An international conference connecting people
in CAD research, education and business
Copyright (C) CAD Solutions, LLC. All rights reserved.
Proceedings of CAD'17, 2017, 201-206
Parametric Comparing for Local Inspection of Industrial Plants by Using As-built Model Acquired from Laser Scan Data
Abstract. Owing to the development of technology, industrial plants have become increasingly more complex, often including hundreds of thousands of components; therefore, performing inspection jobs has become more difficult in terms of both as-built inspection and maintenance. Laser scan measurement devices with the accuracy up to 1 cm provide a feasible solution which is fast and reliable; however, the number of studies undertaken in this field is very limited. Although the approach may differ, most methods that utilize laser scan data for inspecting as-built plants follow a general process as shown in Fig. 1. Because the as-built data acquired from laser scan devices is a 3D point cloud, a processing step is required to extract needed information for the inspection process. Several algorithms are available for this process, including the Random Sample Consensus (RANSAC)-based method, the Skeleton-based method and the normal-based region growing method. These methods are efficient and were validated by many test cases; however, they are limited in their application to real inspection problems. Although the inspection process step is crucial, only a few studies have been conducted in this field. The most common approach is the Iterative Closest Point (ICP)-based method.
Keywords. Parametric Comparing, Point Cloud Processing, Local Inspection