小波神经网络在油水两相流软测量中的应用  

Application of Wavelet Neural Network in Oil-Water Two-Phase Flow Soft-Measurement

作　　者：韩骏[1,2] 谭超[1] 徐遥远[1] 董峰[1] 

机构地区：[1]天津市过程检测与控制重点实验室天津大学电气与自动化工程学院,天津300072 [2]首都师范大学教育技术系,北京100037

出　　处：《天津大学学报》2009年第9期808-812,共5页Journal of Tianjin University(Science and Technology)

基　　金：国家自然科学基金资助项目(50776063);天津市应用基础及前沿技术研究计划重点资助项目(08JCZDJC17700)

摘　　要：油水两相流流动参数的准确测量对于众多工业工程的有效监控具有重要作用.针对V型内锥测量油水两相流所获取的差压信号,提出了一种水平管道中油水两相流的质量流量软测量方法.采用的方法中构建了基于自适应小波神经网络的油水两相流质量流量软测量模型,实现了两相混合总质量流量的测量.实验测量结果与油水两相流的均质模型计算结果进行了比较.结果表明,基于V型内锥差压测量和自适应小波神经网络的软测量方法可以应用于油水两相流的总质量流量测量,与理论的均质模型比较,测量误差较小.Accurate measurement of oil-water two-phase flow parameters is of great significance to online monitoring of many industrial processes. A soft-measurement method for the mass flow-rate of oil-water two-phase flow in horizontal pipelines was put forward, in which the V-cone differential pressure meter was adopted to acquire the differential pressure of flowing signal. A soft-measurement model based on the adaptive wavelet neural network was developed to measure the total mass flow-rate of oil-water two-phase flow. Comparison between the experimental results and the calculation results of oil- water two-phase homogeneous model shows that the soft-measurement method which integrates differential pressures measurement with adaptive wavelet network satisfies the demand of the mass flow-rate measurement of oil-water two-phase flow. Compared with the theoretical homogeneous model ,the soft-measurement method has relatively smaller error.

关 键 词：油水两相流 V型内锥 自适应小波神经网络 软测量 均质模型 

分 类 号：TP216.1[自动化与计算机技术—检测技术与自动化装置]