 |
 |
 |
 |
 |
|
|
Rotorcraft Health Usage Monitoring (HUMS)Sponsored by: Office of the Secretary of Defense & U.S. Army Missile Command at Redstone Arsenal
Using funds provided by the Office of the Secretary of Defense (OSD) and in support of the Army rotorcraft programs, AITHER investigated the feasibility of using artificial neural networks to perform regime recognition for usage monitoring of military rotorcraft. AITHER was provided with AH-64 Apache flight test data that was used for both training and validating a neural network algorithm. This testing demonstrated the ability to accurately predict component loads using readily measured aircraft parameters, such as control positions, engine settings, and airspeed. 
Optimized neural network results showing accurate prediction of helicopter flight loads. Results based on actual flight test data from an AH-64 Apache helicopter. The second effort under this project was to develop a methodology for employing the usage monitoring data to reliably and safely extend the life of flight-critical components. The basic methodology developed under this effort was later expanded and tested under a related U.S. Navy Phase I SBIR program. Early results were presented at the 2005 SPIE Non-Destructive Evaluation conference. |
Health and usage monitoring systems (HUMS) offer a great potential to reduce the high maintenance costs of rotorcraft while increasing reliability and safety. Today, health monitoring systems are finding widespread use in many helicopter systems for monitoring the health of engines, transmissions, and other flight critical components. These systems check for abnormal system responses to detect imminent failures, saving lives and reducing secondary damage to the aircraft. The other section of HUMS is to monitor how the helicopter is being flown, usage monitoring. Through usage monitoring, the Army can know how the aircraft is being flown and adjust component lives accordingly.