Learning Algorithms for Preserving Safe Flight Envelope under Adverse Aircraft Conditions
Missouri University of Science & Technology/NASA Langley Research Center, Aeronautics Research Mission Directorate
Textron Aviation and WSU may partner on this project for flight testing on its specifically modified piston engine aircraft (CJ-144). Flight testing will be performed for the proposed learning algorithms for resilient flight control.
Government and industry agree that learning algorithms have potential to provide flight safety in adverse conditions such as degraded modes of operation, loss of control, and imperfect aircraft modeling, and reduce aircraft development costs. However, widespread adoption is hampered by a lack in general and commercial aviation of a-priori, user-defined performance guarantees. Current practice relies heavily on excessive flight testing as a means of performing verification. Besides the cost, the major drawback of excessive flight testing is that it only provides limited performance guarantees for what was tested; the fixed set of initial conditions, pilot commands, and failure profiles. This EPSCoR-funded project will develop and flight test learning algorithms with a-priori performance guarantees under adverse aircraft conditions. The novel feature of this research is that the proposed algorithms will have the capability to preserve a given, user-defined safe flight envelope through formal analytical synthesis, and hence, they will not require excessive (costly) flight testing and tools to validate their performance characteristics during the post-design stage, unlike existing learning algorithms proposed for aerospace applications. In addition, methods will be developed to use these algorithms effectively in the pilot decision support display of NASA Ames that indicates the proximity of the aircraft to safe flight boundaries caused by adverse conditions. The research will impact a broad range of applications utilizing learning algorithms for, among others, safe and effective aircraft control, crew decision-making in complex situations, and CEV/CLV vehicle control. Its outcomes, which include advancement of the theory on verifiable learning algorithms for flight control and pilot awareness systems, simulations at multiple levels of granularity, and flight experiments, will significantly contribute to the current and future NASA research and technology priorities.
The CJ-144 fly-by-wire flight control system is designed around a Guide Star GS-411 system which interfaces with a 5-hole probe on the wing and a GPS antenna. A series of bezel keys on the glass cockpit give the left-seat pilot control over the flight test maneuvers, adaptive control design parameters, data-logging, and provides feedback on aircraft attitude and control. Dr. Tansel Yucelen Science PI Missouri University of Science and Technology www.nasa.gov/epscor/stimuli
Dr. Susan Frost, NASA Technical Monitor, Intelligent Systems Division, NASA Ames Research Center NASA EPSCoR Stimuli 2014-15
Published on Dec 14, 2015
NASA Office of Education’s Aerospace Research & Career Development (ARCD) is pleased to release NASA EPSCoR Stimuli, a collection of univers...