Abstract
Over recent decades, the artificial neural networks (ANNs) have been applied as an effective approach for detecting damage in construction materials. However, to achieve a superior result of defect identification, they have to overcome some shortcomings, for instance slow convergence or stagnancy in local minima. Therefore, optimization algorithms with a global search ability are used to enhance ANNs, i.e. to increase the rate of convergence and to reach a global minimum. This paper introduces a two-stage approach for failure identification in a steel beam. In the first step, the presence of defects and their positions are identified by modal indices. In the second step, a feedforward neural network, improved by a hybrid particle swarm optimization and gravitational search algorithm, namely FNN-PSOGSA, is used to quantify the severity of damage. Finite element (FE) models of the beam for two damage scenarios are used to certify the accuracy and reliability of the proposed method. For comparison, a traditional ANN is also used to estimate the severity of the damage. The obtained results prove that the proposed approach can be used effectively for damage detection and quantification.
Abstract
目的
使用模态损伤指数建立一个简单, 有效的结构健康监测评估工具, 并对钢板进行数值研究, 以确认该方法的可行性。
创新点
为使研究可应用于实际结构, 本文放弃了目前的大量研究中的刚度折减假设, 并在有限元模型中模拟了钢板的切割, 以代表实际结构的失效。
方法
1. 一个有名的混合优化算法, 即粒子群优化-引力搜索算法(PSOGSA), 被用于优化前馈神经网络(FNN)的连接权重和偏差, 以增强其训练性能。2. 模型的输入变量为由柔度矩阵变化推导出的两个损伤指数, 而输出变量则是损伤严重程度。3. 预测值和目标值之间的均方误差(MSE)是优化过程的适应度函数。
结论
1. 随机的FNN-PSOGSA方法获得了比传统人工神经网络(ANN)更好的损伤量化结果; 其在两种破坏场景下目标和估计之间的严重性差异分别为−0.06%和0.89%, 而在ANN中为−1.91%和1.01%。2. 所提出的方法可以在损伤指数和相应的严重程度之间建立联系, 而如果仅使用损伤指数则无法观察到该联系。3. FNN-PSOGSA方法的准确性和易实施性说明它具有作为真实结构损伤评估工具的潜力。
Similar content being viewed by others
References
Anitescu C, Atroshchenko E, Alajlan N, et al., 2019. Artificial neural network methods for the solution of second order boundary value problems. Computers, Materials & Continua, 59(1):345–359. https://doi.org/10.32604/cmc.2019.06641
Dawari VB, Vesmawala GR, 2013. Modal curvature and modal flexibility methods for honeycomb damage identification in reinforced concrete beams. Procedia Engineering, 51:119–124. https://doi.org/10.1016/j.proeng.2013.01.018
Du YC, Stephanus A, 2018. Levenberg-Marquardt neural network algorithm for degree of arteriovenous fistula stenosis classification using a dual optical photoplethysmography sensor. Sensors, 18(7):2322. https://doi.org/10.3390/s18072322
Garcia-Perez A, Amezquita-Sanchez JP, Dominguez-Gonzalez A, et al., 2013. Fused empirical mode decomposition and wavelets for locating combined damage in a truss-type structure through vibration analysis. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 14(9):615–630. https://doi.org/10.1631/jzus.A1300030
Guo HW, Zhuang XY, Rabczuk T, 2019. A deep collocation method for the bending analysis of Kirchhoff plate. Computers, Materials & Continua, 59(2):433–456. https://doi.org/10.32604/cmc.2019.06660
Ho VL, Tran NH, de Roeck G, et al., 2019. System identification based on vibration testing of a steel I-beam. Proceedings of the 1st International Conference on Numerical Modelling in Engineering, p.254–268. https://doi.org/10.1007/978-981-13-2405-5_21
Ho VL, Hoang TN, de Roeck G, et al., 2020. Effects of measuring techniques on the accuracy of estimating cable tension in a cable-stay bridge. Proceedings of the 13th International Conference on Damage Assessment of Structures, p.433–445. https://doi.org/10.1007/978-981-13-8331-1_31
Kennedy J, Eberhart R, 1995. Particle swarm optimization. Proceedings of International Conference on Neural Networks, p.1942–1948. https://doi.org/10.1109/ICNN.1995.488968
Khatir S, Behtani A, Tiachacht S, et al., 2017. Delamination detection in laminated composite using virtual crack closure technique (VCCT) and modal flexibility based on dynamic analysis. Journal of Physics: Conference Series, 842:012084. https://doi.org/10.1088/1742-6596/842/1/012084
Le-Duc T, Nguyen QH, Nguyen-Xuan H, 2020. Balancing composite motion optimization. Information Sciences, 520:250–270. https://doi.org/10.1016/j.ins.2020.02.013
Liu HB, Song G, Jiao YB, et al., 2014. Damage identification of bridge based on modal flexibility and neural network improved by particle swarm optimization. Mathematical Problems in Engineering, 2014:640925. https://doi.org/10.1155/2014/640925
Mirjalili S, Hashim SZM, Sardroudi HM, 2012. Training feedforward neural networks using hybrid particle swarm optimization and gravitational search algorithm. Applied Mathematics and Computation, 218(22):11125–11137. https://doi.org/10.1016/j.amc.2012.04.069
Mirjalili S, Wang GG, dos S. Coelho L, 2014. Binary optimization using hybrid particle swarm optimization and gravitational search algorithm. Neural Computing and Applications, 25(6):1423–1435. https://doi.org/10.1007/s00521-014-1629-6
Moser P, Moaveni B, 2011. Environmental effects on the identified natural frequencies of the dowling hall footbridge. Mechanical Systems and Signal Processing, 25(7):2336–2357. https://doi.org/10.1016/j.ymssp.2011.03.005
Nguyen HD, Bui TT, de Roeck G, et al., 2019. Damage detection in Ca-Non bridge using transmissibility and artificial neural networks. Structural Engineering and Mechanics, 71(2):175–183. https://doi.org/10.12989/SEM.2019.71.2.175
Nguyen HD, Ho LV, Bui-Tien T, et al., 2020a. Damage evaluation of free-free beam based on vibration testing. Applied Mechanics, 1(2):142–152. https://doi.org/10.3390/applmech1020010
Nguyen TQ, Vuong LC, Le CM, et al., 2020b. A data-driven approach based on wavelet analysis and deep learning for identification of multiple-cracked beam structures under moving load. Measurement, 162:107862. https://doi.org/10.1016/j.measurement.2020.107862
Pandey AK, Biswas M, 1994. Damage detection in structures using changes in flexibility. Journal of Sound and Vibration, 169(1):3–17. https://doi.org/10.1006/Jsvi.1994.1002
Pandey AK, Biswas M, 1995. Experimental verification of flexibility difference method for locating damage in structures. Journal of Sound and Vibration, 184(2):311–328. https://doi.org/10.1006/jsvi.1995.0319
Pandey AK, Biswas M, Samman MM, 1991. Damage detection from changes in curvature mode shapes. Journal of Sound and Vibration, 145(2):321–332. https://doi.org/10.1016/0022-460X(91)90595-B
Peeters B, de Roeck G, 2001. One-year monitoring of the Z24-bridge: environmental effects versus damage events. Earthquake Engineering & Structural Dynamics, 30(2): 149–171. https://doi.org/10.1002/1096-9845(200102)30:2<149::AID-EQE1>3.0.CO;2-Z
Rashedi E, Nezamabadi-Pour H, Saryazdi S, 2009. GSA: a gravitational search algorithm. Information Sciences, 179(13):2232–2248. https://doi.org/10.1016/j.ins.2009.03.004
Rashid T, 2016. Make Your Own Neural Network, 1st Edition. CreateSpace Independent Publishing Platform, North Charleston, SC, USA.
Samaniego E, Anitescu C, Goswami S, et al., 2020. An energy approach to the solution of partial differential equations in computational mechanics via machine learning: concepts, implementation and applications. Computer Methods in Applied Mechanics and Engineering, 362:112790. https://doi.org/10.1016/j.cma.2019.112790
Sharma B, Venugopalan K, 2014. Comparison of neural network training functions for hematoma classification in brain CT images. IOSR Journal of Computer Engineering, 16(1):31–35. https://doi.org/10.9790/0661-16123135
Tran NH, Bui TT, 2019. Damage detection in a steel beam structure using particle swarm optimization and experimentally measured results. Science Journal of Transportation, 9:3–9.
Tran-Ngoc H, Khatir S, de Roeck G, et al., 2019. An efficient artificial neural network for damage detection in bridges and beam-like structures by improving training parameters using cuckoo search algorithm. Engineering Structures, 199:109637. https://doi.org/10.1016/j.engstruct.2019.109637
Valian E, Mohanna S, Tavakoli S, 2011. Improved cuckoo search algorithm for feed forward neural network training. International Journal of Artificial Intelligence & Applications, 2(3):36–43. https://doi.org/10.5121/ijaia.2011.2304
Wickramasinghe WR, Thambiratnam DP, Chan THT, 2015. Use of modal flexibility method to detect damage in suspended cables and the effects of cable parameters. Special Issue: Electronic Journal of Structural Engineering, 14(1):133–144.
Xia Y, Hao H, Zanardo G, et al., 2006. Long term vibration monitoring of an RC slab: temperature and humidity effect. Engineering Structures, 28(3):441–452. https://doi.org/10.1016/j.engstruct.2005.09.001
Zhang JR, Zhang J, Lok TM, et al., 2007. A hybrid particle swarm optimization-back-propagation algorithm for feedforward neural network training. Applied Mathematics and Computation, 185(2):1026–1037. https://doi.org/10.1016/j.amc.2006.07.025
Zhu JJ, Huang M, Lu ZR, 2017. Bird mating optimizer for structural damage detection using a hybrid objective function. Swarm and Evolutionary Computation, 35:41–52. https://doi.org/10.1016/j.swevo.2017.02.006
Author information
Authors and Affiliations
Corresponding author
Additional information
Project supported by the Vlaamse Interuniversitaire Raad University Development Cooperation (VLIR-UOS) Team Project (No. VN2018TEA479A103), the Flemish Government, Belgium
Contributors
Long Viet HO: methodology, wrote the original draft of the manuscript, software; Duong Huong NGUYEN: helped to organize the manuscript, software; Thanh BUI-TIEN, Magd Abdel WAHAB, and Guido de ROECK: supervision and validation.
Conflict of interest
Long Viet HO, Duong Huong NGUYEN, Guido de ROECK, Thanh BUI-TIEN, and Magd Abdel WAHAB declare that they have no conflict of interest.
Rights and permissions
About this article
Cite this article
Ho, L.V., Nguyen, D.H., de Roeck, G. et al. Damage detection in steel plates using feed-forward neural network coupled with hybrid particle swarm optimization and gravitational search algorithm. J. Zhejiang Univ. Sci. A 22, 467–480 (2021). https://doi.org/10.1631/jzus.A2000316
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1631/jzus.A2000316
Key words
- Feedforward neural network-particle swarm optimization and gravitational search algorithm (FNN-PSOGSA)
- Modal damage indices
- Damage detection
- Hybrid algorithm PSOGSA