Abstract
In order to solve the problem of misjudgment caused by the traditional power grid fault diagnosis methods, a new fusion diagnosis method is proposed based on the theory of multisource information fusion. In this method, the fault degree of the power element is deduced by using the Bayesian network. Then, the time-domain singular spectrum entropy, frequencydomain power spectrum entropy and wavelet packet energy spectrum entropy of the electrical signals of each circuit after the failure are extracted, and these three characteristic quantities are taken as the fault support degree of the power components. Finally, the four fault degrees are normalized and classified as four evidence bodies in the D-S evidence theory for multifeature fusion, which reduces the uncertainty brought by a single feature body. Simulation results show that the proposed method can obtain more reliable diagnosis results compared with the traditional methods.
Go to article
Bibliography
[1] Yao Yuantao, Wang Jin, Xie Min, Hu Liqin and Wang Jianye, ”A new approach for fault diagnosis with full-scope simulator based on state information imaging in nuclear power plant”, Annals of Nuclear Energy, 2020, 141, 1-9.
[2] Lei Koua, Chuang Liua, Guo-wei Caia, Zhe Zhangb, ”Fault Diagnosis for Power Electronics Converters based on Deep Feedforward Network and Wavelet Compression”, Electric Power Systems Research, 2020, 185, 1-9.
[3] Haibo Zhang, Kai Jia, Weijin Shi, Jianzhao Guo, Weizhi Su and Li Zhang, ”Power Grid Fault Diagnosis Based on Information Theory and Expert System”, Proceedings of the CSU-EPSA,, 2017, 29(8), 111-118.
[4] Jianfeng Zhou, Genserik Reniers and Laobing Zhang, ”A weighted fuzzy Petri-net based approach for security risk assessment in the chemical industry”, Chemical Engineering Science, 2017, 174, 136-145.
[5] Sen Wang and Xiaorun Li, ”Circuit Breaker Fault Detection Method Based on Bayesian Approach”, Industrial Control Computer, 2018, 31(4), 147-151.
[6] Kaikai Gu and Jiang Guo, ”Transformer Fault Diagnosis Method Based on Compact Fusion of Fuzzy Set and Fault Tree”, High Voltage Engineering , 2014, 40(05), 1507-1513.
[7] Jun Miao, Qikun Yuan, Liwen Liu, Zhipeng You and Zhang Wang, ”Research on robot circuit fault detection method based on dynamic Bayesian network”, Electronic Design Engineering, 2020, 28(9), 184- 188.
[8] Bangcheng Lai and Genxiu Wu, ”The Evidence Combination Method Based on Information Entropy”, Journal of Jiangxi Normal University (Natural Science), 2012, 36(5), 519-523.
[9] Libo Liu, Tingting Zhao, Yancang Li and Bin Wang, ”An Improved Whale Algorithm Based on Information Entry”, Mathematics in practice and theory, 2020, 50(2), 211-219.
[10] Juan Yan, Minfang Peng, et al., ”Fault Diagnosis of Grounding Grids Based on Information Entropy and Evidence Fusion”, Proceedings of the CSU-EPSA, 2017, 29(12),8-13.
[11] Ershadi, Mohammad Mahdi and Seifi, Abbas, ”An efficient Bayesian network for differential diagnosis using experts’ knowledge”, International Journal of Intelligent Computing and Cybernetics, 2020, 13(1), 103-126.
[12] Guan Li, Zhifeng Liu, Ligang Cai and Jun Yan, ”Standing-Posture Recognition in Human–Robot Collaboration Based on Deep Learning and the Dempster–Shafer Evidence Theory”, Sensors, 2020, 20(4), 1- 17.
[13] Xiaofei He, Xiaoyang Tong and Shu Zhou, ”Power system fault diagnosis based on Bayesian network and fault section location”, Power system protection and control, 2010, 38(12), 29-34.
Go to article
en
pl
