A structured PENN controller for a MIMO process

Author

Ishida, Masaru ; Ohba, Takehiro

Author_Institution

Res. Lab. of Resources Utilization, Tokyo Inst. of Technol., Yokohama, Japan

fYear

1996

Firstpage

166

Lastpage

169

Abstract

This paper presents a neural net controller for a multi-input, multi-output (MIMO) process. This controller is based on the PENN (Policy and Experience driven Neural Network) method and is structured with small controllers for SISO processes. The characteristic feature of this scheme is that these PENN controllers cooperate with each other and search for the best cooperation. The simulation results of a crystal-growth process indicate that the proposed controller has the ability to learn the interactions between control variables

Keywords

MIMO systems; cooperative systems; genetic algorithms; learning (artificial intelligence); neurocontrollers; process control; search problems; MIMO process control; Policy and Experience Neural Network; SISO process; control variable interactions; cooperative control; crystal-growth process simulation; genetic algorithms; learning; multi-input multi-output process; neural net controller; search; structured PENN controller; Assembly; Control systems; Laboratories; MIMO; Neural networks; Noise reduction; Noise robustness; Process control; Steady-state; Timing;

fLanguage

English

Publisher

ieee

Conference_Titel

Evolutionary Computation, 1996., Proceedings of IEEE International Conference on

Conference_Location

Nagoya

Print_ISBN

0-7803-2902-3

Type

conf

DOI

10.1109/ICEC.1996.542354

Filename

542354