Model predictive control of nonlinear affine systems based on the general projection neural network and its application to a continuous stirred tank reactor

Model predictive control (MPC) is an advanced technique for process control. It is based on iterative, finite horizon optimization of a cost function associated with a plant model. Neural network is an effective approach for on-line optimization problems. In this paper, we apply the general projection neural network for MPC of nonlinear affine systems. Continuous stirred tank reactor (CSTR) system is a typical chemical reactor widely used in chemical industry and can be characterized as a nonlinear affine system. The general projection neural network based MPC is applied to the CSTR problem with input and output constraints. This application demonstrates the usefulness and effectiveness of proposed MPC approach to industrial problems.

[1]  Tao Zhang,et al.  Nonlinear adaptive control using neural networks and its application to CSTR systems , 1999 .

[2]  Jun Wang,et al.  A primal-dual neural network for online resolving constrained kinematic redundancy in robot motion control , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[3]  Salah Leulmi,et al.  Optimal control of a CSTR process , 2008 .

[4]  A. B. Poore,et al.  On the dynamic behavior of continuous stirred tank reactors , 1974 .

[5]  Piotr Tatjewski,et al.  Advanced Control of Industrial Processes: Structures and Algorithms , 2006 .

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

[7]  Jun Wang,et al.  A projection neural network and its application to constrained optimization problems , 2002 .

[8]  Basil Kouvaritakis,et al.  Nonlinear predictive control : theory and practice , 2001 .

[9]  Chia-Feng Juang,et al.  Recurrent fuzzy network design using hybrid evolutionary learning algorithms , 2007, Neurocomputing.

[10]  Qingshan Liu,et al.  A One-Layer Recurrent Neural Network With a Discontinuous Hard-Limiting Activation Function for Quadratic Programming , 2008, IEEE Transactions on Neural Networks.

[11]  Jun Wang,et al.  A general projection neural network for solving monotone variational inequalities and related optimization problems , 2004, IEEE Transactions on Neural Networks.

[12]  Jun Wang,et al.  A general projection neural network for solving optimization and related problems , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[13]  Fen Wu.  LMI-based robust model predictive control and its application to an industrial CSTR problem , 2001 .

[14]  Shubao Liu,et al.  A Simplified Dual Neural Network for Quadratic Programming With Its KWTA Application , 2006, IEEE Transactions on Neural Networks.

[15]  Xiaolin Hu,et al.  An Improved Dual Neural Network for Solving a Class of Quadratic Programming Problems and Its $k$-Winners-Take-All Application , 2008, IEEE Transactions on Neural Networks.

[16]  Jun Wang,et al.  A recurrent neural network with exponential convergence for solving convex quadratic program and related linear piecewise equations , 2004, Neural Networks.

[17]  Dauda Olurotimi Araromi,et al.  Neural Network Control of CSTR for Reversible Reaction Using Reverence Model Approach , 2007 .

[18]  Jun Wang,et al.  Two neural network approaches to model predictive control , 2008, 2008 American Control Conference.

[19]  Xiaolin Hu,et al.  A New Recurrent Neural Network for Solving Convex Quadratic Programming Problems With an Application to the $k$-Winners-Take-All Problem , 2009, IEEE Transactions on Neural Networks.

[20]  Jun Wang,et al.  Model predictive control for nonlinear affine systems based on the simplified dual neural network , 2009, 2009 IEEE Control Applications, (CCA) & Intelligent Control, (ISIC).