FDD-ON: A New Ontology for VAV HVAC Fault Detection and Diagnostics
The recently created ontology, known as FDD-ON, aims to systematically represent components of variable air volume (VAV) HVAC systems, including fault types, symptom statuses, fault impacts, and relevant attributes. This modular and extensible ontology is intended to connect various data sources, equipment types, and diagnostic outputs within the fault detection and diagnosis (FDD) field. A paper detailing this work is available on arXiv (ID: 2607.29657), which discusses the fragmented information silos that obstruct the adoption of FDD and related technologies, such as AI-driven maintenance systems and digital twin-enabled FDD frameworks. FDD-ON seeks to enhance data interpretability and interoperability, ultimately improving HVAC system reliability, energy efficiency, and maintenance effectiveness. The necessity for structured domain knowledge to facilitate FDD solution implementation in buildings is also highlighted.
Key facts
- FDD-ON is a modular and extensible ontology for VAV HVAC systems.
- It formally represents components, fault types, symptom statuses, fault impacts, and attributes.
- The ontology addresses data interpretability and interoperability in the FDD domain.
- It aims to bridge heterogeneous data sources and diverse equipment types.
- The paper is available on arXiv with ID 2607.29657.
- FDD-ON supports digital twin-enabled FDD frameworks and AI-driven maintenance.
- The work targets improving HVAC reliability, energy efficiency, and maintenance.
- The paper discusses fragmented information silos hindering FDD implementation.
Entities
Institutions
- arXiv