Improvement of Control Performance for Low-Dimensional Number of Fuzzy Labeling Using Simplified Inference

Abstract

One of the important concepts in fuzzy control is fuzzy inference, and simplified inference, which increases the speed of the fuzzy inference, has been used to realize a high-speed fuzzy controller. In designing a fuzzy controller, a high dimension, such as 7 x 7 or 5 x 5 partitions, is frequently used for the number of fuzzy labeling. However, as the number of fuzzy labeling increases, the number of control parameters increases rapidly and tuning of the fuzzy controller becomes difficult. Therefore, a fuzzy controller is required to be partitioned into a low number of fuzzy labeling, such as 3 x 3 partitions. With this in mind, first, a method of improving control performance for a low number of fuzzy labeling using simplified inference which enables high-speed inference, is proposed in this paper. Next, the effectiveness of this improvement method is studied based on the results of several simulations where a first-order lag system with dead time, a representative model for plant characteristics, is used as the controlled system.