Fault diagnosis methods based on deep learning and big data have achieved good results on rotating machinery. However, the conventional deep learning method of bearing fault diagnosis is mostly based on laboratory artificial simulation data, and there is an error with actual fault data, which will reduce the generalization performance of the deep learning method. In addition, labeled data are very precious in real industrial environment. Due to expensive equipment and personnel safety issues, it is difficult to obtain a large amount of high-quality fault labeling data. Therefore, in this paper, we propose a metric-based meta-learning method named Reinforce Relation Network (RRN) for diagnosing bearing faults with few-shot samples. In the proposed method, a 1D convolution neural network is used to extract fault features, and a metric learner is used to predict the similarity between samples under different transfer conditions. Label smoothing and the Adabound algorithm are utilized to further improve the performance of network classification. The performance of the proposed method is verified on a dataset which contains artificial damage and natural damage data. The comparison studies with other methods demonstrate the superiority of the proposed method in the few-shot scenario.

Permanent magnet eddy current couplers (PMECCs) have the characteristics of contactless torque transmission, removal of torque ripple, smooth dynamic process, and adjustable speed, and can be used as couplings, dampers, brakes, and speed governors. Their applications in industry, vehicles, and energy fields are gradually expanding. At the same time, the requirements for the torque density and dynamic performance of PMECCs are increasing. Therefore, a large amount of research work has focused on the fast and accurate modeling, design, and optimization of PMECCs. This paper provides a survey on the development of PMECCs technology. The main topics include the structure and classification of PMECCs, modeling methods, loss and heat transfer analysis modeling, and optimization design. In addition, this paper shows the future trends of PMECCs research. All the highlighted insights and suggestions of this review will hopefully lead to increasing efforts toward the model’s construction and the optimal design of PMECCs for future applications.

Machine learning-based diagnosis methods have achieved remarkable success under the assumption that the training and test data are identically distributed. However, a critical requirement of these methods is the generalization capability to unseen domains when deployed to actual diagnosis scenarios. We introduce the challenging problem of domain generalization, i.e., learning from multiple source domains to produce a model that can directly generalize to unseen domains without target information. We adopt a model-agnostic learning produce that maximizes the dot product of gradients between the source domains. Such a gradient alignment objective encourages finding a common optimization path for all source domains, which helps to focus on invariant representations. Furthermore, we propose two feature regularizations that explicitly regularize the feature space. Global feature regularization aligns class relationships between different domains to preserve the domain-invariant knowledge. Local feature regularization encourages the model to learn domain-agnostic class-specific representations with intraclass compactness and interclass separability. The effectiveness of the proposed method is demonstrated with generalization experiments on two benchmarks.

Permanent magnet eddy current couplers have been widely used in large fan and pump loads to achieve the purpose of speed regulation and energy saving. In order to reduce the coupler axial volume and simplify the actuator, a novel flux adjustable axial flux permanent magnet eddy current coupler (FAAF‐PMECC) is proposed in this paper. The permanent magnet rotor is divided into three parts: the inner, middle and outer parts, where the permanent magnets are embedded in the core and the adjacent poles are magnetised in opposite directions. The middle part is the adjusting permanent magnet ring (AR), which can rotate around the shaft. The inner part and outer part are fixed permanent magnet rings (FR) that are fixed with the shaft, and the output torque can be controlled by adjusting the relative angle of AR and FR. The structure and working principle of FAAF‐PMECC are described in detail, and the output torque analytical model of the whole regulating process is established based on the magnetic equivalent circuit method. The AR regulation process is simulated by the variable reluctance model. The validation results show that the proposed structure can achieve a good speed regulation effect, and the output torque calculated by the analytical model in a certain slip speed range matches well with the output torque obtained using the 3D finite element method and experimental measurements. The sensitivity analysis of the structure parameters is also carried out. The analysis shows that the proposed coupler can achieve a wide speed range.

The objective of this letter is to study the prediction of the electromagnetic field and the output performance of permanent magnet eddy current devices based on a physics-informed sparse neural network (PISNN). In order to achieve this goal, a unified physical model is firstly defined according to different types of permanent magnet eddy current devices, which is equivalent to solving a parameterized magnetic quasi-static problem. A soft constraint module and a hard constraint module, composed of physical equations, are constructed. The soft constraints are then integrated into the neural network's objective function, while the hard constraint module is utilized to predict device performance and physical field. Stochastic gradient descent is used to minimize the residual of the physical equations during PISNN training. Subsequently, the structural parameters and operating parameters of PMECD are modified to verify the generalization ability of the model. Our results indicate that PISNN accurately and efficiently predicts the electromagnetic field distribution and the output torque. Furthermore, our prediction results for permanent magnet eddy current devices with different parameters demonstrate the potential of the proposed method for transfer learning.