A Proposal of Probability Type Fuzzy Inference and its Application to Magnetic Head Adjustment

Abstract

Proficiency in creating a konwledge base is required for high accuracy fuzzy control. To achieve this we propose a new fuzzy inference method utilizing probability density functions of distiributions of mesurement values defined as membership functions. In addition, to consider qualitative knowledge of the data distribution, we propose a method to determine the membership functions using the distributions of grade accumulation. We applied the proposed method to automatic high accuracy adjustment devices for magnetic head, and the experimental results were satisfactory.