Automated modelling of industrial plants
The cost of modelling existing industrial facilities is currently considered to counteract the benefits
of the model in managing and retrofitting the facility. 90% of the modelling cost is typically spent
on labour for converting point cloud data to the final model, hence reducing the cost is only
possible by automating this step. Previous research has successfully validated methods for
modelling specific object types such as cylinders. Yet modelling is still prohibitively expensive.
During this talk, the most important object types of industrial facilities will be identified by ranking
them according to their frequency of appearance and the man-hours required for modelling in a
state of the art software, EdgeWise. This work is the first to rank objects according to their priority
for automated modelling. These are straight pipes, electrical conduit and circular hollow sections
and constitute more than 80 % of industrial plants on average. This is significant because state-ofthe-
art practice has achieved semi-automated cylinder detection saving 64 % of their manual
modelling time for the case studies investigated. Automated detection and semantic classification
methods for the recognition of the abovementioned objects will be analyzed.