摘要
基于12电极电容层析成像系统(ECT),提出了一种油气两相流空隙率测量的新方法。实际测量时,以ECT电容传感器获得的66个电容测量值作为输入,利用空隙率测量模型计算空隙率。建模过程中,首先采用独立分量分析(ICA),对66个电容测量值进行特征提取。然后以特征参数作为输入,空隙率作为输出,用最小二乘支持向量机(LS-SVM)建立回归函数,并运用进化策略(ES)寻找最优LS-SVM参数。实验结果验证了本文方法的有效性,测量精度和实时性满足工业应用的要求。
Based on 12-electrode electrical capacitance tomography（ ECT）, a new method was proposed for voidage measurement of oil-gas two-phase flow. In the measurement process, with the 66 measured capacitances obtained from ECT sensors being the inputs, the voidage was computed by using the voidage model. In the modeling stage, features were extracted from the 66 measured capacitances by Independent Component Analysis （ICA） firstly, and then Least Squares Support Vector Machine（LS-SVM） was used to establish the regression function,in which the features were the inputs and the corresponding voidage value was the output. Evolution Strategy （ES） was employed to search the optimal parameters in LS-SVM. Experimental results prove that the proposed method is effective, and the measurement accuracy and real-time performance satisfy industrial requirements.
出处
《化工自动化及仪表》
CAS
2007年第4期60-62,71,共4页
Control and Instruments in Chemical Industry
基金
国家自然科学基金资助项目(50576084
60532020)
关键词
空隙率
电容层析成像
独立分量分析
最小二乘支持向量机
进化策略
voidage
electrical capacitance tomography
independent component analysis
least squares support vector machine
evolution strategy
