Fault diagnosis and prognosis (FDP) tries to recognize and locate the faults from the captured sensory data, and also predict their failures in advance, which can greatly help to take appropriate actions for maintenance and avoid serious consequences in industrial systems. In recent years, deep learning methods are being widely introduced into FDP due to the powerful feature representation ability, and its rapid development is bringing new opportunities to the promotion of FDP. In order to facilitate the related research, we give a summary of recent advances in deep learning techniques for industrial FDP in this paper. Related concepts and formulations of FDP are firstly given. Seven commonly used deep learning architectures, especially the emerging generative adversarial network, transformer, and graph neural network, are reviewed. Finally, we give insights into the challenges in current applications of deep learning-based methods from four different aspects of imbalanced data, compound fault types, multimodal data fusion, and edge device implementation, and provide possible solutions, respectively. This paper tries to give a comprehensive guideline for further research into the problem of intelligent industrial FDP for the community.

Benefits from the powerful local modeling capability of deep convolutional networks (CNNs), remote sensing image change detection (CD) has made significant progress. In recent years, the rise of Transformers has further driven improvements in global feature extraction for bitemporal remote sensing images. Some prior efforts have tried to integrate CNN and Transformer, but they suffer from the limitation of inefficiently aggregating local features and contextual information. Besides, they struggle to refine change boundaries and exhibit inferior performance in detecting multi-scale and subtle changes. To tackle these interrelated problems, we propose a difference enhanced pyramid pooling dynamic sparse attention network (DPDANet) for CD, which integrates the potential of CNN and pyramid pooling dynamic sparse attention (PDSA) mechanism. Specifically, a pre-trained EfficientNetV2-S network is first used to extract multilevel local fine-grained features. Then, a global semantic enhancement network based on well-designed PDSA mechanism is proposed to extract rich global contextual information. The proposed difference enhancement module (DEM) combines long short term memory (LSTM) and deformable convolution to emphasize relevant and irrelevant changes, capturing precise boundary details of the changing region. A decoder is then employed for step-by-step upsampling of encoded features, with skip connections between local multi-scale features and globally enhanced features. Expensive experiments on four public CD datasets demonstrate that DPDANet outperforms state-of-the-art (SOTA) methods by reducing missed detections and false detections and achieving more accurate boundaries of the changing area.

Rapid fault diagnosis of electromagnetic launch and recovery (EMLR) Systems is of great significance. It is an important research direction to diagnose the system fault by mining the event data collected during the operation of a certain type of arresting gear controller. While event data have the characteristics of high sampling rate, multidimensional coupling, and nonperiodic transient, which belongs to complex large-scale time series, the existing steady-state time series diagnosis methods are not applicable. In order to solve this problem, this article proposes a large-scale time series similarity search method based on Transformer and M-Tree index to realize fault diagnosis. First, the dimension of event data was preliminarily reduced by the proposed piecewise linear representation method integrating important points and piecewise aggregation approximation (PAA). Second, referring to Transformer and its variant models, a feature extraction model was constructed to further extract temporal features, and index was organized through M-Tree to improve search efficiency. Finally, an improved dynamic time warping (DTW) early abandon algorithm was proposed to further optimize the accurate calculation of DTW to quickly match and locate faults. Experimental results show that the proposed method can match working conditions, identify, and locate system abnormalities quickly and accurately, which proves the effectiveness of the algorithm.