Automatic Recognition of Piping System From Large-Scale Terrestrial Laser Scan Data

Abstract

ABSTRACT:Recently, changes in plant equipment have been becoming more frequent because of the short lifetime of the products, and constructing 3D shape models of existing plants (as-built models) from large-scale laser scanned data is expected to make their rebuilding processes more efficient. However, the laser scanned data of the existing plant has massive points, captures tangled objects and includes a large amount of noises, so that the manual reconstruction of a 3D model is very time-consuming and costs a lot. Piping systems especially, account for the greatest proportion of plant equipment. Therefore, the purpose of this research was to propose an algorithm which can automatically recognize a piping system from terrestrial laser scan data of the plant equipment. The straight portion of pipes, connecting parts and connection relationship of the piping system can be recognized in this algorithm. Eigenvalue analysis of the point clouds and of the normal vectors allows for the recognition. Using only point clouds, the recognition algorithm can be applied to registered point clouds and can be performed in a fully automatic way. The preliminary results of the recognition for large-scale scanned data from an oil rig plant have shown the effectiveness of the algorithm.

Study of the Precise Determination of Pipeline Geometries Using UAV Scanning Compared to Terrestrial Scanning, Aerial Scanning and UAV Photogrammetry

“…These displacements are measured using various technologies. One of them is terrestrial laser scanning, which allows one to survey the object with a high accuracy [1][2][3]. The redundancy of TLS scanning data makes it a reliable source of information for deformation analyses, but on the other hand, due to the large spatial extent of the objects, it is both uneconomical and time-consuming [4].…”

A method for modeling selected elements of a building based on the data from terrestrial laser scanning

“…In the modeling process, a variety of tools are used, made available in the software, for processing the product obtained from the TLS measurements, in other words, the point clouds [Fidera et al 2004]. Also, the functions developed for modeling are applied, in software such as MicroStation or AutoCAD [Rabbani et al 2011] and more specialized algorithms for 3D modeling [Kawashima et al 2011]. The modeling of buildings in three-dimensional space is a labour-intensive process, but to a large extent it depends on the complexity of the architectural object in question.…”

Automated pipeline extraction for modeling from laserscanned data

“…Therefore, 3D as-built pipeline models can be used for maintenance and operation phases and expansion or modification of existing plants 5,10,11 . For example, by using 3D asbuilt pipeline models for planning, expansion, and modification of existing plants, collisions between equipment can be detected 3,7 . During the maintenance and operation phase, 3D as-built pipeline models can be used for efficient inspection and part replacement 11 .…”

“…After extraction of laser-scanned data corresponding to each pipeline, the user generates asbuilt pipeline models by using some functions in commercial software. However, manually identifying each pipeline is nearly impossible and is a very timeconsuming and labor-intensive process because the laser-scanned data of the plant is huge and includes other objects such as structural components, containers, and equipment; the pipelines are also intricately entwined like a net 3,7,10 . Thus, to efficiently generate 3D as-built pipeline models, automated pipeline extraction must be performed.…”