A predictive model for estimating formwork and shoring removal time

The challenge of estimating the removal time of formwork and shoring has considerable effect on the overall cost and duration of construction work. In today’s construction practice it is customary to take field-cured samples and test them in laboratories to determine the concrete strength which then can be used to make decisions on whether to commence stripping of formwork and shoring. This process is not only time-consuming, but the samples taken may not represent the actual concrete structure. This leads to cost overruns and longer construction schedules.This research explores two types of machine learning (ML) models to estimate formwork and shoring removal time. The models were built by analyzing 749 concrete mixture data. Random Forest and Deep Neural models have been trained and tested on new data. Their respective outcomes were evaluated and assessed to choose a superior model.The results from the two models showed that form removal time can be predicted using the proposed ML models. The superior model was then used to develop a decision support tool that is easily accessible via the web. This web-based application will enable contractors, project managers, and engineers to estimate the formwork and shoring removal time in advance which will fast-track the construction scheduling process and reduce costs of the project by increasing reusability of forming and shoring material.