APPLICATION OF FUZZY LOGIC FOR TRAIN BRAKING DISTANCE DETERMINATION

Abstract

Determination train braking distance or where should train stop in station represent delicate task which consist of many factors. This factors can be human and technical. In this paper we focused on external factors that mostly affect braking distance and can cause changes in its length. This factors are often imprecisely, crisp data like speed, grade, braking force and braking equipment response time, and for that purpose we use fuzzy logic. A fuzzy logic system that uses rules based on the experience and expert
knowledge of a locomotive drivers and railway operators is proposed and applied to achieve train braking distance.
The aim of this paper is to determine train braking distance and difference between calculated braking distance and data from the field. In this paper an attempt has been made to create model that can represent real state. This model was created and simulated using Matlab fuzzy logic toolbox. Special attention in this paper is paid on sensitivity analysis, which shown the stability of the obtained results. Sensitivity analysis was done through two phases which shown the stability of the results to a change in the types and values of membership functions and change in the defined fuzzy rules. FLS is tested for ten variants for different train categories and
different conditions on the field.