Online Monitoring of Hybrid Systems Using Imprecise Models

Abstract This paper presents a model-based monitoring system which is based on imprecise models where the structure is known and the parameters may be imprecisely specified by numerical intervals. This monitoring approach is applied to hybrid systems and is now able (i) to follow a known sequence of imprecisely modeled modes, (ii) to detect unknown transitions and (iii) to refine the time uncertainty of the transitions as well as the imprecision of mode models. The implemented system is demonstrated by online monitoring of a non-trivial heating system.