Neural Network Compensation Strategy for Preventing Pilot-Induced Oscillations

Award Information
Agency:
Department of Defense
Branch
Air Force
Amount:
$743,839.00
Award Year:
1996
Program:
SBIR
Phase:
Phase II
Contract:
n/a
Agency Tracking Number:
28270
Solicitation Year:
n/a
Solicitation Topic Code:
n/a
Solicitation Number:
n/a
Small Business Information
Accurate Automation Corp
7001 Shallowford Road, Chattanooga, TN, 37421
Hubzone Owned:
N
Socially and Economically Disadvantaged:
N
Woman Owned:
N
Duns:
n/a
Principal Investigator:
Chadwick J. Cox
(615) 894-4646
Business Contact:
() -
Research Institution:
n/a
Abstract
We propose to develop an automated Pilot Induced Oscillation (PIO) detection and compensation system. This will use artificial neural networks to increase speed and the envelope of operation. PIO is caused when a pilot overcompensates during a "high gain" task such as landing, takeoff, refueling, dropping stores, or tracking. It can also be caused by inefficiencies in the inner loop controllers, such as time delays and phase and rate limits. PIO represents a significant danger to aircraft and has resulted in a number of high profile accidents, such as the crash of the YF-22. Some of the most experienced pilots have had PIOs. Because of their proven ability of fast and accurate pattern recognition and new research into the stability of artificial neural network based control systems, neural networks can be used to develop a system superior to current systems such as the Space Shuttle PIO filter and the JAS-39 system.

* information listed above is at the time of submission.

Agency Micro-sites

US Flag An Official Website of the United States Government