Premium
Fault diagnosis of the train communication network based on weighted support vector machine
Author(s) -
Li Zhaozhao,
Wang Lide,
Yang Yueyi
Publication year - 2020
Publication title -
ieej transactions on electrical and electronic engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.254
H-Index - 30
eISSN - 1931-4981
pISSN - 1931-4973
DOI - 10.1002/tee.23153
Subject(s) - support vector machine , feature vector , classifier (uml) , artificial intelligence , margin (machine learning) , computer science , hyperplane , benchmark (surveying) , sample space , pattern recognition (psychology) , sample (material) , network packet , waveform , data mining , engineering , machine learning , telecommunications , computer network , mathematics , radar , chemistry , geometry , geodesy , chromatography , geography
Multifunction vehicle bus (MVB) is the most widely used train communication network which transmits controlling and supervising data. The faults of MVB will heavily affect the train's safe and stable operation. Due to the harsh operating environment and distributed structure, the MVB fault diagnosis has always been a difficult issue in the maintenance of the train. Many MVB faults will distort the physical waveforms and cause serious packet loss. Thus, we have extracted waveform features to characterize different MVB faults and turned the fault diagnosis into a pattern recognition problem. Then a classifier based on weighted support vector machine (WSVM) has been trained to diagnose and locate network faults. Considering that samples locating in different positions of the feature space have different influences on the support vector machine (SVM) hyperplane, we have proposed a multi‐hop edge approaching method to assign sample weights in WSVM. To identify the position of the tested sample, the hops from its location to the classification margin have been counted. The less the hop‐count, the closer to the classification margin and the larger the sample weight. Compared with SVM and other WSVM methods, the proposed method has better performance on the artificial synthetic datasets, the MVB dataset, and the benchmark datasets. © 2020 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.