Expert Polynomial Network Turbine Engine Diagnostician
Department of Defense
Agency Tracking Number:
Solicitation Topic Code:
Small Business Information
700 Harris Street, Charlottesville, VA, 22903
Socially and Economically Disadvantaged:
Gerard J. Montgomery
AbstractThe objective of this effort is to demonstrate a prototype advanced diagnostic system for the T800 turboshaft engine using a hybrid polynomial network and production-rule expert system. The resulting system will demonstrate the feasibility of developing a revolutionary diagnostic capability which can model the engine at a system level, detect failures before they become signficant isolate faults, estimate the loss of efficiency of various engine components, and predict future faults. AbTech has developed an innovative network approach, called polynomial networks, based on over a decade of research in neural networks and advanced statistics. Polynomial networks are simply networks of very powerful high-order polynomial equations. It discusses how networks can be applied to substantially increase the control and diagnostic capabilities of systems in a practical and very cost-effective manner. It then details a specific project to integrate and apply the existing AIM software and a production-rule system to T800 engine diagnostics.
* information listed above is at the time of submission.