A computer program implements the algorithm described in "Hypothetical Scenario Generator for Fault-Tolerant Diagnosis" (NPO-42516), NASA Tech Briefs, Vol. 31, No. 6 (June 2007), page 71. To recapitulate: the Hypothetical Scenario Generator (HSG) is 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. The HSG accepts, as input, possibly incomplete data on the current state of a system (see figure).

End-to-End Prognostic Architecture uses existing diagnostic models to generate predictions.
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.

This program was written by Mark James and Ryan Mackey of Caltech for NASA's Jet Propulsion Laboratory.

This software is available for commercial licensing. Please contact Karina Edmonds of the California Institute of Technology at (626) 395-2322. Refer to NPO-43097.

Topics:
Aircraft Architecture Computer software and hardware Mathematical models Prognostics Simulation and modeling Software Spacecraft Vehicles
This Brief includes a Technical Support Package (TSP).
Document cover
Generating Scenarios When Data Are Missing

(reference NPO-43097) is currently available for download from the TSP library.

Don't have an account?

Magazine cover
NASA Tech Briefs Magazine

This article first appeared in the September, 2007 issue of NASA Tech Briefs Magazine (Vol. 31 No. 9).

Read more articles from the archives here.

Overview

The document discusses the Hypothetical Scenario Generator (HSG), a revolutionary software developed by NASA's Jet Propulsion Laboratory (JPL) that enables the generation of scenarios in the presence of missing data. This capability is crucial for performing predictions on the health of instrumented systems, particularly in aerospace and factory automation applications.

The HSG operates by taking the current state of a system, which includes probabilistic information from data forecasting, and utilizing model-based reasoning techniques to produce an ordered list of potential fault scenarios. These scenarios represent plausible future failure modes of the system. The HSG is tightly integrated with diagnostic processes, functioning in a feedback loop that allows it to generate future state scenarios through hypothetical discovery.

A key feature of the HSG is its ability to model Potential Fault Scenarios (PFS) as an ordered disjunctive tree of conjunctive consequences. This structure helps prioritize the likelihood of various paths based on the current inputs. The results generated by the HSG are then used by model-based intelligent systems to predict the future health of the modeled system.

The document highlights the advancement of using the same model for fault detection, diagnosis, and prediction, which simplifies the process and enhances efficiency. The HSG employs efficient heuristics to manage the large search space of possible scenarios, quickly eliminating dead-end searches and logically inconsistent results. This capability is particularly valuable when data is incomplete, allowing for reasoning and predictions to continue without full information.

The software is designed to run on various platforms, including SUN, HP, Intel, Apple MACs, and flight processors, and can be distributed in both source code and binary form. It requires a LISP compiler, which is widely available. The HSG has been tested on multiple knowledge bases, demonstrating performance and quality that exceed initial predictions.

The document also notes the commercial interest from major aerospace companies such as Boeing, Lockheed, and Northrop, indicating the potential for broad applications of the HSG technology. Overall, the HSG represents a significant advancement in predictive diagnostics and scenario generation, particularly in contexts where data may be missing or incomplete.