Risk predictive evaluation of ultra-deep foundation pit construction in urban core areas using BIM and optimized Elman neural networks
DOI:
https://doi.org/10.14311/CEJ.2026.03.0023Keywords:
Deep learning, Building information model, Risk analysis, Deep foundation pit, Elman neural networkAbstract
The construction of ultra-deep foundation pits has become a major concern as urban subsurface areas continue to expand and be utilized. Projects involving ultra-deep foundation pit construction in urban core locations often face challenges such as crowded surroundings, heavy traffic, limited space, and tight deadlines. The potential hazards associated with the construction of foundation pits can be quite complex. This study employs BIM technology along with the safety risk knowledge base to pinpoint the factors that contribute to safety risks in the construction of deep foundation pits. In addition, a safety risk evaluation index system is established specifically for the construction of ultra-deep foundation pits in the core area of the city. The evaluation approach utilized combines the modified Analytic Hierarchy Process (AHP) method with fuzzy synthesis theory. This method is used to analyze and process the indicators. In addition, a risk prediction and evaluation model is constructed by integrating an enhanced genetic algorithm with an Elman neural network. The results suggest that the improved Elman neural network model demonstrates superior performance compared to both the traditional BP neural network model and the Elman neural network model when assessing safety risks in deep foundation pit construction. It improves the accuracy and dependability of the assessment by efficiently capturing the relationship and development pattern in time series data. This improves the reliability of safety management and risk control in the construction of deep foundation pits.
Received: 04.09.2024
Received in revised form: 13.04.2026
Accepted: 04.11.2026
Downloads
References
Saleem M R ,A. B T ,I. Y A A , et al. Potential features of building information modeling (BIM) for application of project management knowledge areas in the construction industry [J]. Heliyon, 2023, 9 (9): e19697-e19697.
Hussain S K ,Danish K ,Hussain F S , et al. Optimizing Energy Use, Cost and Carbon Emission through Building Information Modelling and a Sustainability Approach: A Case-Study of a Hospital Building[J]. Sustainability, 2021, 13(7): 3675-3675.
DENDLER L, BOEL G-F. Increasing Engagement in Regulatory Science: Reflections from the Field of Risk Assessment[J]. SCIENCE TECHNOLOGY & HUMAN VALUES, 2021, 46(4): 719–754.
PALTRINIERI N, COMFORT L, RENIERS G. Learning about risk: Machine learning for risk assessment[J]. SAFETY SCIENCE, 2019, 118: 475–486.
LI H, ZHANG Z, SUN J, et al. Smart grid information security evaluation method based on risk weight algorithm[C]// ZHANG L., ALSHAWABKEH M. INTERNATIONAL CONFERENCE ON ALGORITHMS, HIGH PERFORMANCE COMPUTING, AND ARTIFICIAL INTELLIGENCE (AHPCAI 2021). Bellingham: Spie-Int Soc Optical Engineering, 2021: 121560X.
Haytham. Benchmarking Studies on Construction Safety Management in China[J].Construct Manage, 2010, 56(15):424~432
Liping H ,Chen W ,Benben C , et al. Employing an Interpretive Structural Modeling–System Dynamics Approach for Deep Foundation Pit Risk Assessment Model [J]. ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering, 2024, 10 (2):
Xiaoduo O ,Yufang W ,Bo W , et al. Improved unascertained measure model for risk evaluation of collapse in highway tunnels [J]. Natural Hazards, 2023, 119 (3): 1149-1170.
Bu L ,Yue H . Quality Risk Perception of Rectification and Reinforcement in a High-Rise Building under Uncertainty [J]. Buildings, 2024, 14 (3):
Aneziris. Construction Safety and Health Risk Management [J]. Oregon State University, 2012, 42(10):113~115.
ZHANG Shengxi, CHEN Weigong, WANG Huihui, et al. Construction risk evaluation of deep foundation pit based on G-FAHP [J]. Journal of Civil Engineering and Management, 2016, 33( 5) : 104-109.
Chitrasen S, Saurav D, Siba Sankar M. Fuzzy based risk assessment module for metropolitan construction project: an empirical study [J] .Engineering Applications of Artificial Intelligence, 2017, 65:449-464.
Huang Yi and Li Sui-ke. Research on risk evaluation method for international engineering projects [J].International Journal of Plant Engineering and Management, 2013, 18(3) :140-145.
LUO J-L, HU Z-H. Risk paradigm and risk evaluation of farmers cooperatives’ technology innovation[J]. ECONOMIC MODELLING, 2015, 44: 80–85.
LONG J, JIANG C, DIMITROV S, et al. Clues from networks: quantifying relational risk for credit risk evaluation of SMEs[J]. FINANCIAL INNOVATION, 2022, 8(1): 91.
NESTICO A. Risk-Analysis Techniques for the Economic Evaluation of Investment Projects[C]// MONDINI G, FATTINNANZI E, OPPIO A, et al INTEGRATED EVALUATION FOR THE MANAGEMENT OF CONTEMPORARY CITIES. New York: Springer, 2018: 617–629.
PENG Y, CHU J, XUE Z. Basin flood control system risk evaluation based on variable sets[J]. SCIENCE CHINA-TECHNOLOGICAL SCIENCES, 2017, 60(1): 153–165.
GANAIE M A, HU M, MALIK A K, et al. Ensemble deep learning: A review[J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2022, 115: 105151.
PARK J S, PARK J H. Enhanced Machine Learning Algorithms: Deep Learning, Reinforcement Learning, ana Q-Learning[J]. JOURNAL OF INFORMATION PROCESSING SYSTEMS, 2020, 16(5): 1001–1007.
JANIESCH C, ZSCHECH P, HEINRICH K. Machine learning and deep learning[J]. ELECTRONIC MARKETS, 2021, 31(3): 685–695.
MATSUO Y, LECUN Y, SAHANI M, et al. Deep learning, reinforcement learning, and world models[J]. NEURAL NETWORKS, 2022, 152: 267–275.
CHIVUKULA A S, LIU W. Adversarial Learning Games with Deep Learning Models[C]// 2017 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN). New York: IEEE, 2017: 2758–2767.
ADATE A, ARYA D, SHAHA A, et al. Impact of Deep Neural Learning on Artificial Intelligence Research[M]// BHATTACHARYYA S, SNASEL V, HASSANIEN A. E, et al DEEP LEARNING: RESEARCH AND APPLICATIONS. Berlin: Walter De Gruyter Gmbh, 2020: 69–84.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Author
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
