Open AccessAn enhanced diagnosis method for weak fault features of bearing acoustic emission signal based on compressed sensing
Author(s) -
Cong Wang,
Chang Liu,
Mengliang Liao,
Qi Yang
Publication year - 2021
Publication title -
mathematical biosciences and engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.451
H-Index - 45
eISSN - 1551-0018
pISSN - 1547-1063
DOI - 10.3934/mbe.2021086
Subject(s) - acoustic emission , pattern recognition (psychology) , bearing (navigation) , particle swarm optimization , compressed sensing , fault (geology) , computer science , support vector machine , signal (programming language) , feature (linguistics) , signal processing , time domain , frequency domain , frequency band , feature vector , artificial intelligence , wavelet packet decomposition , wavelet , engineering , algorithm , acoustics , electronic engineering , wavelet transform , computer vision , bandwidth (computing) , digital signal processing , geology , telecommunications , linguistics , philosophy , physics , seismology , programming language
Aiming at the problems of data transmission, storage, and processing difficulties in the fault diagnosis of bearing acoustic emission (AE) signals, this paper proposes a weak fault feature enhancement diagnosis method for processing bearing AE signals in the compressed domain based on the theory of compressed sensing (CS). This method is based on the frequency band selection scheme of CS and particle swarm optimization (PSO) method. Firstly, the method uses CS technology to compress and sample the bearing AE signal to obtain the compressed signal; then, the compressed AE signals are decomposed by the compression domain wavelet packet decomposition matrix to extract the characteristic parameters of different frequency bands, and then the weighted sum of the characteristic parameters is carried out. At the same time, the PSO method is used to optimize the weight coefficient to obtain the enhanced fault characteristics; finally, a feature-enhanced-support vector machine (SVM) fault diagnosis model is established. Different feature parameters are feature-enhanced to form a feature set, which is used as input, and the SVM method is used for pattern recognition of different types and degrees of bearing faults. The experimental results show that the proposed method can effectively extract the fault features in the bearing AE signal while improving the efficiency of signal processing and analysis and realize the accurate classification of bearing faults.