Improving the dependability of DC point machines with a novel condition monitoring system

Abstract

This paper develops a new approach for fault detection and diagnosis for electric DC point machines operated on the railways in the UK. It is shown that the electric current is an appropriate parameter to acquire and analyse for DC point machine condition monitoring. The new methodology for fault detection and diagnosis proposed in this paper utilises wavelet transforms and support vector machines. It is shown that this method can detect and diagnose faults to a high degree of accuracy and can provide an indication of the severity of the faults.