Hybrid AI for smart building management
HVAC & building management systems are very complex and often contain configuration errors. There is often little budget for extensive testing during start-up phase nor for operational monitoring and optimization. Current systems also contain no personalization, nor incorporation of building dweller preferences/needs.
The goal of this project is:
- to bring all relevant building data (e.g. BIM models, environmental sensor data, user preferences & feedback, etc.) together in a seamless fashion through semantic technologies
- apply and combine data-driven and knowledge-driven AI techniques to extract as much knowledge as possible from the data to provide insights for facility management and dwellers
- optimize building management combining generic objectives (e.g. general comfort & energy efficiency) and individual dweller objectives (e.g. personal preferences regarding temperature)
This project is a collaboration between IDLab Ghent University-imec, IDLab UAntwerp-imec, and imec.