基于模糊逻辑和D⁃S证据理论的变压器故障诊断方法  

Fault Diagnosis Method of Transformer Based on Fuzzy Logic and D⁃S Evidence Theory

作　　者：詹仲强 陈文涛 郝建[3] 杨定乾 王洁 公多虎 ZHAN Zhongqiang;CHEN Wentao;HAO Jian;YANG Dingqian;WANG Jie;GONG Duohu(Xinjiang Key Laboratory of Extreme Environment Operation and Testing Technology for Power Transmission&Transformation Equipment,State Grid Xinjiang Electric Power Research Institute,Urumqi 830000,China;State Grid Xinjiang Electric Power Research Institute,Urumqi 830000,China;State Key Laboratory of Power Transmission Equipment&System Security and New Technology,Chongqing University,Chongqing 400044,China)

机构地区：[1]国网新疆电科院新疆输变电设备极端环境运行与检测技术重点实验室,乌鲁木齐830000 [2]国网新疆电力有限公司电力科学研究院,乌鲁木齐830000 [3]重庆大学输配电装备及系统安全与新技术国家重点实验室,重庆400044

出　　处：《高压电器》2022年第11期160-166,共7页High Voltage Apparatus

基　　金：国家自然科学基金创新研究群体基金(51321063)。

摘　　要：采用扩展模糊逻辑对变压器油中溶解气体和铁心接地在线监测数据进行故障基础概率分配计算,利用Dempster⁃Shafer(D⁃S)证据理论对各类型故障基础概率进行多源信息融合得出变压器故障诊断模型,通过10台变压器样本对模型进行验证,同时对比支持向量机和卷积神经网络故障诊断模型,得出所提出的方法从故障诊断正确率和稳定性更优。The extended fuzzy logic is used to calculate the basic fault probability distribution of dissolved gas in transformer oil and iron core grounding online monitoring data.The Dempster⁃Shafer(D⁃S)evidence theory is adopt⁃ed to perform multi⁃source information fusion of the basic probability of various types of faults to obtain the fault diag⁃nosis model of transformer.The model is verified by 10 sets of transformer samples and,at the same time,the support vector machine and convolutional neural network fault diagnosis models are compared.Finally,it is concluded that the proposed method is better in terms of fault diagnosis accuracy and stability.

关 键 词：变压器 故障诊断 模糊逻辑 Dempster⁃Shafer证据理论 

分 类 号：TM407[电气工程—电器]