Convolutional neural network (CNN), with the ability of feature learning and nonlinear mapping, has demonstrated its effectiveness in prognostics and health management (PHM). However, an explanation on the physical meaning of a CNN architecture has rarely been studied. In this article, a novel wavelet-driven deep neural network, termed as WaveletKernelNet (WKN), is presented, where a continuous wavelet convolutional (CWConv) layer is designed to replace the first convolutional layer of the standard CNN. This enables the first CWConv layer to discover more meaningful kernels. Furthermore, only the scale parameter and translation parameter are directly learned from raw data at this CWConv layer. This provides a very effective way to obtain a customized kernel bank, specifically tuned for extracting defect-related impact component embedded in the vibration signal. In addition, three experimental studies using data from laboratory environment are carried out to verify the effectiveness of the proposed method for mechanical fault diagnosis. The experimental results show that the accuracy of the WKNs is higher than CNN by more than 10%, which indicate the importance of the designed CWConv layer. Besides, through theoretical analysis and feature map visualization, it is found that the WKNs are interpretable, have fewer parameters, and have the ability to converge faster within the same training epochs.

Recent progress on intelligent fault diagnosis (IFD) has greatly depended on deep representation learning and plenty of labeled data. However, machines often operate with various working conditions, or the target task has different distributions with the collected data used for training (the domain shift problem). Besides, the newly collected test data in the target domain are usually unlabeled, leading to unsupervised deep transfer learning (UDTL)-based IFD problem. Although it has achieved huge development, a standard and open source code framework and a comparative study for UDTL-based IFD are not yet established. In this article, we construct a new taxonomy and perform a comprehensive review of UDTL-based IFD according to different tasks. Comparative analysis of some typical methods and datasets reveals some open and essential issues in UDTL-based IFD, which is rarely studied, including transferability of features, the influence of backbones, negative transfer, physical priors, and so on. To emphasize the importance and reproducibility of UDTL-based IFD, the whole test framework will be released to the research community to facilitate future research. In summary, the released framework and comparative study can serve as an extended interface and basic results to carry out new studies on UDTL-based IFD. The code framework is available at https://github.com/ZhaoZhibin/UDTL .

Deep learning (DL) based methods have swept the field of mechanical fault diagnosis, because of the powerful ability of feature representation. However, many of existing DL methods fail in relationship mining between signals explicitly. Unlike those deep neural networks, graph convolutional networks (GCNs) taking graph data with topological structure as input is more efficient for data relationship mining, making GCN to be powerful for feature representation from graph data in non-Euclidean space. Nevertheless, existing GCNs have two limitations. Firstly, most GCNs are constructed on unweighted graphs, considering importance of neighbors as the same, which is not in line with reality. Secondly, the receptive field of GCNs is fixed, which limits the effectiveness of GCNs for feature representation. To address these issues, a multi-receptive field graph convolutional network (MRF-GCN) is proposed for effective intelligent fault diagnosis. In MRF-GCN, data samples are converted into weighted graphs to indicate differences in relationship of data samples. Moreover, MRF-GCN learns not only features from different receptive field, but also fuses learned features as an enhanced feature representation. To verify the efficacy of MRF-GCN for machine fault diagnosis, case studies are implemented, and the results show that MRF-GCN can achieve superior performance even under imbalanced dataset.

Effective fault diagnosis of rotating machinery has multifarious benefits such as improved safety, enhanced reliability and reduced maintenance cost for complex engineered systems. With many kinds of installed sensors for conducting fault diagnosis, one of the key tasks is to develop data fusion strategies which can effectively handle multimodal sensory signals. Most traditional methods use hand-crafted statistical features and then combine these multimodal features simply by concatenating them into a long vector to achieve data fusion. The present study proposes a deep coupling autoencoder (DCAE) model which handles the multimodal sensory signals not residing in a commensurate space, such as vibration and acoustic data, and integrates feature extraction of multimodal data seamlessly into data fusion for fault diagnosis. Specifically, a coupling autoencoder (CAE) is constructed to capture the joint information between different multimodal sensory data, and then a DCAE model is devised for learning the joint feature at a higher level. The CAE is developed by coupling hidden representations of two single-modal autoencoders, which can capture the joint information from multimodal data. The performance of the proposed method is evaluated by two experiments, which shows that the DCAE model succeeds in efficiently utilizing multi-source sensory data to perform accurate fault diagnosis. Compared with other methods, the proposed method exhibits better performance.