Automated Registration of 3D Point Clouds with 3D CAD Models for Remote Assessment of Staged Fabrication

Modularization and preassembly are parts of a trend toward staged fabrication that has been developing in the construction industry in many parts of the world over the past few decades. Successful delivery and transportation of materials in staged fabrication processes always has been a key challenge. Although substantial advances in modularization and prefabrication have been achieved recently, there is still a significant rate of damages and defects occurring during transportation and shipment. In addition, there are inaccuracies in staged-fabricated assemblies because of manually intensive quality control during the fabrication process. Thus, there is a significant need to monitor the fabrication processes continuously to avoid significant rework costs and delays. This paper presents an automated approach to register laser scanned data, which represents as-built status, with 3D CAD models for prefabricated steel assemblies. Moreover, automated registration enhances 3D tolerance analysis for automated quality control of prefabricated assemblies. An iterative closest point (ICP)-based model is used for automated registration in the presented paper. An experimental study is conducted to validate the proposed model for monitoring the fabrication and installation processes. Experimental results show that the presented approach can be used to detect defected parts or fabrication inaccuracies precisely and quickly.