The diagnosis of the key components of rotating machinery systems is essential for the production efficiency and quality of manufacturing processes. The performance of the traditional diagnosis method depends heavily on feature extraction, which relies on the degree of individual's expertise or prior knowledge. Recently, a deep learning (DL) method is applied to automate feature extraction. However, training in the DL method requires a massive amount of sensor data, which is time consuming and poses a challenge for its applications in engineering. In this paper, a new data-driven fault diagnosis method based on compressed sensing (CS) and improved multiscale network (IMSN) is proposed to recognize and classify the faults in rotating machinery. CS is used to reduce the amount of raw data, from which the fault information is discovered. At the same time, it can be used to generate sufficient training samples for the subsequent learning. The one-dimensional compressed signal is converted to two-dimensional image for further learning. An IMSN is established for learning and obtaining deep features. It improves the diagnosis performance of the DL process. The faults of the key components are identified from a softmax model. Experimental analysis is performed to verify effectiveness of the proposed data-driven fault diagnosis method.

Vibration signals always contain noise and irregularities, which makes spectrum analysis difficult to extract high-level features. Recently, graph theory has been applied to spectrum analysis to improve the performance of feature extraction. By converting the raw data into graphs, hidden structural and topological information can be obtained. In this article, a spatial-temporal graph-based feature extraction, called SuperGraph, for rotating machinery fault diagnosis is proposed. Specifically, graph theory-based spectrum analysis is used to construct the spatial-temporal graph. Then, the Laplacian matrix-based feature vector is extracted from the constructed spatial-temporal graph. By this means, the spatial-temporal graph is converted into the one-dimensional (1-D) vector for further constructing SuperGraph, where each node of the SuperGraph represents a spatial-temporal graph and the SuperGraph is composed of many local graphs. In the local graph, only the same type of nodes are connected to form a fully connected graph. Thus, the task of graph classification can be transformed into classifying the nodes in the SuperGraph. After graph convolutional network is established for learning and obtaining deep features, the label of nodes is identified from a $softmax$ model. Experiments are conducted on two benchmarking datasets and a practical experimental platform to verify effectiveness of the proposed fault diagnosis method.

The diagnosis of complicated fault severity problems in rotating machinery systems is an important issue that affects the productivity and quality of manufacturing processes and industrial applications. However, it usually suffers from several deficiencies. (1) A considerable degree of prior knowledge and expertise is required to not only extract and select specific features from raw sensor signals, and but also choose a suitable fusion for sensor information. (2) Traditional artificial neural networks with shallow architectures are usually adopted and they have a limited ability to learn the complex and variable operating conditions. In multi-sensor-based diagnosis applications in particular, massive high-dimensional and high-volume raw sensor signals need to be processed. In this paper, an integrated multi-sensor fusion-based deep feature learning (IMSFDFL) approach is developed to identify the fault severity in rotating machinery processes. First, traditional statistics and energy spectrum features are extracted from multiple sensors with multiple channels and combined. Then, a fused feature vector is constructed from all of the acquisition channels. Further, deep feature learning with stacked auto-encoders is used to obtain the deep features. Finally, the traditional softmax model is applied to identify the fault severity. The effectiveness of the proposed IMSFDFL approach is primarily verified by a one-stage gearbox experimental platform that uses several accelerometers under different operating conditions. This approach can identify fault severity more effectively than the traditional approaches.

Due to its ability to learn the relationship among nodes from graph data, the graph convolution network (GCN) has received extensive attention. In the machine fault diagnosis field, it needs to construct input graphs reflecting features and relationships of the monitoring signals. Thus, the quality of the input graph affects the diagnostic performance. But it still has two limitations: 1) the constructed input graph usually has redundant edges, consuming excessive computational costs; 2) the constructed input graph cannot reflect the relationship between the noisy signals well. In order to overcome them, a dynamic graph-based feature learning with few edges considering noisy samples is proposed for rotating machinery fault diagnosis in this article. Noisy vibration signals are converted into one spectrum feature-based static graph, where redundant edges are simplified by the distance metric function. Edge connections of the input static graph are updated according to the relationship among high-level features extracted by the GCN. Based on this, dynamic input graphs are reconstructed as new graph representations for noisy samples. To verify the effectiveness of the proposed method, validation experiments were conducted on practical platforms, and results show that the dynamic input graph with few edges can effectively improve the diagnostic performance under different SNRs.

Recently, research on multisensor fault diagnosis under noisy signals has gained significant attention. Due to various degrees of external interference and differences in sensor precision, the signal quality across different channels is inconsistent. These discrepancies are often neglected by fault diagnosis models and are also difficult to capture accurately. To solve this problem, this article introduces a multiscale channel attention-driven graph dynamic fusion network for mechanical fault diagnosis. It can mine the differences in importance among channels at multiple scales and calculate the channel attention weights to enhance the node feature representation. Additionally, a graph dynamic fusion framework for multisource features is proposed to process the subgraphs in parallel, which achieves a deep-level feature fusion and enables dynamic adjustments to the fusion process based on real-time model output. With the proposed graph dynamic reconstruction module, the reliability of the feature fusion process is further improved. In the experimental part, three noise distribution scenarios were simulated to validate the robustness of the proposed method on an axial flow pump and a gearbox. The comparative analysis with various state-of-the-art models and traditional deep learning models confirms the effectiveness and superiority of the proposed method.