CLOI: An Automated Benchmark Framework for Generating Geometric Digital Twins of Industrial Facilities

This paper devised, implemented, and benchmarked a novel framework, named CLOI, that can generate accurate individual labelled point clusters of the most important shapes of existing industrial facilities with minimal manual effort in a generic point-level format. CLOI employs a combination of deep learning and geometric methods to segment the points into classes and individual instances. The current geometric digital twin generation from point cloud data in commercial software is a tedious, manual process. Experiments with our CLOI framework revealed that the method reliably can segment complex and incomplete point clouds of industrial facilities, yielding 82% class segmentation accuracy. Compared with the current state of practice, the proposed framework can realize estimated time-savings of 30% on average. CLOI is the first framework of its kind to have achieved geometric digital twinning for the most important objects of industrial factories. It provides the foundation for further research on the generation of semantically enriched digital twins of the built environment. (C) 2021 American Society of Civil Engineers.

Automated summary

The CLOI framework generates accurate individual labeled point clusters of the most important shapes in existing industrial facilities with minimal manual effort. It uses deep learning and geometric methods to segment points and instances, achieving 82% class segmentation accuracy and estimated time savings of 30% compared to current practices. CLOI is the first framework of its kind to achieve geometric digital twinning for important objects in industrial factories, laying the foundation for further research in semantically enriched digital twins.