Abstract：Traction transformers (TRs) are key equipment in the traction power supply system of heavy haul railways (HHRs). With the increase of operating mileage and service time of HHR, the safety hazards caused by their performance degradation have gradually become an important issue for equipment and property safety. In response to the shortcomings of traditional passive maintenance and repair modes, this paper proposes a state evaluation model based on comprehensive health index and iterative prediction to achieve predictive maintenance analysis. This method is divided into two steps. Firstly, based on the internal parameters and routine test parameters of the TR, the status of the TR is evaluated, and a quantitative comprehensive health index is given according to the weight. Then, a risk prediction and evaluation method for traction transformer equipment is designed, using a non equidistant grey prediction model to predict the remaining life of the traction transformer status. Qualitative analysis of the health state of the traction transformer is provided. Through on-site maintenance records, the prediction results are compared with the actual transformer status, and the accuracy of the prediction is statistically analyzed. Based on the prediction results, the model is iteratively optimized to improve the accuracy of the evaluation, Based on this, a “monitoring-evaluation-analysis suggestion” model for the traction transformer of heavy-duty railways is established. Finally, the model mentioned in this paper is verified by the data of the traction transformer of a heavy haul railway traction electrical substation from 2015 to 2020, and the results show that the method is feasible.
杨戈辉, 赵桐浠, 姚鑫, 张万起, 孟令宇. 基于健康指数和非等间隔灰色预测的重载铁路牵引变压器状态评估方法[J]. 电气技术, 2023, 24(11): 10-17.
YANG Gehui, ZHAO Tongxi, YAO Xin, ZHANG Wanqi, MENG Lingyu. A state evaluation method for heavy haul railway traction transformers based on health index and unequal interval grey prediction. Electrical Engineering, 2023, 24(11): 10-17.
[1] NING Bin, TANG Tao, GAO Ziyou, et al.Intelligent railway systems in China[J]. IEEE Intelligent Systems, 2006, 21(5): 80-83. [2] LI Ping, JIA Limin, NIE Axin.Study on railway intel- ligent transportation system architecture[C]//Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems, Shanghai, China, 2003: 1478-1481. [3] DEMIR R, MASAKI I, CRAWLEY E F.System design for intelligent railway systems[C]//Proceedings of Conference on Intelligent Transportation Systems, Boston, MA, USA, 1997. [4] HUANG Yuansheng, ZHANG Huijuan.Grey corre- lation in the combined weights of power load forecasting application[C]//2008 International Con- ference on Information Management Innovation Management and Industrial Engineering, Taipei, China, 2009: 292-295. [5] LIU Yu, LI Zhi, BAI Kai, et al.Short-term power- forecasting method of distributed PV power system for consideration of its effects on load forecasting[J]. The Journal of Engineering, 2017, 2017(13): 865-869. [6] HUANG Zhiwei, GAO Tian, ZHANG Huaving, et al.Transient power quality assessment based on big data analysis[C]//2014 China International Conference on Electricity Distribution (CICED), Shenzhen, China, 2014: 1308-1312. [7] LIN Zhiming, TANG Songping, PENG Gang, et al.An artificial neural network model with Yager com- position theory for transformer state assessment[C]// 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Chongqing, China, 2017: 652-655. [8] JAISWAL G C, BALLAL M S, TUTAKNC D R.ANN based methodology for determination of distribution transformer health status[C]//2017 7th International Conference on Power Systems (ICPS), Pune, India, 2018: 133-138. [9] ISLAM M, LEE G, HETTIWATTE S N, et al.Calcu- lating a health index for power transformers using a subsystem-based GRNN approach[J]. IEEE Transa- ctions on Power Delivery, 2018, 33(4): 1903-1912. [10] CUI Lili, ZHANG Ruipeng, WANG Peng.Method for supplier selection based on ANP and entropy righ[C]// 2009 Second International Conference on Intelligent Computation Technology and Automation, Changsha, China, 2009: 935-940. [11] WU Yuhan, SUN Xiaobo, YANG Pengfei, et al.Trans- former fault diagnosis based on improved particle swarm optimization to support vector machine[C]//3rd International Conference on Mechanical, Electrical and Material Application (MEMA 2020), Chongqing, China, 2020. [12] 郭一帆, 唐家银. 基于机器学习算法的寿命预测与故障诊断技术的发展综述[J]. 计算机测量与控制, 2019, 27(3): 7-13. [13] LI Enwen, SONG Bin.Transformer health status evaluation model based on multi-feature factors[C]// 2014 International Conference on Power System Technology, Chengdu, China, 2014. [14] 熊奇, 张欣, 杨磊, 等. 基于IAHP与FCEM的变压器寿命评估[J]. 电力学报, 2019, 34(4): 387-394. [15] JIANG Jun, CHEN Ruyi, CHEN Min, et al.Dynamic fault prediction of power transformers based on hidden Markov model of dissolved gases analysis[J]. IEEE Transactions on Power Delivery, 2019, 34(4): 1393-1400. [16] 冯玎. 基于运行特性的高铁牵引供电系统可靠性与风险评估研究[D]. 成都: 西南交通大学, 2019. [17] 曲岳晗, 赵洪山, 程晶煜, 等. 基于物联感知数据和张量融合的电力变压器绕组绝缘劣化评估方法[J]. 电工技术学报: 1-13[2023-10-30]. https://doi.org/10.19595/j.cnki.1000-6753.tces.222148. [18] 朱道俊, 张文锋, 李国彬. 基于熵权和TOPSIS法的山区35kV架空线路雷击风险评估[J]. 电气技术, 2022, 23(8): 23-30. [19] 谭翼坤, 陈明, 黄腾, 等. 基于气体成分分析的变压器过热隐患预警方法[J]. 电气技术, 2022, 23(10): 51-58. [20] HU Haitao, SHAO Yang, TANG Li, et al.Overview of harmonic and resonance in railway electrification systems[J]. IEEE Transactions on Industry Appli- cations, 2018, 54(5): 5227-5245.
2023, Vol. 24 
