Title: Non-linear model predictive control based on neural network model with modified differential evolution adapting weights

Authors: A.M. An, X.H. Hao, H.Y. Su, Q. Wang

Addresses: Institute of Electrical Engineering and Information Engineering, Lanzhou University of Technology, 287 Langongping Road, Qilihe District, Lanzhou, Gansu Province, 730050, P.R. China. ' Institute of Electrical Engineering and Information Engineering, Lanzhou University of Technology, 287 Langongping Road, Qilihe District, Lanzhou, Gansu Province, 730050, P.R. China. ' Institute of Cyber-Systems and Control, Zhejiang University, 38 Zheda Road, Yuquan Campus, Hangzhou, Zhejiang Province, 310027, P.R. China. ' Institute of Electrical Engineering and Information Engineering, Lanzhou University of Technology, 287 Langongping Road, Qilihe District, Lanzhou Gansu Province, 730050, P.R. China

Abstract: A modified differential evolution (MDE) optimisation approach is proposed to retrain the network weights of the multi-input multi-output artificial neural network (MIMO-ANN) process model. This is particularly useful for controlling the cases involving changing operating condition as well as highly non-linear processes. The utility of online retraining the network weights using MDE can further improve the predictive performances of the process model including both the possible control accuracy and the computational load reduction. A case study on a distillation column, which is a chemical non-linear process, is used to illustrate the effectiveness of the adaptive ANN based on MDE modelling and control method proposed in this paper. Significant improvements of the proposed strategy were obtained especially when assessing from the perspective of model generalisation.

Keywords: model predictive control; MPC; adaptive neural networks; distillation column; modified differential evolution; MDE; intelligent optimisation; nonlinear control; artificial neural networks; MIMO ANNs.

DOI: 10.1504/IJAMECHS.2010.033043

International Journal of Advanced Mechatronic Systems, 2010 Vol.2 No.3, pp.182 - 191

Published online: 07 May 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article