In recent years, deep learning methods, especially convolutional neural network (CNN), have received extensive attentions and applications in fault diagnosis. However, recent studies have shown that the shift-invariance of CNN is not good enough, resulting in fragile feature extraction and sharp reduction in model performance when the shift occurs in the input. To improve the shift-invariance of CNN, considering the periodic characteristics of vibration signals, a multiscale CNN with feature alignment (MSCNN-FA) is proposed for bearing fault diagnosis under different working conditions. First, by analyzing the operating principles of the convolutional layer and pooling layer, a feature alignment module including single-stride convolution layer, adaptive max-pooling layer, and global average pooling layer is designed to obtain aligned features. Next, to extract shift-invariant robust features from vibration signals, a multiscale convolution strategy is utilized, and a feature-aligned multiscale feature extractor is constructed. Finally, a classifier composed of fully connected (FC) layers is constructed for bearing fault diagnosis. The effectiveness of the method is verified by a rolling bearing experiment, which outperforms other related existing CNN-based methods in terms of diagnosis accuracy and feature robustness.

With advanced measurement technologies and signal analytics algorithms developed rapidly, the past decades have witnessed large amount of successful breakthroughs and applications in the field of intelligent fault diagnosis (IFD). However, the historical IFD methods have difficulties for compound fault diagnosis, when labeled data cannot be collected in advance for new or extreme working conditions. Facing with such challenges, a Deep Adversarial Capsule Network (DACN) is proposed to embed multi-domain generalization into the intelligent compound fault diagnosis, so that the DACN not only can intelligently decouple the compound fault into multiple single faults for industrial equipment (IE) but also can be generalized from certain working conditions to another new. First, a DACN including feature extractor, decoupling classifier and multi-domain classifier is constructed for feature learning, fault decoupling and unsupervised multi-domain adaptation, respectively. Second, adversarial training is introduced into the DACN in training stage via a gradient reversal layer that can build the connection between the feature extractor and domain classifier, which can force the DACN to learn the domain-invariance features. Finally, the DACN is trained using the single-faults data collected under multiple working conditions, and then applied to monitor the health condition of IE under new working conditions. The cross-validation experiments have been implemented on an automobile transmission (AT), which illustrates that the DACN obtains an optimum performance with the highest average accuracy of 97.65% for compound fault diagnosis of IE under multi-domain generalization task, and outperforms other related methods.

Recently, deep transfer learning based intelligent fault diagnosis has been widely investigated, and the tasks that source and target domains share the same fault categories have been well addressed. However, due to complexity and uncertainty of mechanical equipment, unknown new faults may occur unexpectedly. This problem has received less attention in the current research, which seriously limited the application of deep transfer learning. In this paper, a two-stage transfer adversarial network (TSTAN) is proposed for multiple new faults detection of rotating machinery. First, a novel deep transfer learning model is constructed based on adversarial learning strategy, which can effectively separate multiple unlabeled new fault types from labeled known ones. Second, an unsupervised convolutional auto-encoders model with silhouette coefficient is built to recognize the number of new fault types. Extensive experiments on a gearbox dataset validate the practicability of the proposed scheme. The results suggest that it is promising to address fault diagnosis transfer tasks in which the multiple new faults occur in the target domain, which greatly expand the application of deep transfer learning.