Classification and Recognition Method for Bearing Fault based on IFOA-SVM
In order to identify the nonlinear classification of bearing fault features more accurately， a fault identification method based on IFOA-SVM is proposed. Firstly， the variational mode decomposition method is used to decompose the vibration signals of the bearing， and the fuzzy approximate entropy an...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Journal of Mechanical Transmission
2021-02-01
|
| Series: | Jixie chuandong |
| Subjects: | |
| Online Access: | http://www.jxcd.net.cn/thesisDetails#10.16578/j.issn.1004.2539.2021.02.023 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In order to identify the nonlinear classification of bearing fault features more accurately， a fault identification method based on IFOA-SVM is proposed. Firstly， the variational mode decomposition method is used to decompose the vibration signals of the bearing， and the fuzzy approximate entropy and energy entropy of the modal component is used to form fault characteristics. Based on “one versus one” strategy， an OVO-SVM multi-classifier is designed， and the hybrid kernel function combined with polynomial kernel function and radial basis kernel function is constructed. Then， the key parameters such as the ratio coefficient of the kernel function <inline-formula><alternatives><math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M3"><mi>λ</mi></math><graphic specific-use="big" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="alternativeImage/CBC0F59B-F91E-4c39-864E-1346B6B72A10-M003.jpg"><?fx-imagestate width="2.28600001" height="2.62466669"?></graphic><graphic specific-use="small" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="alternativeImage/CBC0F59B-F91E-4c39-864E-1346B6B72A10-M003c.jpg"><?fx-imagestate width="2.28600001" height="2.62466669"?></graphic></alternatives></inline-formula>， the width parameter of the radial basis kernel function <inline-formula><alternatives><math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M4"><mi>σ</mi></math><graphic specific-use="big" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="alternativeImage/CBC0F59B-F91E-4c39-864E-1346B6B72A10-M004.jpg"><?fx-imagestate width="2.45533323" height="2.62466669"?></graphic><graphic specific-use="small" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="alternativeImage/CBC0F59B-F91E-4c39-864E-1346B6B72A10-M004c.jpg"><?fx-imagestate width="2.45533323" height="2.62466669"?></graphic></alternatives></inline-formula>， the penalty factor <italic>C</italic> is optimized by IFOA algorithm， and the IFOA-SVM fault multi-classification identification model is built. The process of bearing fault identification is presented. Finally， the experimental results show that the method can realize accurate and efficient identification of the fault features of bearing. |
|---|---|
| ISSN: | 1004-2539 |