What Makes a Good BIM Design? Quantifying the Link between Design Behavior and Quality
Automation in Construction, 2025
引用方式: Ni, X.R., Pan, P., Lin, J.R.* (2025). What Makes a Good BIM Design? Quantifying the Link between Design Behavior and Quality. Automation in Construction, 171, 105992. doi: 10.1016/j.autcon.2025.105992 http://doi.org/10.1016/j.autcon.2025.105992
摘要
在建筑工程与施工 (AEC) 行业,设计行为如何影响设计质量仍不清楚。本文面向基于建筑信息模型 (BIM) 的设计场景,首次提出了识别并定量描述设计行为与设计质量之间关系的方法。研究首先构建了集成实时采集和日志挖掘的设计行为数据跟踪方法;然后,利用特征工程和各种机器学习模型提取了系列设计行为特征,并结合可解释机器学习构建了有关特征与设计质量的定量关系。结果表明,设计行为与设计质量直接具有清晰的定量关系,且可以被既有机器学习模型高效学习和表征。其中,极端随机树模型表现最佳,在测试集上的R2高达0.88。研究同时揭示了设计师技能水平和设计意图变化相关的行为特征对设计质量具有显著影响。本研究为加深了我们对设计过程的理解,并帮助我们创建更高质量的BIM模型带来了新的启示和方法。
In the Architecture Engineering & Construction (AEC) industry, how design behaviors impact design quality remains unclear. This paper proposes the first approach that identifies and quantitatively describes the relationship between design behaviors and design quality based on Building Information Modeling (BIM). Real-time collection and log mining are integrated to collect raw data on design behaviors. Feature engineering and various machine learning models are then utilized for quantitative modeling and interpretation. Results confirm an existing quantifiable relationship which can be learned by various models. The best-performing model using Extremely Random Trees achieved an R2 value of 0.88 on the test set. Behavioral features related to designer’s skill level and changes of design intentions are identified as having significant impacts on design quality. These findings deepen our understanding of the design process and can help us create BIM designs of better quality.
The authors are grateful for the financial support received from the National Natural Science Foundation of China (No. 52378306).
发表评论