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.
作者
詹仲强
陈文涛
郝建
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)
出处
《高压电器》
CAS
CSCD
北大核心
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)。
