压缩感知理论在ECT流型辨识中的应用

吴新杰; 黄国兴; 王静文

doi:10.3788/OPE.20132104.1062

您当前的位置：

首页 >

文章列表页 >

压缩感知理论在ECT流型辨识中的应用

信息科学 | 更新时间：2020-08-12

- 压缩感知理论在ECT流型辨识中的应用
- Application of Compressed Sensing in Flow Pattern Identification of ECT
- 光学精密工程 2013年21卷第4期页码：1062-1068
- 作者机构：
  
  辽宁大学物理学院,辽宁沈阳,110036
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目(No.91023049)
- DOI：10.3788/OPE.20132104.1062
  中图分类号： TP391.4
- 收稿日期：2012-12-03，
  
  修回日期：2013-01-21，
  
  网络出版日期：2013-04-20，
  
  纸质出版日期：2013-04-15
- 稿件说明：
移动端阅览
吴新杰黄国兴王静文. 压缩感知理论在ECT流型辨识中的应用[J]. 光学精密工程, 2013,21(4): 1062-1068

WU Xin-Jie HUANG Guo-xing WANG Jing-wen. Application of Compressed Sensing in Flow Pattern Identification of ECT[J]. Editorial Office of Optics and Precision Engineering, 2013,21(4): 1062-1068
吴新杰黄国兴王静文. 压缩感知理论在ECT流型辨识中的应用[J]. 光学精密工程, 2013,21(4): 1062-1068 DOI： 10.3788/OPE.20132104.1062.

WU Xin-Jie HUANG Guo-xing WANG Jing-wen. Application of Compressed Sensing in Flow Pattern Identification of ECT[J]. Editorial Office of Optics and Precision Engineering, 2013,21(4): 1062-1068 DOI： 10.3788/OPE.20132104.1062.

摘要

针对传统电容层析成像（ECT）流型辨识方法识别率较低的问题，提出一种基于压缩感知理论的ECT流型辨识方法。首先，将ECT系统获得的测量电容向量归一化，并表示为训练样本集的过完备字典稀疏线性组合；然后，将随机高斯矩阵作为测量矩阵对测试样本和标准样本分别进行采样，并利用压缩感知信号重构算法求解L0范数下的最优化问题，从而得到各样本在训练样本集上的稀疏表示；根据待测样本和标准样本稀疏解之间的线性相关程度来确定归属流型。对典型流型的仿真实验结果显示，在无噪声、40 dB、20 dB信噪比的情况下，流型辨识准确率分别为100%、99.25%和98.12%，表明本文方法抗噪声干扰能力强，是一种有效、准确率较高的ECT流型辨识方法，为ECT流型辨识技术的研究提供了一种新的手段。

Abstract

In view of lower recognition rates of traditional methods in the flow pattern identification of Electrical Capacitance Tomography (ECT)

a identification method for the ECT based on Compressed Sensing (CS) was put forward. Firstly

measurement capacitance vectors obtained by an ECT system were normalized and represented as a sparse linear combination of training sample set in an over complete dictionary. Then

the random Gaussian matrix was taken as the measurement matrix to sample from the test and standard samples respectively

and the signal reconstruction algorithm based on the CS was used to solve the optimization problem of L0 norm for the sparse representation of each sample on the training sample set. The linear correlation coefficient between the sparse solutions of samples to be tested and the standard samples are calculated to determine the classification of flow pattern. The simulation experiment results of typical flow patterns indicate that the flow pattern identification rates under absence of noise

and signal to Noise Ratios(SNRs) of 40 db and 20 db are 100%

99.25% and 98.12% respectively. It concluds that the flow pattern identification method proposed has high efficiency and accuracy and a good noise immunity

which also provides a new method for the flow pattern identification of ECT.

关键词

Keywords

references

吴新杰，黄国兴，王静文.粒子滤波算法在ECT图像重建中的应用[J].光学精密工程,2012，20(8): 1824-1830.WU X J, HUANG G X, WANG J W. Application of particle filtering algorithm to image reconstruction of ECT[J]. Opt. Precision Eng., 2012, 20(8): 1824-1830. (in Chinese) [2]陈宇，高宝庆，张立新，等.基于加权奇异值分解截断共轭梯度的电容层析图像重建[J].光学精密工程,2010，18(3): 701-707.CHEN Y, GAO B Q, ZHANG L X, et al.. Image reconstruction based on weighted SVD truncation conjugate gradient algorithm for electrical capacitance tomography [J]. Opt. Precision Eng., 2010, 18(3): 701-707. (in Chinese) [3]WANG L, HUANG Z Y, WANG B L, et al.. Flow pattern identification of gas-liquid two-phase flow based on capacitively coupled contactless conductivity detection [J].IEEE Transactions on Instrumentation and Measurement, 2012, 61(5):1466-1475. [4]龙军，冀海峰，王保良，等.经验模态分解和小波分析在小通道气液两相流流型辨识中的应用[J].高校化学工程学报, 2011，25(5):759-764.LONG J, JI H F, WANG B L, et al.. Application of empirical mode decomposition and wavelet analysis to small channel gas-liquid two-phase flow pattern identification [J]. Journal of Chemical Engineering of Chinese Universities, 2011, 25(5):759-764. (in Chinese) [5]黄晓微，陈伟民，章鹏，等.基于K-最近邻算法的挠度传感器有效度研究[J].仪器仪表学报,2012，33(5): 1090-1095.HUANG X W, CHEN W M, ZHANG P, et al.. Research on deflection sensor validity based on K-neighbor algorithm [J]. Chinese Journal of Scientific Instrument, 2012, 33(5):1090-1095. (in Chinese) [6]ACI M, AVCI M. K nearest neighbor reinforced expectation maximization method [J]. Expert Systems with Applications, 2011, 38(10): 12585-12591. [7]吴新杰，刘石，许超.基于神经网络和D-S证据理论辨识两相流流型[J].传感器与微系统,2009，28(11): 43-45.WU X J, L IU S, XU C, et al.. Two-phase flow pattern identification based on neural networks and D-S evidence theory [J]. Transducer and Microsystem Technologies, 2009, 28(11): 43-45. (in Chinese) [8]CHAKRABARTI D P, PILGRIM A, SASTRY M K S, et al.. Identification of liquid-liquid flow pattern in a horizontal pipe using artificial neural networks [J]. Chemical Engineering Communications, 2011, 198(2): 273-285. [9]王莉莉，乔立勇，陈宇，等. 基于特征提取和RBF神经网络的ECT流型辨识[J].计算机工程与应用,2011，47(5): 175-178.WANG L L, QIAO L Y, CHEN Y, et al.. Flow pattern identification based on feature extraction and RBF neural network for electrical capacitance tomography [J]. Computer Engineering and Applications, 2011, 47(5):175-178. (in Chinese) [10]HAN J, DONG F, XU Y Y. Entropy feature extraction on flow pattern of gas/liquid two-phase flow based on cross-section measurement [J]. Journal of Physics: Conference Series, 2009, 147(1): 1742-6588.[11]DONOHO D L. Compressed sensing [J]. IEEE Transactions on Information Theory, 2006, 52(4):1289-1306.[12]JI J, LI X, WANG Q. A synthetic aperture radar image compression algorithm based on compressed sensing [J]. Advanced Science Letters, 2012, 7(3):320-322.[13]WANG X, ZHAO Z F, XIA Y, et al.. Compressed sensing for efficient random routing in multi-hop wireless sensor networks [J]. International Journal of Communication Networks and Distributed Systems, 2011,7(3):275-292.[14]FAZEL F, FAZEL M, STOJANOVIC M. Compressed sensing in random access networks with applications to underwater monitoring [J]. Physical Communication, 2012, 5(2):148-160.[15]石文轩，李婕.最小化预测残差的图像序列压缩感知[J].光学精密工程,2012，20(9): 2095-2102.SHI W X, LI J. Image sequence compressed sensing by minimizing prediction errors [J]. Opt. Precision Eng., 2012, 20(9): 2095-2102. (in Chinese) [16]HONG M J, YU Y Y, WANG H, et al.. Compressed sensing MRI with singular value decomposition-based sparsity basis [J]. Physics in Medicine and Biology, 2011, 56(19):6311.[17]BARANIUK R, DAVENPORT M, DEVORE R, et al.. A simple proof of the restricted isometry property for random [J]. Matrices Constructive Approximation, 2008, 28(3): 253-263.[18]刘欣悦，董磊，王建立.稀疏采样傅里叶望远镜成像[J].光学精密工程,2010，18(3): 521-527.LIU X Y, DONG L, WANG J L. Fourier telescopy imaging via sparse sampling [J]. Opt. Precision Eng., 2010, 18(3): 521-527. (in Chinese) [19]沈跃，刘国海，刘慧.随机降维映射稀疏表示的电能质量扰动多分类研究[J].仪器仪表学报,2011，32(6): 1371-1376.SHEN Y, LIU G H, LIU H. Study on classification method of power quality disturbances based on random dimensionality reduction projection and sparse representation [J]. Chinese Journal of Scientific Instrument, 2011, 32(6):1371-1376. (in Chinese)

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

粒子滤波算法在ECT图像重建中的应用

双超混沌系统结合压缩感知和Fibonacci变换的彩色图像加密

面向光学遥感影像的高效编码与重构

基于测量基优化的低采样率单像素成像

基于跨尺度字典学习的图像盲解卷积算法