A novel automatic process for construction progress tracking based on laser scanning for industrial plants

Abstract

As-built modelling has potentials in progress tracking and quality control in industrial plants construction. Although noted work has been conducted, there remain gaps in sophistication of automation and the extent of recognition for semantic information during the process is low. This paper developed a new modelling process for industrial components to fill in these gaps by incorporating 3D object recognition and graph matching techniques. The new process firstly groups the point cloud data of industrial components into geometric primitives. The process is also developed to recognize industrial components by matching connection graph, which is retrieved from geometric primitives, of as-built model with that of as-designed model. Furthermore, the tracking process is able to identify schedule delays by deviation analysis between as-built and as-designed model. A pilot study is carried out and proves that the developed process enables as-built modelling with semantic information and automatic construction progress tracking. Results show that the developed method is promising in saving time and labor cost during construction.