BIM-to-BRICK: Using graph modeling for IoT/BMS and spatial semantic data interoperability within digital data models of buildings

TL;DR

This paper introduces BIM-to-BRICK, an automated method that converts building information models into semantic knowledge graphs, enhancing data interoperability across IoT, BMS, and spatial data in buildings.

Contribution

It presents a novel automated approach to integrate BIM data into BRICK-based knowledge graphs, reducing manual effort and improving interoperability.

Findings

Generated 458 BRICK objects and 1219 relationships in 17 seconds

Automated data integration outperforms manual mapping efforts

Demonstrated on the SDE4 building in Singapore

Abstract

The holistic management of a building requires data from heterogeneous sources such as building management systems (BMS), Internet-of-Things (IoT) sensor networks, and building information models. Data interoperability is a key component to eliminate silos of information, and using semantic web technologies like the BRICK schema, an effort to standardize semantic descriptions of the physical, logical, and virtual assets in buildings and the relationships between them, is a suitable approach. However, current data integration processes can involve significant manual interventions. This paper presents a methodology to automatically collect, assemble, and integrate information from a building information model to a knowledge graph. The resulting application, called BIM-to-BRICK, is run on the SDE4 building located in Singapore. BIM-to-BRICK generated a bidirectional link between a BIM model of 932 instances and experimental data collected for 17 subjects into 458 BRICK objects and 1219 relationships in 17 seconds. The automation of this approach can be compared to traditional manual mapping of data types. This scientific innovation incentivizes the convergence of disparate data types and structures in built-environment applications.