The Fuzzy Rule Base Automatic Optimization Method of Intelligent Controllers for Technical Objects Using Fuzzy Clustering

Abstract

The goal of this work is to develop a fuzzy rule base optimization method of intelligent controllers for technical objects using fuzzy clustering. To achieve the goal of the study, a hybrid model is developed in which the control of a technical object is implemented using the PID-classical and PID-FUZZY controllers with the generated structure of the Sugeno-type fuzzy inference system and the developed model of the adaptive neuro-fuzzy inference system, which allows to form a base of fuzzy rules, which is independent of an expert knowledge in the subject area, a method for optimization the fuzzy controller rule base based on clustering methods is proposed, allows you to reduce the number of fuzzy inference rules and increase the control system speed of the technical object. A hybrid model was simulated before and after fuzzy clustering, which proves the high efficiency of the proposed method for optimization the fuzzy controller rule base by reducing the number of fuzzy inference rules and the number of membership functions required to describe linguistic variables.