基于SVM及电容层析成像的两相流流型识别

Identification of two-phase flow regime based on support vector machine and electrical capacitance tomography technique

两相流测量中,流型的准确识别是流动参数准确测量的基础。电容层析成像(ECT)技术是自20世纪80年代发展起来的新型检测技术,可用于两相流/多相流流型识别及固相浓度测量。支持向量机是一种基于统计学习理论的机器学习算法,即使在小样本情况下也能得到很好的分类效果。应用ECT系统测量的包含流型信息的电容测量数据,采用支持向量机算法进行流型识别,对4种典型空气-油两相流流型识别分别进行了仿真和静态实验。结果表明,该方法辨识速度快,可准确地识别典型的流型。

The correct identification of two-phase flow regime is the basis for the accurate measurement of other flow parameters in two-phase flow measurement. Electrical capacitance tomography （ECT） is a new measurement technology. It is often used to identify two-phase/multi-phase flow regime and investigate the distribution of solids. Support vector machine （SVM） is a machine-learning algorithm based on statistical learning theory （SLT）, which has desirable classification ability with fewer training samples. This paper provides a new approach for flow regime identification. The capacitance measurement data obtained from ECT system contain flow regime information. Using these data and SVM method, simulation and static experiments were carried out for typical flow regimes. The results show that this method is fast in speed and can identify these flow regimes correctly.