State Evaluation of HVDC Core Equipment Based on BP Neural Network

Authors

  • Lipeng Ren
  • Weijie Hang

DOI:

https://doi.org/10.54097/t6gvv640

Keywords:

Transmission core equipment, State evaluation, BP neural network, Time-varying weight, TOPSIS analysis

Abstract

The damage of core power equipment will cause serious losses to the power grid, and the evaluation and diagnosis of power equipment status can effectively avoid the economic loss of the power grid. In this paper, combining the operating characteristics of the DC transmission system and the impact of related core equipment on the stability of the system, the set value iteration method and BP neural network are used to determine the time-varying weight of the evaluation index of the core equipment of the DC transmission. Ideal samples and negative ideal samples, calculate the gray correlation degree between each sample and the positive and negative ideal samples and calculate the closeness of the core equipment status to realize the real-time status evaluation of the core equipment. Finally, take the voltage source converter as an example to establish an evaluation index system for real-time evaluation of equipment status.

Downloads

Download data is not yet available.

References

[1] LIAO Ruijin, WANG Youyuan, LIU Hang, et al. Research status of condition assessment method for power equipment [J]. High Voltage Engineering, 2018, 44(11): 3454-3464.

[2] Qi Bo, Zhang Peng, Zhang Shuqi, Zhao Linjie, Wang Hongbin, Huang Meng, Tang Zhiguo, Ji Mao, Li Chengrong. Application status and development prospect of digital twin technology in condition assessment of power transmission and transformation equipment [J]. High Voltage Technology, 2021, 47 (05):1522-1538.

[3] HUANG Haibo, LEI Hongcai, ZHOU Weihua, et al. Research on transformer condition-based maintenance optimization based on nonpower-off detection [J]. High Voltage Engineering, 2019, 45(10):3300-3307.

[4] Cao Lei. HVDC converter valve fault early warning and optimized design for phase commutation failure [D]. Shandong University, 2014.

[5] Gong Hao, Luo Chuanxian, Wang Yaqian, Xu Xiaolu, Zhou Zhengqin, Ni Hui. A method of substation equipment evaluation based on correlation hierarchy weighting and discrete fuzzy number [J]. Science Technology and Engineering, 2021, 21(04):1394-1401.

[6] Xue Wei. Research on Power Equipment Maintenance Strategy Based on Condition Monitoring [D]. Inner Mongolia University of Science and Technology, 2019.

[7] Li Erxia, Kang Chaoqun, Li Yuling, Fan Yonghua, Ma Guoming, Du Yue. Optimization model of distribution network maintenance plan based on equipment status evaluation and grid loss risk [J]. HighVoltageTechnology, 2018, 44(11):3751-3759.

[8] Nan Dongliang, Wang Weiqing, Zhang Ling, Chen Kai, Yang Guosheng, Zhang Lu, Sun Yonghui. Risk assessment of the operation status of secondary equipment in power grid based on association rule mining and combination weighting-cloud model [J]. Power System Protection and Control, 2021, 49(10):67-76.

[9] Wang Shanshan, Shi Lei, Gu Ran. Based on the TOPSIS method to realize the evaluation of the operation status of the primary equipment in the smart grid [J]. Power Supply, 2021, 38(06):56-60.

[10] Chen Jiahui, Gao Yanjie, Jin Yiwei. Microgrid fault diagnosis method based on MODWT and BP neural network [J]. Journal of Shanghai Electric Power University, 2021, 37(01):57-60+77.

[11] Wang Yangguang, Zhang Xiaojun, Xu Yuxin, Huang Yong, Ye Yuqing, Ma Xiao, Li Zhengtian, Wu Yuqi. Bipolar DC microgrid protection scheme based on circuit breaker action sequence [J]. Power System Protection and Control, 2021, 49(04 ): 81-88.

[12] Vandermaar A J. Condition assessment of power transformers [A]. 2008 IEEE Power and Energy Society General Meeting - Conversion and Delivery of Electrical Energy in the 21st Century [C]. 2008: 1–5.

[13] Hao Kai, Yang Xiaowei. Research on Implementation Strategies for Condition Maintenance of Power Equipment [J]. Low Carbon World, 2018(07): 95–96.

[14] Guo Tao, Huang Yuekui, Liao Huilian, et al. Research and implementation of condition maintenance technology for DC transmission equipment [J]. East China Electric Power, 2011, 39(11): 1816–1819.

[15] Tan Jinhua. Discussion on the status monitoring of the main equipment of the HVDC transmission system [J]. China Electric Power (Technical Edition), 2015(02): 71–73.

[16] Ji Panpan, Hu Siquan, Liao Zhijun et al. Design of an online monitoring system for the operation status of converter valves in flexible DC transmission [J]. Power System and Clean Energy, 2015, 31(12): 68–72.

[17] Xiao Fei, Ye Kang, Deng Xiangli, Wei Congcong, Ke Yang. Power system fault diagnosis method based on optimal code set and intelligent state estimation [J]. Power System Protection and Control, 2021, 49(02):89-97.

[18] McClelland, Rumelhart. Parllel Distributed Processing [M]. Volsland2, MITPress, 1986.

[19] Yang Shu'e, Huang Li. The financial early warning model of listed companies based on BP neural network [J]. System Engineering Theory and Practice, 2005(01):12-18+26.

[20] Qian Wuyong, Dang Yaoguo, Xiong Pingping, Wang Zhengxin. TOPSIS method and its application based on grey relational weight determination [J]. System Engineering, 2009, 27(08):124-126.

[21] SUN Jibo, WANG Yu, LIU Chongru, et al. Pole-to-pole short circuit current calculation of multi-terminal DC grid based on MMC [J]. Electric Power Automation Equipment, 2018, 38(11):72-78.

[22] ZHANG Aixiang, SONG Shizhan, WANG Chuanyong, et al. Plan of active distribution network considering power quality control equipment and interest of different subjects [J]. Power Capacitor & Reactive Power Compensation, 2019, 40(2):113-118, 153.

[23] Shen Huayu, Wang Zhaoxia, Gao Chengyao, Qin Juan, Yao Fubin, Xu Wei. Determination of the number of hidden layer units of BP neural network [J]. Journal of Tianjin University of Technology, 2008(05):13-15.

Downloads

Published

10-02-2026

Issue

Section

Articles