Dissolved Gas Analysis of Insulating Oil for Power Transformer Fault Diagnosis Based on ReLU-DBN

被引：0

作者：

Dai J. ^{[1
]}

Song H. ^{[1
]}

Yang Y. ^{[2
]}

Chen Y. ^{[2
]}

Sheng G. ^{[1
]}

Jiang X. ^{[1
]}

机构：

[1] Department of Electrical Engineering, Shanghai Jiao Tong University, Minhang District, Shanghai

[2] Electric Power Research Institute of Shandong Power Supply Company of State Grid, Jinan, 250002, Shandong Province

来源：

Dianwang Jishu/Power System Technology | 2018年 / 42卷 / 02期

基金：

中国国家自然科学基金;

关键词：

Deep belief networks; Dissolved gas analysis; Fault diagnosis; Non-code ratios; Transformer;

D O I：

10.13335/j.1000-3673.pst.2017.1027

中图分类号：

学科分类号：

摘要：

Dissolved gas analysis (DGA) of insulating oil can provide an important basis for transformer fault diagnosis. To improve diagnosis accuracy, this paper studies a transformer fault diagnosis method based on rectified linear units deep belief networks (ReLU-DBN). By analyzing relationship between the gases dissolved in transformer oil and fault types, non-code ratios of the gases are determined as characteristic parameters of ReLU-DBN model. ReLU-DBN adopts multi-layer and multi-dimension mapping to extract more detailed differences of fault types. In this process, the parameters of diagnosis model are pre-trained, and adjusted with back propagation algorithm with sample labels. Performances of the ReLU-DBN diagnosis model are analyzed with different characteristic parameters, different training dataset and sample dataset. Besides, influence of discharge and overheating multiple-fault on diagnosis model is studied. Diagnosis effect of the model with non-code ratios as characteristic parameters is better than those of the models with IEC ratios, Rogers ratios and Dornenburg ratios. Compared with the results derived from support vector machine (SVM) and back propagation neural network (BPNN), the proposed ReLU-DBN method significantly improves accuracy for power transformer fault diagnosis. Diagnosis effect of the model considering multiple-fault is better than that of the model without multiple-fault. With increase of sample dataset, the diagnostic accuracy is improved. © 2018, Power System Technology Press. All right reserved.

引用

页码：658 / 664

页数：6

共 26 条

[21] Zeiler M.D., Ranzato M., Monga R., Et al., On rectified linear units for speech processing, Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 3517-3521, (2013)
[22] Hinton G., Training products of experts by minimizing contrastive divergence, Neural Computation, 14, 8, pp. 1771-1800, (2002)
[23] Zheng H., Sun C., Li J., Et al., A model and method of degree of grey incidence analysis on transformer fault diagnosis, Proceedings of the CSEE, 21, 10, pp. 106-109, (2001)
[24] Yang T., Zhang H., Huang L., Et al., Incipient fault diagnosis based on improved principal component analysis for power transformer, Electric Power Automation Equipment, 35, 6, (2015)
[25] Hinton G., A practical guide to training restricted Boltzmann machines
[26] Cui Y., Ma H., Tapan S., Improvement of power transformer insulation diagnosis using oil characteristics data preprocessed by SMOTEboost technique, IEEE Transactions on Dielectrics and Electrical Insulation, 21, 5, pp. 2363-2373, (2014)

← 1 2 3 →