Title :
Neural networks for modelling and control of discrete-time nonlinear systems
Author :
Jin, Liang ; Nikiforuk, Peter N. ; Gupta, Madan M.
Author_Institution :
Intelligent Syst. Res. Lab., Saskatchewan Univ., Saskatoon, Sask., Canada
Abstract :
The modelling and control for a class of SISO discrete-time nonlinear systems is discussed in this paper using multilayered feedforward neural networks (MFNNs). The ability of MFNNs to model arbitrary nonlinear functions is incorporated to approximate the unknown nonlinear I/O relationship and its inverse using a novel learning algorithm. In order to overcome the difficulties associated with simultaneous online identification and control in neural networks based control systems, the new learning control architectures which are based on the Kalman filter equations are developed for control systems with online identification and control ability. The simulation results are also provided
Keywords :
Kalman filters; discrete time systems; feedforward neural nets; modelling; multilayer perceptrons; neurocontrollers; nonlinear control systems; Kalman filter equations; MFNN; SISO discrete-time nonlinear systems; control; learning algorithm; modelling; multilayered feedforward neural networks; online identification; unknown nonlinear I/O relationship approximation; Control systems; Convergence; Feedforward neural networks; Intelligent networks; Intelligent systems; Multi-layer neural network; Neural networks; Neurons; Nonlinear control systems; Nonlinear equations; Nonlinear systems;
Conference_Titel :
Systems, Man, and Cybernetics, 1994. Humans, Information and Technology., 1994 IEEE International Conference on
Conference_Location :
San Antonio, TX
Print_ISBN :
0-7803-2129-4
DOI :
10.1109/ICSMC.1994.399994
