The Hypothetical Scenario Generator for Fault-tolerant Diagnostics (HSG) is an algorithm being developed in conjunction with other components of artificial- intelligence systems for automated diagnosis and prognosis of faults in spacecraft, aircraft, and other complex engineering systems. By incorporating prognostic capabilities along with advanced diagnostic capabilities, these developments hold promise to increase the safety and affordability of the affected engineering systems by making it possible to obtain timely and accurate information on the statuses of the systems and predicting impending failures well in advance.
Prognosis is tightly coupled with diagnosis. The simplest approach to prognosis by an artificial-intelligence system involves the use of a diagnostic engine in a controlled feedback loop to project from the current state of the affected engineering system to future states that are elements of scenarios that are discovered hypothetically. A hypothetical-scenario generator is a key element of this approach. A hypothetical- scenario generator accepts, as its input, information on the current state of the engineering system. Then, by means of model-based reasoning techniques, it returns a disjunctive list of fault scenarios that could be reached from the current state.
The HSG is a specific instance of a hypothetical-scenario generator that implements an innovative approach for performing diagnostic reasoning when data are missing. The special purpose served by the HSG is to (1) look for all possible ways in which the present state of the engineering system can be mapped with respect to a given model and (2) generate a prioritized set of future possible states and the scenarios of which they are parts. The HSG models a potential fault scenario as an ordered disjunctive tree of conjunctive consequences, wherein the ordering is based upon the likelihood that a particular conjunctive path will be taken for the given set of inputs. The computation of likelihood is based partly on a numerical ranking of the degree of completeness of data with respect to satisfaction of the antecedent conditions of prognostic rules. The results from the HSG are then used by a modelbased artificial-intelligence subsystem to predict realistic scenarios and states.
To avoid the need to create special models to generate hypothetical scenarios, the HSG uses the same model that is used to perform fault-detection and other diagnostic functions but interprets the results generated by the model in a manner unique to the generation of hypothetical scenarios. An important additional advantage of this approach is that a future state can be diagnosed by the same model as that used to diagnose the current state.
This work was done by Mark James of Caltech for NASA's Jet Propulsion Laboratory. For more information, download the Technical Support Package (free white paper) at www.techbriefs.com/tsp under the Information Sciences category.
The software used in this innovation is available for commercial licensing. Please contact Karina Edmonds of the California Institute of Technology at (626) 395-2322. Refer to NPO-42516.