基于深度学习的阵列相位误差校正策略分析  

Analysis of Array Phase Error Correction Strategy Based on Deep Learning

作　　者：徐振刚 杨代虎 项兆佳 赵寒琼 谭江龙 张利 XU Zhengang;YANG Daihu;XIANG Zhaojia;ZHAO Hanqiong;TAN Jianglong;ZHANG Li(School of Big Data and Information Engineering,Guizhou University,Guizhou 550025,China)

机构地区：[1]贵州大学大数据与信息工程学院,贵州550025

出　　处：《集成电路应用》2024年第11期80-81,共2页Application of IC

摘　　要：阐述针对阵列观测时相位误差的问题,在Strip-former模型基础上,融合多个Selective Kernel(SK)块单元堆叠成的selective Kernel Networks(SKNets),用于消除相位误差引起的通量误差与成像伪影。This paper describes the issue of phase error in array observation.Based on the Stripe former model,it integrates multiple Selective Kernel(SK)block units stacked into a Selective Kernel Network(SKNets)to eliminate flux errors and imaging artifacts caused by phase errors.

关 键 词：深度学习 块单元堆叠 相位误差 成像伪影 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]