Fuzzy制御による列車定位置停止制御

Abstract

A predictive fuzzy control system that uses rules based on the experience of a skilled human operator is proposed and applied to achieve automatic stop operation for trains. In recent years, automatic train operation (ATO) systems using microcomputers to replace human operators have been developed for new transit systems, including subways, monorails and new public transit systems. Because the train operation is a typical uncertain nonlinear system, improvement of performance indices such as safety, riding comfort of passengers, and accuracy of the stopgap is great challenge to ATO. Up to now, ATO systems have been developed using linear control of the target pattern. However, it is difficult to control a train automatically in a manner similar to control by a human operator using linear control. In this paper, we propose a predictive fuzzy control system that selects the most likely control rule from a set of control rules. The system is described as follows: ”If (u is C → x is A and y is B) then u is C.”. The proposed fuzzy control system is applied to a train automatic stop control system that takes into account passenger comfort, accuracy of a stopgap and running time. Simulation results of this newly developed fuzzy control system indicate that the system can directly adjust system performance as desired in a manner similar to control by a skilled operator and thereby stop the train comfortably and accurately.