An algorithm for improved performance of railway condition monitoring equipment: Alternating-current point machine case study

• Published in: Transportation research. Part C, Emerging technologies Vol. 30; pp. 81 - 92
• Main Authors: Asada, T., Roberts, C., Koseki, T.
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier India Pvt Ltd 01.05.2013; Elsevier
• Subjects: Applied sciences; Condition monitoring; Exact sciences and technology; Fault diagnosis; Ground, air and sea transportation, marine construction; Point machine; Railway transportation and traffic; Support Vector Machine; Wavelet Transform; Condition monitoring; Fault diagnosis; Wavelet Transform; Point machine; Support Vector Machine; Measurement sensor; Support vector machine; Algorithm; Case study; Requirement; Experimental result; Wavelet transformation; Railroad switch; Rail transportation; Detection; Fault diagnostic; Monitoring; Data gathering
• ISSN: 0968-090X; 1879-2359
• DOI: 10.1016/j.trc.2013.01.008

► The paper aims to develop a robust approach to fault diagnosis of point machines. ► Drive force, current and voltage data were collected and analysed. ► A k-means clustering algorithm was used to find an appropriate parameter. ► The methodology proposed utilises Wavelet Transforms and Support Vector Machines. ► It was found that the method can diagnose faults to a high degree of accuracy. This paper develops a new approach for fault detection and diagnosis utilising parameters collected from low-cost and accessible sensors. An electrical railway point machine within a railway junction is used as a case study. The paper shows that electrical active power collected from electrical current and electrical voltage sensors can be used for condition monitoring systems. The methodology proposed in this paper utilises Wavelet Transforms and Support Vector Machines. It was found that together these methods can detect and diagnose misalignment faults of electrical railway point machine to a high degree of accuracy. Furthermore, it was proved that the approach can provide an indication of the severity of the faults. This work was carried out in collaboration between the University of Birmingham and Central Japan Railway Company.