基于极限学习机的变压器故障诊断方法研究

苑津莎; 张利伟; 王瑜; 尚海昆

苑津莎，张利伟，王瑜，尚海昆.基于极限学习机的变压器故障诊断方法研究[J].电测与仪表,2013,50(12):.
.Study of Transformers Fault Diagnosis Based on Extreme Learning[J].Electrical Measurement & Instrumentation,2013,50(12):.

基于极限学习机的变压器故障诊断方法研究

Study of Transformers Fault Diagnosis Based on Extreme Learning

DOI：

中文关键词: 变压器故障诊断极限学习机 ELM 神经网络激活函数

英文关键词:transformers, fault diagnosis, extreme learning machine, neural network, active function

基金项目:

作者中文名	作者英文名	单位
苑津莎，张利伟，王瑜，尚海昆		华北电力大学电气与电子工程学院

摘要点击次数: 1851

中文摘要:

针对基于传统智能学习方法的变压器故障诊断存在训练速度慢、需调整的参数多及参数确定困难的问题,本文提出了基于极限学习机(Extreme Learning Machine,ELM)的变压器故障诊断方法。文中根据变压器故障的特点选取输入特征向量,分析了激活函数、隐含层节点数目对诊断性能的影响,并与基于BP神经网络和SVM的诊断方法进行了对比。实验结果表明,文中提出的变压器故障诊断方法性能明显优于BP神经网络,与SVM的诊断正确率相当,需要预先设置的参数更少,训练速度更快,更加便于工程应用。

英文摘要:

Transformer fault diagnosis based on conventional learning methods face some drawbacks: slow learning speed, trivial tuned parameters and difficult parameter determination. To overcome these drawbacks, transformer fault diagnosis based on extreme learning machine (ELM) was proposed in this paper. In this paper,input feature vector was selected according to the characteristic of transformer fault, and then the influence of active functions and hidden layer node number to the diagnosis performance was studied, at last the proposed model was compared with the diagnosis based on BP neural network (BPNN) and SVM. Experimental results show that, the proposed diagnosis method is better than diagnosis based on BPNN at performance, similar to SVM at correct diagnosis rate but more convenient to engineering application with quicker learning speed and less human tuned parameters.

查看全文查看/发表评论下载PDF阅读器

关闭