Intelligent flight control system

Last updated
NASA's NF-15B was used for the project. NASA NF-15B 837 ECANS.jpg
NASA's NF-15B was used for the project.

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 NASA's 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.

Contents

Objectives of IFCS

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. [1] 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.

  1. To develop a flight control system that can identify aircraft characteristics through the use of neural network technology in order to optimize aircraft performance.
  2. To develop a neural network that can train itself to analyze the flight properties of the aircraft.
  3. To be able to demonstrate the aforementioned properties on a modified F-15 ACTIVE aircraft during flight, which is the testbed for the IFCS project.

Theory of operation

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.

Project history

Generation 1

Generation 1 IFCS flight tests were conducted in 2003 to test the outputs of the neural network. [1] In this phase, the neural network was pre-trained using flight characteristics obtained for the McDonnell Douglas F-15 STOL/MTD in a wind tunnel test and did not actually provide any control adjustments in flight. [2] The outputs of the neural network were run directly to instrumentation for data collection purposes only.

Generation 2

Generation 2 IFCS tests were conducted in 2005 and used a fully integrated neural network as described in the theory of operation. [3] It is a direct adaptive system that continuously provides error corrections and then measures the effects of these corrections in order to learn new flight models or adjust existing ones. [1] To measure the aircraft state, the neural network takes 31 inputs from the roll, pitch, and yaw axes and the control surfaces. [3] If there is a difference between the aircraft state and model, the neural network adjusts the outputs of the primary flight computer through a dynamic inversion controller to bring the difference to zero before they are sent to the actuator control electronics which move the control surfaces.

Intelligent autopilot system

A different research and development project with the goal of designing an intelligent flight control system is being carried out at University College London. Their prototype is known as the Intelligent Autopilot System which has Artificial Neural Networks capable of learning from human teachers by imitation. The system is capable of handling severe weather conditions and flight emergencies such as engine failure or fire, emergency landing, and performing Rejected Take Off (RTO) in a flight simulator. [4]

See also

Related Research Articles

<span class="mw-page-title-main">Fly-by-wire</span> Electronic flight control system

Fly-by-wire (FBW) is a system that replaces the conventional manual flight controls of an aircraft with an electronic interface. The movements of flight controls are converted to electronic signals, and flight control computers determine how to move the actuators at each control surface to provide the ordered response. Implementations either use mechanical flight control backup systems or else are fully electronic.

<span class="mw-page-title-main">Ames Research Center</span> Research center operated by NASA

The Ames Research Center (ARC), also known as NASA Ames, is a major NASA research center at Moffett Federal Airfield in California's Silicon Valley. It was founded in 1939 as the second National Advisory Committee for Aeronautics (NACA) laboratory. That agency was dissolved and its assets and personnel transferred to the newly created National Aeronautics and Space Administration (NASA) on October 1, 1958. NASA Ames is named in honor of Joseph Sweetman Ames, a physicist and one of the founding members of NACA. At last estimate NASA Ames had over US$3 billion in capital equipment, 2,300 research personnel and a US$860 million annual budget.

<span class="mw-page-title-main">Aeroelasticity</span> Interactions among inertial, elastic, and aerodynamic forces

Aeroelasticity is the branch of physics and engineering studying the interactions between the inertial, elastic, and aerodynamic forces occurring while an elastic body is exposed to a fluid flow. The study of aeroelasticity may be broadly classified into two fields: static aeroelasticity dealing with the static or steady state response of an elastic body to a fluid flow, and dynamic aeroelasticity dealing with the body's dynamic response.

<span class="mw-page-title-main">Bell X-1</span> Experimental rocket-powered aircraft

The Bell X-1 is a rocket engine–powered aircraft, designated originally as the XS-1, and was a joint National Advisory Committee for Aeronautics–U.S. Army Air Forces–U.S. Air Force supersonic research project built by Bell Aircraft. Conceived during 1944 and designed and built in 1945, it achieved a speed of nearly 1,000 miles per hour in 1948. A derivative of this same design, the Bell X-1A, having greater fuel capacity and hence longer rocket burning time, exceeded 1,600 miles per hour in 1954. The X-1 aircraft #46-062, nicknamed Glamorous Glennis and flown by Chuck Yeager, was the first piloted airplane to exceed the speed of sound in level flight and was the first of the X-planes, a series of American experimental rocket planes designed for testing new technologies.

<span class="mw-page-title-main">Armstrong Flight Research Center</span> United States aerospace research facility

The NASA Neil A. Armstrong Flight Research Center (AFRC) is an aeronautical research center operated by NASA. Its primary campus is located inside Edwards Air Force Base in California and is considered NASA's premier site for aeronautical research. AFRC operates some of the most advanced aircraft in the world and is known for many aviation firsts, including supporting the first crewed airplane to exceed the speed of sound in level flight, highest speed by a crewed, powered aircraft, the first pure digital fly-by-wire aircraft, and many others. AFRC operates a second site next to Air Force Plant 42 in Palmdale, California, known as Building 703, once the former Rockwell International/North American Aviation production facility. There, AFRC houses and operates several of NASA's Science Mission Directorate aircraft including SOFIA, a DC-8 Flying Laboratory, a Gulfstream C-20A UAVSAR and ER-2 High Altitude Platform. As of 2023, Bradley Flick is the center's director.

<span class="mw-page-title-main">Autopilot</span> System to maintain vehicle trajectory in lieu of direct operator command

An autopilot is a system used to control the path of a vehicle without requiring constant manual control by a human operator. Autopilots do not replace human operators. Instead, the autopilot assists the operator's control of the vehicle, allowing the operator to focus on broader aspects of operations.

<span class="mw-page-title-main">Shuttle Carrier Aircraft</span> Extensively modified Boeing 747 airliners that NASA used to transport Space Shuttle orbiters

The Shuttle Carrier Aircraft (SCA) are two extensively modified Boeing 747 airliners that NASA used to transport Space Shuttle orbiters. One (N905NA) is a 747-100 model, while the other (N911NA) is a short-range 747-100SR. Both are now retired.

<span class="mw-page-title-main">Grumman X-29</span> 1984 experimental aircraft family by Grumman

The Grumman X-29 is an American experimental aircraft that tested a forward-swept wing, canard control surfaces, and other novel aircraft technologies. Funded by NASA, the United States Air Force and DARPA, the X-29 was developed by Grumman, and the two built were flown by NASA and the United States Air Force. The aerodynamic instability of the X-29's airframe required the use of computerized fly-by-wire control. Composite materials were used to control the aeroelastic divergent twisting experienced by forward-swept wings, and to reduce weight. The aircraft first flew in 1984, and two X-29s were flight tested through 1991.

<span class="mw-page-title-main">Lunar Landing Research Vehicle</span> Apollo human lunar landing training vehicle

The Bell Aerosystems Lunar Landing Research Vehicle was a Project Apollo era program to build a simulator for the Moon landings. The LLRVs were used by the FRC, now known as the NASA Armstrong Flight Research Center, at Edwards Air Force Base, California, to study and analyze piloting techniques needed to fly and land the Apollo Lunar Module in the Moon's low gravity environment.

<span class="mw-page-title-main">Boeing X-48</span> Airplane

The Boeing X-48 is an American experimental unmanned aerial vehicle (UAV) built to investigate the characteristics of blended wing body (BWB) aircraft. Boeing designed the X-48 and two examples were built by Cranfield Aerospace in the UK. Boeing began flight testing the X-48B version for NASA in 2007. The X-48B was later modified into the X-48C version, which was flight tested from August 2012 to April 2013. Boeing and NASA plan to develop a larger BWB demonstrator.

<span class="mw-page-title-main">Scaled Composites Proteus</span> Experimental aircraft

The Scaled Composites Model 281 Proteus is a tandem-wing high-altitude long-endurance aircraft designed by Burt Rutan to investigate the use of aircraft as high-altitude telecommunications relays. The Proteus is a multi-mission vehicle able to carry various payloads on a ventral pylon. The Proteus has an extremely efficient design and can orbit a point at over 19,800 m for more than 18 hours. It is currently owned by Northrop Grumman.

<span class="mw-page-title-main">Northrop M2-F2</span> Lifting body prototype

The Northrop M2-F2 was a heavyweight lifting body based on studies at NASA's Ames and Langley research centers and built by the Northrop Corporation in 1966.

<span class="mw-page-title-main">Northrop M2-F3</span> Lifting body prototype aircraft

The Northrop M2-F3 is a heavyweight lifting body rebuilt from the Northrop M2-F2 after it crashed at the Dryden Flight Research Center in 1967. It was modified with an additional third vertical fin - centered between the tip fins - to improve control characteristics. The "M" refers to "manned" and "F" refers to "flight" version.

In machine learning, a common task is the study and construction of algorithms that can learn from and make predictions on data. Such algorithms function by making data-driven predictions or decisions, through building a mathematical model from input data. These input data used to build the model are usually divided into multiple data sets. In particular, three data sets are commonly used in different stages of the creation of the model: training, validation, and test sets.

<span class="mw-page-title-main">Autoland</span> Automated aircraft landing procedure

In aviation, autoland describes a system that fully automates the landing procedure of an aircraft's flight, with the flight crew supervising the process. Such systems enable airliners to land in weather conditions that would otherwise be dangerous or impossible to operate in.

Fault tolerance is the ability of a system to maintain proper operation despite failures or faults in one or more of its components. This capability is essential for high-availability, mission-critical, or even life-critical systems.

<span class="mw-page-title-main">McDonnell Douglas F-15 STOL/MTD</span> USAF/NASA R&D aircraft

The McDonnell Douglas F-15 STOL/MTD is a modified F-15 Eagle. Developed as a technology demonstrator, the F-15 STOL/MTD carried out research for studying the effects of thrust vectoring and enhanced maneuverability. The aircraft used for the project was pre-production TF-15A (F-15B) No. 1, the first two-seat F-15 Eagle built by McDonnell Douglas, the sixth F-15 off the assembly line, and was the oldest F-15 flying up to its retirement. It was also used as the avionics testbed for the F-15E Strike Eagle program. The plane was on loan to NASA from the United States Air Force.

<span class="mw-page-title-main">NASA AD-1</span> NASA experimental oblique wing aircraft

The NASA AD-1 is both an aircraft and an associated flight test program conducted between 1979 and 1982 at the NASA Dryden Flight Research Center, Edwards California, which successfully demonstrated an aircraft wing that could be pivoted obliquely from zero to 60 degrees during flight.

Hardware-in-the-loop (HIL) simulation, also known by various acronyms such as HiL, HITL, and HWIL, is a technique that is used in the development and testing of complex real-time embedded systems. HIL simulation provides an effective testing platform by adding the complexity of the process-actuator system, known as a plant, to the test platform. The complexity of the plant under control is included in testing and development by adding a mathematical representation of all related dynamic systems. These mathematical representations are referred to as the "plant simulation". The embedded system to be tested interacts with this plant simulation.

Throughout a normal flight, a pilot controls an aircraft through the use of flight controls including maintaining straight and level flight, as well as turns, climbing, and descending. Some controls, such as a "yoke" or "stick" move and adjust the control surfaces which affects the aircraft's attitude in the three axes of pitch, roll, and yaw. Other controls include those for adjusting wing characteristics and those that control the power or thrust of the propulsion systems. The loss of primary control systems in any phase of flight is an emergency. Aircraft are not designed to be flown under such circumstances; however, some pilots faced with such an emergency have had limited success flying and landing aircraft with disabled controls.

References

  1. ^ a b c "NASA Dryden Flight Research Center Fact Sheets: Intelligent Flight Control System". NASA Dryden Flight Research Center. July 21, 2006. Archived from the original on 2010-03-24. Retrieved 2007-02-25.
  2. ^ a Davidson, Ron (October 2003). "Flight test of an intelligent flight-control system". Associated Business Publications. Retrieved 2007-02-25.
  3. ^ a b Peggy S. Williams-Hayes (August 25, 2005). "Flight Test Implementation of a Second Generation Intelligent Flight Control System" (PDF). NASA Dryden Flight Research Center.
  4. ^ a "The Intelligent Autopilot System IAS". Haitham Baomar. August 15, 2016. Retrieved 2016-09-05.