Active control of wind-tunnel model aeroelastic response using neural networks

Under a joint research and development effort conducted by NASA and The Boe ing Company (formerly McDonnell Douglas), three neural-network-based contro l systems were developed and tested. The control systems were experimentall y evaluated using a transonic wind-tunnel model in the NASA Langley Researc h Center Transonic Dynamics Tunnel, One system used a neural network to sch edule Butter suppression control laws, another employed a neural network in a predictive control scheme, and the third employed a neural network in an inverse model control scheme. All three of these control schemes successfu lly suppressed flutter to or near the limits of the testing apparatus and r epresent the first experimental applications of neural networks to Butter s uppression. The findings of this project are summarized.