基于支持向量机的变压器故障诊断
|
摘要
针对油浸式电力变压器在不同工作状态时,变压器油中溶解气体的类型和含量的不同,通过检测变压器油中的不同气体的类型和含量就成了判别变压器工作状态的重要方法。本文基于支持向量机(SVM)模型,利用支持向量机对于非线性问题的优良解决方法,给出了一种判别变压器工作方式的方法,经测试,判别正确率高达96.8%,满足对于变压器故障判别的精度要求。
According to the different working states of oil-immersed power transformer, the type and content of dissolved gas in transformer oil are different. Based on the support vector machine(SVM) model and by using the support vector machine to solve the nonlinear problem, this paper presents a method to distinguish the transformer working mode.
According to the different working states of oil-immersed power transformer, the type and content of dissolved gas in transformer oil are different. Based on the support vector machine(SVM) model and by using the support vector machine to solve the nonlinear problem, this paper presents a method to distinguish the transformer working mode.
引文
[1]王汉林,杨超,唐华.油中溶解气体分析的电力变压器故障诊断[J].自动化仪表,2018,39(10):66-69.
[2]张善强.油浸电力变压器故障诊断及检修技术的研究[J].花炮科技与市场,2018(03):36,39.
[3]Xiaolian Liu,Yu Tian,Xiaohui Lei,Mei Liu,Xin Wen,Haocheng Huang,Hao Wang.Deep forest based intelligent fault diagnosis of hydraulic turbine[J].Journal of Mechanical Science and Technology,2019,33(5).
[4]XianBo Wang,Zhi-Xin Yang,Pak Kin Wong,Chao Deng.Novel paralleled extreme learning machine networks for fault diagnosis of wind turbine drivetrain[J].Memetic Computing,2019,11(2).
[5]刘振宇.基于DGA的变压器在线监测与故障诊断方法研究[J].通信电源技术,2019,36(04):11-12.
[6]和娜娜.半监督分类法在变压器故障诊断中的应用[J].煤矿机电,2018(05):64-66.
[7]Xunshi Yan,Zhe Sun,Jingjing Zhao,Zhengang Shi,Chen-an Zhang.Fault diagnosis of rotating machinery equipped with multiple sensors using space-time fragments[J].Journal of Sound and Vibration,2019.
[8]荣智海,齐波,李成榕,朱双静,陈玉峰,辜超.面向变压器油中溶解气体分析的组合DBN诊断方法[J/OL].电网技术:1-9[2019-06-11].https://doi.org/10.13335/j.1000-3673.pst.2019.0422.
[9]胡善芝,周冬旭,唐仁权.一种基于综合推理的变压器故障诊断方法[J].电工电气,2019(03):23-28.
[10]马松龄,郭小艳,张清敏,代一楠.基于改进粒子群优化RBF网络的变压器故障诊断[J].水电能源科学,2019,37(04):184-186,191.图5混淆矩阵
[2]张善强.油浸电力变压器故障诊断及检修技术的研究[J].花炮科技与市场,2018(03):36,39.
[3]Xiaolian Liu,Yu Tian,Xiaohui Lei,Mei Liu,Xin Wen,Haocheng Huang,Hao Wang.Deep forest based intelligent fault diagnosis of hydraulic turbine[J].Journal of Mechanical Science and Technology,2019,33(5).
[4]XianBo Wang,Zhi-Xin Yang,Pak Kin Wong,Chao Deng.Novel paralleled extreme learning machine networks for fault diagnosis of wind turbine drivetrain[J].Memetic Computing,2019,11(2).
[5]刘振宇.基于DGA的变压器在线监测与故障诊断方法研究[J].通信电源技术,2019,36(04):11-12.
[6]和娜娜.半监督分类法在变压器故障诊断中的应用[J].煤矿机电,2018(05):64-66.
[7]Xunshi Yan,Zhe Sun,Jingjing Zhao,Zhengang Shi,Chen-an Zhang.Fault diagnosis of rotating machinery equipped with multiple sensors using space-time fragments[J].Journal of Sound and Vibration,2019.
[8]荣智海,齐波,李成榕,朱双静,陈玉峰,辜超.面向变压器油中溶解气体分析的组合DBN诊断方法[J/OL].电网技术:1-9[2019-06-11].https://doi.org/10.13335/j.1000-3673.pst.2019.0422.
[9]胡善芝,周冬旭,唐仁权.一种基于综合推理的变压器故障诊断方法[J].电工电气,2019(03):23-28.
[10]马松龄,郭小艳,张清敏,代一楠.基于改进粒子群优化RBF网络的变压器故障诊断[J].水电能源科学,2019,37(04):184-186,191.图5混淆矩阵