计算机应用与软件2024，Vol.41Issue(5)：177-182,6.DOI:10.3969/j.issn.1000-386x.2024.05.028
多尺度卷积神经网络的电阻层析成像算法
MULTI-SCALE CONVOLUTIONAL NEURAL NETWORK ALGORITHM FOR ELECTRICAL RESISTANCE TOMOGRAPHY
摘要
Abstract
Aimed at the problem of low imaging accuracy of classical algorithms(LBP,Landweber,etc.)for electrical resistance tomography(ERT)in complex flow patterns,an image reconstruction algorithm based on multi-scale convolutional neural network(MS-CNN)for electrical resistance tomography is proposed.According to the characteristics of gas-liquid two-phase flow pattern,a finite element model was built to obtain 20,000 data sets containing"boundary voltage vector-conductivity distribution".On the basis of typical convolutional neural networks Resnet50 and VGG16,MS-CNN for ERT image reconstruction was constructed.The simulation results show that compared with Landweber iterative algorithm and single-scale convolutional neural network algorithm,the ICC of MS-CNN algorithm is improved by 0.715 and 0.023,and the RIE is decreased by 0.812 and 0.057 respectively.The anti-noise test and static test results show that the MS-CNN algorithm has good image reconstruction results and robustness.关键词
卷积神经网络/计量学/电阻层析成像/Landweber/电导率分布Key words
Convolutional neural network/Metrology/Electrical resistance tomography/Landweber/Electrical conductivity distribution分类
信息技术与安全科学引用本文复制引用
仝卫国,曾世超,张立峰..多尺度卷积神经网络的电阻层析成像算法[J].计算机应用与软件,2024,41(5):177-182,6.基金项目
国家自然科学基金项目(61773160). （61773160）
