A modified Smith predictive scheme based back-propagation neural network approach for FOPDT processes control

Abstract In this paper, a novel control scheme to deal with process uncertainties in the form of disturbance loads and modelling errors, as well as time-varying process parameters is proposed by applying the back-propagation neural network (BPNN) approach. A BPNN predictive controller that replaces the entire Smith predictor structure is initially trained offline. Lyapunov direct method is used to prove that the convergence of this BPNN is guaranteed by selecting a suitable learning rate during the learning process. However, the Smith predictor based BPNN control is an off-line training based algorithm, which is a time consuming method and requires a known process plant input from the controller. A desired control input to the process is difficult to obtain for the training of the network. As a result a group of proper training data (target control inputs and outputs) can hardly be provided. In order to overcome this problem, a BPNN with an on-line training algorithm is introduced for the control of a First Order plus Dead Time (FOPDT) process. The stability analysis is carried out using the Lyapunov criterion to demonstrate the network convergence ability. Simulation results show that this proposed online trained neural Smith predictor based controller provides excellent robustness to process modelling errors and disturbance loads, and high adaptability to time varying processes parameters.

[1]  Zoubir Zouaoui,et al.  A neuro-fuzzy compensator based Smith predictive control for FOPLDT process , 2011, 2011 IEEE International Conference on Mechatronics and Automation.

[2]  Frank L. Lewis,et al.  Output feedback control of rigid robots using dynamic neural networks , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[3]  Frank L. Lewis,et al.  Neural net robot controller with guaranteed tracking performance , 1995, IEEE Trans. Neural Networks.

[4]  Tien Chi Chen,et al.  Model reference robust speed control for induction-motor drive with time delay based on neural network , 2001, IEEE Trans. Syst. Man Cybern. Part A.

[5]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[6]  Pei-Guang Wang,et al.  Smith predictive control based on NN , 2005, 2005 International Conference on Machine Learning and Cybernetics.

[7]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[8]  Takayuki Yamada,et al.  Learning control using neural networks , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[9]  Frank L. Lewis,et al.  ROBUST ADAPTIVE CONTROL OF ROBOTS USING NEURAL NETWORK: GLOBAL STABILITY , 2008 .

[10]  Hao Chen,et al.  Neuro-fuzzy-based Smith predictor for FOPLDT process control , 2012, Int. J. Mechatronics Autom..

[11]  Pedro Albertos,et al.  Robust control design for long time-delay systems , 2009 .

[12]  Kwang Y. Lee,et al.  Diagonal recurrent neural networks for dynamic systems control , 1995, IEEE Trans. Neural Networks.

[13]  Léon Personnaz,et al.  Nonlinear internal model control using neural networks: application to processes with delay and design issues , 2000, IEEE Trans. Neural Networks Learn. Syst..

[14]  Ching-Hung Lee,et al.  Identification and Fuzzy Controller Design for Nonlinear Uncertain Systems with Input Time-Delay , 2009 .

[15]  O. J. M. Smith,et al.  A controller to overcome dead time , 1959 .

[16]  M. Elarafi,et al.  Modeling and control of pH neutralization using neural network predictive controller , 2008, 2008 International Conference on Control, Automation and Systems.

[17]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[18]  Fuchun Sun,et al.  Neural network control of flexible-link manipulators using sliding mode , 2006, Neurocomputing.

[19]  Hao-guang Chen,et al.  Application of fuzzy logic to reduce modelling errors in PIDSP for FOPDT process control , 2011, 2011 19th Mediterranean Conference on Control & Automation (MED).

[20]  Elder M. Hemerly,et al.  Direct adaptive control using feedforward neural networks , 2003 .

[21]  Frank L. Lewis,et al.  Multilayer neural-net robot controller with guaranteed tracking performance , 1996, IEEE Trans. Neural Networks.

[22]  Furong Gao,et al.  Double-controller scheme for control of processes with dominant delay , 1998 .

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

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