Open AccessResearch on Fault Diagnosis Method of Switch Machine Based on KFCM
Author(s) -
Song Ya kun,
TongChuan He,
Wu Cheng
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1972/1/012029
Subject(s) - fault (geology) , cluster analysis , outlier , fuzzy logic , computer science , fault coverage , decomposition , data mining , engineering , artificial intelligence , pattern recognition (psychology) , algorithm , ecology , electrical engineering , seismology , electronic circuit , biology , geology
as one of the most important equipment in railway system, the failure of switch machine has a great impact on the safety and benefit of railway transportation. In order to realize the rapid fault diagnosis of switch machine, according to the power curve of switch machine detected by centralized monitoring system of railway signal, a new fault diagnosis method of switch machine based on variational mode decomposition (VMD) and improved fuzzy clustering algorithm is proposed. Firstly, VMD decomposition method is used to preprocess the collected fault data to remove the outliers and noise; then, the kernel fuzzy c-means clustering algorithm is used to classify different fault types into classes, and the classification results are obtained according to the dynamic clustering graph, so as to realize fault diagnosis. Through simulation analysis and experimental data verification, the algorithm can accurately extract fault features and support multiple fault detection at the same time, which effectively improves the accuracy and efficiency of S700K switch machine fault diagnosis.