Intelligent Fault Diagnosis of Rolling Bearings Based on an Improved Empirical Wavelet Transform and ResNet Under Variable Conditions

作者：Lei Fu, Sinian Wang, Rupeng Chen, Zepeng Ma, Jianhui Ma, Bowen Yao, Fang Xu · 发表于：IEEE Sensors Journal · 年份：2023 · DOI：10.1109/jsen.2023.3313582 · 被引用次数：20 · 研究领域：Machine Fault Diagnosis Techniques、Gear and Bearing Dynamics Analysis、Advanced machining processes and optimization

Rolling bearing failures can lead to machinery breakdowns and loss of control, posing significant operational and safety risks. Traditional algorithms based on the empirical wavelet transform (EWT) face challenges in accurately extracting valid components under variable conditions. Additionally, conventional max-pooling methods often overlook critical features, while fully connected layers tend to overfit due to excessive parameterization. To address these challenges, an enhanced algorithm is proposed, defined as the improved EWT-improved residual network (IEWT-IResNet) method. First, the vibration signals are preprocessed to enhance resilience under variable conditions. Second, an improved EWT (IEWT) is proposed with an optimal ridge-curve extraction strategy. It incorporates an efficient weighted energy entropy (EWEE) as a sensitive indicator for signal reconstruction. Additionally, the 1-D angular-serial signals are transformed into 2-D image matrices using the generalized S-transform. Finally, an optimized residual network (ResNet) model is presented, incorporating singular value decomposition (SVD) pooling and global SVD pooling (GSP) strategies in the pooling and full connection layers. These enhancements benefit the optimal feature extraction while mitigating overfitting. The experimental results demonstrate the superior feature extraction capabilities of the proposed method when processing noisy and nonstationary signals. Furthermore, the effectiveness of the approach...