Search

In response to the difficulty in extracting early fault feature signals of rolling bearings, a joint fault diagnosis method based on Improved Complete Ensemble Empirical Mode Decomposition (ICEEMD) and Independent Component Analysis(ICA) was proposed. This method utilized the kurtosis criterion to reconstruct the Intrinsic Mode Function (IMF) obtained from ICEEMD and combined it with Fast Independent Component Analysis (FastICA) for noise reduction and unmixing, significantly reducing the noise in the measured signals. The maximum energy amplitude was obtained at the fault feature frequency, making it easy to identify fault features. Through experimental research and analysis, it is shown that this method can significantly reduce noise interference and highlight fault frequency components. Compared with the method combining ICEEMD and envelope spectrum, the signal-to-noise ratio is inereased by 29.54%, which can more accurately identify fault features and meet the discrimination requirements for rolling bearing faults, thus providing a new approach for bearing fault feature extraction.

Copyright of Journal of Mechanical Strength / Jixie Qiangdu is the property of Zhengzhou Research Institute of Mechanical Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)