摘要
This paper establishes a formal model for hybrid diagnosis, novelfeatures including: (1) It provides a unified theoretical framework for utilizing de-vice models and heuristics in diagnosis, which naturally integrates all the importantcomponents of diagnosis - the structural and behavioral description of devices, faultmodes, the lower and upper fault bounds, fault possibilities and heuristic rules -into a diagnostic system. Device models predict outputs from inputs, heuristic rulesinfer the possibilities of certain components being faulty from symptoms, and yetthe combination of both constrains each other for us to reduce the hypothesis space.(2) It presents a typical way of modeling behavior of devices, to which the key isthe introduction of I-O functions with indefinite inputs/outputs. (3) It can easily beimplemented over a forward-chaining inference engine.
This paper establishes a formal model for hybrid diagnosis, novelfeatures including: (1) It provides a unified theoretical framework for utilizing de-vice models and heuristics in diagnosis, which naturally integrates all the importantcomponents of diagnosis - the structural and behavioral description of devices, faultmodes, the lower and upper fault bounds, fault possibilities and heuristic rules -into a diagnostic system. Device models predict outputs from inputs, heuristic rulesinfer the possibilities of certain components being faulty from symptoms, and yetthe combination of both constrains each other for us to reduce the hypothesis space.(2) It presents a typical way of modeling behavior of devices, to which the key isthe introduction of I-O functions with indefinite inputs/outputs. (3) It can easily beimplemented over a forward-chaining inference engine.