motor bearing fault diagnosis based on vibration signal, wavelet denoising, and cnn

Induction motors are broadly applied in different industries because of their low cost, high efficiency, and reliability. although failures in such motors could cause significant issues like decreased efficiency, unexpected shutdown, and damage to other system sections. diagnosing bearing failures is critical to reducing maintenance costs and operational failures. bearing failures are a major cause of machine vibrations. unfortunately, existing methods are optimized for controlled environments and disregard realistic conditions such as variable load, time-varying rotational speeds, and the non-stationary nature of vibration. this study presents an integration of time analysis and deep learning techniques to diagnose bearing failures under time-varying speeds and varying noise levels. in this study, we present an approach to diagnosing bearing failures employing vibration signals and convolutional neural networks (cnn) with pre-processing of the vibration signal by using the discrete wavelet transform (dwt) to remove the effect of variable frequency drive (vfd), which causes odd harmonics. the experimental outcomes show that the presented technique surpasses conventional techniques in the two computational efficiency as well as accuracy to diagnose bearing failures. this work paves the way for further research in the field of bearing fault diagnosis and provides a promising solution for real-world applications.