Automatic BIM Model Auditing for Quantity Take-off Using Knowledge Graph Techniques

Abstract

Building Information Modeling (BIM) models require sufficient semantic information and consistent modeling style to conduct Quantity Take-off (QTO) smoothly. However, BIM models created by different BIM modelers may have various mistakes about these requirements and auditing such BIM model behavior involves tremendous human effort for manual inspection or the development of rule sets. This study proposes an automatic and efficient BIM model auditing framework for QTO utilizing knowledge graph (KG) techniques. It begins at establishing a BIM-KG definition via identifying required information for auditing purposes. Subsequently, BIM data is automatically transformed into the BIM-KG representations, the embeddings of which are trained using a knowledge graph embedding model. Automatic mechanisms are then developed to utilize the computable embeddings to effectively identify mistake BIM elements. The framework is validated using illustrative examples and the results show that 100% mistake elements can be identified successfully without human intervention.