多信号变压器局部放电特征提取及故障识别  

Feature Extraction and Fault Identification of Partial Dischargein Multi-signal Transformer

作　　者：安琪 杨攀烁[1] 安国庆 韩晓慧 杨晓锐 李沂隆 刘东升 何平[4] 王苏[5] 高伟超 AN Qi;YANG Pan-shuo;AN Guo-qing;HAN Xiao-hui;YANG Xiao-rui;LI Yi-long;LIU Dong-sheng;HE Ping;WANG Su;GAO Wei-chao(School of Electrical Engineering,Hebei University of Science and Technology,Shijiazhuang 050018,China;Hebei Key Laboratory of Power Internet of Things Technology,North China Electric Power University,Baoding 071003,China;Hebei Key Laboratory of Electromagnetic&Structural Performance of Power Transmission and Transformation Equipment,Baoding Tianwei Baobian Electric Co.,Ltd.,Baoding 071056,China;Baoding Tianwei Xinyu Technology Development Co.,Ltd.,Baoding 071056,China;Hebei Xuhui Electric Co.,Ltd.,Shijiazhuang 050081,China)

机构地区：[1]河北科技大学电气工程学院,石家庄050018 [2]华北电力大学河北省电力物联网技术重点实验室,保定071003 [3]保定天威保变电气股份有限公司河北省输变电装备电磁与结构性能重点实验室,保定071056 [4]保定天威新域科技发展有限公司,保定071056 [5]河北旭辉电气股份有限公司,石家庄050081

出　　处：《科学技术与工程》2024年第34期14699-14708,共10页Science Technology and Engineering

基　　金：河北省第一批“揭榜挂帅”项目(JGK231209);河北省重点研发计划(20312101D);河北省省级科技计划(SZX2020034)。

摘　　要：局部放电模式识别已被确定为监测电气设备运行的标准诊断工具。智能状态识别是变压器状态识别的发展趋势,但现有的智能状态识别存在模型单一、识别精度低等缺点。为了克服这一缺点,提出了一种基于D-S证据理论的多维信息源变压器局部放电故障识别方法。首先,采用小波包分解对局部放电高频信号和超声信号进行能量特征的提取。然后,根据选取的特征集,分别建立卷积神经网络(convolutional neural networks, CNN)模型和卷积神经网络-支持向量机(CNN-SVM)模型。最后,通过D-S(dempster-shafer)证据理论对两种信号识别模型的输出结果进行有效的整合。结果表明,以所提出的小波包分解能量特征集作为输入向量,两种信号CNN-SVM模型的识别率达到了95%和81.67%,分别较CNN提升了3.33%和8.34%。D-S证据理论融合方法的整体性能优于CNN和CNN-SVM,准确度和一致性较融合之前分别提高3.33%和16.66%;验证了本文方法的有效性和可行性。Partial discharge pattern recognition has been established as a standard diagnostic tool for monitoring the operation of electrical equipment.Intelligent state recognition is the development trend of transformer state recognition,but the existing intelligent state recognition has the disadvantages of single model and low recognition accuracy.In order to overcome this shortcoming,a multi-dimensional information source transformer partial discharge fault identification method based on D-S evidence theory was proposed.Firstly,wavelet packet decomposition was used to extract the energy features of high frequency partial discharge signal and ultrasonic signal.Then,according to the selected feature set,the CNN(convolutional neural networks)model and CNN-SVM(convolutional neural networks-support vector machine)model were established respectively.Finally,the D-S(dempster-shafer)evidence theory was used to effectively integrate the output results of the two signal recognition models.The results show that using the proposed wavelet packet decomposition energy feature set as input vector,the recognition rates of the two signals CNN-SVM models reach 95%and 81.67%,which are 3.33%and 8.34%higher than CNN respectively.The overall performance of D-S evidence theory fusion method is better than that of CNN and CNN-SVM,and the accuracy and consistency are improved by 3.33%and 16.66%respectively.The effectiveness and feasibility of this method are verified.

关 键 词：局部放电 小波包分解 D-S证据理论 信号融合 故障诊断 

分 类 号：TM855[电气工程—高电压与绝缘技术]