Open AccessA self‐adaptive phase‐segmentation and health assessment framework for point machines
Author(s) -
Wang Ning,
Kou Linlin,
Zhang Huiyue,
Jia Limin,
Qin Yong,
Wang Hongguang,
Wang Zhipeng
Publication year - 2023
Publication title -
iet intelligent transport systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.579
H-Index - 45
eISSN - 1751-9578
pISSN - 1751-956X
DOI - 10.1049/itr2.12299
Subject(s) - mahalanobis distance , computer science , segmentation , dynamic time warping , artificial intelligence , consistency (knowledge bases) , data mining , machine learning
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.