The deep belief network is widely used in fault diagnosis and health management of rotating machinery. However, on the one hand, deep belief networks only tend to focus on the global information of bearing vibration, ignoring local information. On the other hand, the single deep belief network has limited learning ability and cannot diagnose the health of rotating machinery more accurately and stably. As a non-recursive variational signal decomposition method, variational mode decomposition can easily obtain local information of signals. And the ensemble deep belief network composed of multiple deep belief networks also improves the accuracy and stability of the health status diagnosis of rotating machinery. This paper combines the advantages of ensemble deep belief network and variational mode decomposition to propose a novel diagnostic method for rolling bearings. Firstly, the variational mode decomposition is used to decompose the vibration data of the rolling bearing into intrinsic mode functions with local information. Then, using the deep belief network based on cross-entropy to learn the intrinsic mode functions of the rolling bearing data and reconstruct the vibration data. Finally, In the decision-making layer, the improved combination strategy is used to process the health status information of the bearings obtained by multiple deep belief networks to obtain a more accurate and stable diagnosis result. This method is used to diagnose experimental bearing vibration data. The results show that the method can simultaneously focus on and learn the global and local information of bearing vibration data and overcome the limitations of individual deep learning models. Experiments show that it is more effective than the existing intelligent diagnosis methods.

Data-driven fault diagnosis is critical for the rolling bearing to improve its healthy states and save invaluable cost. Nowadays, various intelligent fault diagnosis methods using machine learning (ML) or deep learning (DL) techniques have achieved much success. The convolutional neural network (CNN) based method, as a representative DL technique, can extract the features of raw data automatically for its excellent sparse connectivity and weight sharing properties. In this paper, a novel data-driven intelligent fault diagnosis method of rolling bearing under variable working loads has been proposed by using 1-D stacked dilated convolutional neural network (1D-SDCNN). First, 1-D vibration signals were used as input data without additional signal processing and diagnostic expertise. Second, the stacked dilated convolution, which can capture larger scale associated information and achieve large receptive fields with a few layers, was used to replace the traditional convolution and pooling structure. Third, the 1D-SDCNN architecture was flexible which is based on the relationship between receptive fields and the length of the input signal. And the number of network layers can be adjusted according to signal length. Further, it can adapt to the changing working loads of the mechanical environment. Finally, the effectiveness of the proposed method was confirmed through the experiment. And the results demonstrated that 1D-SDCNN was able to learn indeep features under three variable working loads and the average accuracy was 96.8%.

Electromechanical actuators (EMA) are becoming more and more widely used. As the core technology of EMA, servo control technology determines their performance. In this paper, an active disturbance rejection control (ADRC) method with an improved extended state observer (ESO) is proposed to design a cascade controller of EMA based on permanent magnet synchronous motor (PMSM). The mathematical model of PMSM in a two-phase rotating coordinate system is established, then it is decoupled by an $i_d=0$ current control method to realize the vector control of the motor. In a three closed-loop vector control system, a PID controller including current loop, speed loop and position loop is designed. To solve the problems caused by measurement noise, the filter link and system are modeled as a whole, and an improved ESO is constructed. On this basis, an ADRC controller of the speed loop and position loop of PMSM is designed and simulated based on Simulink. Based on the physical test platform, a load step test and load disturbance test of ADRC are completed. The results show that, in comparison to the PID method, the ADRC method shortens the response time by 25% on average, and reduces the overshoot by 60% on average. So, it can be concluded that ADRC has good static and dynamic performance, which has a good guiding role for engineering practice.

With the continuous development of actuator technology, the Electro-Mechanical Actuator (EMA) is gradually becoming the first choice in the aviation field. Permanent Magnet Synchronous Motor (PMSM) is one of the core components of EMA, and its healthy state determines the working performance of EMA. In this paper, the interturn short-circuit fault of PMSM is taken as the typical fault, and a new fault diagnosis framework is proposed based on a wide-kernel convolutional neural network (WCNN) and few-shot learning. Firstly, the wide convolution kernel is added as the first layer to extract short-time features while automatically learning deeply oriented features oriented to diagnosis and removing useless features. Then, the twin neural network is introduced to establish a wide kernel convolutional neural network, which can also achieve good diagnostic results under a few-shot learning framework. The effectiveness of the proposed method is verified by the general data set. The results show that the accuracy of few-shot learning is 9% higher than that of WCNN when the fault data are small. Finally, a fault test platform was built for EMA to collect three-phase current data under different fault states, and the collected data were used to complete the fault diagnosis of PMSM. With limited data, the accuracy of few-shot learning increased by 8% on average compared with WCNN, which has good engineering value.

Insulated gate bipolar transistors (IGBTs) are widely used in power electronic devices, and their health prediction problems have attracted much attention in the field of power electronic equipment health management. The performance degradation of IGBT gate oxide is one of the most important failure modes. In order to analyze this failure mechanism and the ease of implementation of a monitoring circuit, the gate leakage current of IGBTs was selected as the fault precursor parameter for the degradation of their gate oxide performance, and feature selection and fusion were carried out by using time domain characteristic analysis, grayscale correlation, Mahalanobis distance, Kalman filter, and other methods. Thus, a health indicator was obtained to characterize the degradation of IGBT performance, which was used to indicate the degree of aging of the IGBT gate oxide layer. In this paper, we propose an improved degradation prediction model called MultiScaleFormer, inspired by advanced design ideas of the iTransformer network architecture, combined with the health parameters of IGBTs to construct a degradation prediction model for the IGBT gate oxide layer. MultiScaleFormer showed the highest fitting accuracy compared with the Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), Support Vector Regression (SVR), Gaussian Process Regression (GPR), CNN-LSTM, and Transformer models in our experiment. The mean absolute error (MAE) of the MultiScaleFormer prediction was as low as 0.0087. Extraction of the health indicator and the construction and verification of the degradation prediction model were carried out on the dataset released by the NASA-Ames Laboratory. These results demonstrate the feasibility of the gate leakage current as a fault precursor parameter for IGBT gate oxide failure, and the feasibility and accuracy of the MultiScaleFormer prediction model for IGBT performance degradation.