Temperature Prediction Method of Transformer Bushing Based on EMD and OS-ELM

ZHANG Qingping; YAN Zhenhua; ZHANG Shenxi; KANG Jiayu; LI Xiuguang; GAO Bo

doi:10.13296/j.1001-1609.hva.2026.01.012

您当前的位置：

首页 >

文章列表页 >

Temperature Prediction Method of Transformer Bushing Based on EMD and OS-ELM

Research & Analysis | 更新时间：2026-04-13

- Temperature Prediction Method of Transformer Bushing Based on EMD and OS-ELM
- High Voltage Apparatus Vol. 62, Issue 1, Pages: 95-102(2026)
- 作者机构：
  
  国网宁夏电力有限公司电力科学研究院，银川　750000
  上海交通大学电力传输与功率变换控制教育部重点实验室，上海　200240
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2026.01.012
  CLC：
- Received：15 July 2025，
  
  Revised：2025-10-15，
  
  Published：16 January 2026
- 稿件说明：
移动端阅览
ZHANG Qingping, YAN Zhenhua, ZHANG Shenxi, et al. Temperature Prediction Method of Transformer Bushing Based on EMD and OS-ELM[J]. High Voltage Apparatus, 2026, 62(1): 95-102.
DOI：

ZHANG Qingping, YAN Zhenhua, ZHANG Shenxi, et al. Temperature Prediction Method of Transformer Bushing Based on EMD and OS-ELM[J]. High Voltage Apparatus, 2026, 62(1): 95-102. DOI： 10.13296/j.1001-1609.hva.2026.01.012.

摘要

为了提高变压器套管温度的预测精度，提出了一种基于经验模态分解（empirical mode decomposition， EMD）和在线序列极限学习机（online sequential-extreme learning machine，OS-ELM）的变压器套管温度预测方法。首先，采用EMD法对变压器套管温度时序数据进行分解，得到若干内涵模态分量；其次，利用滑动窗口法处理各个分量形成带标签的数据集，并输入OS-ELM模型对各个分量的数据集进行训练；最后，通过叠加各个序列分量的预测结果得到最终的变压器套管温度预测结果。实例仿真结果表明：EMD预处理可提升模型的预测精度；对比极限学习机（ELM）、反向传播神经网络（back propagation neural network，BPNN）和支持向量机（support vector machine，SVM）方法，文中所提方法预测精度更高。

Abstract

For improving temperature prediction accuracy of transformer bushing

in this paper a temperature prediction method for transformer bushing based on empirical mode decomposition (EMD) and online sequential-extreme learning machine (OS-ELM) is proposed. First

the temperature time series data of transformer bushing is decomposed by EMD

method and several intrinsic mode functions are obtained. Then

each component is processed by sliding window method to form dataset with label

and then input into OS-ELM model to train the datasets of each component. Finally

the final temperature prediction results of transformer bushing are obtained by superimposing the prediction results of each sequential component. The simulation results of the example show that EMD preprocess can improve the prediction accuracy of the model. The method propsoed in this paper

compared with extreme learning machine (ELM)

back propagation neural network (BPNN) and support vector machine (SVM) methods

has higher prediction accuracy.

关键词

Keywords

references

梁栋,朱建华,张翠,等.变压器状态评估及故障诊断研究综述[J].变压器2024,61(2):35-43.

LIANG Dong,ZHU Jianhua,ZHANG Cui,et al.Review of transformer condition assessment and fault diagnosis[J]. Transformer, 2024,61(2):35-43.

邱晟璇,王松,刘子瑞,等.基于FRA法和CNN的变压器绕组故障诊断研究[J].大电机技术,2025(3):108-116.

QIU Shengxuan,WANG Song,LIU Zirui,et al.Research on fault diagnosis of transformer windings based on FRA method and CNN[J]. Large Electric Machine and Hydraulic Turbine,2025(3):108-116.

杨昊,胡文秀,张璐,等.基于ADASYN数据平衡化的PSO-BPNN变压器套管故障诊断[J].电力工程技术,2024,43(2):170-178.

YANG Hao,HU Wenxiu,ZHANG Lu,et al.Fault diagnosis of transformer oil-paper bushings inPSO-BPNNalgorithm based on ADASYN data balancing[J]. Electric Power Engineering Technology,2024,43(2):170-178.

KHORRAMDEL B,CHUNG C Y,SAFARI N,et al.A fuzzy adaptive probabilistic wind power prediction framework using diffusion kernel density estimators[J]. IEEE Transactions on Power Systems, 2018,33(6):7109-7121.

曹辰,路敦林,王雪,等.变压器温度和机械振动特性的仿真与分析[J].变压器,2024,61(1):17-23.

CAO Chen,LU Dunlin,WANG Xue,et al.Simulation and analysis of temperature mechanical vibration characteristics of transformers[J]. Transformer,2024,61(1):17-23.

范慧芳,咸日常,刘兴华,等.基于能量系数的电力变压器热故障严重性评估方法[J].电测与仪表,2024,61(2):83-88.

FAN Huifang,XIAN Richang,LIU Xinghua,et al. Evaluation method of thermal fault severity of power transformer based on energy coefficient[J]. Electrical Measurement & Instrumentation, 2024,61(2):83-88.

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.

钱国超,胡锦,代维菊,等.基于振动非线性特征的变压器绕组状态检测[J].电力工程技术,2024,43(6):194-202.

QIAN Guochao,HU Jin,DAI Weiju,et al. Transformer winding condition detection based on the nonlinear characteristics of vibrations[J]. Electric Power Engineering Technology,2024,43(6):194-202.

吕志华,顾雅青.基于卡尔曼滤波算法的油浸式变压器绕组热点温度预测研究[J].变压器,2023,60(4):44-49.

LYU Zhihua,GU Yaqing.Research on prediction of winding hot spot temperature of oil-immersed transformer based on Kalman filter algorithm[J]. Transformer,2023,60(4):44-49.

朱建勇,凤冰霞,杨辉,等.基于特征气体加权的油浸式变压器故障预报[J].控制工程,2022,29(10):1743-1751.

ZHU Jianyong,FENG Bingxia,YANG Hui,et al. Fault prediction for oil-immersed transformer based on characteristic gas weighting[J]. Control Engineering of China,2022,29(10):1743-1751.

徐名,方洋洋,杨鹏.基于灰色模型算法的电力变压器油温预测[J].电力学报,2018,33(5):359-364.

XU Ming,FANG Yangyang,YANG Peng.Study on prediction of oil temperature for power transformer based on improved grey model[J]. Journal of Electric Power,2018,33(5):359-364.

刘慧鑫,张江龙,连鸿松,等.基于时间序列模型的变压器油中溶解气体预测[J].高压电器,2019,55(12):193-199.

LIU Huixin,ZHANG Jianglong,LIAN Hongsong,et al. Prediction of the gases dissolved in transformer oil by sequential learning[J]. High Voltage Apparatus,2019,55(12):193-199.

赵一钧,石雷,齐笑,等.基于加强灰狼优化VMD-DBN的变压器故障检测[J].电测与仪表,2024,61(2):157-163.

ZHAO Yijun,SHI Lei,QI Xiao,et al.Transformer fault detection based on enhanced gray wolf optimizationVMD-DBN[J]. Electrical Measurement & Instrumentation,2024,61(2):157-163.

张卫庆,王成亮,徐洪,等.基于有限元法的油浸式变压器绕组温度场数值模拟分析[J].自动化与仪器仪表,2020(4):56-59.

ZHANG Weiqing,WANG Chengliang,XU Hong,et al.Numerical simulation analysis of winding temperature field of oil-immersed transformer based on finite element method[J]. Automation and Instrumentation,2020(4):56-59.

刘弘景,张丹丹,李伟,等.大型油浸式变压器绕组温度场的有限元分析[J].高压电器,2019,55(12):83-89.

LIU Hongjing,ZHANG Dandan,LI Wei,et al. Finite element analysis for temperature field of winding in large oil-immersed transformer[J]. High Voltage Apparatus,2019,55(12):83-89.

PARK K H,LEE H J,HAHN S C. Finite-element modeling and experimental verification of stray-loss reduction in power transformer tank with wall shunt[J]. IEEE Transactions on Magnetics,2019,55 (12):1-4.

HAN H,LIU H Y,ZUO X Y,et al.Optimal sizing considering power uncertainty and power supply reliability based on LSTM and MOPSO for SWPBMs[J]. IEEE Systems Journal,2022,16(3):4013-4023.

侯赛,成润坤,刘达.基于二次采样和集成学习方法的变压器故障预测[J].智慧电力,2024,52(7):40-47.

HOU Sai,CHENG Runkun,LIU Da.Transformer fault forecast based on re-sampling and integrated learning approach[J]. Smart Power,2024,52(7):40-47.

马骁雨,张慧芬,王植,等.基于SSA-BPNN-ARIMA残差校正的变压器套管温度预测[J].国外电子测量技术,2022,41(2):151-156.

MA Xiaoyu,ZHANG Huifen,WANG Zhi,et al. Prediction of transformer bushing temperature based onSSA-BPNN-ARIMAresidual correction[J]. Foreign Electronic Measurement Technology,2022, 41(2):151-156.

陈铁,陈卫东,李咸善,等.基于EMD和GCT的变压器油中溶解气体预测[J].高压电器,2022,58(4):70-79.

CHEN Tie,CHEN Weidong,LI Xianshan,et al. Dissolved gas prediction in transformer oil based on EMD and GCT[J]. High Voltage Apparatus,2022,58(4):70-79.

宗琳,周晓华,罗文广,等.蜣螂算法优化概率神经网络的变压器故障诊断[J].智慧电力,2024,52(5):98-104.

ZONG Lin,ZHOU Xiaohua,LUO Wenguang,et al.Transformer fault diagnosis based on probabilistic neural network optimized by dung beetle optimizer[J]. Smart Power,2024,52(5):98-104.

杨金鑫,廖才波,胡雄,等.基于DGA与TPE-LightGBM的变压器故障诊断[J].电力科学与技术学报,2024,39(4):70-77.

YANG Jinxin,LIAO Caibo,HU Xiong,et al. Transformer fault diagnosis based on DGA and TPE-LightGBM[J]. Journal of Electric Power Science and Technology,2024,39(4):70-77.

MA Xin,HU Hao,SHANG Yizi.A new method for transformer fault prediction based on multifeature enhancement and refined long short-term memory[J]. IEEE Transactions on Instrumentation and Measurement,2021(70):1-11.

FOROS J,ISTAD M.Health index,risk and remaining lifetime estimation of power transformers[J]. IEEE Transactions on Power Delivery,2020,35(6):2612-2620.

DONG M,NASSIF A B,LI B.A data-driven residential transformer overloading risk assessment method[J]. IEEE Transactions on Power Delivery,2019,34(1):387-396.

缪希仁,林蔚青,肖洒,等.基于条件互信息与LSTNet的特高压变压器顶层油温预测方法[J].电网技术,2022,46(7):2601-2609.

MIAO Xiren,LIN Weiqing,XIAO Sa,et al. Forecasting method for top oil temperature in ultra-high voltage transformers based on conditional mutual information and LSTNet[J]. Power System Technology,2022,46(7):2601-2609.

HUANG N E,SHEN Z,LONG S R,et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society A:Mathematical,Physical and Engineering Sciences,1998(454):903-995.

HUANG G B,ZHU Q Y,SIEW C K. Extreme learning machine:Theory and applications[J]. Neurocomputing,2006,70(1/3):489-501.

LAN Y,SOH Y C,HUANG G B.Ensemble of online sequential extreme learning machine[J]. Neurocomputing,2009,72(13):3391-3395.

SAFAEI A,WU Q M J,AKILAN T,et al. System-on-a-Chip(SoC)-based hardware acceleration for an online sequential extreme learning machine(OS-ELM)[J]. IEEE Transactions on ComputerAided Design of Integrated Circuits and Systems,2019,38(11):2127-2138.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Study on Generation and Diffusion Characteristics of Acetylene Under High Voltage Bushing Fault of Transformer

Seismic Test and Stiffness Analysis on Mechanical Clamped Type Bushing for 500 kV Transformer

Study on the Designing of Transformer Bushing with Oil-separated Structure and Its Verifying

Analysis and Treatment of the Flaws on Transformer Bushing Coupler

Fault Diagnosis of Power Transformer On-load Tap Changer Based on EMD-HT Analysis of Vibration Signal

Related Author

CHEN Siyang

LIU Bo

MENG Yanzong

ZHU Xuran

CHEN Chuan

ZHANG Wei

SHEN Leyu

MA Qingyue

Related Institution

国网宁夏电力有限公司超高压公司，银川 750011State Grid Ningxia Electric Power Co., Ltd. Ultra High Voltage Company, Yinchuan 750011, China

中国电力科学研究院有限公司，北京 102209China Electric Power Research Institute Co., Ltd., Beijing 102209, China

State Grid Sichuan Electric Power Research Institute

College of Civil Engineering, Tongji University

China Electric Power Research Institute

⁰