基于遗忘因子和LMBP神经网络的混合试验在线模型更新方法

Abstract
Figure/Table
References (27)
Related Citation (14)

Download: PDF (1784 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Recently the application of neural networks to the online model updating of hybrid testings is an important research direction.How to improve the adaptability, stability and anti-noise ability of online model updating algorithm of neural network is a key problem.An on-line model updating method for hybrid testings based on the forgetting factor and LMBP neural network was proposed, namely in each time step the historical experimental data of the test substructure were used to form a dynamic window sample with a forgetting factor.Then the LMBP neural network was trained with the sample set by the incremental training method, and the restoring force of the numerical element with the same constitutive model was predicted synchronously.The model updating hybrid testing on a 2-DOF nonlinear system was simulated and the RMSD of the predicted restoring force of numerical substructure was found to be 0.023 0 finally.The results show that the online model updating method of hybrid testings based on the forgetting factor and LMBP neural network has good adaptability, stability and anti-noise ability.

Key words： online model updating hybrid testing incremental training LMBP neural network forgetting factor

Received: 29 April 2019 Published: 28 April 2020

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	WANG Yanhua
	LV Jing
	WU Jing

Cite this article:

WANG Yanhua,LV Jing,WU Jing. On-line model updating method for hybrid testings based on the forgetting factor and LMBP neural network[J]. JOURNAL OF VIBRATION AND SHOCK, 2020, 39(9): 42-48.

URL:

http://jvs.sjtu.edu.cn/EN/ OR http://jvs.sjtu.edu.cn/EN/Y2020/V39/I9/42

[1] M.Nakashima,H.Takai. Use of substructure techniques in pseudodynamic testing, BRI Research Paper,1985,111(23):350—365 [2] Tang Z Y, Chen S C, Zhang J X, et al. Study on the stability prediction of real-time dynamic substructuring system based on shaking table[J]. Engineering Mechanics, 2016, 33(12): 217-224. [3] 王凤来, 陈再现, 王焕定,等. 底部框支配筋砌块短肢砌体剪力墙结构抗震性能试验研究[J]. 土木工程学报, 2009(11):71-78. WANG Fenglai, CHEN Zaixian, WANG Huanding, et al. Experimental study on seismic behavior of a frame-supported reinforced masonry short-limb shear wall structure[J].China Civil Engineering Journal , 2009 (11): 71-78. [4] Kim S J , Holub C J , Elnashai A S . Experimental investigation of the behavior of RC bridge piers subjected to horizontal and vertical earthquake motion[J]. Engineering Structures, 2011, 33(7):2221-2235. [5] Wu B , Xu G , Wang Q , et al. Operator-splitting method for real-time substructure testing[J]. Earthquake Engineering & Structural Dynamics, 2010, 35(3):293-314. [6] Wu B , Bao H , Ou J , et al. Stability and accuracy analysis of the central difference method for real-time substructure testing[J]. 2005, 34(7):705-718. [7] M.Nakashima, H.Kato, E.Takaoka. Development of a Real-time PseudodynamicTesting. Earthquake Engineering and Structural Dynamics, 1992, 21(1):79~92 [8] 王贞, 王照然, 杨婧,等. MTS控制系统的二次开发及其在混合试验中的应用[J]. 地震工程与工程振动, 2015, 01(2):22-29. WANG Zhen, WANG Zhaoran, YANG Jing, et al. Secondary development of MTS control system and its application to hybrid test [J].Earthquake Engineering and Engineering Vibration, 2015, 01 (2): 22-29. [9] 徐伟杰, 郭彤, 陈城. 实时混合模拟逆补偿参数α的研究[J]. 工程力学, 2016, 33(6):61-67. XU Weijie, GUO Tong, CHEN Cheng. Research in parameter α of inverse compensation for real-time hybrid simulation[J]. Engineering Mechanics, 2016, 33 (6): 61-67. [10] 吴斌, 宁西占, 许国山,等考虑不完整边界条件的新型混合试验方法[J]. 振动与冲击, 2018(15):150-155. WU Bin,NING Xizhan, XU Guoshan, et al. A novel hybrid simulation method considering incomplete boundary conditions [J]. Journal of Vibration and Shock, 2018 (15): 150-155. [11] Kwon O S , Elnashai A S , Spencer B F . A framework for distributed analytical and hybrid simulations[J]. Structural Engineering & Mechanics, 2008, 30(3):331-350. [12] 王涛, 吴斌. 基于约束UKF模型更新的混合试验方法[J]. 地震工程与工程振动, 2013, 33(5):100-109. WANG Tao, WU Bin. Hybrid testing method based on model updating with constrained unscented Kalman filter [J]. Earthquake Engineering and Engineering Vibration, 2013, 33 (5): 100-109. [13] 陈永盛. 基于截面屈服面模型更新的框架结构混合试验方法[D]. 2015. CHEN Yongsheng.Hybrid testing of frame structures based on model updating of sectional yield surface[D]. 2015. [14] Yang W J, Nakano Y. Substructure online test by using real-time hysteresis modeling with a neural network[J]. Advances in Experimental Structural Engineering, 2005, 38: 267-274. [15] Chuang M C, Hsieh S H, Tsai K C, et al. Parameter identification for on‐line model updating in hybrid simulations using a gradient‐based method[J]. Earthquake Engineering & Structural Dynamics, 2018, 47(2): 269-293. [16] Yang, YuanSen；Hsieh, TungJu；Elnashai, et al. An online optimization method for bridge dynamic hybrid simulations[J]. Simulation Modelling Practice & Theory, 2012, 28(11):42-54. [17] Wang T, Wu B, Zhang J. Online Identification with Least Square Method for Pseudo-Dynamic Tests[J]. Advanced Materials Research, 2011, 250-253:2455-2459. [18] Gun Jin Yun, Jamshid Ghaboussi, Amr S. Elnashiai. A new network-based model for hysteretic behavior of materials. International Journal for Numerical Methods in Engineering. 2008,73(4): 447-467. [19] Yun G J , Ghaboussi J , Elnashai A S . Self-learning simulation method for inverse nonlinear modeling of cyclic behavior of connections[J]. Computer Methods in Applied Mechanics and Engineering, 2008, 197(33-40):2836-2857. [20] 张健. 自适应子结构拟动力试验方法[D]. 哈尔滨:哈尔滨工业大学硕士学位论文, 2010. ZHANG Jian. Adaptive substructure pseudo-dynamic testing method [D]. Harbin: Master's Degree Thesis, Harbin University of Technology, 2010. [21] Elanwar H H, Elnashai A S. Framework for online model updating in earthquake hybrid simulations[J]. Journal of Earthquake Engineering, 2016, 20(1):80-100. [22] 王涛, 翟绪恒, 孟丽岩,等. 基于在线神经网络算法的混合试验方法[J]. 振动与冲击, 2017, 36(14):1-8. WANG Tao, ZHAI Xuheng, MENG Liyan, et al.Hybrid testing method based on an online neural network algorithm [J]. Journal of Vibration and Shock, 2017, 36 (14): 1-8. [23] 王涛, 翟绪恒，孟丽岩. 在线自适应神经网络算法及参数鲁棒性分析[J]. 振动与冲击, 2019, 38(8): 210-217. WANG Ta，ZHAI Xuheng，MENG Liyan. An online adaptive neural network algorithm and its parameters robustness analysis. Journal of Vibration and Shock, 2019, 38(8): 210-217. [24] 面向MATLAB工具箱的神经网络理论与应用(第3版)[M]. 2003. Neural Network theory and application oriented to MATLAB toolbox (3rd edition) [M]. 2003. [25] MoréJJ. The Levenberg-Marquardt algorithm: Implementation and theory[J]. Lecture Notes in Mathematics, 1978, 630:105-116. [26] Ma F, Zhang H, Bockstedte A, et al. Parameter analysis of the differential model of hysteresis[J]. Journal of Applied Mechanics, 2004, 71(3): 342-349. [27] Kim J H, Ghaboussi J, Elnashai A S. Hysteretic mechanical–informational modeling of bolted steel frameconnections[J]. Engineering Structures, 2012, 45: 1-11.