Towards Data Mining and Knowledge Discovery for AECO Applications Using BIM Embedded Data: A Systematic Review

Abstract

With the growth of Building Information Modelling (BIM) applications in the Architecture, Engineering, Construction and Operation (AECO) industry worldwide, a tremendous volume of data has been generated, providing a unique opportunity to extract and utilise valuable information for various purposes. For instance, BIM authoring software usually records details of the design modelling process in log files. Data mining techniques and learning algorithms are utilised to discover knowledge from data and assist stakeholders with various applications such as predicting design commands, project bottleneck diagnosis, progress prediction, and discovering design social networks. This work presents a systematic review of the studies in the field of BIM-embedded knowledge discovery and analyses them from an application-based perspective. As a result, seven major applications of BIM-embedded knowledge were identified. It was revealed that most applications mainly use BIM log files compared to other file formats, which can limit their applicability in other application domains. The K-means algorithm was also deployed to cluster similar features used in the relevant studies. It turned out that Start time, User (ID), Duration, and Command features are the frequently used attributes in BIM knowledge extraction applications. This study demonstrates the use of hidden knowledge in BIM models to enhance team efficiency and data-driven decision-making while also providing insights for researchers on existing applications and potential applications of BIM data mining and knowledge discovery for the AECO industry.