Automated Extraction of Information from Building Information Models into a Semantic Logic-Based Representation

Abstract

One of the major goals of building information modeling is to support automated compliance checking (ACC). To support ACC, building design information needs to be extracted from building information models (BIMs) and transformed into a representation that would allow for automated reasoning about those design information in combination with information from regulatory documents. However, existing BIM information extraction (IE) efforts are limited in supporting complete automation of ACC. Complete automation of ACC requires (1) automating both the extraction of information from BIMs and the extraction of regulatory information from regulatory documents and (2) aligning the instances of information concepts and relations extracted from a BIM with those extracted from regulatory documents, in order to facilitate direct automated reasoning about both information for compliance assessment. To address this gap, this paper proposes an automated BIM IE method for extracting design information from industry foundation classes (IFC)-based BIMs into a semantic logic-based representation that is aligned with a matching semantic logic-based representation of regulatory information. The proposed BIM IE method utilizes semantic natural language processing (NLP) techniques and java standard data access interface (JSDAI) techniques to automatically extract project information from IFC-based BIMs and transform it into a logic format (logic facts) that is ready to be automatically checked against logicrepresented regulatory rules (logic rules). The BIM IE method was tested on extracting design information from a Duplex Apartment BIM model. Compared to a manually developed gold standard, the testing results showed 100% precision and a short time of 15.02 seconds for processing 38,898 lines of data.