摘要
BIM与人工智能相融合可以充分发挥各种技术的优势,深度挖掘工程数据信息,实现"1+1> 2"的功能效果。为此以文献调研为基础,对BIM在工程项目中的研究情况进行分析,综述了BIM与传统人工智能技术以及深度神经网络相融合可解决的问题类型、实现的功能以及应用情况。结果表明:BIM与遗传算法、推理技术、浅层神经网络等传统的人工智能技术相融合可解决多目标优化、搜索、规则检查、事件决策以及预测问题,实现设计方案的合理选择与检查优化、成本管理、施工进度与质量管理、能耗管理、风险与安全管理、自动控制以及辅助决策;与深度神经网络相融合可解决预测以及图像识别问题,实现施工安全与风险管理、设施管理。同时针对存在的人工智能技术不完善、技术的选择不合理、数据接入以及共享问题等提出相关建议,并对其未来发展方向进行展望。
The advantages of various technologies can be brought into full play,the engineering data information can be deeply explored,and the functional effect of "1 + 1 > 2"is able to be realized with the integration of BIM and artificial intelligence.To this end,the research of BIM in engineering projects was analyzed based on literature research,and the types of problems that can be solved,the functions achieved and the applications by the integration of BIM with traditional artificial intelligence technology and deep neural networks were summarized.The results show that with the integration of BIM and traditional artificial intelligence technologies such as genetic algorithms, inference techniques, and shallow neural networks, multi-objective optimization, search, rule checking,event decision-making,and prediction problems can be solved,and the reasonable selection and inspection optimization of design scheme,cost management,construction progress and quality management,energy consumption management,risk and safety management,automatic control can be realized.With the integration of BIM and deep neural networks,prediction and image recognition problems can be solved,construction safety and risk management,as well as facility management can be realized.Moreover,relevant suggestions for the existing imperfect artificial intelligence technology,unreasonable technology selection,data access and sharing issues were proposed,and its future development direction was prospected.
作者
盖彤彤
于德湖
孙宝娣
杨淑娟
GAI Tongtong;YU Dehu;SUN Baodi;YANG Shujuan(School of Civil Engineering,Qingdao University of Technology,Qingdao 266033,Shandong,China;Cooperative Innovation Center of Engineering Construction and Safety in Shandong Blue Economic Zone,Qingdao University of Technology,Qingdao 266033,Shandong,China)
出处
《建筑科学》
CSCD
北大核心
2020年第6期119-126,共8页
Building Science
基金
山东省重点研发计划项目“基于数字流域的水生态时空大数据平台系统建设及应用”(2019GGX101013)。
关键词
BIM
人工智能
神经网络
融合应用
研究进展
building information model (BIM)
artificial intelligence
neural networks
fusion application
research progress
