基于多源判据的变电站二次设备故障自动化诊断研究  

Research on Automatic Fault Diagnosis of Secondary Equipment in Substation Based on Multiple Source Criteria

作　　者：曾乔迪 陈煜敏 蒋文辉 梁书原 ZENG Qiaodi;CHEN Yumin;JIANG Wenhui;LIANG Shuyuan(China Southern Power Grid Digital Power Grid Technology(Guangdong)Co.,Ltd.,Guangzhou 510520,China)

机构地区：[1]南方电网数字电网科技(广东)有限公司,广州510520

出　　处：《自动化与仪表》2023年第10期57-61,共5页Automation & Instrumentation

摘　　要：为了解决变电站二次设备故障诊断效率低、精度差的问题,该文提出一种基于多源判据的变电站二次设备故障自动化诊断方法,建立变电站二次设备体系结构模型,分析产生故障的根本原因;采用支持向量机方法分类电力二次设备数据组,通过主分量分析技术对电力信号降维;结合阻抗值、电流、电压多源征兆测量阻抗判据值,通过阻抗判断值诊断电路中是否有故障,实现变电站二次设备故障自动化诊断。实验结果表明,所提方法可以诊断出设备气体泄漏故障、绝缘材料腐蚀故障、电弧重燃故障,且故障诊断准确率在85%以上。In order to solve the problems of low efficiency and poor accuracy in fault diagnosis of secondary equipment in substations,a comprehensive diagnosis method for secondary equipment faults in substations based on multi-source symptoms is proposed.A structural model of secondary equipment in substations is established,and the root causes of faults are analyzed.Using support vector machine method to classify power secondary equipment data sets,and using principal component analysis technology to reduce the dimensionality of power signals.By combining the impedance value,current,and voltage multi-source symptom measurement impedance criterion value,the impedance judgment value is used to diagnose whether there is a fault in the circuit,and to achieve comprehensive diagnosis of secondary equipment faults in the substation.The experimental results show that the proposed method can diagnose equipment gas leakage faults,insulation material corrosion faults,and arc reignition faults,with a fault diagnosis accuracy of over 85%.

关 键 词：变电站 二次设备 故障诊断 支持向量机 主分量分析技术 广义变比 电力信号降维 多元分类器 

分 类 号：TP206.3[自动化与计算机技术—检测技术与自动化装置] TH-39[自动化与计算机技术—控制科学与工程]