Pervasive diagnosis: the integration of diagnostic goals into production plans

Abstract

In model-based control, a planner uses a system description to create a plan that achieves production goals (Fikes & Nilsson 1971). The same description can be used by model-based diagnosis to infer the condition of components in a system from partially informative sensors. Prior work has demonstrated that diagnosis can be used to adapt the con-trol of a system to changes in its components. However diagnosis must either make inferences from passive obser-vations of production, or production must be halted to take diagnostic actions. We observe that the declarative nature of model-based control allows the planner to achieve pro-duction goals in multiple ways. This flexibility can be ex-ploited with a novel paradigm we call pervasive diagnosis which produces diagnostic production plans that simultane-ously achieve production goals while uncovering additional information about component health. We present an effi-cient heuristic search for these diagnostic production plans and show through experiments on a model of an industrial digital printing press that the theoretical increase in infor-mation can be realized on practical real-time systems. We obtain higher long-run productivity than a decoupled com-bination of planning and diagnosis.