计算机科学 ›› 2017, Vol. 44 ›› Issue (10): 203-208.doi: 10.11896/j.issn.1002-137X.2017.10.037

• 人工智能 • 上一篇    下一篇

基于动态函数连接神经网络的自适应逆控制系统辨识研究

虎涛涛,康波,单要楠   

  1. 电子科技大学电子科学技术研究院 成都611731,电子科技大学自动化工程学院 成都611731,电子科技大学数学科学学院 成都611731
  • 出版日期:2018-12-01 发布日期:2018-12-01

Study on Identification of Adaptive Inverse Control System Based on Dynamic Function Link Neural Network

HU Tao-tao, KANG Bo and SHAN Yao-nan   

  • Online:2018-12-01 Published:2018-12-01

摘要: 自适应逆控制将系统扰动消除和动态响应性能独立分开控制,其性能的优劣取决于系统对象、逆对象及逆控制器模型辨识精度的高低。文中提出用动态函数连接神经网络来实现自适应逆控制系统对象、逆对象的同时在线建模和逆控制器的离线建模,并将模型参数的辨识转化为空间参数寻优。针对混沌初始化对已收敛种群结构的破坏性,提出用变参数混沌粒子群优化算法对神经网络权值进行全局寻优,通过仿真实验可以看出基于动态函数连接神经网络的建模误差小,辨识精度高;与当前的参考模型自适应控制方法进行对比分析,所提方法能取得较好的扰动消除效果,并能使系统的跟踪响应性能得到提高,从而验证了方法的有效性、可行性。

关键词: 自适应逆控制,扰动消除,系统辨识,动态函数连接神经网络,变参数,混沌粒子群算法

Abstract: Adaptive inverse control can eliminate the disturbance of the system and control the performance of dynamic response independently,and the performance of the adaptive inverse control system depends on the accuracy of the system object,the inverse object and the controller identification model.In this paper,the dynamic functional link neural network was proposed to realize the simultaneous on-line modeling of the adaptive inverse control system object and inverse object,and realize the off-line modeling of the controller,and the identification of model parameters was transformed into optimization of spatial parameters.Aiming at the destruction of convergent population structure by chaos initialization,this paper presented variable parameter chaotic particle swarm optimization algorithm to optimize the weights of the neural network.Through the simulation experiment,we can see that the modeling error based on the dynamic function link neural network is small and the identification accuracy based on the dynamic function link neural network is high.Compared with the current reference model adaptive control methods,the method in this paper can achieve better disturbance cancellation effect and improve the tracking response performance of the system,thus verifying the effectiveness and feasibility of the method.

Key words: Adaptive inverse control,Disturbance elimination,System identification,Dynamic function link neural network,Variable parameter,Chaos particle swarm optimization algorithm

[1] WIDROW B,WALACH E.自适应逆控制[M].刘绍棠,韩崇昭,译.西安:西安交通大学出版社,2000.
[2] 卢志刚,吴士昌,于灵慧.非线性自适应逆控制及其应用[M].北京:国防工业出版社,2004.
[3] COCHOFEL H J,WOOTEN D,PRINCIPE J.A neural network development environment for adaptive inverse control [J].IEEE World Congress on Computational Intelligence,1998,2:963-967.
[4] FAUSZ J L,CHELLABOINA V S,HADDAD M M.Inverse optimal adaptive control for nonlinear uncertain systems with exogenous disturbances [C]∥Proceedings of the 36th Confe-rence on Decision and Control.1998:2654-2659.
[5] XIE S Y.Adaptive inverse control and its application [D].Shandong:Shandong University,2007.(in Chinese) 解淑英.自适应逆控制及其应用研究[D].山东:山东大学,2007.
[6] LIU S,YU J S.Composite control combining neuro-fuzzy in-verse control with pid control and its application in a continuous stirred tank reactor[J].Control Theory and Applications,2001,18(5):769-773.
[7] MIREA,LETITIA.System identification using functional-linkneural networks with dynamic structure [C]∥15th Triennial World Congress.Barcelona,Spain,2002.
[8] LU H J.A new optimization algorithm based on Chaos [J].Zhejiang University Science A,2006,7(4):539-542.
[9] HAN H.The study of adaptive inverse control algorithm based on LMS [D].Changsha:Central South University,2008.(in Chinese) 韩华.基于LMS算法的自适应逆控制方法研究[D].长沙:中南大学,2008.
[10] LIU T,HAN H T,MA J.Study on model identification of Hammerstein sensor based on the function link neural network [J].Acta Metrologica Sinica,2015,36(1):97-101.(in Chinese) 刘滔,韩华亭,马婧.基于函数连接神经网络的传感器Hammerstein模型辨识研究[J].计量学报,2015,6(1):97-101.
[11] GUO Q M,HU H.The On-Line Monitoring System of Tower Crane Load Based on FLNN [J].Advanced Materials Research,2012,466-467:1373-1377.
[12] GONG Y L.The research of adaptive inverse control strategy for permanent magnet synchronous motor servo system [D].Changchu:Changchun University of Science and Technology,2013.(in Chinese) 宫玉琳.永磁同步电动机伺服系统自适应逆控制策略研究[D].长春:长春理工大学,2013.
[13] BAI Y.Research on high precision stabilized platform based on adaptive inverse control [D].Harbin:Harbin Institute of Technology,2012.(in Chinese) 白杨.基于自适应逆控制的高精度稳定平台的研究[D].哈尔滨:哈尔滨工业大学,2012.
[14] LI J W,CHENG Y M,CHEN K Z.Chaotic particle swarm optimization algorithm based on adaptive inertia weight[C]∥Control and Decision Conference.Beijing:IEEE,2014:1310-1315.
[15] PAN T S,DAO T K,CHU S C.Hybrid particle swarm optimization with bat algorithm [M].Switzerland:Springer International Publishing,2015:37-47.
[16] 胡寿松.自动控制原理[M].北京:科学出版社,2013
[17] LI J,QI X H,LIU X H,et al.Improved model reference adaptive control and its application in decoupling control [J].Journal of Electrical and Control,2015,19(5):112-120.(in Chinese) 李杰,齐晓慧,刘新海,等.改进模型参考自适应控制及其在解耦控制中的应用[J].电机与控制学报,2015,19(5):112-120.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 雷丽晖,王静. 可能性测度下的LTL模型检测并行化研究[J]. 计算机科学, 2018, 45(4): 71 -75, 88 .
[2] 夏庆勋,庄毅. 一种基于局部性原理的远程验证机制[J]. 计算机科学, 2018, 45(4): 148 -151, 162 .
[3] 厉柏伸,李领治,孙涌,朱艳琴. 基于伪梯度提升决策树的内网防御算法[J]. 计算机科学, 2018, 45(4): 157 -162 .
[4] 王欢,张云峰,张艳. 一种基于CFDs规则的修复序列快速判定方法[J]. 计算机科学, 2018, 45(3): 311 -316 .
[5] 孙启,金燕,何琨,徐凌轩. 用于求解混合车辆路径问题的混合进化算法[J]. 计算机科学, 2018, 45(4): 76 -82 .
[6] 张佳男,肖鸣宇. 带权混合支配问题的近似算法研究[J]. 计算机科学, 2018, 45(4): 83 -88 .
[7] 伍建辉,黄中祥,李武,吴健辉,彭鑫,张生. 城市道路建设时序决策的鲁棒优化[J]. 计算机科学, 2018, 45(4): 89 -93 .
[8] 刘琴. 计算机取证过程中基于约束的数据质量问题研究[J]. 计算机科学, 2018, 45(4): 169 -172 .
[9] 钟菲,杨斌. 基于主成分分析网络的车牌检测方法[J]. 计算机科学, 2018, 45(3): 268 -273 .
[10] 史雯隽,武继刚,罗裕春. 针对移动云计算任务迁移的快速高效调度算法[J]. 计算机科学, 2018, 45(4): 94 -99, 116 .