摘要
两相流体具有复杂性的流动特性,图像重建的精度是两相流参数准确测量的基础。针对电阻层析成像系统存在的软场特性、强非线性和不适定性,使得重建的图像质量差、计算时间长等问题,基于代数运算的神经网络,给出了一种基于代数神经网络电阻层析成像图像重建算法。该算法通过建立代数神经网络,以测量的边界电压值作为神经网络的输入,将图像重建转变为一个严格对角占优的线性方程组的求解问题,以达到图像快速、准确的重建目的。通过实验仿真分析,该方法具有收敛速度快、代价低和误差小等特点。
Two-phase fluid has complex flow characteristic and the accurate identification of flow regime is the basis of the accurate measurement of two-phase flow＇s parameter.There are still many defects such as low reconstruction quality and low recon- struction speed in image reconstryction algorithm because of soft field characteristic, strong nonlinear and ill-posedness of electrical resistance tomography.This paper puts forward a new image reconstruction algorithm for ERT based on algebraic neural net- work.This algorithm transforms image reconstruction into a problem of solving strictly diagonal-dominant linear equations.Through the simulation experiment analysis,this method has characteristics such as fast convergence,low cost and small error.
出处
《计算机工程与应用》
CSCD
北大核心
2009年第32期19-21,共3页
Computer Engineering and Applications
基金
国家自然科学基金No.60572153
高等院校博士学科点专项科研基金No.200802140001
国家教育部春晖计划No.Z2007-1-15013
黑龙江省自然科学基金No.F200609~~
关键词
电阻层析成像
两相流
图像重建算法
代数神经网络
Electrical Resistance Tomography（ERT）
two phase flow
image reconstruction algorithm
algebraic neural network
