Abstract
The majority of faults occurring in rotating electrical machinery is attributed to bearings. To reduce downtime, it is desired to apply various diagnostic methods so that bearing degradation can be detected in good time prior to a complete failure. The work presented in this paper utilizes a data-driven machine learning approach based on convolutional neural networks (CNNs) in order to diagnose different types of bearing faults. A one-dimensional CNN is trained on vibration signals and compared to a two-dimensional CNN trained in time-frequency domain using continuous wavelet transform (CWT). The proposed method is demonstrated on data collected from run-to-failure tests.The results show that the one-dimensional network can be trained to predict bearing faults during degradation at a fairly high rate. The outcome of utilizing the two-dimensional CNN shows that extracting more information from the signals can, in some cases, result in even higher prediction accuracy. However, it also shows the importance of narrowing down the range of relevant features to extract.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.