[1]郭 毅,车艳亮,伏学文,等.基于退化感知多尺度Transformer的电力设备状态评估方法[J].机械与电子,2026,44(09):120-126.
　GUO Yi,CHE Yanliang,FU Xuewen,et al.Degradation-aware Multi-scale Transformer for Power Equipment Condition Assessment[J].Machinery & Electronics,2026,44(09):120-126.
点击复制

基于退化感知多尺度Transformer的电力设备状态评估方法()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
44
期数:
2026年09期
页码:
120-126
栏目:
电力控制
出版日期:
2026-09-25

文章信息/Info

Title:
Degradation-aware Multi-scale Transformer for Power Equipment Condition Assessment
文章编号:
1001-2257(2026)09-0120-07
作者:
郭 毅1; 车艳亮2; 伏学文2; 康 文2; 党海铭2
1.国家能源集团甘肃电力有限公司,甘肃 兰州 730030;
2.国能(甘肃)新能源有限公司,甘肃 白银 730900
Author(s):
GUO Yi1; CHE Yanliang2; FU Xuewen2; KANG Wen2; DANG Haiming2
(1.Gansu Electric Power Co.,Ltd.,National Energy Group,Lanzhou 730030,China;
2.Guoneng (Gansu) New Energy Co.,Ltd.,Baiyin 730900,China)
关键词:
电力变压器; 溶解气体分析; 多尺度特征; Transformer; 状态评估
Keywords:
power transformer; dissolved gas analysis; multi-scale features; Transformer; condition assessment
分类号:
TM507
文献标志码:
A
摘要:
针对油中溶解气体分析在低维特征表征和退化过程建模方面存在不足、难以充分刻画故障演变规律的问题,提出一种退化感知多尺度Transformer模型用于电力设备状态评估。该模型通过多尺度语义特征解耦机制,将原始5维溶解气体分析(DGA)数据扩展为微观物理量、中观关系量和宏观状态量3个互补尺度;同时构建基于退化轨迹重构的时序化方法,将静态DGA 样本集转化为伪退化序列,使模型能够学习故障演变规律。在IEEE DataPort公开DGA 数据集上的实验表明,所提方法故障分类准确率达到95.7%,宏平均F1值为95.3%。
Abstract:
Dissolved gas analysis (DGA) suffers from inherent limitations in low-dimensional feature representation and degradation process modeling,which hinders its capability to fully characterize fault evolution patterns in power equipment.To address this issue,this paper proposes a Degradation aware Multi-Scale Transformer model for power equipment condition assessment.The model incorporates a multi-scale semantic feature decoupling mechanism that expands the original five-dimensional DGA data into three complementary scales:microscopic physical quantities,mesoscopic relational quantities,and macroscopic state quantities.Meanwhile,a temporalization method based on degradation trajectory reconstruction is constructed to convert static DGA sample sets into pseudo degradation sequences,enabling the model to learn fault evolution regularities.Experiments conducted on the IEEE DataPort public DGA dataset demonstrate that the proposed method achieves a fault classification accuracy of 95.7% and a macro-averaged F1-score of 95.3%.

参考文献/References:

[1] 马桂琴,李卫疆,曹洪建,等.电力设备状态监测与智能预警技术的应用研究[J].信息与电脑,2026,38(9):127-129.

[2] Huang Can,Tong Jie,Tang Pengfei,et al.An algorithm of oil-immersed transformer fault classification based on improved active deep learning framework[J].Review of Scientific Instruments,2024,95(11):115109.
[3] Ewasiuk K,Jacob N,Kordi B.Enhancing transformer oil dissolved gas analysis using deep learning and ensemble classification [D].Winnipeg:University of Manitoba,2024.
[4] Jina E,Zhang Yunyi,He Wei,et al.A new method for oil-immersed transformers fault diagnosis based on evidential reasoning rule with optimized probabilistic distributed[J].IEEE Access,2024,12:34289-34305.
[5] Wang Lin,Littler T,Liu Xueqin.Dynamic incipient fault forecasting for power transformers using an LSTM model[J].IEEE Transactions on Dielectrics and Electrical Insulation,2023,30(2):563-572.
[6] 晋兆安.复杂场景下针对电力设备状态感知的多模态融合诊断方法[J].光源与照明,2026(2):101-103.
[7] 宁海波.油浸式电力变压器在线状态监测系统设计与应用研究[J].家电维修,2026(2):135-137.
[8] 康佳宇,张沈习,张庆平,等.基于ANOVA 和BO-SVM 的变压器故障诊断方法[J].高电压技术,2023,49(5):1882-1891.
[9] Taha I B M,Ibrahim S,Mansour D E A.Power transformer fault diagnosis based on DGA using a convolutional neural network with noise in measurements[J].IEEE Access,2021,9:111162-111170.
[10] 李明聪.基于深度学习的电厂电力设备运行状态研究[J].仪器仪表用户,2026,33(1):73-75.
[11] 鲁家俊,俞航,陈子睿.基于RNN 算法的变电站电力设备绝缘状态监测研究[J].自动化应用,2025,66(22):15-17.
[12] 王坤.基于多特征融合的油浸式电力变压器绝缘状态检测[J].电气技术与经济,2025(6):99-101.
[13] 齐子豪,仝杰,张中浩,等.基于多粒度知识特征和Transformer网络的电力变压器故障声纹辨识方法[J].中国电机工程学报,2025,45(4):1311-1322.
[14] Liu Hao,Sun Youchao,Wang Xiaoyu,et al.NPFormer: interpretable rotating machinery fault diagnosis architecture design under heavy noise operating scenarios[ J].Mechanical Systems and Signal Processing,2025,223:111878.
[15] Li Zihao,He Yigang,Xing Zhikai,et al.Transformer fault diagnosis based on improved deep coupled dense convolutional neural network[J].Electric Power Systems Research,2022,209:107969.

相似文献/References:

[1]王 峰.基于模糊神经网络的电力变压器绝缘状态预测方法[J].机械与电子,2022,(03):50.
　WANG Feng.Prediction Method of Insulation State of Power Transformer Based on Fuzzy Neural Network[J].Machinery & Electronics,2022,(09):50.
[2]王子伟,疏佳铭,陆 斌,等.基于 GASF 及双输入 AlexNet-SVM 的变压器励磁涌流检测[J].机械与电子,2025,(08):30.
　WANG Ziwei,SHU Jiaming,LU Bin,et al.Transformer Inrush Current Detection Based on GASF and Dual-input AlexNet-SVM[J].Machinery & Electronics,2025,(09):30.
[3]张义虎,李恒山,李会骞,等.基于动态设备关联GAT的电力设备状态评估方法[J].机械与电子,2026,44(09):96.
　ZHANG Yihu,LI Hengshan,LI Huiqian,et al.A Dynamic Association Graph Attention Network for Power Equipment Condition Assessment[J].Machinery & Electronics,2026,44(09):96.

备注/Memo

备注/Memo:
收稿日期:2026-06-02
基金项目:国能(甘肃)新能源有限公司科技项目(E586700018)
作者简介:郭 毅 (1985 ),男,宁夏青铜峡人,硕士,工程师,研究方向为电力设备在线监测。
更新日期/Last Update: 2026-10-13