A structured PENN controller for a MIMO process

摘要

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.