广东电力2017，Vol.30Issue(7)：89-95,7.DOI:10.3969/j.issn.1007-290X.2017.07.016
基于小波包和模糊自适应共振神经网络的变压器绕组状态识别
State Recognition for Transformer Winding Based on Wavelet Packet and Fuzzy Adaptive Resonance Theory Neural Network
摘要
Abstract
Though there are great deal of state information in transformer vibration signals, it is hard to extract effective features to recognize winding looseness state of the transformer.Therefore, this paper presents a state recognition method for transformer winding looseness based on fuzzy adaptive resonance theory (Fuzzy-ART) neural network.Firstly, it sets nine kinds of winding looseness states for short-circuit test and measuring vibration signal on the surface of oil tank.Then, it applies four layers wavelet packet transform for vibration signal and extracts wavelet packet energy of state feature bands of effective measuring points to form feature vectors.Finally, it takes feature vectors as input of Fuzzy-ART neural network for recognizing different winding looseness states.Test results indicate that the Fuzzy-ART neural network based on wavelet packet can rapidly and stably classify winding looseness state which is available for online monitoring and diagnosis on transformer winding looseness state.关键词
变压器/绕组松动/振动信号/小波包能量/Fuzzy-ART神经网络/状态识别Key words
transformer/winding looseness/vibration signal/wavelet packet energy/fuzzy adaptive resonance theory neural network/state recognition分类
信息技术与安全科学引用本文复制引用
黄春梅,马宏忠,张艳,李勇,许洪华..基于小波包和模糊自适应共振神经网络的变压器绕组状态识别[J].广东电力,2017,30(7):89-95,7.基金项目
国网江苏省电力公司重点科技项目(J2014055) （J2014055）
