6 February 2023 in IEEE Transactions on Intelligent Transportation Systems
Turnouts are crucial to the safety of high-speed railways. Due to the intensive use and complex environment, breakdowns caused by different faults occur frequently in practice. Considering that the operation of turnouts is a multi-stage process during which each stage has its specific health characteristics, this paper proposes segmentalized maximal-relevancy and minimal-redundancy (mRMR) for feature extraction from each stage separately. Based on mathematical analysis of the turnout mechanism, the electric power curve is segmented into four stages, from which time-domain analysis and mRMR are combined to extract valid features corresponding to different movements respectively. Then, a novel classifier named cost-sensitive Extreme Learning Machine with fixed inputs (cf-ELM) is proposed for fault classification. We modify the inputs of ELM and define a new formula to limit the input weights and biases for the sake of stability of the network structure. Besides, a cost-sensitive optimization method is also presented in this classifier to embed the failure degree and data proportion into cost calculation rules to deal with data imbalance. To verify our proposed method, real data collected from a turnout of Beijing-Shanghai high-speed railway is used. It is proven by comparisons that the accuracy of our method has achieved 100% with fast running speed and also outperforms traditional methods in terms of stability and generalization remarkably.
11 March 2025 in Engineering Applications of Artificial Intelligence
18 October 2022 in IET Intelligent Transport Systems
Health assessment for point machines is crucial to the safety of rail systems. The operation of the point machine is a typical multi‐stage process, each with its own characteristic features that allow a health assessment. Therefore, to segment various phases self‐adaptively is quite essential to assess the health state of the point machine. Besides, the degradation of the point machine is characterized as non‐linear. However, these issues are barely discussed when assessing the degradation degree. By converting it into a multi‐classification problem, this paper proposes a novel phase segmentation method based on dimensionless time‐domain features and characteristics of time series by utilizing the adaptive Multiclass Mahalanobis Taguchi System (aMMTS) to segment the signal self‐adaptively. Furthermore, this paper proposes a novel algorithm named Non‐linear Dynamic Time Warping (NLDTW), which modifies the conventional Dynamic Time Warping (DTW) by using a non‐linear distance to overcome the lack of global consistency in the non‐linear degradation assessment. Finally, a modified formula of confidence value is presented to assess the actual degradation degree. The efficiency and feasibility of the proposed framework have been verified by the actual data collected from the point machines of Guangzhou Metro.
4 April 2020 in Lecture Notes in Electrical Engineering
4 April 2020 in Lecture Notes in Electrical Engineering