Research Proposal

1. Proposal Title
Enhancing construction management through an integrated BIM platform

2. Introduction
Construction schedule management and construction safety management are two critical aspects
of project execution and play a pivotal role in the successful completion of construction projects.
By effectively managing construction schedules, project stakeholders can optimize resource
allocation, control costs, mitigate risks, foster coordination, and ultimately enhance client
satisfaction. At the same time, some work’s safety accidents have a bad influence on schedule
mangement. The high number of annual safety accidents and casualties reflects the problems of
slow detection of safety accidents and untimely early warnings in current construction safety
management, and China urgently needs new methods and technologies to improve the schedule
and safety management efficiency of the construction industry. However, there are fewer
achievements in the use of new technologies for intelligent construction schedule and safety
management, and most of the research focuses on intrusion detection and specific event alarms,
which cannot be well implemented for systematic early warning functions.

In recent years, the architecture, engineering, and construction industry has witnessed a
transformative shift with the adoption of Building Information Modeling (BIM). BIM technology
enables the simulation of the entire construction process and facilitates the monitoring of
construction progress. However, a limitation of BIM models is their static nature, as they are
detached from the dynamic on-site conditions, which hinders regular and accurate monitoring of
construction progress. Some researchers have explored the use of point cloud reconstruction
techniques and oblique photography methods to continuously update the construction status.
However, challenges arise when personnel and construction equipment obstruct the captured
images, leading to difficulties in achieving optimal model reconstruction and accurate assessment
of construction progress. Consequently, these limitations adversely affect decision-making
processes.

Based on the existing research and the characteristics of early warning scenarios, this study
introduces the integration of Building Information Modeling (BIM) with real-time data from deep
learning (DL) and computer vision (CV) technology presents a powerful paradigm for applications
to improve construction and operational efficiencies. Meanwhile the data from camera could be
used to unsafe behaviour casued by workers and alarm them in time.

3. Research Problems
Problems:
(a) The reconstruction of construction sites using computer vision techniques is often vulnerable
to interference from construction personnel and equipment, such as scaffolding and concrete
mixers.

(b) At each modeling and safety monitor aspect within the process of construction, there are
related software tools to perform the required works. Nevertheless, nowadays, no tool
 integrates the functionalities of the previously described modeling software in each aspect to
accomplish the all-process construction modeling and safety monitor.

Aims:
(a) Optimize the results of 3D point cloud reconstruction from oblique photography by
leveraging deep learning techniques.

(b) Facilitate timely detection of safety issues by integrating other technologies. The integration
of a multi-physical integration model enables accurate representation and analysis of the real
state and behavior of physical products in their respective environments. This approach
allows for the assessment of functions and performance of physical products in a virtual
environment, potentially replacing the need for physical prototypes. Moreover, it addresses
the limitations of traditional methods, where each physical characteristic is individually
analyzed without considering their interdependencies. Additionally, this approach offers the
potential to predict the health status and remaining lifespan of the product.

4. Methodology
To ensure effective monitoring of construction project progress, a methodology combining oblique
photography and BIM technology was proposed. The methodology involved the following steps:

(a) Construction Site Information Collection: The methodology involved the rapid collection of
information data from the construction site using oblique photography techniques, enabling
the construction of a 3D real scene model. Additionally, a deep learning model, trained on a
significant number of cases, was utilized to optimize the point cloud model. The collected
images from oblique photography were also employed to identify any unsafe acts.

(b) Project Schedule BIM Model Construction: A project schedule BIM model was constructed
using BIM technology, simulating the construction process based on the construction
schedule.

(c) Construction Progress Analysis: A construction progress analysis plug-in was developed on
the platform. This plug-in incorporated algorithms for matching, segmentation, and
calculation between the 3D real scene model and the BIM model. These analyses facilitated
the generation of a construction progress sheet, which was then compared with the project
schedule BIM model to provide a visual representation of any deviations in the construction
schedule. This enabled construction management personnel to promptly monitor construction
progress and identify potential safety problems.

In the future, the potential integration of internet-based technologies and augmented reality (AR)
could further enhance the management of worker-induced unsafe acts.

5. Outcomes
The platform offers several significant advantages:
(a) Enhanced Point Cloud Quality through Deep Learning: Deep learning techniques are
employed to improve the quality of the point cloud data.

(b) Real-time Control: During construction projects, real-time analysis of constructing process
data enables effective control over the quality and progress of construction. Additionally,
real-time analysis of image data allows for monitoring the safe problems on construction site.

(c) Bridging the Gap from BIM to Digital Twin: Building Information Model (BIM) is
essentially a static modeling approach that requires additional data and technologies to
realize more ambitious goals, such as digital twin. This study focuses on bridging some gaps
between BIM and real-world construction projects to facilitate comprehensive
interdisciplinary integration.

6. Reference
Chen, G., Chen, J., Tang, Y., Li, Q. and Luo, X. (2022) Identifying Effective Collaborative Behaviors in
Building Information Modeling–Enabled Construction Projects. Journal of Construction Engineering
and Management 148(6).
Chong, H.-Y., Lee, C.-Y. and Wang, X. (2017) A mixed review of the adoption of Building Information
Modelling (BIM) for sustainability. Journal of Cleaner Production 142, 4114-4126.
Ghaffarianhoseini, A., Tookey, J., Ghaffarianhoseini, A., Naismith, N., Azhar, S., Efimova, O. and
Raahemifar, K. (2017) Building Information Modelling (BIM) uptake: Clear benefits, understanding its
implementation, risks and challenges. Renewable & Sustainable Energy Reviews 75, 1046-1053.
Jiang, F., Ma, L., Broyd, T. and Chen, K. (2021) Digital twin and its implementations in the civil
engineering sector. Automation in Construction 130.
Kim, Y.-S., Lee, J.Y., Yoon, Y.-G. and Oh, T.-K. (2022) Effectiveness Analysis for Smart Construction
Safety Technology (SCST) by Test Bed Operation on Small- and Medium-Sized Construction Sites.
International Journal of Environmental Research and Public Health 19(9).
Liu, M., Luo, X., Wang, G. and Lu, W.-Z. (2023) Intelligent information extraction from government
on-site inspection reports of construction projects: A graph-based text mining approach. Advanced
Engineering Informatics 58.
Sepasgozar, S.M.E. (2021) Differentiating Digital Twin from Digital Shadow: Elucidating a Paradigm
Shift to Expedite a Smart, Sustainable Built Environment. Buildings 11(4).
Soust-Verdaguer, B., Llatas, C. and Garcia-Martinez, A. (2017) Critical review of bim-based LCA
method to buildings. Energy and Buildings 136, 110-120.
Tang, S., Shelden, D.R., Eastman, C.M., Pishdad-Bozorgi, P. and Gao, X. (2019) A review of building
information modeling (BIM) and the internet of things (IoT) devices integration: Present status and
future trends. Automation in Construction 101, 127-139.
Tao, F., Xiao, B., Qi, Q., Cheng, J. and Ji, P. (2022) Digital twin modeling. Journal of Manufacturing
Systems 64, 372-389.
Volk, R., Stengel, J. and Schultmann, F. (2014) Building Information Modeling (BIM) for existing
buildings - literature review and future needs. Automation in Construction 38, 109-127.
Wong, J.K.W. and Zhou, J. (2015) Enhancing environmental sustainability over building life cycles
through green BIM: A review. Automation in Construction 57, 156-165.
Wu, J., Yang, Y., Cheng, X.U.N., Zuo, H. and Cheng, Z. (2020) The Development of Digital Twin
Technology Review, pp. 4901-4906.
Yuan, J., Chen, C., Yang, W., Liu, M., Xia, J. and Liu, S. (2021) A survey of visual analytics techniques
for machine learning. Computational Visual Media 7(1), 3-36.
Zhao, X. (2017) A scientometric review of global BIM research: Analysis and visualization.
Automation in Construction 80, 37-47.