基于包络滤波的电磁超声检测数据降噪算法  

An EMAT denoising algorithm based on envelope filtering

作　　者：童允[1] 黄松岭[1] 赵伟[1] 田贵云[2] 

机构地区：[1]清华大学电机系电力系统国家重点实验室,北京100084 [2]Newcastle大学计算机与电子工程学院英国

出　　处：《高技术通讯》2010年第9期960-964,共5页Chinese High Technology Letters

基　　金：863计划(2007AA06Z223)资助项目

摘　　要：针对电磁超声检测中的噪声问题,提出了基于包络滤波技术的噪声消除方法。该方法利用三次多项式插值曲线拟合法求取原始信号的包络曲线,按照设定的降噪阈值用上下包络线分别分段地对原始信号进行修正,最后对上下包络修正的结果取平均,从而实现平滑信号和抑制杂波的作用。该方法的处理过程不会损伤信号的主体特征,对于混叠在信号中的多种类型的高频噪声都能进行很好的抑制。利用电磁超声表面波的实验数据对算法进行了检验,实验结果表明,基于包络滤波的降噪算法可以有效地消除检测信号中的杂波和毛刺干扰,抑制噪声的幅度,提高信噪比。To reduce the noise in the inspection data from an electromagnetic acoustic transducer （EMAT）, the paper proposes a denoising method based on envelope filtering. It uses a cubic polynomial interpolation curve fitting method to obtain the envelope of the original signals, and uses the up envelope and the down envelope separately to modify the original signals according to the given denoising threshold, and then averages the up and down modified signals to get the final result of smoothing the signals mixed in the signals, and with suppressing the clutters. The algorithm can suppress various types of high frequency noises out damaging the main feature of the signals. The algorithm was tested by the experiment with surface wave data. The result shows that the denoising algorithm based on envelope filtering can effectively eliminate the clutters and burrs in the inspection data, suppress the noise amplitude, and improve the signal to noise ratio.

关 键 词：电磁超声换能器(EMAT) 包络滤波 降噪算法 希尔伯特变换 HERMITE插值 

分 类 号：TP274.53[自动化与计算机技术—检测技术与自动化装置]