A GA-based neural fuzzy system for temperature control

This paper addresses the structure and an associated learning algorithm of a feedforward multilayered connectionist network for realizing the basic elements and functions of a traditional fuzzy logic controller. The genetic algorithm-based neural fuzzy system (GA-NFS) is based on Takagi-Sugeno-Kang (TSK) type model possessing a neural network's learning ability. A hybrid learning algorithm is proposed for parameters learning. The proposed algorithm combines the genetic algorithm (GA) and the least-squares estimate (LSE) method to construct the GA-NFS. The genetic algorithm is used to tune membership functions at the precondition part of fuzzy rules while the LSE method is used to tune parameters at the consequent part of fuzzy rules. The performance of the GA-NFS is compared to that of the traditional PID controller and fuzzy logic controller on the water bath temperature control system. (C) 2003 Elsevier B.V. All rights reserved.