Ontology-based automatic setup of virtual sensors in building automation systems

Abstract

Effective monitoring, fault detection and diagnostics (FDD) of building automation systems require a large number of datapoints. But the set of available sensors in a building is typically limited. Virtual sensors (VS) can be applied as cost saving alternative to real sensors. Implementing and setting up VS however can be a complex tasks that urgently needs to be automated. A novel approach for computer-aided, automatic setup of VS is presented. It is based on reusing generic, pre-implemented VS algorithms. Using OWL, the characteristics, requirements and configuration of the VS algorithms are specified in a machine-interpretable way. By that, the approach can match the specific characteristics and requirements of the VS algorithms in a formal evaluation process with the specific circumstances in the BAS, which are described in an ontology-based building information model (BIM). All applicable VS algorithms can be determined and subsequently configured to the individual characteristics of the BAS.