基于BIM与机器学习的建筑智能巡检眼镜研究  

The Search of Intelligent Architectural Inspection Glasses Based on BIM and Machine Learning

作　　者：杨雅钧 石轩潞 唐禧妍 靳晓勇 许镇[1] Yang Yajun;Shi Xuanlu;Tang Xiyan;Jin Xiaoyong;Xu Zhen(University of Science and Technology Beijing,Beijing 100083,China)

机构地区：[1]北京科技大学,北京100083

出　　处：《土木建筑工程信息技术》2022年第1期20-26,共7页Journal of Information Technology in Civil Engineering and Architecture

基　　金：教育部协同育人项目“装配式设计与BIM课程教学融合与改革”;中央高校基本科研业务费(编号:FRF-DF-20-01)。

摘　　要：如今我国BIM行业发展迅速,与人工智能结合应用已成为热门趋势。针对建筑巡检时仪器携带不便,且人工误差难以避免等问题,设计了基于BIM与机器学习的建筑智能巡检眼镜,实现了巡检设备的便携化与自动化。首先基于机器学习对建筑构件图片进行训练,实现构件识别功能;其次通过Dynamo可视化编程快速提取建筑构件信息;最后以树莓派为硬件载体设计建筑智能巡检眼镜,可准确识别建筑构件类型。本文方法可以大幅提升巡检效率,实现BIM技术与人工智能等领域的进一步融合。With the rapid development of BIM industry,the application of BIM combined with artificial intelligence has become a prevalent trend.In order to solve the problems of inconvenient carrying apparatus and unavoidable manual errors in building inspection,intelligent inspection glasses based on BIM and machine learning are designed,which enables the process to be portable and automated.Firstly,building component images are trained based on machine learning to realize component recognition;secondly,information of architectural components should be fetched quickly through the visualization program-Dynamo;finally,Raspberry Pi(RPi)is used to design intelligent inspection glasses,and the detection results can accurately identify the types of building components.This method can not only greatly improve the efficiency of inspection but also make the further integration of BIM technology and artificial intelligence realized.

关 键 词：BIM 机器学习 树莓派 构件信息提取 智能巡检 

分 类 号：TU17[建筑科学—建筑理论]