IFCS

The Intelligent Flight Control System (IFCS) is a next-generation flight control system designed to provide increased safety for the crew and passengers of aircraft as well as to optimize the aircraft performance under normal conditions. The main benefit of this system is that it will allow a pilot to control an aircraft even under failure conditions that would normally cause it to crash. The IFCS is being developed under the direction of the NASA Dryden Flight Research Center with the collaboration of the NASA Ames Research Center, Boeing Phantom Works, the Institute for Scientific Research at West Virginia University, and the Georgia Institute of Technology.

The main purpose of the IFCS project is to create a system for use in civilian and military aircraft that is both adaptive and fault tolerant. This is accomplished through the use of upgrades to the flight control software that incorporate self-learning neural network technology. The goals of the IFCS neural network project are.

The neural network of the IFCS learns flight characteristics in real time through the aircraft’s sensors and from error corrections from the primary flight computer, and then uses this information to create different flight characteristic models for the aircraft. The neural network only learns when the aircraft is in a stable flight condition, and will discard any characteristics that would cause the aircraft to go into a failure condition. If the aircraft’s condition changes from stable to failure, for example, if one of the control surfaces becomes damaged and unresponsive, the IFCS can detect this fault and switch the flight characteristic model for the aircraft. The neural network then works to drive the error between the reference model and the actual aircraft state to zero.

Generation 1 IFCS flight tests were conducted in 2003 to test the outputs of the neural network. In this phase, the neural network was pre-trained using flight characteristics obtained for the F-15S/MTD in a wind tunnel test and did not actually provide any control adjustments in flight. The outputs of the neural network were run directly to instrumentation for data collection purposes only.

...
Wikipedia