A vision based diagnosis approach for multi rail surface faults using fuzzy classificiation in railways

Abstract

The heavy construction of railway transportation vehicles is affecting the transportation route. The rail line, which is made with great care, can be damaged by the movements of freight trains. As a result of the use of rail lines, many faults occur. These failures are caused by the manufacturing error or use of the rails. There are many methods for early detection and repair of failures. One of these methods is the camera-based method. The rail components are inspected by taking images from the cameras fixed to the railway vehicle. Faults occurring in rail components are detected. In this study, a method for detecting and classifying faults on railway track surfaces is proposed. In the proposed method, the rail surface was detected using image processing techniques. Property extraction on the rail surface is performed. In addition, the type of fault is determined by using fuzzy logic.