神经网络预测控制局部优化初值确定方法.PDFVIP

31 6 Vol. 31 No. 6 2014 6 Control Theory Applications Jun. 2014 DOI: 10.7641/CTA.2014.31262 , , (1. , 221008; 2. , 221111) : , . , , . BP, , , , . : ; ; ; : TP273 : A Method to determine initial value of local optimization for neural network predictive control FAN Zhao-feng , MA Xiao-ping, SHAO Xiao-gen (1. School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou Jiangsu 221008, China; 2. Department of College of Information and Electrical Engineering, Xuzhou Institute of Technology, Xuzhou Jiangsu 221111, China) Abstract: To deal with the performance degradation caused by improper initial values in neural network local optimiza- tion predictive control, we propose a method to dynamically determine the initial values. In each optimization cycle the minimum output error point is selected by calculating the inverse neural network. The existence of the minimal value of the objective function between this point and the current control point can be ensured and proved through modifying the weighting factor. Finally, a simulation experiment is carried out to verify the proposed method using a back propagation (BP) neural network as the predictive model, and the Newton-Raphson algorithm is employed as the receding horizon op- timization strategy. The results show that the initial value problem can be solved to improve the reliability of the control system. Key words: neural networks; model predictive control; optimization; initial value problems 1 (Introduction) [3] (MPC), (GD), (N–R)L