Introduction
Bimonthly, started in 1957
Administrator
Shanxi Provincial Education Department
Sponsor
Taiyuan University of Technology
Publisher
Ed. Office of Journal of TYUT
Editor-in-Chief
SUN Hongbin
ISSN: 1007-9432
CN: 14-1220/N
Administrator
Shanxi Provincial Education Department
Sponsor
Taiyuan University of Technology
Publisher
Ed. Office of Journal of TYUT
Editor-in-Chief
SUN Hongbin
ISSN: 1007-9432
CN: 14-1220/N
location: home > paper >
PDFdownloadsize：760KBviewed：download：
Fault Diagnosis of Rolling Bearing Based on Laplacian Score and Whale Optimization Algorithms Optimi
DOI:
10.16355/j.cnki.issn1007-9432tyut.2019.06.018
Received:
Accepted:
| Corresponding author | Institute | |
| HAN Zhennan | College of Mechanical and Vehicle Engineering, Taiyuan University of Technology |
abstract:
The vibration signal of rolling bearing often presents non-Gaussian and non-linear character, which makes it difficult to identify fault type and severity accurately. An intelligent fault diagnosis method based on Laplacian Score(LS) and Whale Optimization Algorithms(WOA) optimized Support Vector Machine(WOASVM) was proposed. First, the statistical features of original vibration signal in time domain, frequency domain and time-frequency domain are extracted, and the more sensitive and more representative features are selected by using LS to form fault feature vectors. Then, the penalty factor and kernel parameters of the support vector machine(SVM) are optimized by WOA, and the classifier model is constructed to recognize the fault pattern and determine the fault type of the rolling bearing. The advantages of WOA were demonstrated by comparing various optimization algorithms. At the same time, the validity of this method in extracting fault feature information of rolling bearings was verified by many experimental data and the classification and recognition accuracy was high.
Keywords:
laplacian score;whale optimization algorithm;support vector machine;rolling bearing;fault diagnosis