摘要
利用信号与测量噪声在小波分析中不同尺度上的传播特性,研究了小波技术在涡流无损检测信号除噪中的应用。分析了传统的去除测量噪声的两种小波方法,Mallat多尺度边缘检测方法和阈值方法,针对两种方法的不足,提出了一种新方法:低分辨率下的小波分解系数全部保留,高分辨率下的小波系数则只有被确认为有用信号特征值及其附近各点才予以保留,其余的都加以去除。结果表明,此方法能有效地降低测量噪声。
Based on the characteristics at different scales between singular signal and measure noise, the wavelet denoise method on eddy current nondestructive detection （ECNDT） signals is studied, After analyzing the two current denoise methods using wavelet transform, such as Mallat multi-scaling edge detecting or threshol dmethod, against their disadvantages respectively, a new method is introduced, the wavelet coefficients at large scaling remain unchanged, at small scaling, coefficients only near to the edge closely remain unchanged, others are set to zero. The result shows that this method is better than two others.
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2005年第7期738-740,763,共4页
Chinese Journal of Scientific Instrument
基金
河北省自然科学基金(602378)
河北省教育厅博士基金(B2001206)资助项目。
关键词
涡流无损检测
除噪
阈值方法
特征值
ECNDT Denoise Thresholds method Characteristic values
