Rolling Bearing Fault Feature Extraction Using Chirplet Decomposition Based on Genetic Algorithm

Ying Lin, Hongkai Jiang, Yanan Hu, Dongdong Wei

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Vibration signals acquired from rolling bearing usually are complex, and it is difficult to extract fault features from strong noise background. In this paper, a chirplet decomposition method based on genetic algorithm is proposed. The absolute value of the inner product of the vibration signal and the basis function of chirplet is constructed as the optimization object function, using the genetic algorithm to search the chirplet which is best matched with the analyzed signal. Then a series of linear combination of chirplet are obtained, by which the time-frequency domain characteristic of the analyzed signal are indicated. The results confirm that the chirplet based on the genetic algorithm is more effective in extracting fault feature from strong noise background than the adaptive chirplet.

源语言英语
主期刊名Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018
编辑Chuan Li, Dian Wang, Diego Cabrera, Yong Zhou, Chunlin Zhang
出版商Institute of Electrical and Electronics Engineers Inc.
79-84
页数6
ISBN(电子版)9781538660577
DOI
出版状态已出版 - 2 7月 2018
活动2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018 - Xi'an, 中国
期限: 15 8月 201817 8月 2018

出版系列

姓名Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018

会议

会议2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018
国家/地区中国
Xi'an
时期15/08/1817/08/18

指纹

探究 'Rolling Bearing Fault Feature Extraction Using Chirplet Decomposition Based on Genetic Algorithm' 的科研主题。它们共同构成独一无二的指纹。

引用此