Using a Systems-Centric Knowledge Graph to support Facility Maintenance

Throughout an asset's lifecycle, rates of early failure, random failure, and wear-out failure underscore the need for robust maintenance strategies, including Corrective, Preventive, and Predictive approaches. Even though the use of BIM has increased in recent years in the field of facility maintenance and management, the BIM technology is not utilized to its full potential to make the facility management more proactive and cost efficient. While existing research focused on developing systems-centric FM-Capable BIMs, there are limitations in how the data is stored and accessed. Existing research also shows that access to the right data at the right time is very crucial for proactive maintenance decision making and cost management. The literature review of recent efforts uncovered gaps in research regarding the utilization of knowledge graphs for facility management. This research presents a novel approach to represent Building Information Modeling (BIM) data as a systems-centric knowledge graph. This systems-centric knowledge graph enhances facility management by facilitating efficient queries for maintenance and emergency scenarios. To validate the utilization of knowledge graphs for systems-centric searches, authors selected a case study as a mechanical zone of an elementary school building. To create the knowledge graph of the case study, authors divided the systems in the zone into subsystems and developed small component knowledge graphs for each subsystem. Later all the component graphs were merged to create a federated knowledge graph of the selected zone. This process allowed authors to create the knowledge graph without complications and helped in quality control by eliminating any input errors. The developed knowledge graph was queried for various emergency scenarios developed based on the discussions with FM staff. The queried results were highlighted in the Navisworks 3D model to display. This research implementation offers practical implications for facility managers, emphasizing the potential for further advancements in Digital Twin development.