Using Machine Learning to Enhance Design Evaluation and Rule Compliance**

使用机器学习增强设计评估和规则合规性**

• 批准号: 536355-2018
• 负责人: ElDiraby, Tamer
• 金额: $ 1.82万
• 依托单位: University of Toronto
• 依托单位国家: 加拿大
• 项目类别: Engage Grants Program
• 财政年份: 2018
• 资助国家: 加拿大
• 起止时间: 2018-01-01 至 2019-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=650034
• 关键词: Using; Machine; Learning; Enhance; Design

This project aims to synthesize best practices in using BIM-based automated code checking in other countries; and develop a model and roadmap for its implementation by Canadian AEC companies. The aim is not just to deploy rule-based system on top of BIM. Rather, study how the implementation of machine learning in checking the rules can create an analytics layer on top of BIM. In other words, as the new system checks for rules, it detects patterns and learns from repeated use.

该项目旨在综合其他国家使用基于BIM的自动代码检查的最佳实践，并为加拿大AEC公司的实施制定模型和路线图。我们的目标不仅仅是在BIM之上部署基于规则的系统。相反，研究机器学习在检查规则时的实现如何在BIM之上创建分析层。换句话说，当新系统检查规则时，它会检测模式并从重复使用中学习。