Data-driven controller design for general MIMO nonlinear systems via virtual reference feedback tuning and neural networks
作者： Pengfei Yan , Derong Liu , Ding Wang , Hongwen Ma
DOI: 10.1016/J.NEUCOM.2015.07.017
关键词: Optimization problem 、 Control theory 、 Transfer function 、 Linear filter 、 Linear system 、 Artificial neural network 、 Nonlinear system 、 Data-driven 、 MIMO 、 Computer science
摘要: In this paper, we develop a novel data-driven multivariate nonlinear controller design method for multi-input-multi-output (MIMO) systems via virtual reference feedback tuning (VRFT) and neural networks. To the best of authors' knowledge, it is first time to introduce VRFT MIMO in theory. Unlike standard linear systems, restate model control problem with time-domain absence transfer functions simplify objective function without filter. Then, prove that reaches minimum at same point as optimization give relationship between bounds two problems VRFT. A three-layer network used implement developed method. Finally, simulations are conducted verify validity our
acm.org
elsevier.com
sci-hub.se 参考文章(47)
Changyun Wen, Yangquan Chen, Iterative Learning Control: Convergence, Robustness and Applications ,(1999)
S. Formentin, S.M. Savaresi, L. Del Re, Non-iterative direct data-driven controller tuning for multivariable systems: theory and application Iet Control Theory and Applications. ,vol. 6, pp. 1250- 1257 ,(2012) , 10.1049/IET-CTA.2011.0204
Kevin L. Moore, Michael J. Grimble, M. Johnson, Iterative Learning Control for Deterministic Systems ,(1992)
H. Hjalmarsson, S. Gunnarsson, M. Gevers, A convergent iterative restricted complexity control design scheme conference on decision and control. ,vol. 2, pp. 1735- 1740 ,(1994) , 10.1109/CDC.1994.411185
J.C. Spall, J.A. Cristion, Model-free control of general discrete-time systems conference on decision and control. pp. 2792- 2797 ,(1993) , 10.1109/CDC.1993.325704
Simone Formentin, Klaske van Heusden, Alireza Karimi, A comparison of model‐based and data‐driven controller tuning International Journal of Adaptive Control and Signal Processing. ,vol. 28, pp. 882- 897 ,(2014) , 10.1002/ACS.2415
Yuzhu Huang, Derong Liu, Neural-network-based optimal tracking control scheme for a class of unknown discrete-time nonlinear systems using iterative ADP algorithm Neurocomputing. ,vol. 125, pp. 46- 56 ,(2014) , 10.1016/J.NEUCOM.2012.07.047
Jie Pan, Xuesong Wang, Yuhu Cheng, Ge Cao, Multi-source transfer ELM-based Q learning Neurocomputing. ,vol. 137, pp. 57- 64 ,(2014) , 10.1016/J.NEUCOM.2013.04.045
Ding Wang, Derong Liu, Neuro-optimal control for a class of unknown nonlinear dynamic systems using SN-DHP technique Neurocomputing. ,vol. 121, pp. 218- 225 ,(2013) , 10.1016/J.NEUCOM.2013.04.006
Xiong Yang, Derong Liu, Ding Wang, Reinforcement learning for adaptive optimal control of unknown continuous-time nonlinear systems with input constraints International Journal of Control. ,vol. 87, pp. 553- 566 ,(2014) , 10.1080/00207179.2013.848292