DE-based neural network nonlinear model predictive control and its application for the pH neutralization reactor control

In this paper, a nonlinear model predictive control (NMPC) algorithm based on differential evolution (DE) and radial base function (RBF) neural network is proposed. RBF neural network is used for the modeling. And DE algorithm is used to solve the optimal predictive control input due to its characteristic of global optimum, easy implementation and fast convergence. The simulation results on the pH control of the neutralization rector by the proposed DE-RBF-MPC show that this control strategy is effective.

[1]  Yu Huanjun.  DIFFERENTIAL EVOLUTION ALGORITHM BASED ON EUGENIC STRATEGY AND ITS APPLICATION TO CHEMICAL ENGINEERING , 2004 .

[2]  Jia Ping.  pH Neutralization Process Multi step Predictive Control Strategy Based on Neural Network , 2000 .

[3]  Stephen Piche,et al.  Nonlinear model predictive control using neural networks , 2000 .

[4]  Jin Yi-hui.  Advances in differential evolution , 2007 .

[5]  Gu Xing-sheng.  Development of Differential Evolution Algorithm , 2007 .

[6]  S. Joe Qin,et al.  A survey of industrial model predictive control technology , 2003 .

[7]  R. Storn,et al.  On the usage of differential evolution for function optimization , 1996, Proceedings of North American Fuzzy Information Processing.

[8]  Li Shu-chen.  An Overview of New Algorithms in Predictive Control , 2004 .

[9]  B. Bequette.  Nonlinear control of chemical processes: a review , 1991 .

[10]  Zhao Ying.  Predictive Control of Nonlinear System Based on RBF Neural Network , 2002 .

[11]  Anthony Rossiter.  Recent developments in predictive control , 2006 .

[12]  Zhang Yan.  A Survey on Neural-Network Based Nonlinear Predictive Control , 2002 .

[13]  R. Storn,et al.  Differential Evolution - A simple and efficient adaptive scheme for global optimization over continuous spaces , 2004 .

[14]  James B. Rawlings,et al.  Tutorial overview of model predictive control , 2000 .

[15]  F. L. Lewis,et al.  Neural-network predictive control for nonlinear dynamic systems with time-delay , 2003, IEEE Trans. Neural Networks.

[16]  Weng Xue.  Neural network predictive control based on predicted steady state error , 2000 .

[17]  Peng Yun-feng.  MPC Algorithm Research Based on Models , 2002 .

[18]  Chyi Hwang,et al.  Optimal approximation of linear systems by a differential evolution algorithm , 2001, IEEE Trans. Syst. Man Cybern. Part A.

[19]  Michael A. Henson,et al.  Nonlinear model predictive control: current status and future directions , 1998 .

[20]  Jay H. Lee,et al.  Model predictive control: past, present and future , 1999 .

[21]  Wang Shuqing.  Neural network based multi-step predictive control for nonlinear systems , 2005 .

[22]  Haralambos Sarimveis,et al.  A Simulated Annealing Algorithm for Prioritized Multiobjective Optimization—Implementation in an Adaptive Model Predictive Control Configuration , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[23]  Ma Wen.  On Research Development and Application of Dynamic Matrix Control , 2005 .

[24]  Venugopal G. Krishnapura,et al.  A neural adaptive controller , 2000 .

[25]  Sebastian Engell,et al.  Model Predictive Control Using Neural Networks [25 Years Ago] , 1995, IEEE Control Systems.

[26]  Wang Xudong.  THE THEORY OF RBF NEURAL NETWORK AND ITS APPLICATION IN CONTROL , 1997 .

[27]  Bhu Dev Sharma,et al.  Bounds on Distortion Due to Error for Rates Below and Above the Channel Capacity , 1974, Inf. Control..