Knowledge-based Fault Propagation in Building Automation Systems

This paper describes a knowledge-based approach that can reason about effects of faults and causes of abnormal situations in building automation systems (BAS). Combining an ontology-based building information model (BIM), which models a BAS formally and semantically, with rules encoding expert knowledge, the fault propagation approach can automatically determine causalities in BAS and propagate faults along the causalities in both forward and backward direction. This enables an immediate assessment of potential consequences of faults respectively an analysis of the root cause(s). The fault propagation approach can enhance fault detection and diagnosis by considering BAS as a whole, being aware of the potentially far reaching consequences of faults, instead of just focusing on single pieces of equipment or zones. This provides a better understanding of BAS and improves the decision making and prioritization of the right emergency and maintenance actions.