大型结构自适应学习率RBF神经网络滑模分散控制研究

doi:10.6052/j.issn.1000-4750.2018.07.0429

工程力学 ›› 2019, Vol. 36 ›› Issue (9): 120-127.doi: 10.6052/j.issn.1000-4750.2018.07.0429

大型结构自适应学习率RBF神经网络滑模分散控制研究

潘兆东¹, 刘良坤¹, 谭平², 周福霖²

1. 东莞理工学院建筑工程系, 东莞 523808;
2. 广州大学工程抗震研究中心, 广州 510405

收稿日期:2018-07-28 修回日期:2019-07-23 出版日期:2019-09-25 发布日期:2019-07-26
通讯作者: 谭平(1973-),男,湖南人,教授,博士,主要从事结构抗震、减隔震研究(E-mail:ptan@gzhu.edu.cn). E-mail:ptan@gzhu.edu.cn
作者简介:潘兆东(1986-),男,陕西人,博士,主要从事工程结构减震控制研究(E-mail:pzd0101@126.com);刘良坤(1988-),男,江西人,博士,从事结构振动控制研究(E-mail:liuhaikunlzlg@163.com);周福霖(1939-),男,广东人,教授,硕士,中国工程院院士,主要从事结构抗震与减震方面的研究(E-mail:zhoufl@cae.cn).
基金资助:
教育部创新团队项目（IRT13057）；国家自然科学基金项目（51478129，51408142）；东莞理工学院博士科研启动专项经费项目（GC300502-30）

RESEARCH ON SLIDING MODE DECENTRALIZED CONTROL BASED ON ADAPTIVE LEARNING RATE RBF NEURAL NETWORK FOR LARGE-SCALE ENGINEERING STRUCTURES

PAN Zhao-dong¹, LIU Liang-kun¹, TAN Ping², ZHOU Fu-lin²

1. Department Civil Engineering, Dongguan University of Technology, Dongguan 523808, China;
2. Earthquake Engineering Research & Test Center, Guangzhou University, Guangzhou 510405, China

Received:2018-07-28 Revised:2019-07-23 Online:2019-09-25 Published:2019-07-26

摘要/Abstract

摘要： 为了有效处理土木工程结构分散振动控制中子系统间相互影响力和外界荷载不确定性的影响，提出了自适应学习率RBF神经网络滑模分散控制算法（DALRBFSMC）。首先利用Lyapunov稳定性理论设计了仅依赖于子系统位移和速度响应反馈信息的滑模分散控制律，在此基础上，结合RBF神经网络理论和经典梯度下降法，引入Lyapunov函数，推导了调整RBF网络权值的自适应学习率，进而得到能实时调节滑模分散控制律切换增益项的自适应学习率RBF神经网络滑模分散控制算法（DALRBFSMC）。同时，针对子系统不同划分方式及子控制器之间存在重叠，提出了多种分散控制设计策略。对ASCE 9层Benchmark模型进行多种分散控制和集中控制设计。仿真分析结果表明，该分散控制算法适用于不同的分散控制策略，重叠分散控制策略较传统集中控制策略而言有更好的控制效果；同时能使分散控制系统内各作动器均处于功效最大状态。

关键词: 分散控制, 滑模控制, 自适应学习率, RBF神经网络, Lyapunov稳定性理论

Abstract: This paper Proposes a decentralized adaptive learning rate RBF neural network sliding mode control (DALRBFSMC) algorithm for dealing with the influence and the uncertainty of the interaction forces between subsystems and the external loads. Lyapunov stability theory is employed to design the decentralized sliding mode control law which depends only on the displacement and the velocity response of relevant subsystems. Combined with RBF neural network theory and the classical gradient descent method, the adaptive learning rate of RBF network weights-adjustment is derived by using a Lyapunov function. And then the decentralized adaptive learning rate RBF neural network sliding mode control (DALRBFSMC) is designed, which can adjust the switching gain of the sliding mode control law in real time. An ASCE 9-story benchmark building is selected as a numerical example to evaluate the control performances of decentralized control and centralized control. Numerical simulation results indicate that the DALRBFSMC algorithm is suitable for different decentralized control strategy, and that overlapping decentralized control can perform up to a superior control performance when comparing with traditional centralized control, and also guarantee each of the actuators to be operating at maximum efficiency.

Key words: decentralized control, sliding mode control, adaptive learning rate, RBF neural network, Lyapunov stability theory

中图分类号:

TU31

潘兆东, 刘良坤, 谭平, 周福霖. 大型结构自适应学习率RBF神经网络滑模分散控制研究[J]. 工程力学, 2019, 36(9): 120-127.

PAN Zhao-dong, LIU Liang-kun, TAN Ping, ZHOU Fu-lin. RESEARCH ON SLIDING MODE DECENTRALIZED CONTROL BASED ON ADAPTIVE LEARNING RATE RBF NEURAL NETWORK FOR LARGE-SCALE ENGINEERING STRUCTURES[J]. Engineering Mechanics, 2019, 36(9): 120-127.

参考文献

[1] 席裕庚. 动态大系统方法导论[M]. 北京:国防工业出版社, 1988:160-161. Xi Yugeng. Introduction of large scale dynamic systems[M]. Beijing:National Defense of Industry Press, 1988:160-161. (in Chinese)
[2] Lynch J P, Law K H. Decentralized control techniques for large-scale civil structural systems[C]//Proc. of the 20th Int. Modal Analysis Conference (IMAC XX), 2002:406-413.
[3] Xu B, Wu Z S, Yokoyama K. Neural networks for decentralized control of cable-stayed bridge[J]. Journal of Bridge Engineering, 2003, 8(4):229-236.
[4] Rofooei F R, Monajemi-Nezhad S. Decentralized control of tall buildings[J]. The Structural Design of Tall and Special Buildings, 2006, 15(2):153-170.
[5] Monajemi-Nezhad S, Rofooei F R. Decentralized sliding mode control of multistory buildings[J]. The Structural Design of Tall and Special Buildings, 2007, 16(2):181-204.
[6] Ma T W, Xu N S, Tang Y. Decentralized robust control of building structures under seismic excitations[J]. Earthquake Engineering & Structural Dynamics, 2008, 37(1):121-140.
[7] 孙万泉, 李庆斌. 基于LMI的高层建筑结构分散H₂/H_∞鲁棒控制[J]. 地震工程与工程振动, 2007(6):218-222. Sun Wanquan, Li Qingbin. Decentralized H₂/H_∞ robust control for large-scale building structure based on linear matrix inequalities (LMI)[J]. Journal of Earthquake Engineering and Engineering Vibration, 2007(6):218-222. (in Chinese)
[8] Loh C H, Chang C M. Application of centralized and decentralized control to building structure:analytical study[J]. Journal of Engineering Mechanics, 2008, 134(11):970-982.
[9] 李宏男, 李瀛, 李钢. 地震作用下建筑结构的分散控制研究[J]. 土木工程学报, 2008, 41(9):27-33. Li Hongnan, Li Ying, Li Gang. Decentralized control of structures under earthquakes[J]. China Civil Engineering Journal, 2008, 41(9):27-33. (in Chinese)
[10] Wang Y. Wireless sensing and decentralized control for civil structures:theory and implementation[D]. California:Stanford University, 2007:11-14.
[11] Wang Y, Lynch J P, Law K H. Decentralized H∞ controller design for large-scale civil structures[J]. Earthquake Engineering & Structural Dynamics, 2009, 38(3):377-401.
[12] 汪权, 王建国, 裴阳阳. 地震作用下高层建筑结构的分散模糊迭代学习控制研究[J]. 计算力学学报, 2012, 29(5):681-686. Wang Quan, Wang Jianguo, Pei Yangyang. Decentralized fuzzy iterative learning control of tall buildings under earthquakes[J]. Chinese Journal of Computational Mechanics, 2012, 29(5):681-686. (in Chinese)
[13] 蒋扬, 周星德, 王玉. 建筑结构鲁棒分散控制方法研究[J]. 振动与冲击, 2012, 31(6):37-41. Jang Yang, Zhou Xingde, Wang Yu. A robust discentranzed control method for architectural structures[J]. Journal of Vibration and Shock, 2012, 31(6):37-41. (in Chinese)
[14] 雷鹰, 伍德挺, 刘中华. 一种适用于大型工程结构的分散振动控制方法[J]. 振动工程学报, 2012, 25(4):411-417. Lei Ying, Wu Deting, Liu Zhonghua. A decentralized vibration control algorithm for large-scale engineering structures[J]. Journal of Vibration Engineering, 2012, 25(4):411-417. (in Chinese)
[15] 潘兆东, 谭平, 周福霖. 大型结构分散控制系统的优化研究[J]. 工程力学, 2017, 34(1):154-162. Pan Zhaodong, Tan Ping, Zhou Fulin. Study on optimization of large-scale structural decentralized control[J]. Engineering Mechanics, 2017, 34(1):154-162. (in Chinese)
[16] Park J, Sandberg I W. Universal approximation using radial-basis-function networks[J]. Neural computation, 1991, 3(2):246-257.
[17] 刘金琨. 滑模变结构控制MATLAB仿真[M]. 北京:清华大学出版, 2005:188-189. Liu Jinkun. MATLAB simulation of sliding mode variable structure control[M]. Beijing:Publishing House of Tsinghua University, 2005:188-189. (in Chinese)
[18] Lin F J, Wai R J. Sliding-mode-controlled slider-crank mechanism with fuzzy neural network[J]. Industrial Electronics, IEEE Transactions on, 2001, 48(1):60-70.
[19] Ohtori Y, Christenson R E, Spencer Jr B F, et al. Benchmark control problems for seismically excited nonlinear buildings[J]. Journal of Engineering Mechanics, 2004, 130(4):366-385.
[20] Kirkpatrick S, Vecchi M P. Optimization by simulated annealing[J]. Science, 1983, 220(4598):671-680.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

大型结构自适应学习率RBF神经网络滑模分散控制研究

RESEARCH ON SLIDING MODE DECENTRALIZED CONTROL BASED ON ADAPTIVE LEARNING RATE RBF NEURAL NETWORK FOR LARGE-SCALE ENGINEERING STRUCTURES

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

Metrics

本文评价

推荐阅读 10

[1]	潘兆东, 谭平, 周福霖. 不确定结构输出反馈H_∞保性能鲁棒分散控制研究[J]. 工程力学, 2018, 35(4): 160-167.
[2]	潘兆东, 谭平, 周福霖. 基于保性能自适应RBF神经网络的MR半主动非线性鲁棒分散控制[J]. 工程力学, 2018, 35(10): 47-55.
[3]	潘兆东, 谭平, 周福霖. 大型结构小增益分散稳定化容错控制研究[J]. 工程力学, 2017, 34(6): 128-136.
[4]	李志军，邓子辰，顾致平. ATMD-结构带有补偿器的模糊滑模控制[J]. 工程力学, 2013, 30(1): 198-204.
[5]	徐炳伟;姜忻良. 基于BP-RBF神经网络的地下连续墙变形预测[J]. 工程力学, 2009, 26(增刊 I): 163-166.
[6]	郭益深;陈力. 漂浮基空间机械臂姿态、末端爪手协调运动的自适应神经网络控制[J]. 工程力学, 2009, 26(7): 181-187.
[7]	郭益深;陈力. 漂浮基双臂空间机器人协调运动的Terminal滑模控制[J]. 工程力学, 2009, 26(5): 221-227.
[8]	董会丽;郑世杰. 基于RBF神经网络的复合材料层合壳荷载识别[J]. 工程力学, 2008, 25(3): 0-067.
[9]	韩军;高德平;金海波;陈高杰. 基于RBF网络的步行式底盘内力计算优化方法[J]. 工程力学, 2007, 24(8): 0-026,.
[10]	张宇星;邱志平;段志信. 基于神经网络的固体火箭发动机比冲性能的预示研究[J]. 工程力学, 2006, 23(S1): 236-240,.
[11]	孙峰. 线性时滞系统的离散滑模砰砰控制方法[J]. 工程力学, 2005, 22(5): 209-213.