李晓峰,周峰等,机电学院,Computer-Aided Civil and Infrastructure Engineering (2021),Deep learningbased nondestructive evaluation of reinforcement bars using ground‐penetrating radar and electromagnetic induction data

发布人:徐红发表时间:2021-12-08点击:

近日,我院周峰副教授团队在土木工程领域顶级期刊《Computer-Aided Civil and Infrastructure Engineering》上在线发表了题为《Deep learning-based nondestructive evaluation of reinforcement bars using ground-penetrating radar and electromagnetic induction data》的论文。硕士研究生李晓峰为该文章的第一作者,周峰副教授为通信作者,其他合作作者分别来自广州大学土木学校、英国阿伯丁大学地球科学学院和荷兰代尔夫特理工大学土木与地球科学学院。根据Clarivate Analytics2020年的期刊索引报告,《Computer-Aided Civil and Infrastructure Engineering》期刊在各领域的排名如下:2/112 (Computer Science, Interdisciplinary Applications)1/67 (Construction & Building Technology)1/137 (Engineering Civil), 1/38 (Transportation Science & Technology),年均发文量仅100篇左右,最新影响因子为11.775

该文章针对工程验收阶段的混凝土钢筋无损检测精度不高、评估误差较大的问题,提出使用探地雷达和电磁感应进行同步数据采集和信息融合,同时采用基于深度学习的算法对多源电磁数据进行自动信息处理和解释,实验结果表明该方法在无先验信息的情况下可以同时对钢筋的保护层厚度和直径实现1毫米精度的无损评估,无论从检测精度和检测效率上均高于现有的无损检测方法。

该项研究成果受到国家自然科学基金项目资助。

论文信息:

Title: Deep learning-based nondestructive evaluation of reinforcement bars using ground-penetrating radar and electromagnetic induction data

Authors: Xiaofeng Li, Hai Liu, Feng Zhou, Zhongchang Chen, Iraklis Giannakis, Evert Slob

Source: Computer-Aided Civil and Infrastructure Engineering

DOI: 10.1111/mice.12798

Published online: 27 November 2021