A Data Matching Method of Partial Discharge Data Based on Auto-encoding Variational Bayes

作者：Song, Hui; Dai, Jiejie; Zhang, Weidong; Bi, Kai; Luo, Lingen; Sheng, Gehao; Jiang, Xiuchen

来源：Proceedings of the CSEE, 2018, 38(19): 5869-5877.

DOI：10.13334/j.0258-8013.pcsee.180136

• Data matching
• Deep belief network (DBN)
• Deep convolutional neural networks
• Feature extraction methods
• Linear discriminant analyses (LDA)
• Partial discharge detection
• Statistical features
• Variational bayes

With the accumulation of partial discharge detection cases, it is an effective attempt to do deep data mining by computing the match degree between the detected partial discharge data and historical case database data under a big data background. Therefore, this paper proposed a data matching method based on auto-encoding variational Bayes (AEVB). An AEVB network model for partial discharge data was constructed to extract the deep eigenvalues. Then the cosine distance was used to calculate the match degree among different partial discharge data. To verify the advantages of the proposed method, a partial discharge data set was established by the partial discharge experiment and the live detection on the substation site. The proposed method was compared with other feature extraction methods and matching methods including statistical feature, deep belief networks (DBN), deep convolutional neural networks (CNN), principal component analysis (PCA) and linear discriminant analysis (LDA), Euclidean distance, information entropy. The experimental results show that the cosine distance match degree based on the AEVB feature vector can effectively detect the similar partial discharge data compared to other data matching methods.

• 出版日期2018
• 单位上海交通大学