Scaffolding progress monitoring of LNG plant maintenance project using BIM and image processing technologies

Scaffolding tasks are the most significant workitems in Liquefied Nature Gas (LNG) plant maintenance projects and an effective progress monitoring approach can be beneficial to stakeholders through the better control to the budget and schedule of the entire project. This research is focused on discussing findings and lesson learnt from the scaffolding progress monitoring case study of a LNG plant maintenance project. A novel approach by using Building Information Modelling (BIM) and image processing technologies to automatically estimate scaffolding progress through site photos is being developing. The case study by adopting the developing approach at a real LNG plant is currently carried on. The collected scaffolding photos have been used to iteratively improve the developing approach. The plan of the case execution is outlined and introduced in the paper including the development of an image recognition algorithm for scaffolding progress estimations and a Navisworks plug-in for productivity analysis in terms of cost and schedule. By going through site data collections, observations, data analysis and discussions with related contractors and the operator at site, the feasibility of the approach adoption and related implementation issues are identified. The feedback from industry partners can be summarized into five perspectives: (1) the complexity of scaffolding structure affects the performance of the proposed recognition algorithm a lot; (2) the proposed approach is considered reliable if the average accuracy of the progress estimation can be slightly higher than that of the conventional way; (3) a guideline for data collection process is necessary; (4) reduce site work and shift the work load back to the office is preferred and; (5) the proposed approach benefits implementation contractors the most. It is expected that these findings among the ongoing study can further adjust the development direction and identify following studies for the proposed approach in the future.