30 August 2024 in Journal of Physics D: Applied Physics
Perfluoroisobutyronitrile (C4F7N) gas mixture is considered one of the most promising alternative gases for SF6 due to its excellent environmental protection and insulation performance. At present, the Shanghai region of China has adopted 8.5% C4F7N-86% CO2-5.5% O2 proportion gas mixture as the insulation medium for 126 kV gas insulated switchgear and has put it into practical engineering application. This paper conducted decomposition experiments on the proportion gas mixture under spark discharge, suspension discharge, and corona discharge conditions, respectively. The composition analysis of the decomposition products was carried out using a gas chromatography mass spectrometry and a gas chromatography-pulsed discharge helium ionization detector, which got decomposition products of the C4F7N/CO2/O2 gas mixture under discharge faults mainly include CO, CF4, C3F8, C4F8, C3F6, and CF3CN. According to the decomposition path of the C4F7N gas mixture, this paper selected three primary decomposition products (CO, CF4, C3F8) and one secondary decomposition product (C4F8) for the correlation characterization of discharge types, and proposed the ratios of c(CO)/c(CF4) and c(C4F8)/c(C3F8) as the characteristic quantities to characterize the different discharge types. Finally, in order to accurately identify the C4F7N/CO2/O2 gas mixture discharge type, this paper chose the decision tree algorithm to build a identification tree. The final identification result indicates that the ratio of c (CO)/c (CF4) and c (C4F8)/c (C3F8) can be used as the identification criterion for typical discharge fault types.
29 July 2024 in IEEE Transactions on Dielectrics and Electrical Insulation
The correlation between the decomposition products and discharge faults in the electrical equipment with the environmentally friendly insulating gas mixture C 4 F 7 N/CO 2 /O 2 remains inadequately revealed. and the corresponding characterization methods also need to be determined. In this paper, a feature fusion algorithm based on the stacking-attention mechanism is proposed. The ratios of decomposition products from C 4 F 7 N/CO 2 /O 2 mixtures in various proportions under different discharge conditions are utilized as the dataset. Multiple feature extraction algorithms are employed as base learners to derive feature subsets from diverse dimensions. Subsequently, these feature subsets are fused using the attention mechanism as the meta-learner, and the contribution of each feature value is determined, thereby identifying the optimal feature subset. Experimental results demonstrate that the optimal feature values extracted by this method, when applied to classification algorithms such as Support Vector Machines (SVM) and Artificial Neural Networks (ANN), effectively distinguish between defects including corona discharge, spark discharge, and suspended discharge in environmentally friendly gas-insulated equipment. Based on the decomposition characteristics, the ratios of CO/(C 3 F 6 +CF 4 ) and CF 4 /C 3 F 8 are proposed as diagnostic indicators for identifying discharge faults in engineering applications of C 4 F 7 N/CO 2 /O 2 gas-insulated equipment. The research results of this paper provide both theoretical and technical support for the operation and maintenance of gas-insulated electrical equipment.