Adaptive flight control systems have the potential to be more resilient to extreme changes in airplane behavior. Extreme changes could be a result of a system failure or of damage to the airplane. A direct adaptive neural-network-based flight control system was developed for the National Aeronautics and Space Administration NF-15B Intelligent Flight Control System airplane and subjected to an inflight simulation of a failed (frozen) (unmovable) stabilator. Formation flight handling qualities evaluations were performed with and without neural network adaptation. The results of these flight tests are presented. Comparison with simulation predictions and analysis of the performance of the adaptation system are discussed. The performance of the adaptation system is assessed in terms of its ability to decouple the roll and pitch response and reestablish good onboard model tracking. Flight evaluation with the simulated stabilator failure and adaptation engaged showed that there was generally improvement in the pitch response; however, a tendency for roll pilot-induced oscillation was experienced. A detailed discussion of the cause of the mixed results is presented. Nomenclature
The X-56 Multi-Utility Technology Testbed aircraft system is a versatile experimental research flight platform. The system was primarily designed to investigate active control of lightweight flexible structures, but is reconfigurable and capable of hosting a wide breadth of research. Current research includes flight experimentation of a Lockheed Martin designed active control flutter suppression system. Future research plans continue experimentation with alternative control systems, explore the use of novel sensor systems, and experiments with the use of novel control effectors. This paper describes the aircraft system, current research efforts designed around the system, and future planned research efforts that will be hosted on the aircraft system.
This paper presents some of the unique verification, validation, and certification challenges that must be addressed during the development of adaptive system software for use in safety-critical aerospace applications. The paper first discusses the challenges imposed by the current regulatory guidelines for aviation software. Next, a number of individual technologies being researched by NASA and others are discussed that focus on various aspects of the software challenges. These technologies include the formal methods of model checking, compositional verification, static analysis, program synthesis, and runtime analysis. Then the paper presents some validation challenges for adaptive control, including proving convergence over long durations, guaranteeing controller stability, using new tools to compute statistical error bounds, identifying problems in fault-tolerant software, and testing in the presence of adaptation. These specific challenges are presented in the context of a software validation effort in testing the Integrated Flight Control System (IFCS) neural control software at the Dryden Flight Research Center. Lastly, the challenges to develop technologies to help prevent aircraft system failures, detect and identify failures that do occur, and provide enhanced guidance and control capability to prevent and recover from vehicle loss of control are briefly cited in connection with ongoing work at the NASA Langley Research Center.
Adaptive flight control systems have the potential to be resilient to extreme changes in airplane behavior. Extreme changes could be a result of a system failure or of damage to the airplane. The goal for the adaptive system is to provide an increase in survivability in the event that these extreme changes occur. A direct adaptive neural-network-based flight control system was developed for the National Aeronautics and Space Administration NF-15B Intelligent Flight Control System airplane. The adaptive element was incorporated into a dynamic inversion controller with explicit reference model-following. As a test the system was subjected to an abrupt change in plant stability simulating a destabilizing failure. Flight evaluations were performed with and without neural network adaptation. The results of these flight tests are presented. Comparison with simulation predictions and analysis of the performance of the adaptation system are discussed. The performance of the adaptation system is assessed in terms of its ability to stabilize the vehicle and reestablish good onboard reference model-following. Flight evaluation with the simulated destabilizing failure and adaptation engaged showed improvement in the vehicle stability margins. The convergent properties of this initial system warrant additional improvement since continued maneuvering caused continued adaptation change. Compared to the non-adaptive system the adaptive system provided better closed-loop behavior with improved matching of the onboard reference model. A detailed discussion of the flight results is presented. Nomenclature
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.