Modeling Uncertain Temporal Evolutions in Model-Based Diagnosis
This addresses the challenge of model-based diagnosis for dynamic systems in practical applications, representing an incremental advancement by applying reliability theory assumptions to temporal diagnosis.
The paper tackles the problem of diagnosing time-varying systems with uncertain temporal evolutions by proposing a novel approach using Markov chains to model probabilistic temporal knowledge, and shows how to discard very unlikely diagnoses in the diagnostic process.
Although the notion of diagnostic problem has been extensively investigated in the context of static systems, in most practical applications the behavior of the modeled system is significantly variable during time. The goal of the paper is to propose a novel approach to the modeling of uncertainty about temporal evolutions of time-varying systems and a characterization of model-based temporal diagnosis. Since in most real world cases knowledge about the temporal evolution of the system to be diagnosed is uncertain, we consider the case when probabilistic temporal knowledge is available for each component of the system and we choose to model it by means of Markov chains. In fact, we aim at exploiting the statistical assumptions underlying reliability theory in the context of the diagnosis of timevarying systems. We finally show how to exploit Markov chain theory in order to discard, in the diagnostic process, very unlikely diagnoses.