基于小波包新阈值量化处理的发动机振动信号降噪  

Engine Vibration Signal De-noising Based on New Threshold Quantization of Wavelet Packet

作　　者：宋越[1] 王立勇[1] 陈涛[1] 许宝杰[1] 

机构地区：[1]北京信息科技大学现代测控教育部重点实验室,北京100192

出　　处：《机械工程与自动化》2015年第6期1-2,共2页Mechanical Engineering & Automation

基　　金：国家自然科学基金资助项目(51105041;51275052);教育部科学技术研究重点项目(212002);北京市青年拔尖人才项目(CIT&TCD201404112)

摘　　要：在小波包降噪中利用小波包分析技术对振动信号进行多层次划分,克服了小波分析中高频部分频率分辨率差的缺点;针对阈值降噪方法中软、硬阈值量化处理的不足,提出了介于软阈值和硬阈值之间的新阈值量化处理算法,构造的阈值量化函数既连续又与实际信号偏差较小。发动机降噪实验结果表明,与软、硬阈值量化处理方法相比,新阈值量化处理方法降噪效果较好。In this paper ,the vibration signal is decomposed into multi-level functions by wavelet packet de-noising ,which overcomes the disadvantages of poor high frequency resolution in wavelet analysis .During de-noising process ,a reasonable threshold selection method is proposed .The threshold function based on the frequency of the acquisition signal and the interference signal is continuous and deviating little from the actual signal function .Compared with soft threshold and hard threshold ,the new method has improved the signal to noise ratio .

关 键 词：发动机 小波包降噪 阈值 信噪比 

分 类 号：TN911.7[电子电信—通信与信息系统] U464[电子电信—信息与通信工程]