Transformer Fault Diagnosis Method Based on KELM Optimized by Improved Sparrow Search Algorithm

XU Songxiao; ZHAO Junyu; ZHANG Yuanbo; LU Xiaojun; WANG Yan; LI Wei

doi:10.13296/j.1001-1609.hva.2026.06.006

您当前的位置：

首页 >

文章列表页 >

Transformer Fault Diagnosis Method Based on KELM Optimized by Improved Sparrow Search Algorithm

Research & Analysis | 更新时间：2026-06-10

- Transformer Fault Diagnosis Method Based on KELM Optimized by Improved Sparrow Search Algorithm
- High Voltage Apparatus Vol. 62, Issue 6, Pages: 50-58(2026)
- 作者机构：
  
  国网保定供电公司，河北保定 071051
  华北电力大学电气与电子工程学院，河北保定 071003
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2026.06.006
  CLC：
- Received：15 November 2025，
  
  Revised：2026-02-02，
  
  Published：16 June 2026
- 稿件说明：
移动端阅览
XU Songxiao, ZHAO Junyu, ZHANG Yuanbo, et al. Transformer Fault Diagnosis Method Based on KELM Optimized by Improved Sparrow Search Algorithm[J]. High Voltage Apparatus, 2026, 62(6): 50-58.
DOI：

XU Songxiao, ZHAO Junyu, ZHANG Yuanbo, et al. Transformer Fault Diagnosis Method Based on KELM Optimized by Improved Sparrow Search Algorithm[J]. High Voltage Apparatus, 2026, 62(6): 50-58. DOI： 10.13296/j.1001-1609.hva.2026.06.006.

摘要

针对传统浅层机器学习在特征提取方面的不足，为增强其对变压器故障诊断的能力，提出一种基于改进麻雀搜索算法优化KELM的变压器故障诊断方法。首先利用深度置信网络（deep belief networks，DBN）对变压器故障样本数据进行特征提取；其次，将引入惩罚因子C和核函数参数S的核极限学习机（kernel extreme learning machine，KELM）作为分类器，深入分析易混淆样本的特征值与变压器故障类型间的关联性，进一步提高故障诊断模型的稳定性和泛化能力；然后，利用Levy变异因子改进的麻雀搜索算法（improved sparrow search algorithm，ISSA）优化KELM的惩罚因子C和核函数参数S，以增强的麻雀搜索算法的全局搜索能力，进一步提高故障诊断模型的稳定性和准确率。最后，基于油中溶解气体数据的变压器故障诊断实验结果表明：所提基于ISSA优化KELM的变压器故障诊断方法，收敛速度更快、稳定性更好、诊断准确率更高，适用于变压器故障诊断。

Abstract

To address the limitations of traditional shallow machine learning in feature extraction and to enhance its capability for transformer fault diagnosis

a transformer fault disgnosis method based on KELM optimized by an improved sparrow search algorithm is proposed. First

the deep belief networks (DBN) is used for feature extraction of transformer fault sample data.Then

the kernel extreme learning machine (KELM) with penalty factor C and kernel function parameter S is used as a classifier to analyze deeply the correlation between features of confusable samples and fault types and improve the stability and generalization ability of the model.After that

the improved sparrow search algorithm (SSA) with Levy mutation factor is used to optimize the penalty factor C and kernel function parameter S of KELM to enhance the global search ability of the algorithm and improve both stability and accuracy of fault diagnosis of the model. Finally

the experimental results of transformer fault diagnosis based on dissolved gas data in oil show that the proposedISSA-KELMtransformer fault diagnosis method has faster convergence speed

better stability and higher diagnostic accuracy

and is suitable for transformer fault diagnosis.

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.

王杰,李永鑫,张军亮,等.基于SBOA-TVFEMD的变压器油中溶解气体浓度预测[J].变压器,2025,62(5):23-31.

WANG Jie, LI Yongxin, ZHANG Junliang, et al. Prediction of dissolved gas concentration in transformer oil based on SBOA-TVFEMD[J]. Transformer,2025,62(5):23-31.

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.

邹阳,黄煜,俞豪奕,等.融合频谱特性与聚类云—证据推理的油纸绝缘老化程度诊断[J].电力系统保护与控制,2024,52 (17):105-114.

ZOU Yang, HUANG Yu, YU Haoyi, et al.Diagnosis of oil-paper insulation aging degree by fusing spectral properties and clustered cloud-evidence reasoning[J]. Power System Protection and Control, 2024,52(17):105-114.

林师.基于改进灰狼算法优化BP神经网络的变压器故障高精度诊断方法[J].电子设计工程,2025,33(14):144-149.

LIN Shi.The high-precision diagnosis method for transformer fault based on the improved gray wolf algorithm to optimize BP neural network[J]. Electronic Design Engineering,2025,33(14):144-149.

沈国堂,郭振宇,黄道均,等.基于特征提取和神经网络的电力变压器声纹诊断方法建立与应用[J].变压器,2024,61(6):39-43.

SHEN Guotang, GUO Zhenyu, HUANG Daojun, et al.Establishment and application of power transformer voiceprint diagnosis method based on feature fusion and neural network[J]. Transformer,2024,61(6):39-43.

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.

李峰,陈皖皖,李晓华,等.基于SVMD-CMSEE与GSA-SVM的新型电力系统变压器故障状态智能诊断方法[J].电测与仪表, 2024,61(12):17-25.

LI Feng, CHEN Wanwan, LI Xiaohua, et al.An intelligent fault diagnosis method for transformer in novel power system based on SVMD-CMSEEand GSA-SVM[J]. Electrical Measurement & Instrumentation,2024,61(12):17-25.

孙世明,岑红星,白建民,等.基于集成SAO优化互相关熵极限学习机模型的变压器故障诊断方法[J].电测与仪表,2024,61 (9):56-64.

SUN Shiming, CEN Hongxing, BAI Jianmin, et al.Transformer fault diagnosis method based on integrated correntropy extremelearning machine model optimized by SAO[J]. Electrical Measurement & Instrumentation,2024,61(9):56-64.

代杰杰,宋辉,杨祎,等.基于油中气体分析的变压器故障诊断ReLU-DBN方法[J].电网技术,2018,42(2):658-664.

DAI Jiejie, SONG Hui, YANG Yi, et al.Dissolved gas analysis of insulating oil for power transformer fault diagnosis based on ReLU-DBN[J]. Power System Technology,2018,42(2):658-664.

刘建锋,董倩雯,田书欣,等.基于ReliefF-mRMR漏磁场特征优选和改进LSSVM的变压器绕组早期故障诊断[J].电测与仪表, 2025,62(11):198-209.

LIU Jianfeng, DONG Qianwen, TIAN Shuxin, et al.Early fault diagnosis of transformer winding based on ReliefF-mRMR leakage magnetic field feature optimization and improved LSSVM[J]. Electrical Measurement & Instrumentation,2025,62(11):198-209.

吴杰康,覃炜梅,梁浩浩,等.基于自适应极限学习机的变压器故障识别方法[J].电力自动化设备,2019,39(10):181-186.

WU Jiekang, QIN Weimei, LIANG Haohao, et al. Transformer fault identification method based on self-adaptive extreme learning machine[J]. Electric Power Automation Equipment,2019,39(10):181-186.

王晓蓉,等.基于大数据挖掘的电力变压器健康状态差异预警规则策略[J].电测与仪表,2024,61(2):216-224.

WANG Xiaorong.Early warning rule strategy of power transformer health status difference based on big data mining[J]. Electrical Measurement & Instrumentation,2024,61(2):216-224.

HINTON G E, OSINDERO S, TEH Y W.A fast learning algorithm for deep belief nets[J]. Neural Computation,2006,18(7):1527-1554.

HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science,2006,313(5786):504-507.

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 optimizationVMDDBN[J]. Electrical Measurement & Instrumentation,2024,61(2):157-163.

周萱,吴伟丽.基于改进SMOTE不均衡样本处理和IHPO-DBN的变压器故障诊断方法研究[J].电力系统保护与控制, 2024,52(11):21-30.

ZHOU Xuan, WU Weili.Transformer fault diagnosis method based on improved SMOTE unbalanced sample processing and IHPO-DBN[J]. Power System Protection and Control,2024,52(11):21-30.

李璞,王奕,张博.基于深度学习的电力变压器匝间短路故障辨识方法[J].变压器,2025,62(6):41-50.

LI Pu, WANG Yi, ZHANG Bo.Fault identification method for interturn short circuit of power transformer based on deep learning[J]. Transformer,2025,62(6):41-50.

李元,李星辉,孙渭薇,等.基于多模型级联的油浸式电力变压器故障诊断方法[J].智慧电力,2023,51(6):86-92.

LI Yuan, LI Xinghui, SUN Weiwei, et al.Fault diagnosis method of oil-immersed power transformer based on multi-model cascade fusion[J]. Smart Power,2023,51(6):86-92.

孙同敏.基于DBN-SVM的航空发动机健康状态评估方法[J].控制工程,2021,28(6):1163-1170.

SUN Tongmin.Research on aero engine health state assessment using DBN and SVM[J]. Control Engineering of China,2021,28(6):1163-1170.

HINTON G E.Training products of experts by minimizing contrastive divergence[J]. Neural Computation,2002,14(8):1771-1800.

HUANG Guangbin, ZHOU Hongming, DING Xiaojian, et al.Extreme learning machine for regression and multiclass classification[J]. IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics:A Publication of the IEEE Systems, Man, and Cybernetics Society,2012,42(2):513-529.

HUANG Guangbin.An insight into extreme learning machines:Random neurons, random features and kernels[J]. Cognitive Computation,2014,6(3):376-390.

杨锡运,关文渊,刘玉奇,等.基于粒子群优化的核极限学习机模型的风电功率区间预测方法[J].中国电机工程学报,2015 (s1):146-153.

YANG Xiyun, GUAN Wenyuan, LIU Yuqi, et al. Prediction intervals forecasts of wind power based onPSO - KELM[J]. Proceedings of the CSEE,2015(s1):146-153.

XUE Jiankai, BO Shen.A novel swarm intelligence optimization approach:Sparrow search algorithm[J]. Systems Science & Control Engineering,2020,8(1):22-34.

李雅丽,王淑琴,陈倩茹,等.若干新型群智能优化算法的对比研究[J].计算机工程与应用,2020,56(22):1-12.

LI Yali, WANG Shuqin, CHEN Qianru, et al. Comparative study of several new swarm intelligence optimization algorithms[J]. Computer Engineering and Applications,2020,56(22):1-12.

毛清华,张强,毛承成,等.混合正弦余弦算法和Lévy飞行的麻雀算法[J].山西大学学报(自然科学版),2021(6):1086-1091.

MAO Qinghua, ZHANG Qiang, MAO Chengcheng, et al.Mixing sine and cosine algorithm with Lévy flying chaotic sparrow algorithm[J]. Journal of Shanxi University(Natural Science Edition), 2021(6):1086-1091.

李腾飞,郝玉杰,袁方,等.基于多源特征信息融合的油浸式变压器故障智能诊断模型[J].电工电能新技术,2023,42(1):48-57.

LI Tengfei, HAO Yujie, YUAN Fang, et al. Intelligent transformer fault diagnosis model based on multi-source feature information fusion[J]. Advanced Technology of Electrical Engineering and Energy,2023,42(1):48-57.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Leakage Recognition Method of Photovoltaic Connected to Distribution Network Based on Neighborhood Component Analysis and Optimized Kernel Extreme Learning Machine

Fault Diagnosis Model of Transformer Based on GJO Feature Optimization and AO-RF

Research on Diagnosis Method of Transformer Winding Deformation Fault Based on Dynamic Time Warping

New Approach to Transformer Fault Diagnosis Based on ANN

APPLICATION OF INFORMATION FUSION TECHNIQUE TO TRANSFORMER FAULT DIAGNOSIS

Related Author

WANG Wentian

HUI Hui

WANG Ming

LI Gang

XU Honghua

WANG Zihu

YE Yulin

LIU Sen

Related Institution

State Grid Jiangsu Nanjing Electric Power Supply Company

China Electric Power Research Institute

China Nuclear Power Engineering Co., Ltd.

School of Electrical Engineering, Hebei University of Science and Technology

Hebei Provincial Key Laboratory of Electromagnetic & Structural Performance of Power Transmission and Transformation Equipment, Baoding Tianwei Baobian Electric Co., Ltd.

⁰