Since most process systems have nonlinearities, it is necessary to consider controller design schemes to deal with such systems. A new method of the generalized minimum variance control (GMVC) for nonlinear systems is proposed. In designing the GMVC, the predictive outputs must be estimated exactly by using the nonlinear model. However, because most nonlinear systems have a complex structure, it is difficult to make a suitable model for such systems. Then, the new method of modeling for nonlinear systems is also proposed by using GA. According to the newly proposed scheme, the structure and parameters of the nonlinear model are automatically generated. Finally, the effectiveness of the proposed scheme is numerically evaluated on a simulation example.
[1]
Shigeru Okuma,et al.
System Identification for Structure-Unknown Linear Dynamical System by Evolutionary Computation
,
2000
.
[2]
Sirish L. Shah,et al.
Design and experimental evaluation of a multivariable self-tuning PID controller
,
1998,
Proceedings of the 1998 IEEE International Conference on Control Applications (Cat. No.98CH36104).
[3]
Toru Yamamoto,et al.
A Design of Generalized Minimum Variance Controllers Using a GMDH Network for Nonlinear Systems
,
2001
.
[4]
Kumpati S. Narendra,et al.
Identification and control of dynamical systems using neural networks
,
1990,
IEEE Trans. Neural Networks.