改进的小波消噪阈值方法在油气水三相流图像信号中的应用  

An Improved Wavelet Threshold Denoising Method and Its Application on the Oil-gas-liquid Three-phase Flow

作　　者：周云龙[1] 张慧冬[1] 李洪伟[2] 肖倩[3] 柴忠良[2] 

机构地区：[1]东北电力大学能源与机械工程学院,吉林吉林132012 [2]东北电力大学自动化工程学院,吉林吉林132012 [3]东北大学流程工业综合自动化教育部重点实验室,沈阳110004

出　　处：《化工自动化及仪表》2009年第4期49-53,共5页Control and Instruments in Chemical Industry

基　　金：吉林省科技发展项目(20040513)

摘　　要：应用高速摄像机拍摄了油气水三相流典型流型的图像视频,提取其灰度均值构成时间序列,为了更好地研究其流动机理,需将时间序列进行消噪。在研究传统的平稳小波理论和分析传统阈值函数存在问题的基础上,提出了一种新的小波消噪阈值方法。在MATLAB实验平台上证明了这种新的阈值方法能有效弥补传统软、硬阈值的不足,并具有很好的数学性质。将基于平稳小波变换的新阈值方法应用到灰度时间序列的消噪中,实验结果表明,该方法能很好地保留油气水三相流图像信号的特征并能有效地消除噪声,有利于对油气水三相流流动特性的理解。Used high-speed video camera filming the flow image video of oil-gas-water typical flow pattern. The mean gray of each image and composition of the time series were extracted. In order to study the flow mechanism better, it need to take the time series denoising, based on the introduction of stationary wavelet theory and analysis of existing problems of traditional threshold functions, a novel wavelet threshold denoising method was proposed. In the MATLAB experimental platform, it was proved that this new threshold method could compensate for the deficiency of the traditional soft/hard threshold methods, and also had very good mathematical character. The new threshold method based on the stationary wavelet transform was applied to noise reduction of grayscale signals. The experiment result indicates that the new method can better reserve the characteristic of grayscale and eliminate noise effectively.

关 键 词：平稳小波变换 油气水三相流 灰度时间序列 阈值 混沌特征 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]