14 October 1996 On-board fault diagnostics for fly-by-light flight control systems using neural network flight processors
Author Affiliations +
Fly-by-Light control systems offer higher performance for fighter and transport aircraft, with efficient fiber optic data transmission, electric control surface actuation, and multi-channel high capacity centralized processing combining to provide maximum aircraft flight control system handling qualities and safety. The key to efficient support for these vehicles is timely and accurate fault diagnostics of all control system components. These diagnostic tests are best conducted during flight when all facts relating to the failure are present. The resulting data can be used by the ground crew for efficient repair and turnaround of the aircraft, saving time and money in support costs. These difficult to diagnose (Cannot Duplicate) fault indications average 40 - 50% of maintenance activities on today's fighter and transport aircraft, adding significantly to fleet support cost. Fiber optic data transmission can support a wealth of data for fault monitoring; the most efficient method of fault diagnostics is accurate modeling of the component response under normal and failed conditions for use in comparison with the actual component flight data. Neural Network hardware processors offer an efficient and cost-effective method to install fault diagnostics in flight systems, permitting on-board diagnostic modeling of very complex subsystems. Task 2C of the ARPA FLASH program is a design demonstration of this diagnostics approach, using the very high speed computation of the Adaptive Solutions Neural Network processor to monitor an advanced Electrohydrostatic control surface actuator linked through a AS-1773A fiber optic bus. This paper describes the design approach and projected performance of this on-line diagnostics system.
© (1996) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
James M. Urnes, James M. Urnes, John Cushing, John Cushing, William E. Bond, William E. Bond, Steve Nunes, Steve Nunes, } "On-board fault diagnostics for fly-by-light flight control systems using neural network flight processors", Proc. SPIE 2840, Fly-by-Light III, (14 October 1996); doi: 10.1117/12.254211; https://doi.org/10.1117/12.254211


Fly-by-light flight control systems
Proceedings of SPIE (May 22 1995)
Enhanced Memory Capacity Of A Hopfield Neural Network
Proceedings of SPIE (March 23 1986)
Effect of model error on actuator and damper placement for...
Proceedings of SPIE (September 08 1993)
A framework for autonomy
Proceedings of SPIE (October 02 2006)

Back to Top