Optimized deep learning neural network predictive controller for continuous stirred tank reactor

Abstract In this paper, a deep learning neural network model predictive controller (DLNNMPC) is designed to analyse the performance of a non-linear continuous stirred tank reactor (CSTR) that performs parallel and series reactions. The data generated employing the state space model of CSTR is used to train the designed deep learning neural network controller. Deep Learning Neural Network (DLNN) progresses the training with its weights tuned by the proposed hybrid version of evolutionary algorithms – Particle Swarm Optimization (PSO) and Gravitational Search Algorithm (GSA). The developed hybrid PSO – GSA based DLNN model of continuous stirred tank reactor is employed in this paper for model predictive controller design. The effectiveness of the proposed DLNNMPC tuned by hybrid PSO – GSA for CSTR is validated for its performance on comparison with that of other designed Proportional – Integral (PI) and Proportional – Integral – Derivative (PID) controllers as available in early literatures for the same problem under consideration.

[1]  Xiaoping Luo,et al.  Direct Inverse Model Control Based on a New Improved CMAC Neural Network , 2010, ICIC.

[2]  Xuemei Ren,et al.  Adaptive non-linear compensation control based on neural networks for non-linear systems with time delay , 2009, Int. J. Syst. Sci..

[3]  R. Rajeswari,et al.  Neural Network Predictive Controller Based Nonlinearity Identification Case Study: Nonlinear Process Reactor - CSTR , 2014 .

[4]  Yu Guo,et al.  Adaptive neural network predictive control for nonlinear pure feedback systems with input delay , 2012 .

[5]  Haralambos Sarimveis,et al.  An offset-free neural controller based on a non-extrapolating scheme for approximating the inverse process dynamics , 2013 .

[6]  Marcin Kurdziel,et al.  Encouraging orthogonality between weight vectors in pretrained deep neural networks , 2016, Neurocomputing.

[7]  Haralambos Sarimveis,et al.  Direct versus indirect neural control based on radial basis function networks , 2014, 2014 6th Computer Science and Electronic Engineering Conference (CEEC).

[8]  Jing Feng.  Intelligent PID Control of Continuous Stirred Tank Reactors , 2009 .

[9]  Dong-Juan Li,et al.  Adaptive controller design-based neural networks for output constraint continuous stirred tank reactor , 2015, Neurocomputing.

[10]  Dong-Juan Li.  Neural network control for a class of continuous stirred tank reactor process with dead-zone input , 2014, Neurocomputing.

[11]  Ginuga Prabhaker Reddy,et al.  Control of Continuous Stirred Tank Reactor Using Artificial Neural Networks Based Predictive Control , 2012 .

[12]  A. Vasickaninova,et al.  Neural Network Predictive Control Of A Chemical Reactor , 2009, ECMS.

[13]  Dong-Juan Li.  Adaptive neural network control for a class of continuous stirred tank reactor systems , 2013, Science China Information Sciences.

[14]  Ruchi Varshney,et al.  ANN based IMC scheme for CSTR , 2009, ICAC3 '09.

[15]  Azah Mohamed,et al.  Control of Continuous Stirred Tank Reactor using Neural Networks , 2016 .

[16]  Haralambos Sarimveis,et al.  Control of processes with multiple steady states using MPC and RBF neural networks , 2011 .

[17]  Huaimin Wang,et al.  MABP: an optimal resource allocation approach in data center networks , 2014, Science China Information Sciences.

[18]  New SISO and MISO Adaptive Nonlinear Predictive Controllers based on self organizing RBF neural networks , 2008, 2008 3rd International Symposium on Communications, Control and Signal Processing.

[19]  Lin Li-jun.  Application of adaptive inverse control based on neural network for CSTR system , 2009 .

[20]  Mohammad Hosein Kazemi,et al.  Optimal design of PID controller for a CSTR system using particle swarm optimization , 2010, Proceedings of 14th International Power Electronics and Motion Control Conference EPE-PEMC 2010.

[21]  Margarita Terziyska,et al.  Recurrent Fuzzy-Neural Network with Fast Learning Algorithm for Predictive Control , 2013, ICANN.

[22]  Shao Cheng.  Neural network predictive control of continuous stirred-tank reactor based on Hammerstein-Wiener model , 2011 .

[23]  Jafari Nasr Mohammad Reza,et al.  ADAPTIVE PREDICTIVE CONTROLLERS USING A GROWING AND PRUNING RBF NEURAL NETWORK , 2011 .

[24]  M. Shahriari-kahkeshi,et al.  Nonlinear continuous stirred tank reactor (CSTR) identification and control using recurrent neural network trained Shuffled Frog Leaping Algorithm , 2011, The 2nd International Conference on Control, Instrumentation and Automation.

[25]  F. Bavafa,et al.  New approach to design a nonlinear PI controller for a CSTR system , 2011, The 2nd International Conference on Control, Instrumentation and Automation.