Automated Generation of Steel Connections of BIM by Machine Learning

The recent use of building information modeling (BIM) has made available a significant amount of digital data in the construction industry. This makes possible the use of machine learning techniques in the BIM field. However,... [ view full abstract ]

The recent use of building information modeling (BIM) has made available a significant amount of digital data in the construction industry. This makes possible the use of machine learning techniques in the BIM field. However, this use remains rare.

Here, we investigate which machine learning techniques are best suited for improving the efficiency of BIM in steel connection design. From this analysis, we produced a new toolkit for the automatic detection of structural connections between members. The toolkit consists of modules developed in C# and Python, with the machine learning module being implemented using the latter.

For this module, we applied the k-nearest neighbors (k-NN) algorithm to a training set consisting of BIM models. By creating a training set from finished models, we find that it is possible to predict and automatically insert valid structural connections in new BIM models. Overall, our findings suggest that our methodology promises to be of significant assistance in improving present methods of generating steel connections in building design.