Neural emulator and controller with decoupled adaptive rates for nonlinear systems : application to chemical reactors

In this paper, we develop an indirect adaptive control structure based on recurrent neural networks. An adaptive emulator inspired from the Real Time recurrent Learning algorithm is presented. Neural network does not learn the plant dynamics but emulates the input-output mapping with a small time window. Thereafter, a controller with a structure similar to neural emulator is described. Both emulator and controller adapt their parameters using an online adaptation algorithm in order to track the process variations. Independent adaptation of networks parameters improve controller performances. Regulation and tracking problems are investigated according to nonlinear system simulations. The satisfactory obtained results show a very good performances in terms of neural emulation and control of nonlinear systems. The contributions of this paper are the validation of our emulator with experimental data from the batch reactor of National Engineering of Gabes, Tunisia and the application of the real time control algorithm with decoupled adaptive rates to large scale process: Tennessee Eastman Challenge Process (TECP).

[1]  Fabrice Druaux,et al.  Neural network control for large scale systems with faults and perturbations , 2010, 2010 Conference on Control and Fault-Tolerant Systems (SysTol).

[2]  Jie Zhang,et al.  Batch-to-batch optimal control of a batch polymerisation process based on stacked neural network models , 2008 .

[3]  N. L. Ricker,et al.  Multi-objective control of the Tennessee Eastman challenge process , 1995, Proceedings of 1995 American Control Conference - ACC'95.

[4]  Mekki Ksouri,et al.  Application of Adaptive Controllers for the Temperature Control of a Semi-Batch Reactor , 2001, Int. J. Comput. Eng. Sci..

[5]  Chi-Tsung Huang,et al.  Estimate of process compositions and plantwide control from multiple secondary measurements using artificial neural networks , 2003, Comput. Chem. Eng..

[6]  Insoo Lee,et al.  Neural network indirect adaptive control with fast learning algorithm , 1996, Neurocomputing.

[7]  Shuzhi Sam Ge,et al.  Adaptive control of partially known nonlinear multivariable systems using neural networks , 2001, Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206).

[8]  Fabrice Druaux,et al.  Neural emulation applied to chemical reactors , 2010, 2010 7th International Multi- Conference on Systems, Signals and Devices.

[9]  O. Nelles.  Nonlinear System Identification , 2001 .

[10]  Ben C. Juricek,et al.  Process control applications of subspace and regression-based identification and monitoring methods , 2005, Proceedings of the 2005, American Control Conference, 2005..

[11]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[12]  I. Elhanany,et al.  TRTRL: A Localized Resource-Efficient Learning Algorithm for Recurrent Neural Netowrks , 2006, 2006 49th IEEE International Midwest Symposium on Circuits and Systems.

[13]  Ronald J. Williams,et al.  Adaptive state representation and estimation using recurrent connectionist networks , 1990 .

[14]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[15]  Fabrice Druaux,et al.  Indirect neural control for plant-wide systems: Application to the Tennessee Eastman Challenge Process , 2010, Comput. Chem. Eng..

[16]  Fabrice Druaux,et al.  STABLE ADAPTIVE CONTROL WITH RECURRENT NEURAL NETWORKS , 2005 .

[17]  E. F. Vogel,et al.  A plant-wide industrial process control problem , 1993 .

[18]  Ridha Ben Abdennour,et al.  Real-time application of discrete second order sliding mode control to a chemical reactor , 2009 .

[19]  ZerkaouiSalem,et al.  Stable adaptive control with recurrent neural networks for square MIMO non-linear systems , 2009 .

[20]  Fabrice Druaux,et al.  Autonomous learning algorithm for fully connected recurrent networks , 2003, ESANN.

[21]  Curtis Collins,et al.  A dynamic recurrent neural network-based controller for a rigid–flexible manipulator system , 2004 .

[22]  Tommy W. S. Chow,et al.  A recurrent neural-network-based real-time learning control strategy applying to nonlinear systems with unknown dynamics , 1998, IEEE Trans. Ind. Electron..

[23]  Jin Zhang,et al.  Adaptive neural network control for a class of MIMO nonlinear systems with disturbances in discrete-time , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[24]  Marimuthu Palaniswami,et al.  An adaptive tracking controller using neural networks for a class of nonlinear systems , 1998, IEEE Trans. Neural Networks.

[25]  Dale E. Seborg,et al.  Identification of the Tennessee Eastman Challenge Process with Subspace Methods , 2000 .

[26]  Rong-Jong Wai,et al.  Hybrid controller using fuzzy neural networks for identification and control of induction servo motor drive , 2000, Neurocomputing.

[27]  Ridha Ben Abdennour,et al.  Supervision based on partial predictors for a multimodel generalised predictive control: experimental validation on a semi-batch reactor , 2009, Int. J. Model. Identif. Control..