Open AccessResearch on Fault Diagnosis Method of Train Rolling Bearing Based on Variational Modal Decomposition and Bat Algorithm-Support Vector Machine
Author(s) -
Zhenzhen Jin,
Deqiang He,
Yanjun Chen,
Chenyu Liu,
Sheng Shan
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 - 10.1088/1742-6596/1820/1/012170
Subject(s) - support vector machine , modal , bearing (navigation) , fault (geology) , vibration , algorithm , pattern recognition (psychology) , nonlinear system , feature extraction , computer science , hilbert–huang transform , artificial intelligence , feature vector , signal (programming language) , control theory (sociology) , engineering , computer vision , acoustics , chemistry , physics , control (management) , filter (signal processing) , quantum mechanics , seismology , polymer chemistry , programming language , geology
Aiming at the problem that the vibration signal of train rolling bearing presents nonlinear and non-stationary characteristics, which leads to the difficulty of fault feature extraction, a fault diagnosis method of train bogie rolling bearing based on variational mode decomposition (VMD) and bat algorithm optimization support vector machine (BA-SVM) is proposed. Firstly, the center frequency method is used to determine the K value of VMD algorithm. Then, the original signal is decomposed into a series of intrinsic mode components and the distribution entropy of each component is calculated as the feature vector, and the bat algorithm is used to optimize the model parameters of support vector machine. Finally, the BA-SVM model is used for fault pattern recognition of train rolling bearing. The experimental results show that this method can effectively extract the fault characteristics of train rolling bearings and realize fault diagnosis, and the recognition rate is better than that of the comparison method.