电器与能效管理技术Issue(8)：12-16,28,6.DOI:10.16628/j.cnki.2095-8188.2017.08.003
小波包系数能量百分比在局部放电模式识别中的应用研究
Application of Wavelet Packet Coefficients Energy Percentage in Pattern Recognition of Partial Discharge
摘要
Abstract
Four kinds of discharge waveforms are denoising processed,based on it,wavelet packet was decomposed the percentage of energy of wavelet packet coefficients was caleulated in different frequency bands,which as the feature vectors,was input into SVM and BP neural network to be recognized.The recognition results show that the eigenvectors composed by the percentage of energy of wavelet packet coefficients can well reflect the characteristics of the original signal,and that based on SVM has better recognition performance than the BP neural network.关键词
局部放电/小波包分解/能量百分比/特征提取/支持向量机/模式识别Key words
partial discharge/wavelet packet decomposition/percentage of energy/feature extraction/support vector machine(SVM)/pattern recognition分类
信息技术与安全科学引用本文复制引用
吴炬卓,牛海清,许佳..小波包系数能量百分比在局部放电模式识别中的应用研究[J].电器与能效管理技术,2017,(8):12-16,28,6.基金项目
国家863计划资助项目(2011AA05A120) （2011AA05A120）
