In vision-based defect recognition, deep learning (DL) is a research hotspot. However, DL is sensitive to image quality, and it is hard to collect enough high-quality defect images. The low-quality images usually lose some useful information and may mislead the DL methods into poor results. To overcome this problem, this paper proposes a generative adversarial network (GAN)-based DL method for low-quality defect image recognition. A GAN is used to reconstruct the low-quality defect images, and a VGG16 network is built to recognize the reconstructed images. The experimental results under low-quality defect images show that the proposed method achieves very good performances, which has accuracies of 95.53%-99.62% with different masks and noises, and they are improved greatly compared with the other methods. Furthermore, the results on PSNR, SSIM, cosine and mutual information indicate that the quality of the reconstructed image is improved greatly, which is very helpful for defect analysis.

Crossing different working conditions is a common scenario in rotating machinery fault diagnosis, which can be solved by cross-domain transfer learning. However, the existing diagnosis methods do not consider possibly new and unknown faults, i.e., open-set fault diagnosis scenarios, which would cause diagnosis performance degradation. To address this issue, in this article, the self-supervised-enabled open-set cross-domain (SEOC) approach is proposed for fault diagnosis of rotary machines under various working conditions. Specifically, open-set risk minimization and self-supervised contrastive learning are proposed to improve distinguishability and stability. A pseudolabel consistency self-training is designed to decrease the domain shift. A novel open-set identification strategy with the designed squeeze confidence rule is developed for unknown- and known-class fault detection. Experiments on three-phase motor and bearing datasets illustrate the superior and efficient performance of the proposed SEOC method. The proposed SEOC framework improves the overall classification accuracies by at least 9%, and the average accuracy of unknown fault identification is more than 97.68% in motor and bearing fault diagnosis.

Bearing fault diagnosis is important to ensure safe operation and reduce loss for most rotating machinery. In recent years, deep learning (DL) has been widely used for bearing fault diagnosis and has achieved excellent results. Continuous wavelet transform (CWT), which can convert original sensor data to time–frequency images, is often used to preprocess vibration data for the DL model. However, in time–frequency images, some frequency components may be important, and some may be unimportant for DL models for fault diagnosis. So, how to choose a frequency range of important frequency components is needed for CWT. In this paper, an Integrated Gradient-based continuous wavelet transform (IG-CWT) method is proposed to address this issue. Through IG-CWT, the important frequency components and the component frequency range can be detected and used for data preprocessing. To verify our method, experiments are conducted on four famous bearing datasets using 3 DL models, separately, and compared with CWT, and the results are compared with the original CWT. The comparisons show that the proposed IG-CWT can achieve higher fault diagnosis accuracy.