介电常数未知条件下ECT图像重建的SVC算法  

ECT Reconstruction Image Based on SVC Under Unknown Dielectric Constant

作　　者：何世钧[1] 张婷[1] 程小龙[1] HE Shi-jun ZHANG Ting CHENG Xiao-long(College of Information Technology, Shanghai Ocean University, Shanghai 201306, China)

机构地区：[1]上海海洋大学信息学院,上海201306

出　　处：《测控技术》2017年第9期27-30,共4页Measurement & Control Technology

基　　金：上海市科委科研计划资助项目(10510502800)

摘　　要：在电容层析成像(ECT)系统的实际应用中,两相流和多相流是最普遍的流体情况。不仅是由于被测介质的介电常数会随着温度等环境的变化而变化,而且还由于被测场域中存在其他介质,会使得测量时出现介质未知的情况。利用支持向量机(SVM)算法具有良好泛化性的特点,提出采用基于SVC(support vector classification)的电容层析成像图像重建算法对未知介电常数对象进行图像重建。仿真结果表明,该算法能有效适应介质多样性变化,即对于不同介质,该算法都能有较高的图像重建精度。In the practical application of electrical capacitance tomography（ECT） system, two phase and multi- phase flow are the most common fluid conditions. The unknown dielectric constant usually appears not only due to the dielectric constant of measured medium with temperature changes and other environmental changes, but also due to other impurities in the measured field. Based on the characteristics of good generalization of support vector machine （SVM） algorithm, the image reconstruction algorithm based on SVC（ support vector classifica- tion） for ECT is used to study the image reconstruction under unknown dielectric constant. The simulation re- sults show that the algorithm can effectively adapt to the change of medium diversity. This means that for differ- ent medium, the algorithm can have a higher precision of image reconstruction.

关 键 词：介电常数 图像重建 支持向量分类机 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]