基于数字孪生的变压器故障诊断方法研究

doi:10.16182/j.issn1004731x.joss.23-1402

摘要/Abstract

摘要：

针对已有的变压器故障诊断智能算法并不能快速高效的识别变压器故障，导致故障误检及不能被及时检测的问题，提出了一种利用改进麻雀优化算法优化XGBoost的双层故障诊断模型结合数字孪生技术的变压器故障诊断方法。采用先进传感器采集变压器的油气数据和温度数据，利用5G模块将实时数据传到数字孪生系统，设置设备告警阈值实时监控温度数据；使用改进麻雀优化算法优化XGBoost的双层故障诊断模型对油气数据进行实时故障识别处理，结合数字孪生技术对故障进行识别与预警。实验结果表明：该方法提高了故障识别与预警的效率和稳定性，且相较于现有的变压器故障诊断方法具有显著优势。

关键词: 变压器, 数字孪生, 故障诊断, 实时监控, 预警

Abstract:

Aiming at the inability of existing intelligent algorithms for transformer fault diagnosis to quickly and efficiently identify transformer faults, resulting in fault misdetection and untimely detection, this paper proposes a transformer fault diagnosis method using the improved sparrow optimization algorithm to optimize the two-layer fault diagnostic model of XGBoost combined with the digital twin technology. The method adopts advanced sensors to collect oil and gas data and temperature data of the transformer, uses 5G module to transmit the real-time data to the digital twin system. The system monitors the temperature data in real-time by setting the equipment alarm threshold; optimizes the two-layer fault diagnostic model of XGBoost using the improved sparrow optimization algorithm to process real-time fault identification of the oil and gas data, and finally identifies and warns of faults by combining with the digital twin technology. Experimental results indicate that this method significantly enhances the efficiency and stability of fault identification and early warning, demonstrating substantial advantages compared to existing transformer fault diagnosis methods.

Key words: transformer, digital twins, fault diagnosis, real time monitoring, warn

中图分类号:

TP274

江伦,王大江,孙文磊等 . 基于数字孪生的变压器故障诊断方法研究[J]. 系统仿真学报, 2025, 37(3): 775-790.

Jiang Lun,Wang Dajiang,Sun Wenlei,et al . Research on Transformer Fault Diagnosis Method Based on Digital Twin[J]. Journal of System Simulation, 2025, 37(3): 775-790.

图/表 22

图1

图2

图3

图4

表1

空气热物理性质

T/℃	$ρ / (k g · m 3)$	$λ$ $/ [W · (m · K) - 1]$	К $/ (m 2 · s - 1)$	$ν / (m 2 · s - 1)$	$P r$ /(m/s)
-30	1.450	2.20×10^-2	14.9×10^-6	10.80×10^-6	0.723
-20	1.395	2.28×10^-2	16.2×10^-6	11.62×10^-6	0.716
-10	1.342	2.35×10^-2	17.4×10^-6	12.45×10^-6	0.710
0	1.293	2.44×10^-2	18.8×10^-6	13.28×10^-6	0.708
10	1.247	2.50×10^-2	20.0×10^-6	14.15×10^-6	0.706
20	1.206	2.57×10^-2	21.3×10^-6	15.07×10^-6	0.704
30	1.165	2.64×10^-2	22.9×10^-6	16.00×10^-6	0.702
40	1.127	2.76×10^-2	24.3×10^-6	16.96×10^-6	0.699

表1

图5

图6

图7

图8

图9

图10

表2

变压器主要技术参数

参数	铭牌值
额定电压/kV	10
额定输入功率/Hz	50
额定容量/kVA	30
冷却方式	ONAN
油箱尺寸/mm	$1 130 × 780 ×$ 1 010
额定输出功率/Hz	50
初级线圈/匝	1 000
次级线圈/匝	20
空载/W	100
负载/W	600

表2

图11

图12

表3

表4

变压器油物理参数

物性参数	矿物绝缘油
密度 $ρ / (k g · m - 3)$	1 098.72-0.712 T
导热系数k/(W· $m - 1 K - 1$ )	0.159-7.101 $× 10 - 5 T$
动力粘度 $μ k g · m - 1 · s - 1$	0.084 67-0.000 4 T+5 $× 10 - 7 T 2$
定压比热 $c p / (J · k g - 1 · K - 1)$	807.163+3.58 T

表4

图13

图14

图15

图16

图17

图18

参考文献 27

1	Grieves M W. Product Lifecycle Management: The New Paradigm for Enterprises[J]. International Journal of Product Development, 2005, 2(1/2): 71-84.
2	Grieves M, Vickers J. Digital Twin: Mitigating Unpredictable, Undesirable Emergent Behavior in Complex Systems[M]//Franz Josef Kahlen, Flumerfelt S, Anabela Alves. Transdisciplinary Perspectives on Complex Systems: New Findings and Approaches. Cham: Springer International Publishing, 2017: 85-113.
3	石运东, 王爽, 程浩峰, 等. 一种易维护变压器呼吸器的方案设计[J]. 变压器, 2023, 60(2): 6-9.
	Shi Yundong, Wang Shuang, Cheng Haofeng, et al. Development and Application of a Transformer Respirator Easy to Maintain[J]. Transformer, 2023, 60(2): 6-9.
4	Morais D R, Rolim J G. A Hybrid Tool for Detection of Incipient Faults in Transformers Based on the Dissolved Gas Analysis of Insulating Oil[J]. IEEE Transactions on Power Delivery, 2006, 21(2): 673-680.
5	Fan Jingmin, Wang Feng, Sun Qiuqin, et al. Hybrid RVM-ANFIS Algorithm for Transformer Fault Diagnosis[J]. IET Generation Transmission & Distribution, 2017, 11(14): 3637-3643.
6	Hazlee Azil Illias, Chai Xinrui, Ab Halim Abu Bakar. Hybrid Modified Evolutionary Particle Swarm Optimisation-time Varying Acceleration Coefficient-artificial Neural Network for Power Transformer Fault Diagnosis[J]. Measurement, 2016, 90: 94-102.
7	Huang Xinyi, Huang Xiaoli, Wang Binrong, et al. Fault Diagnosis of Transformer Based on Modified Grey Wolf Optimization Algorithm and Support Vector Machine[J]. IEEJ Transactions on Electrical and Electronic Engineering, 2020, 15(3): 409-417.
8	Teng Wenhui, Fan Shuxian, Gong Zheng, et al. Fault Diagnosis of Transformer Based on Fuzzy Clustering and the Optimized Wavelet Neural Network[J]. Systems Science & Control Engineering, 2018, 6(3): 359-363.
9	Rao Shaowei, Zou Guoping, Yang Shiyou, et al. Fault Diagnosis of Power Transformers Using ANN and SMOTE Algorithm[J]. International Journal of Applied Electromagnetics and Mechanics, 2022, 70(4): 345-355.
10	Hu Qin, Mo Jiaqing, Ruan Saisai, et al. Fault Diagnosis of Oil-immersed Power Transformers Using SVM and Logarithmic Arctangent Transform[J]. IEEJ Transactions on Electrical and Electronic Engineering, 2022, 17(11): 1562-1569.
11	Ji Xingquan, Zhang Yuzhen, Liu Qi. Insulation Condition Assessment of Power Transformers Employing Fused Information in Time and Space Dimensions[J]. Electric Power Components and Systems, 2020, 48(1/2): 213-223.
12	Musliyarakath Aneesa Farhan, Shanti Swarup K. Mathematical Morphology-based Islanding Detection for Distributed Generation[J]. IET Generation, Transmission & Distribution, 2017, 11(14): 3449-3457.
13	Zhang Delong, Ye Zhijun, Chen Huipeng, et al. Research on Digital Twin Model and Visualization of Power Transformer[C]//2021 IEEE International Conference on Networking, Sensing and Control (ICNSC). Piscataway: IEEE, 2021: 1-5.
14	Gao Zhengzhong, Yin Xiucheng, Zhao Fanzhe, et al. A Two-layer SSA-XGBoost-MLR Continuous Multi-day Peak Load Forecasting Method Based on Hybrid Aggregated Two-phase Decomposition[J]. Energy Reports, 2022, 8: 12426-12441.
15	Wu Chao, Lin Junlian, Yu Zongchao, et al. Thermal State Prediction of Transformers Based on ISSA-LSTM[C]//2022 5th International Conference on Energy, Electrical and Power Engineering (CEEPE). Piscataway: IEEE, 2022: 160-165.
16	Rommel D P, Di Maio D. Transformer Hot Spot Temperature Prediction Based on Basic Operator Information[J]. International Journal of Electrical Power & Energy Systems, 2021, 124: 106340.
17	Xu Dapeng, Mao Yu, Yang Xiaohui, et al. Analysis of Winding Temperature Field Under Dynamic Variable Load of Oil-immersed Transformer[J]. Thermal Science, 2021, 25(4 Part B): 3009-3019.
18	张永超. 基于数字孪生技术的变压器温度预测及热寿命损失分析[D]. 沈阳: 沈阳工业大学, 2022.
	Zhang Yongchao. Transformer Temperature Prediction and Thermal Life Loss Analysis Based on Digital Twin Technology[D]. Shenyang: Shenyang University of Technology, 2022.
19	Zhu Shenglong, Qin Shaorui, Li Jianlin, et al. Steady-state Simulation on Temperature and Flow Fields of ONAF Transformer[C]//2021 3rd International Conference on Smart Power & Internet Energy Systems (SPIES). Piscataway: IEEE, 2021: 143-146.
20	鲁非, 王圣康, 李浩波, 等. 对流—辐射边界对变压器温度场影响的解耦研究[J]. 高压电器, 2022, 58(11): 17-23, 30.
	Lu Fei, Wang Shengkang, Li Haobo, et al. Decoupling Study on Influence of Convective-radiation Boundary on Transformer Temperature Field[J]. High Voltage Apparatus, 2022, 58(11): 17-23, 30.
21	张又文, 冯斌, 陈页, 等. 基于遗传算法优化XGBoost的油浸式变压器故障诊断方法[J]. 电力自动化设备, 2021, 41(2): 200-206.
	Zhang Youwen, Feng Bin, Chen Ye, et al. Fault Diagnosis Method for Oil-immersed Transformer Based on XGBoost Optimized by Genetic Algorithm[J]. Electric Power Automation Equipment, 2021, 41(2): 200-206.
22	Julio Cesar Guimarães, Daniel Flores Cortez, Alceu André Badin. Single-phase Hybrid Switched-capacitor Interleaved AC-DC Boost Converter[J]. IEEE Access, 2021, 9: 140799-140808.
23	唐炬, 王存超, 陈娇, 等. 变压器局部放电的泰勒遗传综合定位法[J]. 电工技术学报, 2010, 25(7): 165-171.
	Tang Ju, Wang Cunchao, Chen Jiao, et al. Taylor-genetic Algorithm Using for PD Location in Power Transformer[J]. Transactions of China Electrotechnical Society, 2010, 25(7): 165-171.
24	王伟, 唐庆华, 刘力卿, 等. 基于加权综合损失优化深度学习和DGA的变压器故障诊断方法[J]. 南方电网技术, 2020, 14(3): 29-34.
	Wang Wei, Tang Qinghua, Liu Liqing, et al. Transformer Fault Diagnosis Method Based on Weighted Comprehensive Loss Optimization Deep Learning and DGA[J]. Southern Power System Technology, 2020, 14(3): 29-34.
25	何庆, 林杰, 徐航. 混合柯西变异和均匀分布的蝗虫优化算法[J]. 控制与决策, 2021, 36(7): 1558-1568.
	He Qing, Lin Jie, Xu Hang. Hybrid Cauchy Mutation and Uniform Distribution of Grasshopper Optimization Algorithm[J]. Control and Decision, 2021, 36(7): 1558-1568.
26	王雨虹, 王志中. 基于RFRFE与ISSA-XGBoost的变压器故障辨识方法[J]. 电子测量与仪器学报, 2021, 35(12): 142-150.
	Wang Yuhong, Wang Zhizhong. Transformer Fault Identification Method Based on RFRFE and ISSA-XGBoost[J]. Journal of Electronic Measurement and Instrumentation, 2021, 35(12): 142-150.
27	廖才波, 阮江军, 刘超, 等. 油浸式变压器三维电磁-流体-温度场耦合分析方法[J]. 电力自动化设备, 2015, 35(9): 150-155.
	Liao Caibo, Ruan Jiangjun, Liu Chao, et al. Comprehensive Analysis of 3-D Electromagnetic-fluid-thermal Fields of Oil-immersed Transformer[J]. Electric Power Automation Equipment, 2015, 35(9): 150-155.

构建	密度/(kg/m^-3)	导热系数/ (W·m^-1·k^-1)	比热容/ (J·kg^-1K^-1)
铁芯	7 650	45	460
绕组	8 900	385	390
油箱	7 850	50	485
变压器油	895	0.135	0.5

[1]	张曦阳, 林旭升, 周瑞, 胡毅. 数控系统数字孪生体系结构及应用研究[J]. 系统仿真学报, 2025, 37(1): 183-198.
[2]	巫庆辉, 鲍亚庆, 赵忠鑫, 黄旭, 魏宇晨. 矿井排水监控数字孪生系统研究与实现[J]. 系统仿真学报, 2025, 37(1): 199-210.
[3]	赵佰亭, 施建国, 贾晓芬. 井筒提升机数字孪生系统研究[J]. 系统仿真学报, 2024, 36(9): 2054-2064.
[4]	李冬雪, 刘岩, 沈博垚, 井永腾, 马强, 刘然. 基于数字孪生技术的电力变压器碳足迹分析及低碳优化方法仿真研究[J]. 系统仿真学报, 2024, 36(9): 2075-2085.
[5]	徐健, 刘高峰, 赵一剑, 郑自立, 闫焕营. 装配机器人的数字孪生虚实同步及抓取方法[J]. 系统仿真学报, 2024, 36(9): 2181-2192.
[6]	曹宇, 李杰, 王芳, 刘智翔, 汪雪良. 基于仿真数据库的深潜球壳应力场数字孪生方法[J]. 系统仿真学报, 2024, 36(8): 1764-1779.
[7]	雷震, 刘宇华, 丁凯, 陈浩祥, 李东伟. 数字孪生驱动的射电望远镜结构热变形补偿系统[J]. 系统仿真学报, 2024, 36(8): 1869-1883.
[8]	任乾坤, 熊鑫立, 刘京菊, 姚倩. 网络空间安全中的数字孪生技术研究[J]. 系统仿真学报, 2024, 36(8): 1944-1957.
[9]	李颖, 高岚, 朱志松. 面向智能制造场景的机器人数字孪生建模与控制[J]. 系统仿真学报, 2024, 36(7): 1536-1545.
[10]	党宏杰, 余文广, 杨华晖. 基于数字孪生与平行试验的装备体系试验鉴定数字化应用[J]. 系统仿真学报, 2024, 36(7): 1729-1736.
[11]	王红军, 林俊强, 邹湘军, 张坡, 周铭轩, 邹伟锐, 唐昀超, 罗陆锋. 基于数字孪生的果园虚拟交互系统构建[J]. 系统仿真学报, 2024, 36(6): 1493-1508.
[12]	梁宏涛, 孔翎超, 刘国柱, 董文轩, 刘香怡. 融合数字孪生的风电机组故障检测ASL-CatBoost方法[J]. 系统仿真学报, 2024, 36(4): 873-887.
[13]	胡阳, 王蔚然, 房方, 宋子秋, 许昱涵, 刘吉臻. 风电机组运行动态数字孪生建模及半物理仿真[J]. 系统仿真学报, 2024, 36(3): 636-648.
[14]	赵莹莹, 董普森, 朱天晨, 李凡, 苏运, 邰振赢, 孙庆赟, 凡航. 面向电网拓扑调度仿真的采样效率优化方法研究[J]. 系统仿真学报, 2024, 36(2): 283-295.
[15]	缪天越, 王璐, 何家孝, 谢能刚. 融合强化学习的工业机器人数字孪生仿真方法研究[J]. 系统仿真学报, 2024, 36(12): 2971-2983.