AI based BIM Studies For Pipelines
Piping system takes an important place in the architecture, engineering, and construction (AEC), as well as operation and maintenance (O&M) with many industries including petrochemical business. To leverage Building Information Modeling (BIM) for efficient OM, as-built BIM is needed for plants.
Modeling of the as-built BIM is currently practiced in a manual and tedious way, requiring a considerable amount of time and effort even for a skilled modeler. We proposes a solution that automatically reconstructs the as-built BIM of piping systems from point cloud data generated via LiDAR scanning in two stages. AI deep learning method is developed to reconstruct pipe system. The output is converted to the Industry Foundation Classes format. The solution is validated on both synthetic and actual scan data, and the results demonstrate its robustness, fast speed, and accuracy.