In practical industrial scenarios, mechanical equipment frequently operates within dynamic working conditions. To address the challenge posed by the incongruent data distribution between source and target domains amidst varying operational contexts, particularly in the absence of labels within the target domain, this study presents a solution involving deep feature construction and an unsupervised domain adaptation strategy for rolling bearing fault diagnosis across varying working conditions. The proposed methodology commences by subjecting the original vibration signal of the bearing to a fast Fourier transform (FFT) to extract spectral information. Subsequently, an innovative amalgamation of a one-dimensional convolutional layer and an auto-encoder were introduced to construct a convolutional auto-encoder (CAE) dedicated to acquiring depth features from the spectrum. In a subsequent step, leveraging the depth features gleaned from the convolutional auto-encoder, a balanced distribution adaptation (BDA) mechanism was introduced to facilitate the domain adaptation of features from both the source and target domains. The culminating stage entails the classification of adapted features using the K-nearest neighbor (KNN) algorithm to attain cross-domain diagnosis. Empirical evaluations are conducted on two extensively used datasets. The findings substantiate that the proposed approach is capable of accomplishing the cross-domain fault diagnosis task even without labeled data within the target domain. Furthermore, the diagnostic accuracy and stability of the proposed method surpass those of various other migration and deep learning approaches.
Bearings in actual working environments typically operate in healthy conditions, resulting in an imbalance in the data collected data. The majority of the collected data are related to bearings in healthy conditions, with insufficient data related to faults. This imbalance leads to accuracy and stability issues in deep learning models used for diagnosis purposes. To address this issue, we propose employing a residual factorized hierarchical search-based generative adversarial network (RFH-GAN) and a residual shrinkage network with pyramidal squeezed attention (PSA-DRSN) for unbalanced fault diagnosis. The process involves transforming vibration signals collected from bearings into time-frequency (TF) domain images through the utilization of the continuous wavelet transform (CWT). The enhanced RFH-GAN generates synthetic fault samples with authentic characteristics, while the PSA-DRSN performs fault diagnosis. The experimental findings substantiate that our method improves the quality of the generated samples, mitigates the data imbalance issues that are inherent in conventional diagnosis methods, and attains heightened precision and efficacy in fault diagnosis tasks.