介电常数未知条件下ECT图像重建的SVC算法

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.

ECT Reconstruction Image Based on SVC Under Unknown Dielectric Constant

In the practical application of electrical capacitance tomography(ECT) system,two phase and multiphase 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 classification) for ECT is used to study the image reconstruction under unknown dielectric constant.The simulation results show that the algorithm can effectively adapt to the change of medium diversity.This means that for different medium,the algorithm can have a higher precision of image reconstruction.