Swarm intelligence-based technique to enhance performance of ANN in structural damage detection

  • Ho Viet Long

    Campus in Ho Chi Minh City, University of Transport and Communications, No 450-451 Le Van Viet Street, Ho Chi Minh, Vietnam
  • Trinh Thi Trang

    Campus in Ho Chi Minh City, University of Transport and Communications, No 450-451 Le Van Viet Street, Ho Chi Minh, Vietnam
  • Ho Xuan Ba

    Campus in Ho Chi Minh City, University of Transport and Communications, No 450-451 Le Van Viet Street, Ho Chi Minh, Vietnam
Email: bahx_ph@utc.edu.vn
Từ khóa: model updating, grey wolf optimizer, artificial neural network, hybrid approach, modal flexibility, damage identification

Tóm tắt

Artificial neural network (ANN), a powerful technique, has been used widely over the last decades in many scientific fields including engineering problems. However, the backpropagation algorithm in ANN is based on a gradient descent approach. Therefore, ANN shows high potential in local stagnancy. Besides, choosing the right architecture of ANN for a specific issue is not an easy task to deal with. This paper introduces a simple, effective hybrid approach between an optimization algorithm and a traditional ANN for damage detection. The global search-ability of a heuristic optimization algorithm, namely grey wolf optimizer (GWO), can solve the drawbacks of ANN and also improve the performance of ANN. Firstly, the grey wolf optimizer is used to update the finite element (FE) model of a laboratory steel beam based on the vibration measurement. The updated FE model of the tested beam then is used to generate data for network training. For an effective training process, GWO is utilized to identify the optimal parameters for ANN, such as the number of the hidden nodes, the proportion of dataset for training, validation, test, and the training function. The optimization process provides an optimal structure of ANN that can be used to predict the damages in the beam. The obtained results confirm the accuracy, effectiveness, and reliability of the proposed approach in (1) alleviating the differences between measurement and simulation and (2) damage identification including damage location and severity, in the tested beam considering noise effects. For both applications, dynamic characteristics like natural frequencies and mode shapes of the beam derived from the updated FE model, are collected to calculate the objective function

Tài liệu tham khảo

[1]. L. V. Ho, S. Khatir, G. D. Roeck, T. Bui-Tien, M. A. Wahab, Finite element model updating of a cable-stayed bridge using metaheuristic algorithms combined with Morris method for sensitivity analysis, Smart Structures And Systems, 26 (2020) 451–468. https://doi.org/10.12989/sss.2020.26.4.451
[2]. V. L. Ho, G. De Roeck, T. Bui-Tien, M. Abdel Wahab, Determination of the Effective Stiffness of Half-Open Cross-Section Bars and Orthotropic Steel Deck of a Truss Bridge Using Model Updating, in Proceedings of the 8th International Conference on Fracture, Fatigue and Wear, 2021, Springer, 97–108. https://doi.org/ 10.1007/978-981-15-9893-7_6
[3]. V. L. Ho, N. H. Tran, G. De Roeck, T. T. Bui, M. Abdel Wahab, System identification based on vibration testing of a steel I-beam, in Proceedings of the 1st International Conference on Numerical Modelling in Engineering, 20 (2019) 254–268. https://doi.org/10.1007/978-981-13-2405-5_21
[4]. D. T. Toan, Wireless DAQ using piezoelectric sensor for vibration measurement of bridge structure, Transport and communications science Journal, 2 (2020) 135-144. https://doi.org/10.25073/tcsj.71.2.8
[5]. N.T. Anh, L. H. Bang, Development of ANN-based models to predict the bond strength of GFRP bars and concrete beams, Transport and communications science Journal, 7 (2020) 814-827. https://doi.org/10.47869/tcsj.71.7.7
[6]. L. H. Bang, N. T. Anh, M. T. H. Van, Compressive strength prediction of recycled aggregate concrete by artificial neural network, Transport and communications science Journal, 3 (2021) 369-383. https://doi.org/10.47869/tcsj.72.3.11
[7]. M. Seguini, S. Khatir, D. Boutchicha, D. Nedjar, M. A. Wahab, Crack prediction in pipeline using ANN-PSO based on numerical and experimental modal analysis, Smart Structures and Systems, 27 (2021) 507–523. https://doi.org/10.12989/SSS.2021.27.3.507
[8]. S. Khatir, S. Tiachacht, C.-L. Thanh, T. Q. Bui, M. Abdel Wahab, Damage assessment in composite laminates using ANN-PSO-IGA and Cornwell indicator, Composite Structures, 230 (2019) 111509. https://doi.org/10.1016/j.compstruct.2019.111509
[9]. S. Khatir et al., An efficient hybrid TLBO-PSO-ANN for fast damage identification in steel beam structures using IGA, Smart Structures and Systems, 25 (2020) 605–617. https://doi.org/10.12989/SSS.2020.25.5.605
[10]. L. V. Ho, D. H. Nguyen, G. D. Roeck, T. Bui-Tien, M. A. Wahab, Damage detection in steel plates using feed-forward neural network coupled with hybrid particle swarm optimization and gravitational search algorithm, Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 22 (2021) 467-480. https://doi.org/10.1631/jzus.A2000316
[11]. H. Tran-Ngoc, S. Khatir, G. De Roeck, T. Bui-Tien, M. Abdel Wahab, An efficient artificial neural network for damage detection in bridges and beam-like structures by improving training parameters using cuckoo search algorithm, Engineering Structures, 199 (2019) 109637. https://doi.org/10.1016/j.engstruct.2019.109637
[12]. H. Tran-Ngoc, S. Khatir, H. Ho-Khac, G. De Roeck, T. Bui-Tien, M. Abdel Wahab, Efficient Artificial neural networks based on a hybrid metaheuristic optimization algorithm for damage detection in laminated composite structures, Composite Structures, 262 (2021) 113339. https://doi.org/10.1016/j.compstruct.2020.113339
[13]. K. G. Sheela, S. N. Deepa, Review on Methods to Fix Number of Hidden Neurons in Neural Networks, Mathematical Problems in Engineering, (2013) 1–11. https://doi.org/10.1155/2013/425740
[14]. J. Ke, X. Liu, Empirical Analysis of Optimal Hidden Neurons in Neural Network Modeling for Stock Prediction, in 2008 IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application, Wuhan, China, (2008) 828–832. https://doi.org/10.1109/PACIIA.2008.363
[15]. P. S. Pauletto, G. L. Dotto, N. P. G. Salau, Optimal artificial neural network design for simultaneous modeling of multicomponent adsorption, Journal of Molecular Liquids, 320 (2020) 114418. https://doi.org/doi: 10.1016/j.molliq.2020.114418
[16]. S. Mirjalili, S. M. Mirjalili, A. Lewis, Grey Wolf Optimizer, Advances in Engineering Software, 69 (2014) 46–61. https://doi.org/10.1016/j.advengsoft.2013.12.007
[17]. MACEC 3.2: A Matlab toolbox for experimental and operational modal analysis, Belgium, 2011.
[18]. ANSYS, Inc. Southpointe, 275 Technology Drive, Canonsburg, PA 15317, Release 17.2, 2016.
[19]. A.K. Pandey, M. Biswas, Damage Detection in Structures Using Changes in Flexibility, Journal of Sound and Vibration, 169 (1994) 3-17. https://doi.org/10.1006/jsvi.1994.1002
[20]. Jeff Heaton, Introduction to Neural Networks for Java, 2nd Edition (2nd. ed.), Heaton Research, Inc, USA, 2008.
[21]. Z. Boger, P. O. Box, H. Guterman, Knowledge Extraction from Artificial Neural Networks Models, IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation, 4 (1997) 3030–3035. https://doi.org/10.1109/ICSMC.1997.633051

Tải xuống

Chưa có dữ liệu thống kê