A New Approach to Model-Based Diagnosis Using Probabilistic Logic.
Nikita A. Sakhanenko, Roshan Rammohan, George F. Luger, Carl R. Stern · 2008
We describe a new approach to model construction using transfer function diagrams that are consequently mapped into generalized loopy logic, a first-order, Turing-complete stochastic language. Transfer function diagrams support rep-resentation of dynamic systems with interconnected compo-nents. We demonstrate how these diagrams provide interfaces to a context-sensitive probabilistic modeling system (COS-MOS). As a result, interfaces as well as the notion of context underlying COSMOS are successfully used for model-based diagnosis. This paper describes transfer function diagrams and how they are incorporated into COSMOS. We illustrate our approach with a practical example taken from a “pump system ” modeling problem.