摘要
应用数据融合技术、模糊神经网络及遗传算法构建牵引变压器故障智能诊断模型,通过Matlab软件对该模型进行仿真,训练模糊神经网络以确定其结构和权重,并通过典型实例验证该模型在牵引变压器故障诊断中具有良好的故障诊断性能。
The intelligent fault diagnosis model is designed by application of data fusion technology, fuzzy neural network and genetic algorithm, and it is simulated by MATLAB software to train the fuzzy neural network so as to determine its structure and weight. The typical experiments show that the model has very good functions for diagnosis of traction transformer faults.
引文
[1]Ke M,Zhao-Yang D,Dian-Hui W,et al.A Self-Adaptive RBF Neural Network Classifier for Transformer Fault Analysis[J].Power Systems,IEEE Transactions on.2010,25(3):1350-1360.
[2]徐大可.基于神经网络和模糊数学的变电设备绝缘诊断技术[J].电力自动化设备,2002,22(1):66-68.
[3]王鑫.电气设备的在线监测与故障诊断[D].山东大学,2005.
[4]王冬青,李刚,何飞跃.智能变电站一体化信息平台的设计[J].电网技术,2010(10):20-25.
[5]操敦奎,许维宗,阮国方.变压器运行维护与故障分析处理[M].北京:中国电力出版社,2008.
[6]赵熙临.基于信息融合的电力系统故障诊断技术研究[D].华中科技大学,2009.
[7]Wang Y,Chu F,He Y,et al.Multisensor data fusion for automotive engine fault diagnosis[J].Tsinghua Science and Technology.2004,9(3):262-265.
[8]崔建强.牵引电变压器故障智能诊断方法的研究[D].西南交通大学,2013.