Power semiconductor devices generate mechanical stress wave (MSW) signals during switching processes, which can be used for condition monitoring (CM) of these devices with the advantages of noninvasive and non-destructive monitoring. Existing MSW signal detection methods are susceptible to electromagnetic interference and environmental factors (such as high temperature, high voltage, confined spaces, or structural constraints), which limit their adaptability in complex working conditions. Bare fiber Bragg grating (FBG) sensors offer strong resistance to electromagnetic interference and excellent environmental adaptability. Therefore, this paper proposes a transient high-frequency MSW measurement method for power semiconductor devices based on high-sample-rate bare FBG sensors. The MSW signals generated during the switching process of power semiconductor devices are successfully captured based on high-sample-rate bare FBG sensors for the first time. Comparative signal measurements between single-ended acoustic emission (AE) sensors and bare FBG sensors demonstrate the electromagnetic interference resistance capability of bare FBG sensors. Moreover, this study expands the application range of MSW detection methods for power semiconductor devices and provides new technical support for investigating the generation and propagation mechanisms of MSW signals.

Dissolved Gas Analysis (DGA) is an important method to identify internal faults of transformers. A novel predictive method for dissolved gas content in transformer oil based on temporal convolutional network (TCN) and graph convolutional network (GCN) is proposed in this paper. First, a Temporal Convolutional Network based on dilated causal convolution algorithm is designed to extract feature information from both current data and historical data of each gas content. Since the correlation coefficients among different gases may affect the accuracy of the prediction, a topological structure diagram is constructed to describe the relationship among different gases. Then, a GCN is designed to predict the gas content in the desired time horizon by using the information obtained from the topological structure diagram. The elements in the adjacency matrix of GCN are replaced by Pearson correlation coefficients to improve the accuracy of the prediction. The test results show that the proposed method in this paper achieves high accuracy for the prediction of dissolved gas content in transformer oil. Compared with back propagation neural network (BPNN), long short-term memory (LSTM) network and TCN, the Mean Absolute Error (MAE) of the predicted result by the proposed method is reduced by 12.23%, 11.18% and 3.81%, respectively.

A contactless method based on infrared image matching is presented for zero-value insulator detection on outdoor porcelain insulator string. An improved SIFT (scale-invariant feature transformation) method is developed to extract features and accomplish the pre-matching between the insulator string to be detected and the standard string in the image library. An improved RANSAC (random sampling consistency) algorithm is developed to remove mismatching points and achieve more accurate and faster detection. Firstly, an adaptive circle window is designed to improve the sensitivity of the SIFT operator on arc features extraction from insulators. Then, the dimension of the feature is decreased from128 to 32 by dividing the circle into 4 fan-shaped regions and descript the feature on 8 directions to achieve the lower computation burden and high accuracy. For the SIFT method and RANSAC method uses Euclidean distance to measure the similarity between features extracted from the string to be detected and the string in the standard library, mismatching may be caused. Spatial geometric features of the neighborhood around the feature point are used to construct the error function to improve the RANSAC method and remove the mismatching points. Faster matching is obtained by a threshold control for decreasing the number of data checking for the consensus set data models. Testing results show that the presented method is effective in the detection of zero-value resistances for outdoor insulator string. Compare with the SIFT method and SIFT+RANSAC method, the presented method has higher accuracy and faster detection speed.

This paper considers the problem of distributed online economic dispatch (DOED) from sequential data using reinforcement learning. Learning operation behavior in high-dimension environments with constraints is a major challenge for the DOED of networked microgrids (MGs), where insufficient exploration disables agents to build complex policies. Therefore, this paper develops a hierarchical reinforcement learning (HRL) to handle the DOED problem, where radial basis function (RBF) approximation is incorporated to make policies in continuous space. Based on the hierarchical framework, the HRL algorithm increases the training efficiency and reduces computational cost. The online HRL achieves distributed selfadaption and better performance of real-time dispatch by a modest number of interacting variables. In addition, guided by domain knowledge, the HRL algorithm avoids onerous additional learning beyond feasible action space. In the case of an actual networked MGcluster in Qingdao with real operation data, simulation is conducted to verify that the proposed learning framework can reduce longterm operation costs and enhance operation stability. To explore the learning process, we also provide its convergence condition andanalyze the sensitivity of the learning parameters.

Microwave thermography (MWT) is a non-destructive testing method based on the principle of microwave heating, which is widely used in the detection of debonding defects of various composite materials. Based on the principle of Microwave thermography (MWT), a resonant cavity microwave thermography detection system is proposed in this paper. The temperature variation characteristics of debonding defects in carbon Fiber Reinforced Polymer (CFRP) and radar absorbing material (RAM) are studied. This system consists of a resonator microwave source, an infrared thermal imager, a fan and two computers. This system successfully detects such defects at the pixel level by thermally loading the test piece, collecting the temperature change data of the test piece by the thermal imager, analyzing the temperature difference between the normal area and the defect area. In this paper, the advantages of microwave on the radar absorbing material (RAM) with large specific heat capacity and high thermal conductivity, high heating efficiency, large heating area and negligible damage to the radar absorbing material are verified, and the high performance of the detection system is verified. The experimental results show that microwave thermography can realize high-precision debonding detection and positioning of multilayer heterogeneous radar absorbing material (RAM).