首页 | 本学科首页   官方微博 | 高级检索  
     

基于小波包及隐式马尔科夫模型的局放信号去噪
引用本文:张毅刚,郁惟镛,黄成军,左问. 基于小波包及隐式马尔科夫模型的局放信号去噪[J]. 上海交通大学学报, 2004, 38(8): 1269-1272
作者姓名:张毅刚  郁惟镛  黄成军  左问
作者单位:上海交通大学,电气工程系,上海,200240;上海交通大学,电气工程系,上海,200240;上海交通大学,电气工程系,上海,200240;上海交通大学,电气工程系,上海,200240
摘    要:将基于小波变换的隐式马尔科夫模型(HMM)方法改进并扩展至小波包域,用于去除发电机局部放电信号中的白噪声.采用实测的局部放电信号验证了方法的有效性.结果表明,对比传统的门限去噪算法,基于小波包的HMM方法有更好的去噪效果;而与基于小波变换的HMM方法相比,所建立的模型更能体现信号的特征,对于信号分析乃至进一步的模式识别有着更大的价值.

关 键 词:信号处理  信号去噪  局部放电  隐式马尔科夫模型
文章编号:1006-2467(2004)08-1269-04
修稿时间:2003-08-20

Wavelet Package-Based Partial Discharge Denoising Using Hidden Markov Model
ZHANG Yi-gang,YU Wei-yong,HUANG Cheng-jun,ZUO Wen. Wavelet Package-Based Partial Discharge Denoising Using Hidden Markov Model[J]. Journal of Shanghai Jiaotong University, 2004, 38(8): 1269-1272
Authors:ZHANG Yi-gang  YU Wei-yong  HUANG Cheng-jun  ZUO Wen
Abstract:Wavelet-domain hidden markov models (HMMs) have recently been introduced and applied to signal and image processing. The advantage of the method is that the HMMs measure the dependency between the wavelet coefficients and have no free parameters in denoising. A wavelet-package-based HMMs method was developed to reduce partial discharge (PD) white noise. The effectiveness of the method is demonstrated by using numerical simulations and real-world data of neutral point current of generator. Compared with Shrinkage method, the results shows that the HMMs method is better in enhancing signal-to-noise radio and reserves more PD impulses.
Keywords:signal processing  signal denoising  partial discharge  hidden Markov model(HMM)
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号