| 基于灰色理论及BP神经网络的变压器油击穿电压预测方法 |
| |
| 引用本文： | 胡家元,曹顺安.基于灰色理论及BP神经网络的变压器油击穿电压预测方法[J].计算机与应用化学,2011,28(2). |
| |
| 作者姓名： | 胡家元 曹顺安 |
| |
| 作者单位： | 武汉大学动力与机械学院,湖北,武汉,430072 |
| |
| 摘 要： | 变压器油击穿电压的预测,对于变压器的故障诊断和日常维护具有重要的意义。本文提出了1种击穿电压多参数关联预测方法,即通过对变压器油日常监督数据进行灰色关联分析,挖掘与击穿电压存在强关联性的指标;利用BP网络建立击穿电压与4个强关联性指标的关系模型;采用模糊C均值聚类算法聚类原始样本,以聚类中心训练网络,以解决大样本情况引起的网络结构复杂、收敛性及泛化能力差等神经网络固有问题。仿真结果表明,预测模型精度较高,预测值与实际值的相对误差均在10%以内,能够满足实际应用要求,具有重要的应用价值。
|
| 关 键 词： | 灰色关联分析 BP神经网络 模糊C均值聚类 击穿电压 预测 |
Grey theory and BP neural network-based prediction technique for transformer oil breakdown voltage |
| |
| Hu Jiayuan,Cao Shunan.Grey theory and BP neural network-based prediction technique for transformer oil breakdown voltage[J].Computers and Applied Chemistry,2011,28(2). |
| |
| Authors: | Hu Jiayuan Cao Shunan |
| |
| Affiliation: | Hu Jiayuan and Cao Shunan (College of Power and Mechanical Engineering,Wuhan University,Wuhan,430072,Hubei,China) |
| |
| Abstract: | Prediction of breakdown voltage of transformer oil has a great significance to the fault diagnosis,daily maintenance of transformer.This paper proposed a prediction method of breakdown voltage via multi-parameter correlation.Through examining the routine monitoring data of transformer oil by gray correlation analysis,some parameters which have strong correlation with breakdown voltage were excavated,then a relational model of breakdown voltage and those parameters was further constructed using back-propagat... |
| |
| Keywords: | grey correlation analysis BP neural network fuzzy C-means clustering breakdown voltage prediction |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
