This paper proposed a defect assessment method for high-voltage XLPE cable based on a multi-scale correlation feature fusion convolutional neural network. On the basis of a data-driven approach, this method established the potential relationship model between characteristic gas concentration and defect type by training a convolutional neural network, thereby diagnosing the cable defects based on characteristic gas concentration. Firstly, simulated data were obtained using a data augmentation technique based on mean shift. Then, a 1D convolutional neural network based on multi-scale correlation feature fusion was designed. Finally, the training and defect identification were carried out on the basis of simulation data by using the convolutional neural network. The results show that the method on the synthetic data test set and the real basic data achieves defect recognition accuracies of 92% and 88%, respectively. It is indicated that the proposed method can effectively utilize characteristic gas concentration to diagnose cable defects.

To solve the current problem that the monitoring methods of power cable are relatively simple and lack of multi-parameter comprehensive monitoring and judgment, this paper integrated various partial discharge signals of cable joints, and proposed a cable joint fault monitoring method based on deep learning fusion evidence theory. Then fault identification research was conducted for three situations, including no defects, internal insulation defects, and joint moisture in cable joints. According to convolutional neural network algorithm model, the partial discharge signal graphs were trained and tested separately, and data fusion was carried out by D-S evidence theory to realize fault type identification. The results show that for the situation of internal insulation defects and joint moisture, the best recognition effect of single information source is high frequency partial discharge, and its average recognition rate can reach 85.6%, and the average recognition rate of ultrasonic method is the lowest, which is 78.7%, while the average recognition rate of the identify method proposed by this paper can reach 95.7%. When there is a misjudgment in the recognition result of one of the multi-dimensional information sources, D-S evidence theory fusion can eliminate the interference of the wrong information source, accurately identify the discharge type.

To improve the accuracy of cable insulation status assessment, this paper proposed an assesement model of insulation condition based on Bayesian optimization (BO) algorithm and light gradient boosting machine (LightGBM) algorithm. First, all the features in the dataset were combined to form different feature subsets. By traversing all the feature subsets, the optimal feature combination corresponding to the highest accuracy from five-fold cross-validation was identified to complete the input feature selection. Then, the BO algorithm was used to optimize seven hyperparameters in LightGBM. Finally, the proposed BO-LightGBM algorithm was used to assess the cable insulation status. The results show that the feature subset method proposed in this paper can better improve model performance compared with principal component analysis (PCA) and mutual information-based feature selection methods. After optimization by the BO algorithm, the accuracy of the LightGBM model is further enhanced. Compared with particle swarm optimization (PSO) algorithm and genetic optimization (GA) algorithm, the computational efficiency of BO algorithm increases by approximately 80% and 86.9% at the same accuracy level, respectively. Furthermore, compared with other commonly used machine learning algorithms, the performance metrics of the proposed model are optimal.

Local abnormal heating often occurs in the heat-shrinkable terminals of medium-voltage cables, leading to localized overheating and accelerated ageing of cable insulation, which even causes premature insulation failure. To elucidate the causes of abnormal heating in medium-voltage cable heat-shrinkable terminals, the electric-thermal field of cable heat-shrinkable terminals under various typical fault conditions was simulated by electromagnetic-thermal coupling. The results show that during the long-term operation of the cable, the ageing of the stress control tube leads to localized temperature rise in the insulation. The more severe the ageing, the higher the temperature rise. Furthermore, when the outer surface of the terminal becomes contaminated due to dust accumulation and moisture, a significant hot spot forms near the break of the outer semiconductive layer; however, the hot spot diminishes when the contamination layer is far from the break. Further analysis on the thermal field distribution of the terminal with moisture on the stress control tube reveals that hotspots only appear when the inside of tube is moist. A thermal circuit model considering internal defect hotspots was built, and temperature inversion was implemented to monitor the highest temperature point at the internal insulation interface of heat-shrinkable terminal. It is verified that the method is effective.

To investigate the influence of water on the breakdown position of oil-filled cable terminal, this study simulated and analyzed the failure reason caused by water in the 220 kV oil-filled cable terminal. A cable test platform was established in the laboratory, and the influence of the grounding state and electric field strength on the breakdown position was simulated. The partial discharge (PD) quantity and water film height of the cable in different grounding states and at different electric field strength were recorded by using high frequency current partial discharge detector and camera. The results show that the water content in oil, grounding state, and electric field strength are the important factors affecting the fault location of oil filled cable terminal. When the water is immersed in the cable terminal and reaches a certain amount, and the cable terminal is directly grounded, the higher the electric field strength, the more water molecules escape from the oil-water interface, the higher the water film height, the longer the distance between the breakdown point and the upper surface of stress cone, and the larger the partial discharge. The intensity of PD is positively correlated with water film height, and the silicone oil degradation defects within the cable terminal can be evaluated by partial discharge, which provides a reference for evaluating the insulation status of oil-filled cable terminal.

In this paper, the research progress on new eco-friendly insulating gases at home and abroad was reviewed, and the international mainstream promotion of perfluoroisobutyronitrile (C₄F₇N) gas and its application in electrical equipment were expounded emphatically. The gap and surface insulation characteristics of C₄F₇N gas mixture were summarized, and the design criteria of the related equipment insulation was proposed. The decomposition characteristics and gas-solid compatibility evaluation indices of C₄F₇N gas mixture under different operating conditions were analyzed. Additionally, the research progress on arc-quenching performance of C₄F₇N and its gas mixture and the development and application of a series of eco-friendly equipment were introduced, so as to provide a theoretical reference for the environmental protection upgrade of SF₆ electrical equipment in the current stage. Meanwhile, it was noted that the research and development efforts on new eco-friendly insulating gases with superior performance were still ongoing at home and abroad, which can provide technical support for the construction of a green and low-carbon power grid.

In order to assess the feasibility of using C₅F₁₀O/dry air gas mixture to replace existing dry air or nitrogen in insulation equipment under low partial pressure conditions, we analyzed the insulation performance of C₅F₁₀O/dry air gas mixture systematically. The results show that in a quasi-uniform electric field, when the partial pressure of C₅F₁₀O is 5-10 kPa, the insulation strength of the C₅F₁₀O/dry air gas mixture is 1.1-1.9 times and 1.4-2.3 times bigger than that of dry air and nitrogen under the same condition, respectively, which indicates that even at low partial pressures, the C₅F₁₀O/dry air still demonstrates strong insulation performance and has technical advantages compare to dry air or nitrogen. Furthermore, the C₅F₁₀O/dry air shows good stability in multiple breakdown tests, and the slope of fitting curves between breakdown voltage and breakdown times approaches zero, indicating that its insulation performance has not significantly deteriorated.

C₆F₁₂O has good environmental protection characteristics and insulation properties, and has good application prospects in medium and low voltage gas-insulated equipment. In order to explore the influence of micro-water inside the gas-insulated equipment on the insulation performance and decomposition characteristics of C₆F₁₂O/CO₂ gas mixture, a gas power frequency breakdown test platform was set up, and the breakdown voltage of 4%C₆F₁₂O/96%CO₂ gas mixture under 0.14 MPa pressure within the range of 0-1 000 μL/L micro-water concentration was studied.The influence of different micro-water concentration on the power frequency breakdown characteristics of gas mixture was analyzed. The types and concentrations of the decomposition products of C₆F₁₂O/CO₂ gas mixture were analyzed quantitatively and qualitatively by gas chromatography-mass spectrometry (GC-MS) after breakdown, and the influence laws of micro-water concentration on the concentration of breakdown decomposition products and effective gas production rate were obtained. The results show that micro-water will reduce the power frequency breakdown voltage of C₆F₁₂O/CO₂ gas mixture. The main breakdown decomposition products of C₆F₁₂O/CO₂ gas mixture are CF₄, C₂F₆, C₃F₆, C₃F₈, C₃F₇H, CF₂O, C₄F₁₀, C₅F₁₂, and CF₃H, among them, the concentration and effective gas production rate of CF₄, C₂F₆, and C₃F₇H are positively correlated with the micro-water concentration, and the concentration of CF₄, C₂F₆, C₃F₆, C₃F₈, and C₃F₇H are positively correlated with the breakdown times. Considering the insulation performance and decomposition characteristics, it is recommended to strictly control the concentration of micro-water inside the C₆F₁₂O/CO₂ gas mixtures equipment during engineering application, and increase the test frequency of micro-water in the equipment.

In order to obtain the escape beam characteristics of environmentally friendly insulating gas under the action of nanosecond pulse voltage, the generation laws of the escape electrons in clean air, SF₆, and C₄F₇N/CO₂ gas mixture were studied. An escape electron collection platform was built, and the charge amount of the generated escape electrons was measured when different amplitudes of nanosecond pulse voltages were applied to clean air, SF₆, and C₄F₇N/CO₂ gas mixture under different gas pressures. The results show that the low-energy electrons will accelerate and transform to escape electrons under the action of nanosecond pulse. The higher the nanosecond pulse voltage amplitude, the lower the gas pressure, and the larger the charge amount of escape electrons generated by insulating gas. The clean air has relatively weak inhibition on the generation of escape electrons, and the SF₆ and C₄F₇N/CO₂ gas mixture have obvious inhibition effect on the generation of escape electrons. As the pressure increases, the inhibition effect on the generation of escape electrons of C₄F₇N/CO₂ gas mixture is more obvious than that of SF₆.

Perfluoroisobutyronitrile (C₄F₇N) has excellent eco-friendly and insulation properties, and is the mainstream environmentally friendly gas to replace SF₆ gas. In this paper, a series of power frequency AC corona discharge experiments were conducted on C₄F₇N/CO₂ gas mixture by needle-plate electrode, and then the influences of different electrode materials (stainless steel, aluminum, and brass) and applied voltages on the decomposition characteristics of C₄F₇N/CO₂ gas mixture were analyzed based on gas chromatography/mass spectrometry. The results show that the contents of the characteristic decomposition gases of C₄F₇N/CO₂ gas mixture increase with the increase of applied voltages, and are obviously affected by the chemical activity of metal materials, among them, the total amount of decomposition products under aluminum electrode is the highest. The content ratios of characteristic decomposition gases, that is c[C₂F₆]/c[CF₄] and v[C₂F₄]/v[C₃F₆], have good recognition degree for electrode materials and corona discharge degree.