Complex Fuzzy System Based Predictive Maintenance Approach in Railways

Abstract

In this article, the Industry 4.0 compliant method for condition monitoring and diagnostics on railways has been developed. A complex fuzzy system-based thermography approach is proposed for predictive maintenance on electric railways. The first contribution requires the use of a complex fuzzy approach, as estimator maintenance methods in rail systems depend on seasonal conditions, environmental conditions, daylight, and especially periodic effects such as train speed. The second contribution is that both the rail surface and the pantograph catenary system are very susceptible to thermal changes, as diagnosing faults in image processing and monitored systems requires a significant amount of work. In the literature, in some studies, there is no real-time and reasonably effective method of using thermal imaging in rail systems. In order to validate these novel approaches, the proposed method is applied to experimental data. The experimental results obtained demonstrate the performance of the proposed complex fuzzy system and the performance achieved by processing thermal images.