Hybrid Neural Network Controller Design for a Batch Reactor to Produce Methyl Methacrylate

Methyl methacrylate (MMA) production in an exothermic batch reactor provides a challenging problem for studying its dynamics behavior and temperature control. This work presents a neural network forward model (NN) to predict a concentration of methyl methacrylate, a jacket temperature and temperature profile in the reactor. An optimal NN model has been employed to predict state variables incorporating into a model predictive control (MPC) algorithm to determine optimal control actions. To control the temperature, neural network based control approaches: a neural network direct inverse control (NNDIC) and a neural network based model predictive control (NNMPC) have been formulated. In addition, a dynamic optimization approach has been applied to find out an optimal operating temperature to achieve maximizing the MMA product at specified final time. Simulation results have indicated that the NNMPC is robust and gives the best control results among the PID and NNDIC in all cases.

[1]  D. Himmelblau.  Accounts of Experiences in the Application of Artificial Neural Networks in Chemical Engineering , 2008 .

[2]  Wojciech Stanek,et al.  Neural modelling of steam boilers , 2007 .

[3]  Ai Poh Loh,et al.  Neural network modelling and control strategies for a pH process , 1995 .

[4]  Dingli Yu,et al.  Implementation of neural network predictive control to a multivariable chemical reactor , 2003 .

[5]  Amornchai Arpornwichanop,et al.  On-line dynamic optimization integrated with generic model control of a batch crystallizer , 2008 .

[6]  Iqbal M. Mujtaba,et al.  Batch control improvement by model predictive control based on multiple reduced-models , 2008 .

[7]  Wonhui Cho,et al.  Iterative learning dual-mode control of exothermic batch reactors , 2004, 2004 5th Asian Control Conference (IEEE Cat. No.04EX904).

[8]  Dong-Hoon Lee,et al.  Neural Network-Based System Identification and Controller Synthesis for an Industrial Sewing Machine , 2004 .

[9]  R. Murray-Smith,et al.  Neural networks for modelling and control of a non-linear dynamic system , 1992, Proceedings of the 1992 IEEE International Symposium on Intelligent Control.

[10]  Paisan Kittisupakorn,et al.  Dynamic neural network modeling for hydrochloric acid recovery process , 2005 .

[11]  Soorathep Kheawhom,et al.  MPC for LPV Systems Based on Parameter-Dependent Lyapunov Function with Perturbation on Control Input Strategy , 2012 .

[12]  Iqbal M. Mujtaba,et al.  Optimal control of batch reactors using generic model control (GMC) and neural network , 2000 .

[13]  Amornchai Arpornwichanop,et al.  Control of fed-batch bioreactors by a hybrid on-line optimal control strategy and neural network estimator , 2009, Neurocomputing.

[14]  Iqbal M. Mujtaba,et al.  Performance of different types of controllers in tracking optimal temperature profiles in batch reactors , 2000 .

[15]  Dingli Yu,et al.  Neural model input selection for a MIMO chemical process , 2000 .

[16]  Mohd Azlan Hussain,et al.  Neural network based model predictive control for a steel pickling process , 2009 .

[17]  Iqbal M. Mujtaba,et al.  On-line dynamic optimization and control strategy for improving the performance of batch reactors , 2005 .

[18]  Ferenc Szeifert,et al.  Process dynamics and temperature control of fed-batch reactors , 1995 .

[19]  Iqbal M. Mujtaba,et al.  Neural network based modelling and control of batch reactor. , 2006 .

[21]  Amornchai Arpornwichanop,et al.  Neural network inverse model-based controller for the control of a steel pickling process , 2005, Comput. Chem. Eng..

[22]  J. Spivey,et al.  Novel Catalysts for the Environmentally Friendly Synthesis of Methyl Methacrylate , 1997 .

[23]  Vincenzo Piuri,et al.  Neural modeling of dynamic systems with nonmeasurable state variables , 1999, IEEE Trans. Instrum. Meas..