You are here

Neural Network Compensation Strategy for Preventing Pilot-Induced Oscillations

Award Information
Agency: Department of Defense
Branch: Air Force
Contract: N/A
Agency Tracking Number: 28270
Amount: $743,839.00
Phase: Phase II
Program: SBIR
Solicitation Topic Code: N/A
Solicitation Number: N/A
Timeline
Solicitation Year: N/A
Award Year: 1996
Award Start Date (Proposal Award Date): N/A
Award End Date (Contract End Date): N/A
Small Business Information
7001 Shallowford Road
Chattanooga, TN 37421
United States
DUNS: N/A
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
Principal Investigator
 Chadwick J. Cox
 (615) 894-4646
Business Contact
Phone: () -
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. *

US Flag An Official Website of the United States Government