Thermal Defect Detection for Substation Equipment Based on Infrared Image Using Convolutional Neural Network

Thermal defects of substation equipment have a great impact on the stability of power systems. Temperature is crucial for thermal defect detection in infrared images. The traditional detection methods, which have low efficiency and poor accuracy, record the temperature of infrared images manually. In this study, a thermal defect detection method based on infrared images using a convolutional neural network (CNN) is proposed. Firstly, the improved pre-processing method is applied to reduce background information, and the region of interest is located according to the contour and position information, hence improving the quality of images. Then, the temperature values are segmented to establish the dataset (T-IR11), which contains 11 labels. Finally, the CNN model is constructed to extract features, and the support vector machine is trained for classification. To verify the effectiveness of the proposed method, precision, recall, and F1 score are adopted and 10-fold cross-validation is employed on the T-IR11 dataset. The results demonstrate that the accuracy of the proposed method is 99.50%, and the performance is superior to that of previous methods in terms of infrared images. The proposed method can realize automatic temperature recognition and equipment with thermal defects can be recorded systematically, which has significant practical value for defect detection in substation equipment.

Influence of growth impurities on thermal defect formation in monocrystalline silicon

The influence of growth impurities (oxygen and carbon) on the thermalsdefect formation in silicon single crystals has been studied. Annealing was carried out in the temperature range 700-1100°C in steps of 50°C for 5 hours at each temperature. The magnetic, micromechanical and structural properties of annealed silicon single crystals have been experimentally studied. The distribution of defects formed at different annealing temperatures has been studied. The correlation between changes of magnetic susceptibility, microhardness and rearrangement of structural defects in crystals after their heat treatment is revealed. Concentrations and sizes of magnetically ordered clusters are estimated. Interpretation of the obtained experimental results is offered.

Laser process parameter optimization of dimple created on oriented carbon fiber reinforced epoxy composites

It was mainly aimed at the study to make the optimization of laser parameters to obtain dimples with the desired shape and size. Carbon Fiber EPOXY composite (CF-EPOXY) surfaces were ablated by Nd:YAG laser which has a 1064 nm wavelength. Some important laser process parameters such as focus position, pulse energy, duration and number were optimized to achieve maximum aspect ratio, circular shape and minimum thermal defect. In addition, it has been determined that which laser parameters are more effective to obtain the desired quality surface. These different shapes and geometry of dimples could be used to improve some properties such as wettability, friction, etc. The pulse energy with an effective rate of 55.97 % is the most effective parameter to achieve the larger aspect ratio. The focus position is the most effective parameter with the rates of 66.18 % and 47.94 % to obtain both perfect circularity and minimum thermal defects respectively. Confirmation experiments were performed and the highest aspect ratio was found as 1.14, the best circular dimple and the minimum thermal effects outside the spot area were found with the rates of 1.021. These are the optimum results of 9 experiment sets in this study for each output. The results were supported by confirmation experiments and regression analysis. It can be concluded that the Taguchi method is reliable and saves time and materials.

Thermal defect engineering of precious group metal–organic frameworks: impact on the catalytic cyclopropanation reaction

This work highlights the catalytic cyclopropanation and its characteristics as a novel analytical tool to investigate complex MOF structures.