摘要
在两相流测量问题的研究中,流型的准确识别是其他流动参数准确测量的基础,因此,得到比较高的流型辨识率是研究目的.本文在12电极电阻成像的基础上,采用模糊聚类对ERT系统中的测量电压数据进行模糊化,然后以模糊化后的数据作为BP神经网络的输入,在BP神经网络中,对该模糊化后的测量电压数据进行反复学习训练,来实现对两相流四种流型的辨识.通过实验仿真,四种流型的平均识别率达到了89.4%,提高了流型识别的准确率.
In the investigation of the two -phase flow measurement, the exact identification of flow regime is the foundation of other parameter exact measurement, therefore, the relatively high rate of flow pattern identification is goal of this study. The research in this paper is based on 12 - electrode resistance imaging system, First, fuzzy clustering is adopted to fuzzy the measurement voltage data of the ERT system, then the fuzzy data is taken as input information of the BP network, the fuzzy data of measure voltage are trained repeatedly in BP network, so the four kinds of two - phase flow regime can be identified. Through the experiment simulation analysis, the four kinds of flow regime＇ s recognition rate is up to 89.4%, veracity of the flow pattern identification is imoroved.
出处
《哈尔滨理工大学学报》
CAS
2008年第6期31-34,共4页
Journal of Harbin University of Science and Technology
基金
国家自然科学基金(60572153)
国家教育部重点科技项目(204043)
黑龙江省重点科技攻关项目(GC05A510)
黑龙江省自然科学基金(F200609)
哈尔滨市重点科技攻关项目(2005AA1CG035)
关键词
电阻层析成像
流型辨识
神经网络
模糊神经网络
electrical resistance tomography, flow pattern, neural network, fuzzy neural network
