碩士 / 國立臺北科技大學 / 自動化科技研究所 / 106 / A ball bearing is one of important rotating parts in mechanical equipment; therefore, many mechanical equipment failures are associated with ball bearings. Moreover, the performance of mechanical equipment is directly influenced by the healthy status of the ball bearings. In this study, we investigate wavelet packet transform (WPT) and support vector machine (SVM) according to the experimental database of Case Western Reserve University Bearing Data Center to carry out the research on the fault diagnosis of ball bearings. In the study, the nonstationary vibration signal of ball bearing is analyzed for different conditions, such as the normal condition, with defeat at the inner raceway, with failure ball elements, and with defeat at the outer raceway. Firstly, the vibration characteristics of the ball bearing are analyzed and then the WPT is used to transfer the vibration signal into wavelet packet energy spectrums for feature extraction. Finally, the SVM is used for pattern recognition of the healthy status. To obtain the optimal parameters of the SVM, the particle swarm optimization (PSO) and artificial fish swarm algorithm (AFSA) are used to find the best parameters. The features obtained using wavelet packet energy spectrum are used to train the SVM for classification of the ball bearing’s healthy status. After that, the external samples are input to the SVM for validation of the proposed method.
| Identifer | oai:union.ndltd.org:TW/106TIT05146022 |
| Date | January 2018 |
| Creators | I-Ting Chen, 陳怡婷 |
| Contributors | Chih-Jer Lin, 林志哲 |
| Source Sets | National Digital Library of Theses and Dissertations in Taiwan |
| Language | zh-TW |
| Detected Language | English |
| Type | 學位論文 ; thesis |
| Format | 83 |
Page generated in 0.0171 seconds