基于多模态组合振动图像与堆叠稀疏自编码器的GIS设备机械缺陷诊断方法  

Mechanical Defect Diagnosis Method of GIS Equipment Based on Multi-modal Combined Vibration Image and Stacked Sparse Autoencoder

作　　者：李滢 郝建 丁屹林 李旭 刘清松 钟尧 LI Ying;HAO Jian;DING Yilin;LI Xu;LIU Qingsong;ZHONG Yao(State Key Laboratory of Power Transmission and Transformation Equipment Technology,School of Electrical Engineering,Chongqing University,Chongqing 400044,China)

机构地区：[1]输变电装备技术全国重点实验室(重庆大学电气工程学院),重庆400044

出　　处：《高电压技术》2025年第2期753-765,共13页High Voltage Engineering

基　　金：国家重点研发计划(2022YFB2403700);重庆市自然科学基金(CSTB2022NSCQ-MSX1247)。

摘　　要：气体绝缘金属封闭开关(gas insulated metal enclosed switchgear,GIS)设备机械缺陷已成为电网安全的重要隐患,针对现有缺陷诊断方法特征信息有限导致的准确率不足问题,结合深度学习思想,提出了一种基于多模态组合振动图像与堆叠稀疏自编码器的GIS机械缺陷诊断方法。首先,采用变分模态分解算法获取GIS原始振动信号的模态频谱分量,构建多模态组合的振动信息图像;然后,采用支持向量机构建负载区分模型,并提出双层分类结构的堆叠稀疏自编码器(double classifier-stacked sparse autoencoder,DC-SSAE)建立大范围电流下机械缺陷辨识与严重程度评估模型;最后,基于550 kV GIS设备机械缺陷测试平台开展不同电流下振动模拟试验,验证其有效性。结果表明:多模态组合振动图像相较传统图像特征表达效果更优,诊断模型能充分挖掘图像信息,克服了传统机器学习算法特征选择主观性;融合负载区分与缺陷匹配的DC-SSAE模型实现了GIS机械缺陷有效诊断,缺陷辨识和严重程度评估总体准确率分别达99.38%和99.44%。该文所提方法拥有良好的缺陷诊断效果,可为GIS设备安全稳定运行提供有力技术支撑。The mechanical defect of gas insulated metal enclosed switchgear(GIS)equipment has become an important hidden danger of power grid security.Aiming at the insufficient accuracy of existing defect diagnosis methods due to lim-ited feature information,in combination with deep learning theory,we proposed a GIS mechanical defect diagnosis method based on multi-modal combined vibration images and stacked sparse autoencoder.Firstly,the modal spectrum component of GIS original vibration signal was obtained by using variational mode decomposition algorithm,and the multi-modal combined vibration information image was constructed.Then,the support vector machine algorithm was used to construct a load classification model,and a double-layer stacked sparse autoencoder(DC-SSAE)was proposed to establish mechanical defect identification and severity assessment model under a large range current.Finally,based on the 550 kV GIS equipment mechanical defect test platform,vibration simulation tests under different currents were carried out to verify the effectiveness of the method.The results show that the feature representation of multi-modal combined vibration image is better than the traditional image,and the diagnostic model can fully mine the image information,over-coming the subjectivity of the traditional machine learning algorithm feature selection.The DC-SSAE model combined with load classification and defect matching can effectively diagnose GIS mechanical defects,and the overall accuracy of defect identification and severity evaluation is 99.38%and 99.44%,respectively.The method proposed in this paper has a good defect diagnosis effect,which can provide strong technical support for the safe and stable operation of GIS.

关 键 词：GIS设备 机械缺陷 深度学习 故障诊断 自编码器 

分 类 号：TM595[电气工程—电器] TP18[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]