Smart Controls
By Alan Brown
NASA Photo by Carla Thomas
View attachment 126
The F-15 Advanced Control Technology for Integrated Vehicles (ACTIVE) is testing a neural net that could make future flight controls react automatically when a flight control surface is damaged or inoperative by utilizing the aircraft's other control surfaces to compensate.
Aerospace Projects Writer
NASA is working to help pilots who find themselves in potentially disastrous situations flying severely damaged or malfunctioning aircraft by developing new "smart" software that will enable pilots to control and safely land disabled aircraft.
Dryden is conducting flights to research the new software, which is in line with NASA's goal to reduce commercial aircraft accident rates by a factor of five over the next 10 years.
"If an accident occurs, the aircraft will seek useable control surfaces like flaps, rudders or ailerons that would successfully compensate, restoring control to the pilot," said Dr. Charles Jorgensen of Ames Research Center, Moffett Field, Calif. Jorgensen is the principal investigator for the NASA software program.
The intelligent flight control system employs experimental "neural network" software developed by computer scientists at Ames and the Boeing Company's Phantom Works division, St. Louis, Mo. When it is fully developed, the software will add a significant margin of safety for future military and commercial aircraft that incorporate the system.
The evaluations involved flying the modified F-15 through a variety of maneuvers and formation flying with other aircraft, said Mike Thomson, chief engineer for the flight tests at Dryden.
The maneuvers were flown first in a conventional mode and then with the neural network. Pilots then made comparisons of the two modes.
"The next step is to use the same type of controller with a learning neural net system and actually simulate failures on the aircraft and have the system adapt to those failures," Thomson said.
Jim Smolka, Dryden's chief project pilot for the current flight evaluations, said the system, which also is known as the Intelligent Flight Control System (IFCS), was effective.
"This is a limited-authority system, (so) most of the flight maneuvers we're doing are fairly benign, like pitch, roll and yaw doublets, aileron rolls, some steady heading side-slips, a wind-up turn. We've explored the entire airspeed and altitude capability of the present system," he said. "This is only the beginning for neural network technology."
In addition to Smolka, Dryden research pilots Dana Purifoy and Rogers Smith, Air Force Flight Test Center test pilot Capt. Dawn Dunlop and Boeing Phantom Works test pilot Larry Walker flew evaluation flights of the system. Dryden flight test engineers Gerard Schkolnik, Marty Trout and Bob Meyer, Director of Research Engineering, assisted in the rear cockpit.
Neural network software is distinguished by its ability to "learn" by observing patterns in the data it receives and processes and then performing different tasks in response to new patterns, said Jorgensen. Simple neural network software has been in use since the 1960s with computer modems to enable them to receive error-free data over often-noisy telephone lines, but it never demonstrated that ability in such a complex safety-related environment. Dryden research flights on the highly modified F-15 Advanced Control Technology for Integrated Vehicles (ACTIVE) are demonstrating how this version of the neural network software can correctly identify and respond to changes in aircraft stability and control characteristics. It also will show the system's ability to immediately maintain the best flight performance. The tests involve about a dozen flights over a three-week period.
In its flight control application, the neural network software program takes data from the aircraft's air data sensors - airspeed, direction, pressure and force - and compares the pattern of how the aircraft is actually flying with the pattern of how it should fly. These patterns are based on a series of pre-programmed aeronautical equations or control laws that define how the airplane flies. If there is a mismatch due to equipment failures, combat damage or other reasons, the aircraft's flight control computer uses the new neural network programming to "relearn" to fly the plane with a new pattern six times every second.
For example, a military aircraft may sustain combat damage that disables one or more of its control surfaces, such as an aileron or flap. A commercial aircraft could sustain a major equipment or systems failure, such as the inability of using its flaps or encountering extreme icing, both of which could affect the safe performance of the aircraft.
Using its on'line learning capability, the neural net software would identify changes, then reconfigure the flight control computer system to adapt, making the failure or damage almost "transparent" to the pilot. To enable the pilot to maintain or regain control, it may change the way the remaining functional control surfaces and systems are used to compensate for inoperative or damaged surfaces or equipment.
Future versions of the software could be developed for use in new airplanes that have digital fly'by'wire flight control systems, such as the Boeing 777 jetliner, the Air Force's C'17 transport, or the F'22 fighter. The system also has application to NASA's proposed Mars aircraft concept. These software versions will have faster self'learning capability.
Neural net software developed in this NASA project could have a bearing on other aspects of contemporary life.
"Once we prove neural net software can rapidly learn to fly a crippled aircraft and help pilots land it safely, then engineers will be more likely to use the intelligent software in power plants, automobiles and other less-complicated systems to avoid disasters after equipment failures" he said.
