Development of a prefabricated construction productivity estimation model through BIM and data augmentation processes

The accuracy of productivity estimates remains a significant challenge due to limited data avail-ability. This research addresses the need for precise productivity estimation in construction byintegrating data augmentation techniques, onsite time study data, and Building InformationModeling (BIM) for automated quantity take-offs and design complexity analysis of steel connec-tions. By examining design complexity, the method provides productivity estimates for projectzones, sequences, and individual components, improving overall production management. Fourdata augmentation techniques—normal noise, interpolation, clustering, and Bayesian LinearRegression—were evaluated to enhance time study data. The augmented dataset was used totrain an Artificial Neural Network, validated through case studies. The study identified the nor-mal noise method as the most effective, significantly improving time estimation accuracy.Specifically, the proposed approach yielded a 58%–71% enhancement over current industry esti-mates and a 2.1%–31.1% improvement compared to models without data augmentation. Thisresearch enables managers to optimize resource allocation and reduce potential project delays.