAS 2021 IOP Publishing
Journal of Physics: Conference Series 1969 (2021) 012019 doi:10.1088/1742-6596/1969/1/012019

business models and for doing this Mindsphere powers the IoT solutions by bringing in various advances
in the field of Analytics and AI. The first cloud-based systems on the open Internet of Things (IoT) were
introduced by Siemens with Mindsphere in 2016 which could show full connectivity of physical and
machine interface to the digital world. Several day-to-day challenges are being faced by industrial
decision-makers such as customers demanding their unique products, tougher competitions, and rapidly
changing technologies. These challenges can be solved by bringing in Siemens Mindsphere to make
appropriate decisions with transparency and also to concentrate on the digitalization approach. Steps
that are followed by Siemens Mindsphere in approaching a step closer to solve the real-life problems
are by analyzing and predicting/preventing from unplanned assets downtime; then by monitoring and
controlling solution which helps in optimizing the performance; then finally taking the digitalized
transformation by meeting out the needs and requirements of every customer on their unique products
and developing new business models. For creating time to appreciate industry investments and low code
applications which were only made possible as Mindsphere was built on Mendix, thus introducing global
IoT connectivity and categorization processes. It also plays a vital role in analyzing IoT data with
information from various systems such as SLM, PLM, MES, and so on. Not only that but also well
defined in the field of Closed-Loop Digital Twin by ensuring its perfectly functional while they also
collect live performance data from production lines. A case study on Mindsphere has been chosen for
reasons like technological integration on various fields at connected levels as well as for the open
integration among third parties. Here, a detailed analysis on identifying the partnership type and its need
along with the company type was discussed which led to knowledge about the development of Siemens’s
ecosystem and also to organize a logical generalization on IIoT ecosystems. Initially, there were only a
few boundary resources in the first two phases but with time other phases were seen to be engaging with
150 plus business resources-related actions. Siemens had also partnered with various resellers to
promote its gateway and IIoT. However, various partners by type such as consulting, software
technology, infrastructure, design, academics, end customer to name a few were organized in phases
and their total number of partnerships are calculated to find out in which field Mindsphere outshines the
other. During the late phase, 2 Siemens had a planned partnership with amazon by introducing
Mindsphere to be available on the AWS platform. After the release of Mindsphere 3.0, it had become
popular in more than six countries. Further study on comparable IIoT systems could bring out more
effectiveness in the development of IIoT ecosystems, whose results could be verified for the Mindsphere
ecosystem and its visualization [52]. Another astonishing factor that had evolved during this period is
the Siemens Digitalization Hub located in Singapore, which satisfies the requirements of customers in
Asia and beyond. It also brings in various multi-disciplinary specialists from various fields from
numerous business divisions in Siemens to innovate, learn and develop on future-ready and real-life
scenarios. To digitize their business Siemens provides urban infrastructure as it gives a reliable
efficiency and also integrates various cities to meet their challenges in the upcoming years; secondly,
oil and gas digital center where it not only focuses on the growth of the industry but also the cost,
productivity, reliability, and efficiency; then overall optimization and digitalization of the hub [53]. In
continuation with that Siemens had delegated its experienced heads as the City Account Managers in
the Siemens City Account initiative which suggest decision-makers in more than 60 cities to participate
in various phases right from the planning phase, to develop a city that is environment friendly, improved
quality of life for its residents and also on saving money. So, to fulfill all these purposes, Siemens
Mindsphere comes into play, that is the cloud-based system for IoT, to digitize its infrastructure.

3.3. AI & ML – An integrated view on factory automation

6
IRMAS 2021 IOP Publishing
Journal of Physics: Conference Series 1969 (2021) 012019 doi:10.1088/1742-6596/1969/1/012019

Figure 2. Machine learning- A vital role in IM (Wang L., 2019, p.618).

When we talk about machines and processes gaining knowledge from enormous volumes of data by
themselves it would be of more benefit as it would lead to greater optimization and this can be processed
by the means of introducing artificial intelligence. Artificial Intelligence entirely creates advanced
chances for flexibility, systematic production even if it is of highly customizable product or a complex
one that would be required for small batch production. Over the past 30 years, various research and
studies have been undergone in the field of AI through which a great boost in technology advancement
was observed in hardware, software, and enhanced data transmission and computing power. Artificial
intelligence is something where a machine would perform similar or same tasks as that assigned to
human beings requiring intelligence such as learning, problem-solving and analyzing. Integrating AI
with other advanced technologies in the industrial ecosystem has helped manufacturers gain a strong
foothold in the Industry 4.0 revolution [54]. This application of AI in normal industrial activities started
with language recognition to assist in logistics. For verified testing and predictive maintenance, Siemens
has got its solutions under its portfolios. Then evolved a time where AI and Industry 4.0 came hand in
hand, thus contributing to being more efficient, productive and also minimizing the energy
consumptions. Mindsphere was again the laying foundation for bringing AI into the industry. Machine
learning is one of the fundamentals for real intelligence on” Artificial Intelligence”, where computers
are trained in such a way that irregular data patterns are understood by them through which we expect
the computer to gain knowledge on these data or algorithms and perform tasks on their own. Whereas
deep learning, on the other hand, focuses on deep neural networks, that is to conclude, identify
connections, or make decisions it accesses data at several nodes simultaneously. This deep learning
would also help in solving complex problems without any guidance by the possibility of self-learning
algorithms. By implementing ML with a segment of AI we can collect up various data from sensors,
robots, smart tools and then followed by visualized knowledge and further on converting this knowledge
to actions as exhibited in figure 2. Though ML turns out to be a greater benefit in the customer service
field still it needs to improve a lot in terms of its algorithm as it lacks transparency and less funding. The
applications involving AI technology can be made more optimized and efficient by the use of ML
solutions. A case study on Siemens's implementation of AI for industries, power grids, and rail systems
has been taken up to show how far the impact of AI has contributed to the transformation in today’s
world. For improving the reliability in the power grid by making them technologically smarter and to
control various operational processes AI was used, which in turn enables the devices to restrain the
disturbances present in the grid. Siemens has also come in touch with Deutsche Bahn, where it focuses
on imminent conservation and modification/repair of high-speed trains, where various trends and data
from the train are obtained from software and data analysts [55]. The main purpose of using AI, in this
case, it helps in optimizing the control centers and it's more reliable. There are also other technologies

7
IRMAS 2021 IOP Publishing
Journal of Physics: Conference Series 1969 (2021) 012019 doi:10.1088/1742-6596/1969/1/012019

Siemens has implemented with various other large companies and industries, one such is with Amazon
in implementing Siemens Cybersecurity by using AWS Machine Learning where it can handle more
than 60000 threats per second. Here they had introduced Siemens Cyber Defense Center, whose main
objective is to secure its customers from malware, viruses, and various other forms of cybersecurity
threats or cybercrime [56]. Later, they had also given assurance that their AI-driven cybersecurity
platform was easily among the top and most needed in the world with the present increasing rate of
cybercrimes. Not only that Siemens also contributes to the success story of AI to a greater extent from
optimizing the emission to larger control to working on adjustable fuel valves to bring optimal state for
combustion under various circumstances of weather [57]. This technology witnessed a huge impact as
it had brought down labor costs, improved production speed, and a greater decline in product defects.
Machine learning, Artificial Intelligence, and its integration with Industry 4.0 are seen as a greater
impact in today's world as it is a powered technique where it improves various aspects of manufacturing.
Starting from design to delivery Siemens focuses on every aspect through which it could find solutions
to various real-life problems that have been thrown to the world.

3.4. Integrated Automation (TIA) – An intelligent portal for efficient industry planning

Figure 3. Watchdog agent - A predictive analytics on IM systems (Lee J., 2006, p.489).
Industry 4.0 plays a crucial role in its development which was brought into life through Siemens’
strengths in industrial automation. This is the time when Siemens had launched its “Totally Integrated
Automation” (TIA) Portal during the late 1990s which enabled the companies to coordinate for their
production operation also being interrelated to hardware with software. TIA Portal had proved itself to
be something greater than just an engineering framework by bringing together innovative simulation
tools, transparent plant operation, and integrated engineering by focusing on increased speed, flexibility,
and productivity. When it comes to increasing the flexibility, it talks about increasing the scalable
simulation of the entire plant including Human-Machine Interface, having an open system to create a
systematic program code and also to store TIA Portal projects in the Teamcenter, and finally, the cloud
solutions where there is a networked workflow keeping in mind about maintaining the total data
consistency contributing to the overall digital workflow. The main reason behind TIA being called the
heart of efficient automation is that it reduces our engineering time with highly accessible applications

8
IRMAS 2021 IOP Publishing
Journal of Physics: Conference Series 1969 (2021) 012019 doi:10.1088/1742-6596/1969/1/012019

such as SIMATIC S7-1500R/H CPUs; hardware diagnostics and network integration to integration of
SINAMICS S210 into SIMATIC Microdrive, etc. Also, coordinated teamwork, overcoming faults, and
reduction of time add up to the above are the major reasons that stand with various companies to rely
on Multiuser engineering through TIA Portal. A typical case study is Audi AG, a German automobile
manufacturer that initiated its production of Audi A8 where it had been observed that when Siemens
TIA had been implemented there has been a drop of more than 10 percent in the engineering costs. Also
utilizing TIA's major advantage of handling efficiently and reducing downtime by assuring information
being delivered to central control systems by individual control systems. One of Audi’s factories in
Neckarsulm had about a 25 percent reduction in energy in 2018 which ultimately focuses on boosting
productivity. Moving on to the Kuka Systems situated in Brazil is a global provider of plant and system
technology. This factory concentrates on solutions for logistics as well as optimizing robot workstations
by producing higher numbers of units as well as giving us a definitive robot integration [58]. Considering
the aerospace industry, a huge amount of assembly space is needed for large objects like rockets and
aircraft, when the traditional docking method was being used it resulted in a long manufacturing cycle,
poor reliability, and low accuracy. This challenge was overcome by introducing a coordinate system
developed by Siemens PLC to control Kuka robots dynamically via the KUKA-TIA-Library interface
by fulfilling the needs and requirements of customization and flexibility in the aerospace industry. To
obtain the above interface various applications and configuration of Kuka.PLC.mxAutomation was
studied to transform programming steps of PLC to KRL language of KUKA robot, also focusing on the
TIA Portal for the control of the KUKA robot [59]. Even the world’s largest automated seamless pipe-
making plant, Tenaris situated in the USA depends on Siemens portfolio. They had utilized the TIA
Portal code and Siemens gear in building a 3d model of the plant by testing all the components even
before installation, that is, during their simulation process. By this, Tenaris was able to come across
several adjustments and also stated that a huge amount of their time was saved, also increased quality
and efficiency by integrating with the help of TIA Portal thus opening their plant on time. Every time a
unique problem emerges TIA portal expands itself to obtain ideas and innovations from various
technologies such as augmented reality, artificial intelligence, edge computing also including the latest
5G technology. Thus, the TIA portal acts as a watchdog predictive agent which marks its way by
becoming perfect access to automation in a digital enterprise with space for future innovations and
makes sure that each processing of big data can be transformed into valued information as displayed in
figure 3.

3.5. Digital Twin – A holistic PLM software approach

9
IRMAS 2021 IOP Publishing
Journal of Physics: Conference Series 1969 (2021) 012019 doi:10.1088/1742-6596/1969/1/012019

Figure 4. Bausch + Ströbel’s manufacturing plant – Efficient way to create a digital twin (Source:
Machine Design, March 2019).
In the current world, most complicated products and processes are outlined, tested, and adjusted in the
virtual community before being manufactured in the physical world. Prototype calibration involves
creating and computer-simulating software models of hereafter products, finally leading to the formation
of “digital twins”. Digital twins (DT) are used all over the product lifecycle to predict, simulate, and
optimize the product and manufacturing system before funding physical assets and prototypes. Overall,
there are three kinds of DT – Product, Production, and Performance and are explained for case study
applications. In the case of digital product twin, a typical application is a motorized equipment
manufacturing plant by Siemens which used DT as part of its digital enterprise-broad initiative to
improvise corporate decision-taking by converting data into practical insight. They used these
potentialities to precisely predict failure modes to minimize, spontaneous downtime of apparatus while
in service. The company knew the source of some of the failures but wanted to uncover extra patterns
to recognize causal factors of failure. An experimental project was able to expand models to precisely
predict one-third of failures in machines occurring during manufacturing time longer than 8 hours in the
progress of the event and 7% of failures in machines occurring during manufacturing within 2-8 hours
in the progress of the event. In the case of digital production twins, a worldwide auto manufacturer used
precise models to make suitable manufacturing adjustments to meet close tolerances. This company's
managers had a circumstantial understanding of which variables were tied to issues in the quality of the
product in the company’s cylinder-head production line, but insufficient information to change it. Using
digital twins of the associated processes and production lines, manufacturing quality analysts can run
longer than 500 production-line variables through ominous models. This solution recognizes which
particular processes of the line need to be modified to ensure that products remain within their close
tolerances. The solution also provides ominous insights about which manufacturing assets should be
obstructively maintained to avoid hereafter problems. In the case of digital performance twin, a mining
equipment manufacturer needed to find a way to authorize its engineers to initiate preventive, rather
than responsive, maintenance. Break from unpredicted failure in equipment or unwanted scheduled
maintenance is expensive to companies involved in mining activities. Hence, a new diagnostic
optimization solution that models performance in equipment allows the equipment-suited mining
manufacturer to assist its operators to spot possible problems related to maintenance before the failure

10
IRMAS 2021 IOP Publishing
Journal of Physics: Conference Series 1969 (2021) 012019 doi:10.1088/1742-6596/1969/1/012019

of equipment, thus preventing unwanted downtime for unneeded maintenance. The solution recognized
irregularities in the collection of data from sensors on the heavy equipment that might specify impending
or future problems, giving engineers time to carry out protective maintenance.
Bausch + Ströbel’s manufacturing plant in Germany is following a digital conversion plan with
digital twins at their center. Bausch + Ströbel concentrates on machines for drug companies to fill and
collect the most sensitive material like bottles, ampules, and syringes. Previously, the manufacturer has
used commissioned wood models to design, experiment with the function and usefulness of their
machines. In collaboration with Siemens, they developed a virtual portrayal of the factory in generating
a digital twin platform as depicted in figure 4. It provides various benefits throughout the complete
production cycle: from manufacturing planning to observational operations, analyzing faults, and
increasing the innovation of systems and plants.
Hence, lengthening and integrating various digital twin views will allow companies to better govern
their processes and products over their complete lifecycle, bringing value to the customers and their
companies. Executing a scalable, holistic digital twin requires the cooperation of the service providers,
software providers, and end customers. This transition can take place in a gradual payback framework
where certain use cases are recognized and teamwork projects are built and implemented.

3.6. Industrial Edge - A perspective on cloud & edge computing

Figure 5. Schmalz Siemens Industrial Edge system – Edge and cloud computing systems according to
specific requirements (Source: Industrial Edge, the SIEMENS Edge Computing Platform
[Architectural concept – Overview]).
The escalating layout of related Industry 4.0 and digitalization are influencing our personal lives yet
having an even huge impact on companies. This is presenting obstacles to the transforming industry,
such as small innovation cycles and the accelerating product individuality and manufacturing processes.
To perfect these obstacles and remain ruthless, companies must be able to react to flexible changes as
much as possible. With implementing Industrial Edge, everything is easier, more secure, and more

11
IRMAS 2021 IOP Publishing
Journal of Physics: Conference Series 1969 (2021) 012019 doi:10.1088/1742-6596/1969/1/012019

flexible – for ideal use of data in the field. Complete networked manufacturing and fast transforming of
the created data are crucial here – and this is where cloud and edge computing comes into action. Edge
Computing (EC) and Cloud Computing (CC) cites the latest model in computing that examines as well
as operates a part of information utilizing the computing, storage, and resources related to networks
dispensed on the pathways connecting the origin of data and the center of CC [60]. The implementation
of edge and cloud computing in a manufacturing production plant, mainly integrated with actual
transmission technology’s network and NFV technology, could set up an excellent network connection
linking the cloud platform and the industrial field cloud as well as the platform in edge computing,
achieving flexibility, provide intelligent real-time secure isolated application deployment capabilities
and best-assured manufacturing plant production network with the services of edge computing [61]. A
classic application of edge computing is, Siemens electronics factory in Germany which manufactures
about 16 million controllers yearly for industrial automation objectives where 75% of the value chain is
mechanized. Nilsen and Nyberg [62] described the Siemens Electronics plant from interviews that they
use a factory execution system, which enables the complete factory to be connected. On the usage of
data analytics and sensors, they allow efficient manufacturing with better quality. On implementing the
high level of automation, Siemens has minimized the no. of faults in their manufacturing smart factory
from 500 errors per one million actions (DPM) to 12 DPM. Siemens strengthens its Edge Management
System (EMS) to reduce breaks of individual machines and complete assembly lines at the same time,
which helps to deployment in speed, escalating efficiency, and eventually ROI across all applications in
the factory. Formulated on this system, the teaching of brand-new algorithms can happen in the cloud
going ahead, while the deployment of application at the edge platform promises industrial-grade
reliability of applications, data sovereignty, and flexibility to any network issues [63]. Another typical
application in edge computing is the Siemens Schmalz in Germany, which is the market head in vacuum
automation and ergonomic handling systems. The mechatronic vacuum grippers from Schmalz allow
robots and other industrial automation systems to hold wide-ranging of various workpieces throughout
the manufacturing and logistics process. Different varieties of components such as metal, wood, plastic,
or glass are tightly fixed and controlled with these vacuum grippers. To avoid unpredicted downtime
due to dirty filters and the aging of gripping devices, Schmalz implemented condition monitoring
solutions for both areas according to requirements shown in figure 5. This will allow Schmalz to forecast
downtimes in advance to program organized maintenance activities. Schmalz strengthens for these
applications a combined application lifecycle management system, which runs at the edge platform.
This is most important because Schmalz is considering supplementing further applications to the system
over time. Hence, manufacturing edge and cloud computing platform offers data as well as management
networks which utilizes a delicate interface and approach enterprise-level guidance to distantly upgrade,
supervise and preserve a huge no. of devices and approaches for distant monitoring as well as
configuration. Additionally, it could desensitize with cleaning the gathered information to certify the
accessibility of data thereby the careful data won’t be escaped with integrated contributed tight key
authentication as well as firm booting to offer a reliable domain for production networks.

3.7. Siemens: An Intelligent Manufacturing Factory

12
IRMAS 2021 IOP Publishing
Journal of Physics: Conference Series 1969 (2021) 012019 doi:10.1088/1742-6596/1969/1/012019

Figure 6. Siemens structural diagram of IM standard system. A, B, C are the codes in the IMSA;
HMI: Human–Machine Interface (Source: National intelligent manufacturing standard system
construction guidelines 2018).
Siemens implemented intelligent manufacturing solutions that combine manufacturing data and
processes with engineering in a digital thread offering a lot of benefits to the manufacturers and
engineers. It is a digitalized developed plan that surrounds everything from PCB blueprint to
optimization of the factory floor in including feedback of customers into brand-new designs. The entire
enterprise can collaborate with the Digital Twin of the process and production system. Innovation is
risen by linking through the digital thread to effectively design, computer-simulate, adjust and verify all
production processes before the creation of a physical production system. This helps to synchronize
manufacturing, engineering, production, and service operations for maximizing production efficiency
and smooth launches of the design. One of the fascinating projects that NAVAIR and Siemens have
tackled is executing a model-based digital thread that directly assists intelligent manufacturing at the
light readiness centers in the US. Naval Air Systems Command (NAVAIR) and is responsible for the
sustainment and acquisition of the air assets of the Navy. The focus has been on the arrangement of data
management from engineering through computer simulations and production operations. The aim is to
have manufacturing operations at the air depots directly assist conservation of those air assets and
ultimately come up with operational accessibility of the uptime of those air assets. In the event of
NAVAIR, that digital thread is being enlarged to modern types of equipment in manufacturing at the
Cherry Point Fleet Readiness Center. This guarantees that the right manufacturing operations are taking

13
IRMAS 2021 IOP Publishing
Journal of Physics: Conference Series 1969 (2021) 012019 doi:10.1088/1742-6596/1969/1/012019

place with detectability back through engineering and planning with an understanding of what data was
used at any given point of that product lifecycle. Being able to essentially manufacture these parts more
skillfully, with higher quality, has a direct impact on the accessibility and the uptime of those air assets.
Another typical example of intelligent manufacturing is the case study of Naval Sea Systems Command
(NAVSEA) who were outlined to manufacture and produce submarines and surface ships, but their
mission has changed because the Navy no longer manufactures equipment. The current goal is to
preserve equipment that has been transported to them by the primary equipment manufacturer. Siemens
is leading a team that is in charge of the digital modeling of these shipyards. The models are helping
PMS 555 understand what happens when a submarine or surface ships, fleet, or carrier readiness center
comes into one of these Navy bases, providing insight into how the bases function.
Hence, IMS enables you to close the loop between your manufacturing process and engineering planning
operations, and your actual manufacturing and quality execution operations on the production
conservative floors. It guarantees that all the rich data that is gathered – any discrepancies or
deficiencies, positives or negatives – feeds back into the digital threads along with the digital twin. This
enables you to disrupt and innovate, not just based upon failures, but also based upon successes of how
you manufacture and support your assets. A detailed layout of the Siemens IM standard system is
presented in figure 6 about the IMSA construction guidelines for the development of the Siemens plant.

4. Conclusion
As growing awareness is identified to the fourth industrial revolution, IM is increasingly a major concept
in the development of the present-day economy and industry. IM is examined to be a lead viewpoint in
the future, both application and experimentation, as such a thing offers aid to different systems and
prototypes by putting in advanced innovations to conventional prototypes in production and services.
Key techniques, extensive innovative technologies, and global approaches are outlined in this research.
The case study initiates the implementation on how Siemens manufacturing plant presents the IM
concept, thereby transforming the whole into an intelligent manufacturing industry. In the operation of
selecting these approaches, the manufacturing plant continuously mechanizes its products, informatizes
its management, and digitizes its performance. We desire that the current study can inspire and inform
researchers along with industrial professionals to come up with ideas in progressing the production
industries. Besides, we believe the different approaches presented in this study will arouse exclusive
proposals in the attempt to grasp the much-expected Industry 4.0.

References
[1] Crnjac M, Veza I and Banduka N 2017 From concept to the introduction of industry 4.0 Int. J.
Industrial Engineering and Management 8 pp 21–30
[2] Rojko A 2017 Industry 4.0 concept: Background and overview Int. J. Interactive Mobile
Technologies 11 p 77
[3] Gruber F E 2013 Industry 4.0: A best practice project of the automotive industry Digital Product
and Process Development Systems 411 pp 36–40
[4] Peschl M, Link N, Hoffmeister M, Gonçalves G and Almeida F L F 2011 Designing and
implementation of an intelligent manufacturing system J. Industrial Engineering and
Management 4 pp 718–45
[5] Mekid S, Pruschek P and Hernandez J 2009 Beyond intelligent manufacturing: A new generation
of flexible intelligent NC machines Mechanism and Machine Theory 44 pp 466–76
[6] Shen W, Hao Q, Yoon H J and Norrie D H 2006 Applications of agent-based systems in intelligent
manufacturing: An updated review Advanced Engineering Informatics Advanced Engineering
Informatics 20 pp 415–31
[7] Moyne J, Samantary J and Armacost M 2016 Big data capabilities applied to semiconductor
manufacturing advanced process control IEEE Transactions on Semiconductor Manufacturing
29 pp 283–91
[8] Moyne J, Schulze B and Iskandar J 2016 Next-generation advanced process control: Leveraging

14
IRMAS 2021 IOP Publishing
Journal of Physics: Conference Series 1969 (2021) 012019 doi:10.1088/1742-6596/1969/1/012019

big data and prediction 27th Annual SEMI Advanced Semiconductor Manufacturing Conf.
(ASMC) Saratoga Springs NY USA pp 191–96
[9] Thoben K D, Wiesner S and Wuest T 2017 Industrie 4.0 and smart manufacturing – A review of
research issues and application examples Int. J. Automation Technology 11 pp 4–19
[10] Wang L, Törngren M and Onori M 2015 Current status and advancement of cyber-physical
systems in manufacturing J. Manufacturing Systems 37 pp 517–27
[11] Surdilovic D, Schreck G and Schmidt U 2010 Development of collaborative robots (COBOTS)
for flexible human-integrated assembly automation Proc. ISR/ROBOTIK 1 pp 1–8
[12] Boyes H, Hallaq B, Cunningham J and Watson T 2018 The industrial internet of things (IIoT):
An analysis framework Computers in Industry 101 pp 1–12
[13] Dorsemaine B, Gaulier J P, Wary J P, Kheir N and Urien P 2015 Internet of things: A definition
& taxonomy 9th Int. Conf. on Next Generation Mobile Applications, Services, and
Technologies Cambridge UK pp 72–77
[14] Rose K, Eldridge S and Chapin L 2015 The internet of things: An overview [Internet] The
Internet Society (ISOC) https://www.internetsociety.org/wp-content/uploads/2017/08/ISOC-
IoT-Overview-20151221-en.pdf
[15] Satyavolu P, Setlur B, Thomas P and Iyer G 2014 Designing for manufacturing’s internet of things
[Internet] Cognizant Report, https://www.cognizant.com/InsightsWhitepapers/Designing-for-
Manufacturings-Internet-of-Things.pdf
[16] Tseng M, Edmunds T and Canaran L 2018 Introduction to edge computing in IIoT [Internet] An
Industrial Internet Consortium White Paper (Edge computing Task group) ed Mellor S
https://www.iiconsortium.org/pdf/Introduction_to_Edge_Computing_in_IIoT_2018-06-
18.pdf?utm_source=IIoT-World.com.com&utm_medium=iiot-world.com/news/
[17] Aberle L 2015 A comprehensive guide to enterprise IoT project success [Internet]
https://internetofthingsagenda.techtarget.com/essentialguide/A-comprehensive-guide-to-
enterprise-IoT-project-success
[18] World Economic Forum 2015 Industrial internet of things: Unleashing the potential of connected
products and services World Economic Forum Industrial Internet Report
http://www3.weforum.org/docs/WEFUSA_IndustrialInternet_Report2015.pdf
[19] Helmiö P 2017 Open source in industrial internet of things: A systematic literature review
Master’s Thesis School of Business and Management Lappeenranta University of Technology,
Finland p 21
[20] Gyrard A, Datta S K, Bonnet C and Boudaoud K 2015 Cross-domain internet of things application
development: M3 framework and evaluation Proc. of the 3rd Int. Conf. on Future Internet of
Things and Cloud Rome, Italy pp 9–16
[21] Pan Y 2016 Heading toward artificial intelligence 2.0 Engineering 2 pp 409–13
[22] Li W, Wu W, Wang H, Cheng X, Chen H, Zhou Z and Ding R 2017 Crowd intelligence in AI 2.0
era Frontiers of Information Technology & Electronic Engineering 18 pp 15–43
[23] Wang B, Tao F, Fang X, Liu C, Liu Y and Freiheit T 2020 Smart manufacturing and intelligent
manufacturing: A comparative review Engineering (in press)
[24] Oztemel E 2010 Intelligent manufacturing systems Artificial Intelligence Techniques for
Networked Manufacturing Enterprises Management pp 1–41
[25] Wang J, Ma Y, Zhang L, Gao R X and Wu D 2018 Deep learning for smart manufacturing:
Methods and applications J. Manufacturing Systems 48 pp 144–156
[26] Huang W, Shuai B, Wang L, Antwi E 2017 Railway container station reselection approach and
application: Based on the entropy-cloud model Mathematical Problems in Engineering pp 1–
14 8701081
[27] Wang L 2019 From intelligence science to intelligent manufacturing Engineering 5 pp 615–18
[28] Manyika J, Chui M, Brown B, Bughin J, Dobbs R and Roxburgh C 2011 Big data: The next
frontier for innovation, competition, and productivity McKinsey Global Institute (MGI) Report
https://www.mckinsey.com/~/media/McKinsey/Business%20Functions/McKinsey%20Digit

15
IRMAS 2021 IOP Publishing
Journal of Physics: Conference Series 1969 (2021) 012019 doi:10.1088/1742-6596/1969/1/012019

al/Our%20Insights/Big%20data%20The%20next%20frontier%20for%20innovation/MGI_bi
g_data_full_report.pdf
[29] Lee J, Lapira E, Bagheri B and Kao H 2013 Recent advances and trends in predictive
manufacturing systems in the big data environment Manufacturing Letters 1 pp 38–41
[30] Barton D and Court D 2012 Making advanced analytics work for you. Harvard Business Review
90 pp 78–83
[31] Agarwal R and Weill P 2012 The benefits of combining data with empathy MIT Sloan
Management Review 54 pp 35–41
[32] Lee J, Ni J, Djurdjanovic D, Qui H and Liao H 2006 Intelligent prognostics tools and e-
maintenance Computers in Industry 57 pp 476–89
[33] Lee J, Wu F, Zhao W, Ghaffari M, Liao L and Siegel D 2014 Prognostics and health management
design for rotary machinery systems—Reviews, methodology, and applications Mechanical
Systems and Signal Processing 42 pp 314–34
[34] Brown B, Chui M and Manyika J 2011 Are you ready for the era of ‘big data’? McKinsey
Quarterly
https://www.mckinsey.com/~/media/McKinsey/Business%20Functions/Strategy%20and%20
Corporate%20Finance/Our%20Insights/Are%20you%20ready%20for%20the%20era%20of
%20big%20data/Are%20you%20ready%20for%20the%20era%20of%20big%20data.pdf?sh
ouldIndex=false
[35] Tao F, Cheng J, Qi Q, Zhang M, Zhang H and Sui F 2018 Digital twin-driven product design,
manufacturing, and service with big data Int. J. Advanced Manufacturing Technology 94
3563–76
[36] Tao F, Zhang M, Cheng J and Qi Q 2017 Digital twin workshop: a new paradigm for a future
workshop Computer Integrated Manufacturing Systems 23 pp 1–9
[37] Uhlemann T H J, Lehmann C and Steinhilper R 2017 The digital twin: realizing the cyber-
physical production system for industry 4.0 Procedia CIRP 61 335–40
[38] Glaessgen, Edward H and Stargel D S 2012 The digital twin paradigm for future NASA and US
air force vehicles 53rd Structures, Structural Dynamics, and Materials Conf.: Special Session
on the Digital Twin USA 20120008178
[39] Schleich B, Anwer N, Mathieu L and Wartzack S 2017 Shaping the digital twin for design and
production engineering CIRP Ann 66 pp 141–44
[40] Wang S Y, Wan J F and Zhang D Q 2016 Towards smart factory for Industry 4.0: a self-organized
multi-agent system with big data-based feedback and coordination Computer Networks 101
pp 158–68
[41] Zheng Y, Yang S and Cheng H 2019 An application framework of digital twin and its case study
J. Ambient Intelligence and Humanized Computing 10 pp 1141–53
[42] Zhou G, Zhang C, Li Z, Ding K and Wang C 2020 Knowledge-driven digital twin manufacturing
cell towards intelligent manufacturing Int. J. Production Research 58 pp 1034–51
[43] Liu Y and Xu X 2017 Industry 4.0 and cloud manufacturing: a comparative analysis J.
Manufacturing Science and Engineering 139 034701
[44] Zhang L, Luo Y, Tao F, Li B H, Ren L and Zhang X 2014 Cloud manufacturing: a new
manufacturing paradigm Enterprise Information Systems 8 pp 167–87
[45] Wu D, Rosen D W, Wang L and Schaefer D 2015 Cloud-based design and manufacturing: a new
paradigm in digital manufacturing and design innovation Computer-Aided Design 59 pp 1–14
[46] Xu X 2012 From cloud computing to cloud manufacturing Robot Computer Integrated
Manufacturing 28 pp 75–86
[47] Li B H, Zhang L, Wang S L, Tao F, Cao, J W and Jiang, X D 2010 Cloud manufacturing: a new
service-oriented networked manufacturing model Computer Integrated Manufacturing
Systems 16 pp 1–7
[48] Tao F, Zhang L, Venkatesh V C, Luo Y and Cheng Y 2011 Cloud manufacturing: a computing
and service-oriented manufacturing model Proc. Institution of Mechanical Engineers, Part B

16
IRMAS 2021 IOP Publishing
Journal of Physics: Conference Series 1969 (2021) 012019 doi:10.1088/1742-6596/1969/1/012019

J. Engineering Manufacture 225 pp 1969–76

[49] Valilai O F and Houshmand M 2013 A collaborative and integrated platform to support
distributed manufacturing systems using a service-oriented approach based on the cloud
computing paradigm Robotics and Computer-Integrated Manufacturing 29 pp 110–27
[50] Zhong R Y, Xu X, Klotz E and Newman S T 2017 Intelligent manufacturing in the context of
Industry 4.0: A review Engineering 3 pp 616–30
[51] Zhou J, Li P, Zhou Y, Wang B, Zang J and Meng L 2018 Toward new-generation intelligent
manufacturing Engineering 4 pp 11–20
[52] Hyrynsalmi S, Suoranta M, Duc A N, Tyrväinen P and Abrahamsson P 2019 Software Business
Proc. 10th Int. Conf., ICSOB Jyväskylä, Finland
[53] Siemens AG 2017 Siemens partners with singapore to establish its first fully-integrated
digitalization hub [Internet] Siemens Press Release Report Munich PR2017070365COEN
https://assets.new.siemens.com/siemens/assets/api/uuid:eb1b4fb0-a85d-4e34-93e3-
3c0e49618075/PR2017070365COEN.pdf
[54] Frost and Sullivan 2018 Artificial intelligence in the shop floor [Internet] A Frost & Sullivan
White Paper https://new.siemens.com/global/en/products/automation/topic-areas/tia/future-
topics/whitepaper-shopfloor-ai.html
[55] Roland B 2018 Artificial intelligence: Optimizing industrial operations [Internet]
https://new.siemens.com/global/en/company/stories/research-technologies/artificial-
intelligence/artificial-intelligence-optimizing-industrial-operations.html
[56] Pospisil J 2019 Siemens handles 60,000 cyber threats per second using AWS machine learning
[Internet] https://aws.amazon.com/solutions/case-studies/siemens-cybersecurity
[57] Walker J 2019 Machine learning in manufacturing –Present and future use-cases [Internet] emerj
https://emerj.com/ai-sector-overviews/machine-learning-in-manufacturing/
[58] Siemens 2016 Siemens Totally Integrated Automation (TIA) can reduce engineering time for car
manufacturers [Internet] ARC Advisory Group https://www.arcweb.com/blog/siemens-totally-
integrated-automation-tia-can-reduce-engineering-time-car-manufacturers
[59] Dechao Zheng, Rui Gu, Kai Chang and Jian Yin 2019 Research and development of high
precision robot automatic docking system based on mix automation IOP Conf. Series: J.
Physics: Conf. Series 1267 012100
[60] Weisong Shi, Jie Cao, Quan Zhang, Youhuizi Li and Lanyu Xu 2016 Edge computing: Vision
and challenges IEEE Internet of Things Journal 3 pp 637–46
[61] Tie Qiu, Jiancheng Chi, Xiaobo Zhou, Zhaolong Ning, Mohammed Atiquzzaman and Dapeng
Oliver Wu 2020 Edge computing in industrial internet of things: Architecture, advances, and
challenges IEEE Communications Surveys & Tutorials 22 pp 2462 – 88
[62] Samuel N and Eric N 2016 The adoption of industry 4.0 technologies in manufacturing – a
multiple case study Master of Science Thesis KTH Industrial Engineering and Management
SE-100 44 Stockholm p 79
[63] Siemens and PAC 2020 Impact of edge computing on discrete manufacturing –considerations for
agile industrial application management [Internet] Siemens Edge White Paper ed Vogt A
https://new.siemens.com/global/en/products/automation/topic-areas/industrial-edge/siemens
edge-white-paper-teknowlogy.html

17