Model Based Diagnosis of Multiple Observations with Implicit Hitting Sets

Model based diagnosis finds a growing range of practical applications, and significant performance-wise improvements have been achieved in recent years. Some of these improvements result from formulating the problem with maximum satisfiability (MaxSAT). Whereas recent work focuses on analyzing failing observations separately, it is also the case that in practical settings there may exist many failing observations. This paper first investigates the drawbacks of analyzing failing observations separately. It then shows that existing solutions do not scale for large systems. Finally, the paper proposes a novel approach for diagnosing systems with many failing observations. The proposed approach is based on implicit hitting sets and so is tightly related with the original seminal work on model based diagnosis. The experimental results demonstrate not only the importance of analyzing multiple observations simultaneously, but also the significance of the implicit hitting set approach.