A Hybrid Feature Extraction Method for Fault Detection of Turnouts

Problems related to fault detection of turnouts are discussed in this paper, which is important to guarantee the security of a driving train. Motivated by an existing approach for fault detection of turnouts and to deal with its demerits, a hybrid feature extraction method is given, which extracts information in both time and frequency domains, then support vector machine (SVM) is further used to classify the extracted hybrid features. Compared with the existing method, only using the starting point of the last falling edge in the feature extraction can reduce the influence of inaccurate locations or misdetections of edges, and introducing low frequency characteristics into features makes them sensitive to more types of faults. Experimental results based on the historical field data collected from a real high-speed railway show the effectiveness and the merits of proposed method.