摘要
两相流体具有复杂的流动特性,流型的准确辨识是两相流参数准确测量的基础,流型的在线智能辨识是两相流研究的重点内容之一。以电阻层析成像(ERT)系统和油/水两相流的流型为研究基础,采用主成分分析方法对ERT系统中的边界测量电压数据进行特征提取,然后以提取的特征数据作为基于一对余类策略的支持向量机多类分类模型的输入,从而对两相流的四种流型进行识别。通过实验仿真分析,四种流型的平均识别率达到了88.75%,说明主成分分析和支持向量机的结合是一种两相流流型辨识的有效方法。
Two-phase fluid has complex flow characteristic, and accurate identification of flow regime is the foundation of measuring two-phase flow's parameter. As a result, the online intelligent identification of flow regime is an important role of two-phase flow research. The research in this paper is based on electrical resistance tomography system and flow regime of oil-water two-phase flow. First, principal component analysis is adopted to extract the feature of the border measurement voltage data of the electrical resistance tomography system, then the extracted feature data is taken as input information of the support vector machine multi-class classifier which is based on one to all strategies, so the four kinds of two-phase flow regime can be identified. Through the experiment simulation analysis, the four kinds of flow regime's average recognition rate is up to 88. 75%. It can be concluded that the combination of principal component analysis and support vector machine is an effective method of two-phase flow regime identification.
出处
《电机与控制学报》
EI
CSCD
北大核心
2007年第6期639-643,共5页
Electric Machines and Control
基金
国家自然科学基金(60572153)
国家教育部重点科技项目(204043)
黑龙江省自然科学基金(F200609)
关键词
电阻层析成像
流型辨识
主成分分析
支持向量机
electrical resistance tomography
flow regime identification
principal component analysis
support vector machine