基于电容层析成像和LS-SVM的空隙率测量

Electrical capacitance tomography and LS-SVM based voidage measurement

基于12电极电容层析成像(ECT)和最小二乘支持向量机(LS-SVM),提出了一种油气两相流空隙率在线测量的新方法.该方法运用快速的线性反投影算法重建两相流截面图像,结合模糊模式识别技术辨识流型.把ECT电容传感器得到的66个电容测量值作为空隙率测量模型的输入,利用LS-SVM建立了针对不同截面流型的空隙率测量模型.在实际测量时,首先辨识流型,然后选择与流型相对应的空隙率测量模型计算获得空隙率.该方法省去了采用传统ECT方法测量空隙率时复杂的图像重建过程,提高了空隙率测量的实时性.实验结果表明该测量方法是有效的.

A new method was proposed for on-line voidage measurement of oil-gas two-phase flow based on 12-electrode electrical capacitance tomography （ECT） and least squares support vector machine （LS- SVM）. This method identified flow pattern by using fast back-projection image reconstruction and fuzzy pattern recognition technique. LS-SVM was used to establish the voidage measurement models under different flow patterns. In each model, 66 capacitance values from ECT sensor were the inputs and the corresponding voidage value was the output. In the measurement process, the flow pattern of oil-gas two-phase flow was identified firstly, and then the voidage was computed using the voidage measurement model corresponding to the identified flow pattern. This new method implements voidage measurement without complicated and time-consuming image reconstruction and thus improves the real-time performance of voidage measurement. Experimental results showed the effectiveness of the new method.