Application of Noise Reduction Method Based on Birgé-Massart Threshold  

作　　者：Xu Xiaoli Jiang Zhanglei Zuo Yunbo Wu Guoxin 

机构地区：[1]School of Mechanical and Vehicle Engineering,Beijing Institute of Technology [2]Key Laboratory of Modern Measurement & Control Technology,Ministry of Education, Beijing Information Science and Technology University

出　　处：《仪器仪表学报》2013年第S1期134-137,共4页Chinese Journal of Scientific Instrument

基　　金：partially supported by The National Natural Science Foundation of China(51275052);Natural Science Foundation of Beijing(3131002);The Key Project Supported by Introduction of Foreign Talents and Technologies of Beijing(B201101010);The major projects of the National Social Science Fund(12&ZD234)

摘　　要：Flue gas generator set is a kind of large high-speed rotating machinery in petrochemical industry.This research focuses on noise reduction algorithms basis ontheBirgé-Massartthreshold.Obtained the threshold through Penalization Strategy Provided by Birgé-Massart;constructed different modulus maximum vertex neighborhood on different wavelet transform decomposition scales to influence the search process of modulus maximum point;obtained the appropriate modulus maximum points sequence on various wavelet decomposition scales;highlighted state feature information;finally usedMallat staggered projection to reconstruct signals.In order to validate the effectiveness of the algorithm,it was compared with four kinds of threshold noise suppression methods namely Rigrsure,Sqtwolog,Heursure,Minimaxi.The results show that this algorithm has a better signal to noise ratio and mean-square error.Flue gas generator set is a kind of large high-speed rotating machinery in petrochemical industry.This research focuses on noise reduction algorithms basis ontheBirgé-Massartthreshold.Obtained the threshold through Penalization Strategy Provided by Birgé-Massart;constructed different modulus maximum vertex neighborhood on different wavelet transform decomposition scales to influence the search process of modulus maximum point;obtained the appropriate modulus maximum points sequence on various wavelet decomposition scales;highlighted state feature information;finally usedMallat staggered projection to reconstruct signals.In order to validate the effectiveness of the algorithm,it was compared with four kinds of threshold noise suppression methods namely Rigrsure,Sqtwolog,Heursure,Minimaxi.The results show that this algorithm has a better signal to noise ratio and mean-square error.

关 键 词：FEATURE EXTRACTION MODULUS MAXIMUM PUNISHMENT strategies 

分 类 号：TM314.3[电气工程—电机]