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

doi:10.19595/j.cnki.1000-6753.tces.222148

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (746 KB)
输出: BibTeX | EndNote (RIS)

摘要

针对目前缺乏依托在线物联感知数据的电力变压器绕组绝缘劣化评估方法的问题,本文考虑电、热、机械劣化因素对电力变压器绕组绝缘的损伤累积效应,提出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。首先,研究电、热、机械因素对绕组绝缘的累积损伤机理,依托电压、电流、温度、局部放电物联感知数据构建变压器绕组绝缘的电性能、热性能和机械性能劣化损伤指标;然后,构建三种劣化损伤指标的特征张量,基于张量融合对三种劣化损伤指标进行特征融合,提取劣化损伤指标间的高维劣化特征关联信息;最后,采用基于自组织映射网络（Self-Organizing Map,SOM）的最小量化误差方法构建绕组绝缘的综合劣化评估指标,实现对绕组绝缘劣化状态的评估。本文通过多种评价准则评价所构建的综合劣化指标。算例结果表明,所提方法能准确评估变压器绕组绝缘的真实劣化程度。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	曲岳晗
	赵洪山
	程晶煜
	马利波
	米增强

关键词 ：电力变压器, 绕组绝缘, 劣化评估, 物联感知数据, 张量融合

Abstract：

Online evaluation of winding insulation degradation is of great significance to the stable operation of transformers. Due to the lack of corresponding online sensing means, the traditional degradation evaluation methods relying on data such as furfural content and methanol content in oil cannot realize the online evaluation of winding insulation degradation. Most of the degradation evaluation methods based on online sensing data such as voltage and current only consider the influence of a single factor, and it is difficult to fully reflect the degree of degradation of winding insulation. To solve these problems, we propose a power transformer winding insulation degradation evaluation method based on IoT sensing data and tensor fusion. This method takes the influence of electrical, thermal, and mechanical factors of insulation degradation into account, and relies on voltage, current, temperature, and partial discharge IoT sensing data to realize online evaluation of transformer winding insulation degradation.
Firstly, analyze the cumulative damage mechanism of winding insulation degradation caused by electrical, thermal, and mechanical factors. Relying on the transformer IoT sensing data of voltage, current, temperature and partial discharge to construct the electrical, thermal and mechanical performance degradation damage indicators of winding insulation. Then, based on tensor fusion, we perform feature fusion of three degradation damage indicators, and extract high-dimensional degradation feature correlation information between degradation damage indicators. Finally, we use the minimum quantization error of self-organizing map to quantify the distance between the degradation feature output tensor and the best matching unit weight tensor, construct a comprehensive degradation evaluation index, and realize the online evaluation of the winding insulation degradation degree.
According to the verification results of the proposed method based on the accelerated aging test data, the trend evaluation value, monotonicity evaluation value, robustness evaluation value, scale similarity evaluation value, and fusion evaluation value of the comprehensive degradation evaluation index we constructed are 95.78%, 100.00%, 99.75%, 93.24%, and 97.19%, respectively. The mean absolute error, Mean Square Error, and Root Mean Square Error of the comprehensive degradation evaluation index are all less than 0.05, and the R-Square and Pearson correlation coefficient exceed 97%, the significance test coefficient is less than 0.01. According to the verification result of the actual transformer IoT sensing data and the comparison result of various degradation evaluation methods, the fusion evaluation value of the proposed method exceeds 95%. Compared with other degradation evaluation methods, the proposed method has a higher similarity in trend with the furfural content index of winding insulation.
The conclusions are as follows: (1) The proposed method relies on the IoT sensing data of transformer to quantify the cumulative damage caused by electrical, thermal and mechanical stress to winding insulation from the perspective of mechanism and can accurately describe the degradation trend of winding insulation under multiple stresses. (2) The proposed method fuses the feature tensors of electrical, thermal, and mechanical degradation damage indicators based on tensor fusion, which can extract the high-dimensional degradation correlation information between degradation damage indicators to the greatest extent while retaining the characteristics of each degradation damage. (3) The proposed method can accurately describe the degree of deviation between the winding insulation degradation state and the healthy state through the comprehensive degradation evaluation index constructed by the minimum quantization error. (4) According to the experimental verification results, the proposed method can accurately evaluate the real degradation state of the winding insulation based on the transformer IoT sensing data, and the evaluation results can provide a reference for the maintenance of the winding insulation.

Key words： Power transformer winding insulation degradation evaluation IoT sensing data tensor fusion

收稿日期: 2022-11-15

PACS:

TM41

基金资助:

国家重点研发研究计划政府间国际科技创新合作重点专项 (2018YFE0122200)资助

通讯作者: 赵洪山男,1965年生,博士,教授,博士生导师,主要从事电力系统动态分析与控制,主动配电网以及故障预测等方面的研究。E-mail：zhaohshcn@126.com

作者简介: 曲岳晗男,1995年生,博士研究生,研究方向为电力设备劣化分析与智能运维。E-mail：quyuehan0617@163.com

引用本文:

曲岳晗, 赵洪山, 程晶煜, 马利波, 米增强. 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, 0, (): 127-127. Qu Yuehan, Zhao Hongshan, Cheng Jingyu, Ma Libo, Mi Zengqiang. Evaluation Method for Power Transformer Winding Insulation Degradation Based on IoT Sensing Data and Tensor Fusion. Transactions of China Electrotechnical Society, 0, (): 127-127.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.222148 https://dgjsxb.ces-transaction.com/CN/Y0/V/I/127

[1] Singh J, Singh S. Transformer failure analysis: reasons and methods[J]. International Journal of Engineering Research & Technology, 2016, 4(15): 1-5. https://api.semanticscholar.org/CorpusID:86551574.
[2] Murugan R, Ramasamy R.Understanding the power transformer component failures for health index-based maintenance planning in electric utilities[J]. Engineering Failure Analysis, 2019, 96: 274-288. DOI:10.1016/j.engfailanal.2018.10.011.
[3] Dong M, Zheng H, Zhang Y, et al.A novel maintenance decision making model of power transformers based on reliability and economy assessment[J]. IEEE access, 2019, 7: 28778-28790. DOI: 10.1109/ACCESS.2019.2897606.
[4] Krause C.Power transformer insulation-history, technology and design[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2012, 19(6): 1941-1947. DOI: 10.1109/TDEI.2012.6396951.
[5] Moradzadeh A, Pourhossein K.Early detection of turn-to-turn faults in power transformer winding: an experimental study[C]//2019 International Aegean Conference on Electrical Machines and Power Electronics (ACEMP) & 2019 International Conference on Optimization of Electrical and Electronic Equipment (OPTIM). IEEE, 2019: 199-204. DOI: 10.1109/acemp-optim44294.2019.9007169.
[6] Tenbohlen S, Jagers J, Bastos G, et al. Development and results of a worldwide transformer reliability survey[C]//Proceedings of the CIGRE SC A2 Colloquium, Shanghai, China.2015, 2025. https://www.indianjournals.com/ijor.aspx?target=ijor:wei&volume=58r&issue=9&article=004.
[7] Aslam M, Haq I U, Rehan M S, et al.Health analysis of transformer winding insulation through thermal monitoring and fast Fourier transform (FFT) power spectrum[J]. IEEE Access, 2021, 9: 114207-114217. DOI: 10.1109/access.2021.3104033.
[8] Qu Y, Zhao H, Zhao S, et al.Power transformer oil-paper insulation degradation modelling and prediction method based on functional principal component analysis[J]. IET Science, Measurement & Technology, 2022, 16(8): 441-453. DOI:10.1049/smt2.12117.
[9] 张明泽, 刘骥, 陈昕等. 基于Wiener模型的变压器油纸绝缘老化剩余寿命评估方法[J]. 电工技术学报, 2018, 33(21):5098-5108. DOI:10.19595/j.cnki.1000-6753.tces.171587.
Zhang Mingze, Liu Ji, Chen Xin, et al.Residual Life Evaluation Method of Transformer Oil Paper Insulation Aging Based on Wiener Model[J].Transactions of China electrotechnical society,2018, 33(21):5098-5108. DOI:10.19595/j.cnki.1000-6753.tces.171587.
[10] 彭磊, 付强, 李丽等. 基于变压器油中甲醇含量的绝缘纸聚合度检测方法[J]. 变压器, 2019, 56(03):50-54. DOI:10.19487/j.cnki.1001-8425.2019.03.012.
Peng Lei, Fu Qiang, Li Li, et al.Detection Method for Polymerization Degree of Insulation Paper Based on Methanol Content in Transformer Oil[J]. Transformer, 2019,56(03):50-54.DOI:10.19487/j.cnki.1001-8425.2019.03.012.
[11] 郭蕾,张传辉,廖维,代禄喻,周利军.基于Dissado-Hill模型的油纸绝缘受潮参数特征与评估方法[J].电工技术学报,2021,36(23):5058-5068.DOI:10.19595/j.cnki.1000-6753.tces.200617.
Guo Lei, Zhang Chuanhui, Liao Wei, et al.Oil-Paper Insulation Moisture Parameter Characteristics and Evaluation Method Based on Dissado-Hill Model[J]. Transactions of China Electrotechnical Society,2021,36(23):5058-5068.DOI:10.19595/j.cnki.1000-6753.tces.200617.
[12] 黄彦钦,余浩,尹钧毅,孟国栋,成永红.电力物联网数据传输方案:现状与基于5G技术的展望[J].电工技术学报,2021,36(17):3581-3593.DOI:10.19595/j.cnki.1000-6753.tces.201464.
Huang Yanqin, Yu Hao, Yin Junyi, et al.Data Transmission Schemes of Power Internet of Things:Present and Outlook Based on 5G Technology[J]. Transactions of China Electrotechnical Society,2021,36(17):3581-3593.DOI:10.19595/j.cnki.1000-6753.tces.201464.
[13] Han R, Du W, Wang W, et al.Research on online diagnosis method of transformer winding deformation based on correlation mining of operating voltage and current[C]//2020 IEEE International Conference on High Voltage Engineering and Application (ICHVE). IEEE, 2020: 1-4. DOI:10.1109/ichve49031.2020.9279788.
[14] Lei C, Li L, Yang L, et al.Design of Dry-type Transformer Online Monitoring and Fault Diagnosis System[C]//2020 IEEE 4th Conference on Energy Internet and Energy System Integration (EI2). IEEE, 2020:1010-1013.DOI:10.1109/ei250167.2020.9346640.
[15] Venikar P A, Ballal M S, Umre B S, et al.A novel offline to online approach to detect transformer interturn fault[J]. IEEE Transactions on Power Delivery, 2015, 31(2): 482-492.DOI:10.1109/tpwrd.2015.2440448.
[16] 周凯, 吴广宁, 吴建东等. 基于局部放电统计参量的脉冲电压下绝缘老化分析[J]. 电工技术学报, 2008(04):6-12.DOI:10.19595/j.cnki.1000-6753.tces.2008.04.002.
Kai Zhou, Guangning Wu, Jiandong Wu, et al.Analysis of Aging Properties for Insulation Based on Statistical Parameters of Partial Discharge Under Pulse Voltage[J]. Transactions of China Electrotechnical Society,2008(04):6-12.DOI:10.19595/j.cnki.1000-6753.tces.2008.04.002.
[17] Cheng L, Yu T, Wang G, et al.Hot spot temperature and grey target theory-based dynamic modelling for reliability assessment of transformer oil-paper insulation systems: A practical case study[J]. Energies, 2018, 11(1): 249. DOI:10.20944/preprints201801.0122.v1.
[18] 李莹, 赵晶, 阎明印. 变压器绕组短路机械力理论及试验研究[J]. 变压器, 2017, 54(05):4-7. DOI:10.19487/j.cnki.1001-8425.2017.05.002.
Li Ying, Zhao Jing, Yan Mingyin.Theoretical and experimental study on mechanical force of transformer winding short circuit[J]. Transformer,2017, 54(05):4-7. DOI:10.19487/j.cnki.1001-8425.2017.05.002.
[19] 姜雅男,于永进,李长云.基于改进TOPSIS模型的绝缘纸机-热老化状态评估方法[J].电工技术学报,2022,37(06):1572-1582.DOI:10.19595/j.cnki.1000-6753.tces.201187.
Jiang Yanan, Yu Yongjin, Li Changyun.Evaluation Method of Insulation Paper Deterioration Status with Mechanical-Thermal Synergy Based on Improved TOPSIS Model[J]. Transactions of China Electrotechnical Society, 2022,37(06):1572-1582. DOI:10.19595/j.cnki.1000-6753.tces.201187.
[20] 姜良民, 殷守斌, 徐珂等. 变压器油纸绝缘电热联合老化机理研究[J]. 电网与清洁能源, 2022, 38(05): 86-94. DOI:10.3969/j.issn.1674-3814.2022.05.012.
Liangmin Jiang, Shoubin Yin, Ke Xu, et al.A Study on the Electrical-Thermal Aging Mechanism of Oil-Paper Insulation in Transformers[J]. Power System and Clean Energy, 2022, 38(05):86-94. DOI:10.3969/j.issn.1674-3814.2022.05.012.
[21] 于永进, 姜雅男, 李长云. 基于鲸鱼优化-长短期记忆网络模型的机-热老化绝缘纸剩余寿命预测方法[J].电工技术学报, 2022, 37(12):3162-3171. DOI:10.19595/j.cnki.1000-6753.tces.210110.
Yongjin Yu, Yanan Jiang, Changyun Li.A method for predicting the remaining life of machine-thermal aging insulation paper based on whale optimization-long and short-term memory network model[J]. Transactions of China Electrotechnical Society,2022,37(12):3162-3171. DOI:10.19595/j.cnki.1000-6753.tces.210110.
[22] 边浩然,杨丽君,马志鹏,丁志文,李仲轩.基于累积损伤曲线的电寿命模型步进应力试验方法及在XLPE电缆中的应用[J].中国电力,2020,53(09): 125-132.DOI:10.11930/j.issn.1004-9649.202005062.
Haoran Bian, Lijun Yang, Zhipeng Ma, et al.Step-Stress Test Method for Electrical Life Model Based on Cumulative Damage Curve and Its Application in XLPE Cable[J]. Electric Power, 2020, 53(09):125-132.DOI:10.11930/j.issn.1004-9649.202005062.
[23] 赵洪山, 马利波. 基于张量Tucker分解的智能配电网大数据压缩[J]. 中国电机工程学报, 2019, 39(16):4744-4752+4976.DOI:10.13334/j.0258-8013.pcsee.181447.
Hongshan Zhao, Libo Ma. Big data compression of smart distribution network based on tensor Tucker decomposition[J]. Proceedings of the CSEE, 2019, 39(16): 4744-4752+4976. DOI: 10.13334/j.0258-8013.pcsee.181447.
[24] Zhao H, Ma L.Power distribution system stream data compression based on incremental tensor decomposition[J]. IEEE Transactions on Industrial Informatics, 2019, 16(4): 2469-2476. DOI:10.1109/tii.2019.2934766.
[25] Zadeh A, Chen M, Poria S, et al. Tensor fusion network for multimodal sentiment analysis[J]. arXiv preprint arXiv:1707.07250, 2017.DOI:10.18653/v1/D17-1115.
[26] Zhang L, Qiao F, Wang J.Equipment health assessment and fault-early warning algorithm based on improved SVDD[C]//2018 IEEE 14th International Conference on Automation Science and Engineering (CASE). IEEE, 2018: 716-721. DOI: 10.1109/coase.2018.8560464.
[27] Hill D J T, Le T T, Darveniza M, et al. A study of degradation of cellulosic insulation materials in a power transformer, part 1. Molecular weight study of cellulose insulation paper[J]. Polymer Degradation and Stability, 1995, 48(1): 79-87. DOI: 10.1016/0141-3910(95)00023-f.
[28] 柯春俊, 林春耀, 欧小波等. 步进电压下变压器匝间绝缘电压寿命指数新解法[J]. 哈尔滨理工大学学报, 2016,21(05):66-72.DOI: 10.15938/j.jhust.2016.05.013.
Chunjun Ke, Chunyao Lin, Xiaobo Ou, et al.New Solving Method for Voltage Endurance Coefficient N of Transformer Turn-to-turn Insulation under Step-voltage[J]. Journal of Harbin University of Technology of Science and Technology, 2016, 21(05): 66-72. DOI:10.15938/j.jhust.2016.05.013.
[29] Montanari G C, Seri P, Bononi S F, et al.Partial discharge behavior and accelerated aging upon repetitive DC cable energization and voltage supply polarity inversion[J]. IEEE Transactions on Power Delivery, 2020, 36(2): 578-586. DOI:10.1109/tpwrd.2020.2984766.
[30] Serra S, Montanari G C, Mazzanti G.Theory of inception mechanism and growth of defect-induced damage in polyethylene cable insulation[J]. Journal of applied physics, 2005, 98(3): 034102. DOI:10.1063/1.1978986.
[31] Wang Y, Zhang X, Jiang X, et al.Effect of aging on material properties and partial discharge characteristics of insulating pressboard[J]. BioResources, 2019, 14(1): 1303-1316. DOI:10.15376/biores.14.1.1303-1316.
[32] Li X, Zhang W, Wang H, et al.Surface Degradation of Oil-Immersed Nomex Paper Caused by Partial Discharge of High-Frequency Voltage[J]. Journal of Electronic Materials, 2022: 1-10. DOI:10.1007/s11664-022-10044-8.
[33] Mazzanti G, Montanari G C.Electrical aging and life models: the role of space charge[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2005, 12(5): 876-890. DOI:10.1109/TDEI.2005.1522183.
[34] Montanari G C, Seri P.A partial discharge-based health index for rotating machine condition evaluation[J]. IEEE electrical insulation magazine, 2018, 34(2): 17-23. DOI:10.1109/mei.2018.8300440.
[35] Montanari G C, Seri P, Contin A.How to deal with the severity of different partial discharge sources in rotating machines: the definition of a new health index[C]//2018 IEEE Electrical Insulation Conference (EIC). IEEE, 2018: 469-472. DOI:10.1109/eic.2018.8481118.
[36] 骆东松, 胡晓盼. 低压电机定子绝缘老化应力分析及寿命预测的研究[J].舰船电子工程, 2021, 41(08):173-176+179.DOI:10.3969/j.issn.1672-9730.2021.08.040.
Dongsong Luo, Xiaopan Hu. Research on Stress Analysis and Life Prediction of Stator Insulation of Low-voltage Motor[J]. Ship Electronic Engineering, 2021,41(08):173-176+179.DOI:10.3969/j.issn.1672-9730.2021.08.040.
[37] Wang S, Zhang H, Wang S, et al.Cumulative deformation analysis for transformer winding under short-circuit fault using magnetic-structural coupling model[J]. IEEE Transactions on Applied Superconductivity, 2016, 26(7): 0-5. DOI:10.1109/TASC.2016.2584984.
[38] 赵治刚. 电力变压器绕组变形与短路强度研究[D].华北电力大学,2020. DOI:10.27139/d.cnki.ghbdu.2020.000342.
Zhao Zhigang.Research on Winding Deformation and Short Circuit Strength of Power Transformer[D]. North China Electric Power University,2020. DOI:10.27139/d.cnki.ghbdu.2020.000342.
[39] Zhang B, Zhang L, Xu J.Degradation feature selection for remaining useful life prediction of rolling element bearings[J]. Quality and Reliability Engineering International, 2016, 32(2): 547-554. DOI:10.1002/qre.1771.
[40] Guo L, Lei Y, Li N, et al.Machinery health indicator construction based on convolutional neural networks considering trend burr[J]. Neurocomputing, 2018, 292: 142-150. DOI:10.1016/j.neucom.2018.02.083.
[41] 张伟丽. 变压器油纸绝缘多因子老化特性及特征参数提取方法研究[D].哈尔滨理工大学, 2019. https://kns.cnki.net/KCMS/detail/detail.aspx?dbname=CMFD201902&filename=1019178005.nh.
Weili Zhang. Study on Multi-factor Aging Properties and Characteristic Parameters Extraction Method of Transformer Oil-paper Insulation[D]. Harbin University of Science and Technology, 2019. https://kns.cnki.net/KCMS/detail/detail.aspx?dbname=CMFD201902&filename=1019178005.nh.
[42] 鄢仁武, 高硕勋, 宋微浪等. 基于多参量LSTM模型的变压器油纸绝缘老化诊断方法[J]. 武汉大学学报(工学版), 2021, 54(06):541-550. DOI:10.14188/j.1671-8844.2021-06-009.
Renwu Y, Shuoxun G, Weilang S, et al.Diagnosis method of transformer oil-paper insulation ageing based on multi-parameter LSTM model[J]. Journal of Wuhan University (Engineering Edition), 2021, 54(06): 541-550. DOI:10.14188/j.1671-8844.2021-06-009.