Abstract
It is difficult to apply deep learning theory to realize intelligent fault monitoring and diagnosis of rolling bearings. Therefore, a new method which is to combine a generative adversarial network (GAN) and a stacked sparse autoencoders (SSAE) is proposed in this paper. Specifically, the vibration signals of rolling bearings are through the fast Fourier transform (FFT) preprocessing so that those time domain data are transformed to frequency domain, then the GAN model is used for sample generation and expansion and a SSAE network completes automatic extraction of features and finally a softmax classification layer is added. The experimental results show that this proposed method can achieve excellent diagnostic accuracy.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
