Beyond Dynamic Bayesian Networks: Fusing Temporal Logic Monitors with Probabilistic Diagnosis (Short Paper)

Conventional diagnostic systems often fail to account for temporal dynamics - such as duration, frequency, or sequence of events - which are critical for accurate fault assessment. Existing solutions that model time, like Dynamic Bayesian Networks (DBNs), typically suffer from computational complexity and scalability issues. This paper introduces a hybrid diagnostic architecture that integrates a standard Bayesian Networks (BNs) with a powerful temporal reasoner R2U2 (Realizable Responsive Unobtrusive Unit). By decoupling temporal logic from probabilistic inference, our approach allows the specialized R2U2 engine to efficiently process complex time-dependent conditions and provide nuanced inputs to the BNs. The result is a more scalable, flexible, and robust framework for diagnosing failures in systems where temporal behavior is a key factor. The paper will detail this architecture, its generation from system models, and demonstrate its capabilities using a UAV electric powertrain example.