Computationally efficient nonlinear predictive control based on neural Wiener models

This paper describes a computationally efficient nonlinear model predictive control (MPC) algorithm based on neural Wiener models and its application. The model contains a linear dynamic part in series with a steady-state nonlinear part which is realised by a neural network. In the presented MPC algorithm the model is linearised on-line, as a result the future control policy is easily calculated from a quadratic programming problem. The algorithm gives control performance similar to that obtained in fully fledged nonlinear MPC, which hinges on non-convex optimisation. In order to demonstrate the accuracy and the computational efficiency of the considered MPC algorithm a polymerisation process is studied.

[1]  Mohamed Azlan Hussain,et al.  Review of the applications of neural networks in chemical process control - simulation and online implementation , 1999, Artif. Intell. Eng..

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

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

[4]  Riccardo Scattolini,et al.  On the choice of the horizon in long-range predictive control - Some simple criteria , 1990, Autom..

[5]  Piotr M. Marusak,et al.  Advantages of an easy to design fuzzy predictive algorithm in control systems of nonlinear chemical reactors , 2009, Appl. Soft Comput..

[6]  Maciej Ławryńczuk,et al.  Suboptimal Nonlinear Predictive Control with MIMO Neural Hammerstein Models , 2008 .

[7]  Maciej Ławryńczuk,et al.  SOFT COMPUTING IN MODEL – BASED PREDICTIVE CONTROL † , 2006 .

[8]  Heinz Unbehauen,et al.  Adaptive position control of electrohydraulic servo systems using ANN , 2000 .

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

[10]  Mahdi Mahfouf,et al.  Non-linear generalized predictive control (NLGPC) applied to muscle relaxant anaesthesia , 1998 .

[11]  Ronald K. Pearson,et al.  Nonlinear model-based control using second-order Volterra models , 1995, Autom..

[12]  Niels Kjølstad Poulsen,et al.  Neural Networks for Modelling and Control of Dynamic Systems: A Practitioner’s Handbook , 2000 .

[13]  Ying Chen,et al.  Identifying chaotic systems via a Wiener-type cascade model , 1997 .

[14]  Andrzej Kasiński,et al.  Comparison of supervised learning methods for spike time coding in spiking neural networks , 2006 .

[15]  O. Agamennoni,et al.  A nonlinear model predictive control system based on Wiener piecewise linear models , 2003 .

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

[17]  Maciej Ławryńczuk,et al.  A Family of Model Predictive Control Algorithms With Artificial Neural Networks , 2007, Int. J. Appl. Math. Comput. Sci..

[18]  E. Camacho,et al.  Generalized Predictive Control , 2007 .

[19]  Maciej Ławryńczuk,et al.  Suboptimal Nonlinear Predictive Control Based on Neural Wiener Models , 2008, AIMSA 2008.

[20]  W. R. Cluett,et al.  Linearizing feedforward-feedback control of pH processes based on the Wiener model , 2005 .

[21]  W. R. Cluett,et al.  A new approach to the identification of pH processes based on the Wiener model , 1995 .

[22]  Piotr Tatjewski,et al.  Soft computing in modelbased predictive control footnotemark , 2006 .

[23]  Torbjörn Wigren,et al.  Recursive prediction error identification using the nonlinear wiener model , 1993, Autom..

[24]  Hannu T. Toivonen,et al.  A neural network model predictive controller , 2006 .

[25]  Stephen A. Billings,et al.  Identification of systems containing linear dynamic and static nonlinear elements , 1982, Autom..

[26]  Jan M. Maciejowski,et al.  Predictive control : with constraints , 2002 .

[27]  E. Baeyens,et al.  Wiener model identification and predictive control of a pH neutralisation process , 2004 .

[28]  Haralambos Sarimveis,et al.  Nonlinear adaptive model predictive control based on self‐correcting neural network models , 2005 .

[29]  Yi Cao,et al.  Nonlinear system identification for predictive control using continuous time recurrent neural networks and automatic differentiation , 2008 .

[30]  Niels Kjølstad Poulsen,et al.  Generalized predictive control in the delta-domain , 1995, Proceedings of 1995 American Control Conference - ACC'95.

[31]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[32]  Dingli Yu,et al.  Neural model adaptation and predictive control of a chemical process rig , 2006, IEEE Transactions on Control Systems Technology.

[33]  Ahmet Palazoglu,et al.  Model predictive control based on Wiener models , 1998 .

[34]  Aarne Halme,et al.  Modeling of chromatographic separation process with Wiener-MLP representation , 2001 .

[35]  Andrzej Janczak.  Identification of Nonlinear Systems Using Neural Networks and Polynomial Models , 2005 .

[36]  S. Norquay,et al.  Application of Wiener model predictive control (WMPC) to an industrial C2-splitter , 1999 .

[37]  Fernando José Von Zuben,et al.  Constructive learning neural network applied to identification and control of a fuel-ethanol fermentation process , 2009, Eng. Appl. Artif. Intell..

[38]  H. Bloemen,et al.  Wiener Model Identification and Predictive Control for Dual Composition Control of a Distillation Column , 2001 .

[39]  David W. Clarke,et al.  Generalized predictive control - Part I. The basic algorithm , 1987, Autom..

[40]  A. Janczak,et al.  Identification of Nonlinear Systems Using Neural Networks and Polynomial Models: A Block-Oriented Approach , 2004 .

[41]  Yaman Arkun,et al.  A global solution to the nonlinear model predictive control algorithms using polynomial ARX models , 1997 .

[42]  David W. Clarke,et al.  Generalized Predictive Control - Part II Extensions and interpretations , 1987, Autom..

[43]  W. Greblicki.  Nonparametric identification of Wiener systems by orthogonal series , 1994, IEEE Trans. Autom. Control..

[44]  Maciej Lawrynczuk,et al.  A Computationally Efficient Nonlinear Predictive Control Algorithm with RBF Neural Models and Its Application , 2007, RSEISP.

[45]  Grazyna Pajunen,et al.  Adaptive control of wiener type nonlinear systems , 1992, Autom..

[46]  William L. Luyben,et al.  Process Modeling, Simulation and Control for Chemical Engineers , 1973 .

[47]  Jonas Sjöberg,et al.  Neural networks for modelling and control of dynamic systems, M. Nørgaard, O. Ravn, N. K. Poulsen and L. K. Hansen, Springer, London, 2000, xiv+246pp. , 2001 .

[48]  Thomas E Marlin,et al.  Process Control , 1995 .

[49]  Sirish L. Shah,et al.  Constrained nonlinear MPC using hammerstein and wiener models: PLS framework , 1998 .

[50]  R. Pearson.  Selecting nonlinear model structures for computer control , 2003 .

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

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

[53]  Mokhtar S. Bazaraa,et al.  Nonlinear Programming: Theory and Algorithms , 1993 .

[54]  H. Al. Duwaish,et al.  Use of Multilayer Feedforward Neural Networks in Identification and Control of Wiener Model , 1996 .

[55]  Francisco Jurado,et al.  Model Based Predictive Control of Fuel Cells , 2006 .

[56]  Yi Cao,et al.  Nonlinear model predictive control for the ALSTOM gasifier , 2006 .