基于计算机视觉的预制墙板临时支撑安全合规性检查  

Computer Vision-Based Safety Compliance Checking for the Temporary Support of Precast Walls

作　　者：孙亚康 郭红领[1] 罗柱邦 张智慧[1] SUN Ya-kang;GUO Hong-ling;LUO Zhu-bang;ZHANG Zhi-hui(Department of Construction Management,Tsinghua University,Beijing 100084,China)

机构地区：[1]清华大学建设管理系,北京100084

出　　处：《工程管理学报》2022年第3期97-101,共5页Journal of Engineering Management

基　　金：国家自然科学基金面上项目(51578318)。

摘　　要：预制构件安装过程中临时支撑的安全合规性对装配式施工安全至关重要,对其进行自动检查并辅助施工安全监控具有重要意义。以最为常见且具有代表性的预制混凝土墙板为例,利用YOLO-v5网络构建了预制墙板及其临时支撑的自动识别模型,进而提出了预制墙板临时支撑的安全合规性自动检查方法。测试结果表明,该识别模型的平均精度均值达到95.3%,在充分考虑施工现场不利因素情况下检查方法的准确率达到70.7%,证实了该方法的有效性和可行性。这不仅可以提升预制墙板安装的安全性,而且还可为其他类型预制构件安装的合规性检查提供参考。The safety compliance of temporary supports during the erection of prefabricated components is of importance to prefabricated construction,it’s quite meaningful to carry out automatic checking of the compliance and assist construction safety monitoring.Taking commonly-seen and representative precast concrete walls as an example,this research establishes an object detection model for precast walls and relevant temporary supports based on YOLO-v5 network,and further proposes an automated safety compliance checking method for the temporary support of precast walls.It is shown from a test that the mean Average Precision(m AP)of the detection model is up to 95.3%,and the accuracy of the checking method is 70.7% under a harsh construction environment,showing the validity and feasibility of the proposed method.This research,thus,not only improve the safety level of the erection of precast walls,but also provide a reference for the safety compliance checking of other precast components.

关 键 词：预制墙板 临时支撑 安全合规性检查 计算机视觉 

分 类 号：TU712.3[建筑科学—建筑技术科学]