A CRITICAL REVIEW OF DEEP LEARNING APPLICATIONS, CHALLENGES, AND FUTURE DIRECTIONS IN STRUCTURAL ENGINEERING
Main Article Content
Abstract
Deep learning (DL), a major part of artificial intelligence (AI) is considered as a transformational technology in different areas of science, such as structural engineering. This critical review uncovers the potential contribution of deep learning in solving complex issues facing structural engineering, such as optimizing structural design, predicting and monitoring material behaviour, and monitoring in real-time the structural health. Through developed neural network architectures such as generative adversarial networks (GANs), recurrent neural networks (RNNs), and convolutional neural networks (CNNs), engineers can identify solutions based on traditional deterministic data extraction. However, issues like computational requirements, model interpretability and data scarcity are widely adopted. This review highlights recent advancements, practical applications, and the limitations of deep learning in structural engineering, proposing pathways for future research to enhance its efficacy and integration in real-world scenarios
Downloads
Article Details
Issue
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
How to Cite
References
Ereiz, S., I. Duvnjak, and J.F. Jiménez-Alonso.(2022) Review of finite element model updating methods for structural applications. in Structures. Elsevier. of Conference.
Liu, W.K., S. Li, and H.S. Park,(2022) Eighty years of the finite element method: Birth, evolution, and future Archives of Computational Methods in Engineering, 29, no.6, p.p 4431-4453.
Wu, B., S. Luo, and C.S. Suh,(2024) A Comprehensive Review of Propagation Models in Complex Networks: From Deterministic to Deep Learning Approaches arXiv preprint arXiv:2410.02118.
Fujinuma, N., et al.,(2022) Why big data and compute are not necessarily the path to big materials science Communications Materials, 3, no.1, p.p 59.
Ditlevsen, O. and H.O. Madsen, Structural reliability methods. Vol. 178. 1996: Wiley New York.
Ghosn, M., et al.,(2016) Reliability-based performance indicators for structural members Journal of Structural Engineering, 142, no.9, p.p F4016002.
Etim, B., et al.,(2024) Machine Learning-Based Modeling for Structural Engineering: A Comprehensive Survey and Applications Overview Buildings, 14, no.11, p.p 3515.
Li, Q., et al.,(2024) Classification and Application of Deep Learning in Construction Engineering and Management–A Systematic Literature Review and Future Innovations Case Studies in Construction Materials, p.p e04051.
Sarker, I.H.,(2021) Deep learning: a comprehensive overview on techniques, taxonomy, applications and research directions SN computer science, 2, no.6, p.p 420.
McCulloch, W.S. and W. Pitts,(1943) A logical calculus of the ideas immanent in nervous activity The bulletin of mathematical biophysics, 5, p.p 115-133.
Rosenblatt, F.,(1958) The perceptron: a probabilistic model for information storage and organization in the brain Psychological review, 65, no.6, p.p 386.
Rumelhart, D.E., G.E. Hinton, and R.J. Williams,(1986) Learning representations by back-propagating errors nature, 323, no.6088, p.p 533-536.
Zhao, X., et al.,(2024) A review of convolutional neural networks in computer vision Artificial Intelligence Review, 57, no.4, p.p 99.
Sundaray, S. History of Deep Learning. 2023; Available from: https://medium.com/@sreyan806/history-of-deep-learning-c176e2d3cddf.
Akinosho, T.D., et al.,(2020) Deep learning in the construction industry: A review of present status and future innovations Journal of Building Engineering, 32, p.p 101827.
Khoa, N.L., et al.,(2014) Robust dimensionality reduction and damage detection approaches in structural health monitoring Structural Health Monitoring, 13, no.4, p.p 406-417.
Abbas, H.A., Z. Mohamed, and S.A. Kudus,(2023) Deformation behaviour, crack initiation and crack damage of weathered composite sandstone-shale by using the ultrasonic wave and the acoustic emission under uniaxial compressive stress International Journal of Rock Mechanics and Mining Sciences, 170, p.p 105497.
Dorafshan, S., R.J. Thomas, and M. Maguire,(2018) Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete Construction and Building Materials, 186, p.p 1031-1045.
Gao, Y. and K.M. Mosalam,(2018) Deep transfer learning for image‐based structural damage recognition Computer‐Aided Civil and Infrastructure Engineering, 33, no.9, p.p 748-768.
Deng, Y., et al.,(2024) Abnormal data recovery of structural health monitoring for ancient city wall using deep learning neural network International Journal of Architectural Heritage, 18, no.3, p.p 389-407.
Zhang, R., et al.,(2019) Deep long short-term memory networks for nonlinear structural seismic response prediction Computers & Structures, 220, p.p 55-68.
Wang, Z., T. Hong, and M.A. Piette,(2020) Building thermal load prediction through shallow machine learning and deep learning Applied Energy, 263, p.p 114683.
Lv, R., et al.,(2022) Building thermal load prediction using deep learning method considering time-shifting correlation in feature variables Journal of Building Engineering, 61, p.p 105316.
Raju, M.R., et al.,(2023) Estimation of concrete materials uniaxial compressive strength using soft computing techniques Heliyon, 9, no.11.
Deng, F., et al.,(2018) Compressive strength prediction of recycled concrete based on deep learning Construction and Building Materials, 175, p.p 562-569.
Ahmed, B., T. Park, and J.-S. Jeon,(2023) Blast response and damage assessment of reinforced concrete slabs using convolutional neural networks International Journal of Damage Mechanics, p.p 10567895231204640.
Vafa, M., Optimization of the Profiled Steel Sheeting Dry Board (PSSDB) floor system, in Civil Engineering 2018, Universiti Kebangsaan Malaysia (UKM): Malaysia.
Abueidda, D.W., S. Koric, and N.A. Sobh,(2020) Topology optimization of 2D structures with nonlinearities using deep learning Computers & Structures, 237, p.p 106283.
Almasri, W., et al.(2021) Deep learning architecture for topological optimized mechanical design generation with complex shape criterion. in International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems. Springer. of Conference.
Long, T., Y. Zhang, and H. Zhang,(2024) Generative deep learning for the inverse design of materials arXiv preprint arXiv:2409.19124.
Ferreiro-Cabello, J., et al.,(2018) Metamodel-based design optimization of structural one-way slabs based on deep learning neural networks to reduce environmental impact Engineering Structures, 155, p.p 91-101.
Mai, H.T., et al.,(2023) A novel deep unsupervised learning-based framework for optimization of truss structures Engineering with Computers, 39, no.4, p.p 2585-2608.
Nandy, A., C. Duan, and H.J. Kulik,(2022) Audacity of huge: overcoming challenges of data scarcity and data quality for machine learning in computational materials discovery Current Opinion in Chemical Engineering, 36, p.p 100778.
Rather, I.H., S. Kumar, and A.H. Gandomi,(2024) Breaking the data barrier: a review of deep learning techniques for democratizing AI with small datasets Artificial Intelligence Review, 57, no.9, p.p 226.
Qamar, T. and N.Z. Bawany,(2023) Understanding the black-box: towards interpretable and reliable deep learning models PeerJ Computer Science, 9, p.p e1629.
Ying, X.(2019) An overview of overfitting and its solutions. in Journal of physics: Conference series. IOP Publishing. of Conference.
Giabbanelli, P.J.,(2022) Hybrid Models That Combine Machine Learning and Simulations Computing in Science & Engineering, 24, no.5, p.p 72-76.
Rane, N., et al.,(2024) Artificial intelligence, machine learning, and deep learning for enabling smart and sustainable cities and infrastructure Artificial Intelligence and Industry in Society, 5, p.p 2-25.