Research on Bearing Fault Diagnosis Method Based on IPSO-RVM
Aiming at the problems of poor classification effect of support vector machine in traditional particle swarm optimization support vector machine and inaccuracy of traditional particle swarm optimization in bearing fault diagnosis, an improved particle swarm optimization method for correlation vector...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Harbin University of Science and Technology Publications
2022-10-01
|
| Series: | Journal of Harbin University of Science and Technology |
| Subjects: | |
| Online Access: | https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2139 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Aiming at the problems of poor classification effect of support vector machine in traditional particle swarm optimization support vector machine and inaccuracy of traditional particle swarm optimization in bearing fault diagnosis, an improved particle swarm optimization method for correlation vector machine is proposed in this paper.By using the adaptive inertia weight and acceleration factor, the search speed is faster in the early stage and the convergence speed is faster in the late stage.The classification models of improved particle swarm optimization correlation vector machine (IPSO-RVM), improved particle swarm optimization support vector machine (IPSO-SVM) and particle swarm optimization support vector machine (PSO-SVM) were constructed respectively for comparative experiments.The simulation results show that the classification accuracy of IPSO-RVM is 5.8% higher than IPSO-SVM and 8.7% higher than PSO-SVM.The simulation results show that the classification accuracy of IPSO-RVM is 5.8% higher than ipSO-SVM and 8.7% higher than PSO-SVM.The running time of IPSO-RVM is 0.58 s and 4.28 s slower than that of IPSO-SVM and PSO-SVM, respectively. Compared with PSO-SVM and IPSO-SVM, the accuracy of classification can be improved under the condition that the time running is reasonable. |
|---|---|
| ISSN: | 1007-2683 |