How to optimize the TS‐fuzzy knowledge base to achieve desired performances: Accuracy and robustness

Abstract

AbstractDesigning an effective criterion/learning to find the best rule and optimal structure is a major problem in the design process of fuzzy neural controller. In this paper, we introduce a new robust model of Takagi Sugeno fuzzy logic controller. A hybrid learning algorithm, called hybrid approach to fuzzy supervised learning (HAFSL), which combines the genetic algorithm (GA) and gradient descent technique (GD) is proposed for constructing an efficient and robust fuzzy neural network controller (FNNC). Two phases of design and learning process are presented in this work. A GA is used for finding near optimal structure/parameters of the FNNC that minimizes the number of rules (initialization procedure). The second stage of learning algorithm uses the backpropagation algorithm based on GD method to fine tune the consequent parameters of the controller. The genes of chromosome are arranged into two parts, the first part contains the control genes (the certainty factors) and the second part contains the parameters genes that representing the fuzzy knowledge base. The effectiveness of this chromosome formulation enables the fuzzy sets and rules to be optimally reduced. The performances of the HAFSL are compared to these found by the traditional PI with genetic optimization (GA‐PI). Simulations demonstrate that the proposed HAFSL and GA‐PI algorithms have good generalization capabilities and robustness on the water bath temperature control system. Copyright © 2007 John Wiley & Sons, Ltd.