Page 82 - 无损检测2024年第八期
P. 82
试验研究
试验研究
DOI:10.11973/wsjc202408009
基于机器视觉的装配式建筑混凝土结构损伤检测
王 晨
(无锡市建筑工程质量检测中心,无锡 214028)
摘 要:随着装配式建筑的普及,现有混凝土结构损伤检测方法容易受到噪声环境影响的问题
亟待解决,设计了一套基于机器视觉的装配式建筑混凝土结构损伤检测方法。该机器视觉采集装
置由机器视觉工具(由图像采集卡、CCD摄像头构成)和爬壁机器人构成,将机器视觉工具搭载在
爬壁机器人上完成图像采集。首先,使用加权平均法对采集的图像实施灰度化处理,使用阈值滤波
法实施灰度图像的滤波处理;其次采用由快速区域卷积神经网络Fast R-CNN与区域推荐网络RPN
组成的Faster R-CNN模型实现混凝土结构损伤检测。试验结果表明,该方法在噪声环境下能够实
现有污渍混凝土表面、阴影混凝土表面、粗糙混凝土表面的准确结构损伤检测,检测系统的鲁棒性
较强。
关键词:面阵CCD摄像机;机器视觉;装配式建筑混凝土;结构损伤检测
中图分类号:TP399;TG115.28 文献标志码:A 文章编号:1000-6656(2024)08-0048-06
Damage detection for prefabricated building concrete structures based on machine vision
WANG Chen
(Wuxi Inspection Center of Architectural Quality, Wuxi 214028, China)
Abstract: With the popularization of prefabricated buildings, the existing damage detection methods for concrete
structures are easily affected by noise environment, which is an urgent problem to be solved. Therefore, a machine vision-
based damage detection method for prefabricated concrete structures was designed. The machine vision acquisition device
consisted of machine vision tools including image acquisition cards and CCD cameras and a wall climbing robot. The
machine vision tools were mounted on the wall climbing robot to achieve image acquisition. Firstly, the collected images
were grayscale processed using the weighted average method, and the grayscale images were filtered using the threshold
filtering method; Secondly, the Faster R-CNN model consisting of Fast Regional Convolutional Neural Network and
Regional Recommendation Network (RPN) was used to achieve damage detection in concrete structures. The experimental
results showed that this method can achieve accurate structural damage detection of stained concrete surfaces, shaded
concrete surfaces, and rough concrete surfaces in noisy environments, and the detection results were robust.
Key words: area CCD camera; machine vision; prefabricated building concrete; structural damage detection
传统的建筑方式由于其高能耗、高污染和高成 污染。然而,随着装配式建筑的广泛应用,混凝土结
本的特点,已无法满足社会和经济的发展需求,因此 构的损伤问题逐渐凸显出来。因此,装配式建筑混
装配式建筑应运而生。装配式指将建筑物的某些部 凝土结构的损伤检测成为了一个重要的研究课题。
分在工厂预制,然后在施工现场进行组装 。这种 目前,国外关于建筑混凝土结构损伤检测的研
[1]
方式能够显著提高建筑效率,降低能耗和减少环境 究已经取得了很大进展。MOUSAVI等 提出了一
[2]
种基于自适应噪声经验模态分解的结构损伤检测方
收稿日期:2024-01-03
法,采用经验模态分解和自适应噪声技术,从固有
作者简介:王 晨(1976—),男,本科,高级工程师,主要研究方
模态函数中提取能量、瞬时振幅、解包裹相位和瞬
向为建筑材料检测、轨道交通检测、建筑结构鉴定
通信作者:王 晨,ctionin@163.com 时频率等4个关键特征,对损伤进行定位、量化和检
48
2024 年 第 46 卷 第 8 期
无损检测

