Detection of Pantograph Geometric Model Based on Fuzzy Logic and Image Processing

Abstract

In this study, a model based approach is proposed for the recognition of the pantograph type used in electric trains. The shape of the pantograph-catenary changes according to usage conditions of electric trains. A geometric model of the pantograph is constructed by using images taken from the pantograph-catenary system. The pantograph type is determined by using the constructed model. First, all straight lines are extracted from the image by applying the edge detection and Hough transform to the image. Some knowledge obtained from straight lines are given to fuzzy logic and type of pantograph is determined. The determination of pantograph type is useful to estimate the pantograph height and to analyze of contact point between pantograph and catenary. Therefore, contact point problems such as arcing and excessive contact force can be detected.