基于LS-SVM的油气两相流空隙率测量方法的研究  

A study of the void-fraction measurement of oil-gas two-phase flow based on least squares support vector machine

作　　者：蔡慧林[1] 彭珍瑞[1] 祁文哲[1] 孟建军[1] 

机构地区：[1]兰州交通大学机电工程学院,甘肃兰州730070

出　　处：《工业仪表与自动化装置》2008年第2期75-78,56,共5页Industrial Instrumentation & Automation

基　　金：甘肃省自然科学基金资助项目(3ZS062-B25-016);兰州交通大学"青蓝"人才资助项目

摘　　要：利用12电极电容层析成像系统电容传感器获取的66个电容测量值,基于最小二乘支持向量机(LS-SVM)算法,提出了两相流空隙率在线测量的新方法。该方法用LS-SVM来建立空隙率测量模型。在实际测量时,首先归一化ECT获取的电容测量值,然后将归一化电容值输入已经建立的空隙率模型即可计算出空隙率。实验结果表明:该方法是有效的,避免了复杂耗时的图像重建过程,测量误差在6%以内,测量时间小于0.08 s。Based on 66 capacitance measurement values by 12-electrode capacitance sensor and by using least squares support vector machine （LS-SVM）, a new method for on-line void fraction measurement of two-phase flow was proposed. The sensor of electrical capacitance tomography （ECT） is used to obtain the capacitance measurement values. The void-fraction measurement model established by the LS- SVM method is actually a regression function between the void-fraction and capacitance values. In the process of measurement,the capacitance values obtained by the ECT sensor should be first normalized and then are fed to the measurement model to calculate the vOid-fraction value. Experimental results show that this method is effective and good in the real-time measurement time is less than 0. 08s. performance. Its measurement error is within 6% and the

关 键 词：最小二乘支持向量机 空隙率 两相流 电容 

分 类 号：O359.1[理学—流体力学] TP273[理学—力学]