Premium
Optimization design of RBF‐ARX model and application research on flatness control system
Author(s) -
Zhang XiuLing,
Cheng Long,
Hao Shuang,
Gao WuYang,
Lai YongJin
Publication year - 2016
Publication title -
optimal control applications and methods
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.458
H-Index - 44
eISSN - 1099-1514
pISSN - 0143-2087
DOI - 10.1002/oca.2240
Subject(s) - flatness (cosmology) , control theory (sociology) , nonlinear system , radial basis function , autoregressive model , multivariable calculus , model predictive control , hierarchical rbf , genetic algorithm , computer science , artificial neural network , control engineering , engineering , mathematics , artificial intelligence , control (management) , machine learning , physics , cosmology , quantum mechanics , econometrics
Summary The radial basis function (RBF) network and autoregressive exogenous (ARX) model are combined to form the structure of the RBF‐ARX model. The RBF‐ARX model can describe the global nonlinear dynamic process of the object, and its function coefficients are approximated by data‐driven method. The structured nonlinear parameters optimization method (SNPOM) is generally used to optimize model parameters, but this method is very complicated and hard to be mastered by engineers. However, genetic algorithm (GA) is simple and widely used. So the thought of GA optimizing RBF‐ARX is generated, called GA‐ARX‐RBF, and applied to nonlinear dynamic flatness control system. In this article, the recursive least squares method to optimize linear weights of RBF is also used to improve the SNPOM, which reduces the complexity and storage capacity of data processing. Meanwhile, GA to optimize all the parameters of the RBF‐ARX model replaces SNPOM completely. A GA‐RBF‐ARX modeling and optimizing method is proposed. In order to prove the efficiency of GA‐RBF‐ARX, it is applied into flatness control system, which has the characters of nonlinear, multivariable, and multi‐disturbance. The flatness recognition model and flatness predictive model are established. A predictive controller based on GA‐RBF‐ARX is designed for 900HC reversible cold rolling mill. The simulation results demonstrate that the flatness control system based on GA‐RBF‐ARX is effective and has a better precision. The method is easily mastered by engineers and helps to promote the practical value of RBF‐ARX. Copyright © 2016 John Wiley & Sons, Ltd.