基于蚁群算法的小波降噪双阈值优选方法  

Wavelet de-noising double threshold optimization method based on ant colony algorithm

作　　者：王传鑫[1] 邵诚[1] 韩瑜[2] 

机构地区：[1]大连理工大学先进控制技术研究所,辽宁大连116024 [2]大连理工大学软件学院,辽宁大连116024

出　　处：《控制与决策》2011年第1期115-119,共5页Control and Decision

摘　　要：将相关性分析方法和阈值降噪方法相结合,提出了一种基于蚁群算法的小波降噪双阈值优选方法.首先根据噪声的分布特点确定合理的寻优区间;然后根据信号和噪声的小波系数自相关系数的不同特点确定优化目标函数;最后利用蚁群算法在寻优区间内搜索最优上下阈值.仿真和压缩机振动故障检测的实际应用表明,该方法能够选择最优降噪阈值,有效去除噪声.By combining correlation analysis method and threshold de-noising method, a methord based on ant colony algorithm is given for optimizing wavelet de-noising double-threshold. The reasonable optimization interval is determined according to the charactersitic of distributed of noise. The objective function is chosen according to the difference of autocorrelation coefficient of signal＇s wavelet coefficient and noise＇s wavelet cofficient. Finally the optimal upper threshold and lower threshold are calculated by using ant colony algorithm. Simulation and compressor vibration fault detection application results show that the proposed method can optimize the de-noising threshold and denoise effectively.

关 键 词：小波变换 降噪阈值 相关性分析 蚁群算法 压缩机振动故障检测 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]