A Combined Adaptive Neural Network and Nonlinear Model Predictive Control for Multirate Networked Industrial Process Control

CATEGORY: PROCESS CONTROL 
A Combined Adaptive Neural Network and Nonlinear Model Predictive Control for Multirate Networked Industrial Process Control

Type	Journal Article
Author	T. Wang
Author	H. Gao
URL	http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=7087381&url=http%3A%2F%2Fieeexplore.ieee.org%2Fxpls%2Fabs_all.jsp%3Farnumber%3D7087381
Volume	PP
Issue	99
Pages	1-1
Publication	IEEE Transactions on Neural Networks and Learning Systems
Date	2015
Abstract	Reports a study of the multirate networked industrial process control problem in double-layer architecture. Researchers studied the output tracking problem for sampled-data nonlinear plant at device layer with sampling period Td employing adaptive neural network (NN) control. Results revealed that the outputs of subsystems at device layer can track the decomposed setpoints. The outputs and inputs of the device layer subsystems were then sampled with sampling period Tu at operation layer to form the index prediction, which was used to predict the overall performance index at lower frequency. Radial basis function NN was used as the prediction function due to its approximation ability. Considering the dynamics of the overall closed-loop system, researchers proposed nonlinear model predictive control method to guarantee the system stability and compensate the network-induced delays and packet dropouts. Finally, a continuous stirred tank reactor system was given in the simulation part to demonstrate the effectiveness of the proposed method.