Development of FDD-ON: an Ontology for VAV HVAC System Fault Detection and Diagnostics
A paper published on arXiv on 2026-07-31 presents FDD-ON, a modular and extensible ontology for formally representing variable air volume (VAV) HVAC system components, fault types, symptom statuses, fault impacts, and associated attributes. The ontology integrates HVAC system FDD semantics and provides fault, symptom, and impact libraries to capture operational abnormalities.
Fault detection and diagnosis (FDD) technology is essential for improving HVAC system reliability, energy efficiency, and maintenance effectiveness. However, effective deployment of FDD solutions in buildings requires structured domain knowledge that can bridge heterogeneous data sources, diverse equipment types, and varied diagnostic outputs. Limited data interpretability and interoperability within the FDD domain have led to fragmented information silos, hindering the implementation of FDD and related applications, such as digital twin-enabled FDD frameworks and AI-driven maintenance decision-making systems. This paper presents FDD-ON, a modular and extensible ontology to formally represent VAV HVAC system components, fault types, symptom statuses, fault impacts and associated attributes. FDD-ON integrates HVAC system FDD semantics to provide comprehensive representations of fault and symptom attributes, supported by a well-defined controlled vocabulary. Additionally, FDD-ON offers comprehensive fault, symptom, and impact libraries to capture a broad spectrum of operational abnormalities and their consequences.
FDD-ON uses a modular ontology design to formally represent VAV HVAC components, faults, symptoms, and impacts, enabling semantic interoperability across heterogeneous building data. The ontology includes controlled vocabularies and comprehensive libraries that can be extended to other HVAC systems, potentially improving the accuracy and scalability of AI-driven FDD and digital twin applications.
The development of FDD-ON addresses a key barrier to widespread FDD adoption in commercial buildings: the lack of standardized, machine-readable knowledge representation. By enabling better data integration, this ontology could accelerate the deployment of AI-based maintenance and energy optimization solutions in the building management industry.
FDD-ON can reduce the cost and complexity of implementing FDD solutions by providing a common semantic framework, potentially lowering integration costs for building owners and technology vendors. It may also enable new AI-driven predictive maintenance services and improve energy efficiency, leading to operational savings.
Next signals to watch include the adoption of FDD-ON in building management systems (BMS) or digital twin platforms, integration with existing FDD tools, and extensions to other HVAC equipment types beyond VAV systems. Further validation through real-world case studies and alignment with industry standards like Brick or Project Haystack would indicate progress toward commercialization.