Abstract
A predictive fuzzy control that uses rules based on a skilled human operator's experience is proposed and applied to train automatic stop operations.
In recent years automatic train operation (ATO) systems using a microcomputer instead of a human operator have been developed for new transit systems including subway, monorail and new public-transit systems.
Some problems of the train operation are that it is controled by performance indices such as, safety, riding comfort of passengers, and accuracy of the stop gap. So, train operation is a nonlinear control function. Up to now, this system has been developed by linearlized control using a target pattern. However, it is difficult to control the train in a manner similar to a human operator.
In this paper, we propose a predictive fuzzy control which selects the most likely control rule from the sets of control rules. It is described as follows.: “If (u is C→x is A and y is B) then u is C.”. And the proposed fuzzy control is applied for a train automatic stop control system which evaluates comfort, accuracy of a stop gap and running time.
The simulation result of our newly developed fuzzy control system shows it can directly adjust a system performance as desired in the same way as that controlled by a skilled operator, so it is able to stop a train comfortably and accurately.
