For Release: August 2, 1996

Don Nolan-Proxmire

Headquarters, Washington, DC
(Phone: 202/358-1983)

Mary M. Spracher

Langley Research Center, Hampton, Va.
(Phone: 757/864-6527/6120)

Robert M. Pap

Accurate Automation, Chatanooga, Tenn.
(Phone: 423/894-4646)

RELEASE NO. 96-126

Test Aircraft that Learns by Doing Unveiled in Wisconsin Today

NASA and the U.S. Air Force unveiled a jet-powered aircraft equipped with state-of-the-art flight control technologies at a briefing in Oshkosh, Wis., today. The 8-foot-4-inch aircraft was built to demonstrate a computerized flight control system that learns as it flies -- especially important for the demands of ultra high-speed flight.

The "LoFLYTE" aircraft has been developed by Accurate Automation Corporation in Chatanooga, Tenn., for NASA and the Air Force. Technologies being implemented in the LoFlyte program could eventually find their way into commercial, general aviation and military aircraft.

The experimental LoFLYTE aircraft will be used to explore new flight control techniques involving neural networks, which allow the aircraft control system to learn by mimicking the pilot.

The model is a Mach 5 waverider design which is a futuristic hypersonic aircraft configuration that actually cruises on top of its own shockwave. Waverider aircraft, powered by airbreathing hypersonic engines, would fly at speeds above Mach 4. LoFLYTE represents the first known flying waverider vehicle configuration, but in upcoming flight tests at NASA's Dryden Flight Research Center in California it will be flown at subsonic speeds to explore take-off and landing control issues.

The remotely-piloted aircraft has been designed to demonstrate that neural network flight controls are superior to conventional flight controls. Neural networks are computer systems that actually learn by doing. The computer network consists of many interconnected control systems, or nodes, similar to neurons in the brain. Each node assigns a value to the input from each of its counterparts. As these values are changed, the network can adjust the way it responds.

The LoFLYTE aircraft's flight controller consists of a network of multiple-instruction, multiple-data neural chips. The network will be able to continually alter the aircraft's control laws in order to optimize flight performance and take the pilot's responses into consideration. Over time, the neural network system could be trained to control the aircraft. The use of neural networks in flight would help pilots fly in quick-decision situations and help damaged aircraft land safely even when controls are partially destroyed.

The main objective of LoFLYTE is to demonstrate the utility of such a flight control system that learns through experience, said Robert Pegg of Langley's Hypersonic Vehicles Office. In addition to experimenting with neural networks, the flight of the model is also key as a low-speed demonstration of a hypersonic vehicle. "We're very interested in both outcomes, both the neural net technology and the flight characteristics," Pegg said.

"We see a big advantage to using this type of control system in a hypersonic vehicle," Pegg said. "At those high speeds, things happen so quickly that the pilot cannot control the aircraft as easily as at subsonic speeds."

The initial configuration for the aircraft was developed at NASA Langley and then Accurate Automation Corporation integrated the neural network technology into the Langley design. Successful tests of the waverider concept in Langley's 12-foot Low-Speed Wind Tunnel and 30- by 60-foot Full Scale Tunnel preceded the development of this model aircraft.

The construction of the model was completed at SWB Turbines of Appleton, Wis. This company provided the small turbine engine that powers the model. The shell of the model was made at Mississippi State's Raspet Flight Research Laboratory and then shipped to SWB Turbines so that the radio control gear and the engine could be installed.

The waverider was chosen as the testbed for the neural networks because the configuration has an inherently high hypersonic lift-to-drag ratio. If neural networks can control this "worst-case scenario" configuration, then they should be able to handle any other desired configuration. The waverider configuration was also chosen because it allows for long hypersonic cruise ranges of up to 8,000 miles. At an altitude of 90,000 feet, the Mach 5 waverider would be able to fly at a rate of one mile per second.

The program contracts are being administered through NASA Langley Research Center in Hampton, Va., and the Air Force Wright Laboratory in Dayton, Ohio, under the Small Business Innovative Research (SBIR) program.

Pegg also added another positive implication that LoFLYTE could have. "We want to make the public aware that the government is getting a good return on its SBIR-invested money," he said. "We hope this project will help us further demonstrate to the public that the SBIR program is a viable investment for the American people."

- end -

NASA releases and other info. are available by sending an E-mail message to domo@hq.nasa.gov. In the body of the message (not subject line), type "subscribe press-release" (no quotes). The system will send a confirmation message. A second automatic message will give additional info. on the service. NASA releases are also available via CompuServe using the command GO NASA.

text-only version of this release