Automated 3D compliance checking in pipe spool fabrication

In pipe spool assemblies used in construction, pre-fabrication errors inevitably occur due to the complexity of the tasks involved in the pipe spool fabrication process, the inaccuracy of the tools employed for performing these tasks, human error, and inadequate inspection and monitoring during the process. Permanent deflections may also occur during shipment and transportation. After delivery at construction sites, defective spools must be detected and further consideration given to the erection of the spools to tolerance levels specified; otherwise, the repair and realignment associated with rework can cause schedule delays and consequent substantial costs increases. This paper presents an automated approach for monitoring and assessing fabricated pipe spools using automated scan-to-BIM registration. Defects are detected through a neighborhood-based Iterative Closest Point (ICP) approach for the registration process. While this technique can be broadly employed, this paper focuses on industrial construction facilities with particular emphasis on pipe spool assemblies. Experiments show that the proposed approach can be employed for the automatic and continual monitoring of such assemblies throughout fabrication, assembly and erection to enable timely detection and characterization of deviations. The main contribution of the work presented in this paper is an automated 3D inspection framework and algorithms for construction assemblies in general and pipe spools in particular.