基于粗糙集和RBF神经网络的变压器故障诊断方法研究.docVIP

基于粗糙集和RBF神经网络的变压器故障诊断方法研究2，朱海兵3，龚登才4 （1. 南京工程学院 电力工程学院，南京 211167；2. 江苏省高校“配电网智能技术与装备”协同创新中心，南京 211167；3. 国网江苏省电力公司，南京 210024；4. 国网南通供电公司，南通 226006） 摘要：变压器故障诊断神经网络模型存在网络结构复杂、训练时间长等问题，提出基于粗糙集及RBF神经网络的变压器故障诊断方法。运用粗糙集理论中无决策分析，建立可分辨矩阵信息熵约简，进行数据挖掘，寻找最小约简；以处理后的数据集合作为训练样本，采用函数作为径向基函数，分别求解方差及各层权值，建立变压器故障诊断模型。通过，虽然，但网络结构简单、训练速度快、泛化能力强，对提高神经网络在变压器故障诊断中的应用性能有较好的指导意义。 关键词：变压器；故障诊断；粗糙集；RBF神经网络；信息熵 中图分类号：TM 文献标识码： 文章编号：1001-1390（201）-0000-00 Research on Rough Sets and RBF Neural Network based Transformer Fault Diagnosis Method YANG Zhi-chao1,2, WU Yi3, ZHANG Cheng-long1,2, AN Wei-wei1,2, ZHU Hai-bing3, GONG Deng-cai4 (1. School of Electric Power Engineering, Nanjing Institute of Technology, Nanjing 211167, China. 2. Jiangsu Higher Education Institutions Collaborative Innovation Center for Intelligent Technology and Equipment in Distribution Network, Nanjing 211167, China. 3. State Grid Jiangsu Electric Power Company, Nanjing 210024, China. 4. Nantong Power Supply Company, Nantong 226006, Jiangsu, China) Abstract：Aiming at the problems of complex network structure, long training time and other issues in classical neural networks, a method of RBF neural network combined with rough sets has been proposed in this paper for transformers fault diagnosis. Firstly, the minimum reduction is calculated after data mining based on distinguishes matrix and information entropy in rough set theory. Then, Gaussian function has been taken as the radial basis function, and the variance and weights of layers are calculated by the processed data collection as training samples. Finally, the transformer fault diagnosis model has been built. By comparing the test results, although the algorithm is slightly lower in the view of the diagnostic accuracy, the simple network structure, training speed and strong generalization ability of neural networks to improve application performance in transformer fault diagnosis have better guidance. Key words：RBF neural network, rough