磁流变阻尼器非参数化模型泛化能力的提高

PDF(1582 KB)

振动与冲击 ›› 2017, Vol. 36 ›› Issue (6) : 146-151.

论文

磁流变阻尼器非参数化模型泛化能力的提高

陈昭晖1，倪一清2

作者信息 +

Enhanced generalization of nonparametric model for magnetorheological dampers

CHEN Zhaohui1,NI Yiqing2

Author information +

文章历史 +

摘要

建立磁流变阻尼器的动态模型以描述其强非线性动力学行为是智能磁流变控制系统设计及应用的关键环节之一。泛化能力是衡量基于人工神经网络技术的磁流变阻尼器非参数化模型性能的重要指标，也是保证控制系统稳定性和可靠性的重要因素。本文基于磁流变阻尼器的动力学试验数据，提出贝叶斯推理分析框架下的非线性自回归（nonlinear autoregressive with exogenous inputs，NARX）神经网络技术建立磁流变阻尼器的动态模型，通过网络结构优化和正则化学习算法的结合以有效地提高模型的预测精度和泛化能力。研究结果表明，基于贝叶斯推理的NARX网络模型能够准确地预测磁流变阻尼器在周期和随机激励下的非线性动态行为，同时验证了该模型相比于非正则化模型在泛化性能方面的优越性，因此，有利于实现磁流变控制系统的实时、鲁棒智能化控制。

Abstract

The dynamic modeling for magnetorheological (MR) dampers to describe their highly nonlinear dynamic characteristics is essential for the design and implementation of a smart MR control system.One critical concern in constructing a nonparametric MR damper model by employing the artificial neural network technique is its generalization capability,which is also significant to guarantee the stability and reliability of the MR control system.The paper presents the modeling of MR dampers with the employment of the NARX (nonlinear autoregressive with exogenous inputs) network technique within a Bayesian inference framework,and addresses the enhancement of model prediction accuracy and generalization capability in terms of the network architecture optimization and regularized network learning algorithm.The Bayesian regularized NARX network model for the MR damper is demonstrated to outperform the non-regularized network model with the superior prediction and generalization performance in the scenarios of harmonic and random excitations.Therefore,the proposed model with enhanced generalization is beneficial to realize the real-time and robust smart control of MR systems.

导出引用

陈昭晖1，倪一清2. 磁流变阻尼器非参数化模型泛化能力的提高[J]. 振动与冲击, 2017, 36(6): 146-151

CHEN Zhaohui1,NI Yiqing2. Enhanced generalization of nonparametric model for magnetorheological dampers[J]. Journal of Vibration and Shock, 2017, 36(6): 146-151

参考文献

[1] Caterino N, Spizzuoco M, Occhiuzzi A. Promptness and dissipative capacity of MR dampers: experimental investigations [J]. Structural Control and Health Monitoring, 2013, 20(12): 1424-1440.
[2] Spencer B F Jr, Dyke S J, Sain M K, et al. Phenomenological model for magnetorheological dampers [J]. Journal of Engineering Mechanics, 1997, 123(3): 230-238.
[3] Domínguez-González A, Stiharu I, Sedaghati R. Practical hysteresis model for magnetorheological dampers [J]. Journal of Intelligent Material Systems and Structure, 2014, 25(8): 967-979.
[4] Aguirre N, Ikhouane F, Rodellar J, et al. Parametric identification of the Dahl model for large scale MR dampers [J]. Structural Control and Health Monitoring, 2011, 19(3): 332-347.
[5] Yang F, Sedaghati R, Esmailzadeh E. Development of LuGre friction model for large-scale magneto-rheological fluid damper [J]. Journal of Intelligent Material Systems and Structures, 2009, 20(8): 923-937.
[6] Wang D H, Liao W H. Magnetorheological fluid dampers: a review of parametric modelling [J]. Smart Materials and Structures, 2011, 20(2): 023001.
[7] 王修勇, 宋璨, 陈政清, 等. 磁流变阻尼器的性能试验与神经网络建模[J]. 振动与冲击, 2009, 28(4): 42-46.
WANG Xiu-yong, SONG Can, Chen Zheng-qing, et al. Test of a MR damper and its modeling using neural network [J]. Journal of Vibration and Shock, 2009, 28(4): 42-46.
[8] 王戡, 郑玲, 刘非. 基于广义回归神经网络的磁流变减振器模型辨识[J]. 汽车工程, 2013, 35(7): 619-623.
WANG Kan, ZHENG Ling, LIU Fei. Model identification of MR damper based on generalized regression neural network [J]. Automotive Engineering, 2013, 35(7): 619-623.
[9] Askari M, Li J, Samali B, et al. Experimental forward and inverse modelling of magnetorheological dampers using an optimal Takagi-Sugeno-Kang fuzzy scheme [J]. Journal of Intelligent Material Systems and Structures, 2016, 27(7): 904-914.
[10] 潘公宇, 杨海, 徐腾跃, 等. 磁流变阻尼器试验与建模研究[J]. 振动与冲击, 2015, 34(6): 36-40.
PAN Gong-yu, YANG Hai, XU Teng-yue, et al. Tests and modeling for magneto-rheological (MR) dampers. Journal of Vibration and Shock, 2015, 34(6): 36-40.
[11] Chen S, Billings S A, Grant P M. Non-linear system identification using neural networks [J]. International Journal of Control, 1990, 51(6): 1191-1214.
[12] Hornik K. Approximation capabilities of multilayer feedforward networks [J]. Neural Networks, 1991, 4(2): 251-257.
[13] Suykens J A K, Vandewalle J P L, De Moor B L R. Artificial Neural Networks for Modeling and Control of Non-linear Systems [M]. Boston: Kluwer Academic, 1996.
[14] MacKay D J C. A practical Bayesian framework for backprop networks [J]. Neural Computation, 1992, 4(3): 448-472.
[15] Hagan M T, Menhaj M B. Training feedforward networks with the Marquardt algorithm [J]. IEEE Transactions on Neural Networks, 1994, 6(5): 989-993.