Adaptive Control Using Neural Network Augmentation for a Modified F-15 Aircraft

Burken, John J.; Williams-Hayes, Peggy S.; Kaneshige, John; Stachowiak, Susan J.

doi:10.1109/med.2006.328857

Cited by 20 publications

(20 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 The second flight phase, referred to as "generation 2" ("Gen2"), focused on the development and evaluation of a direct adaptive control method that uses neural networks to generate command augmentation signals to compensate for errors caused by unmodeled dynamics. 2 In principle, this approach does not require information on the nature of the failure or the extent of the damage. This report describes a follow-on effort to the second flight phase, referred to as "generation 2a" ("Gen2a"), to develop and evaluate enhancements to the neural adaptive flight control system.…”

Section: Introduction and Statement Of The Problemmentioning

confidence: 99%

Flight Test Comparison of Different Adaptive Augmentations of Fault Tolerant Control Laws for a Modified F-15 Aircraft

Burken

Hanson

Lee

et al. 2009

AIAA Infotech@Aerospace Conference

View full text Add to dashboard Cite

This report describes the improvements and enhancements to a neural network-based approach for directly adapting to aerodynamic changes resulting from damage or failures. This research is a follow-on effort to flight tests performed on the NASA F-15 aircraft as part of the Intelligent Flight Control System research effort. Previous flight test results demonstrated the potential for performance improvement under destabilizing damage conditions. Little or no improvement was provided under simulated control surface failures, however, and the adaptive system was prone to pilot-induced oscillations. An improved controller was designed to reduce the occurrence of pilot-induced oscillations and increase robustness to failures in general. This report presents an analysis of the neural networks used in the previous flight test, the improved adaptive controller, and the baseline case with no adaptation. Flight test results demonstrate significant improvement in performance by using the new adaptive controller compared with the previous adaptive system and the baseline system for control surface failures. Nomenclature

show abstract

Section: Introduction and Statement Of The Problemmentioning

confidence: 99%

Flight Test Comparison of Different Adaptive Augmentations of Fault Tolerant Control Laws for a Modified F-15 Aircraft

Burken

Hanson

Lee

et al. 2009

AIAA Infotech@Aerospace Conference

View full text Add to dashboard Cite

show abstract

“…3 to 5, and Ref. 6). The neural network is essentially the sum of the products of the inputs and a set of weights.…”

Section: Adaptive Neural Networkmentioning

confidence: 97%

“…5 A more detailed description of the implementation of the neural network for flight-testing can be found in Ref. 6. The main components of the controller are illustrated in Fig.…”

Section: B Description Of the Intelligent Flight Control Systemmentioning

confidence: 99%

Flight Test Results from the NF-15B Intelligent Flight Control System (IFCS) Project with Adaptation to a Simulated Stabilator Failure

Bosworth

Williams-Hayes

2007

AIAA Infotech@Aerospace 2007 Conference and Exhibit

Self Cite

View full text Add to dashboard Cite

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

show abstract

“…6 A more detailed description of the implementation of the neural network for flight-testing can be found in Ref. 7. The main components of the controller are illustrated in Fig.…”

Section: B Description Of the Intelligent Flight Control Systemmentioning

confidence: 99%

Flight Results of the NF-15B Intelligent Flight Control System (IFCS) Aircraft with Adaptation to a Longitudinally Destabilized Plant

Bosworth

2008

AIAA Guidance, Navigation and Control Conference and Exhibit

View full text Add to dashboard Cite

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

show abstract

Adaptive Control Using Neural Network Augmentation for a Modified F-15 Aircraft

Cited by 20 publications

References 7 publications

Flight Test Comparison of Different Adaptive Augmentations of Fault Tolerant Control Laws for a Modified F-15 Aircraft

Flight Test Comparison of Different Adaptive Augmentations of Fault Tolerant Control Laws for a Modified F-15 Aircraft

Flight Test Results from the NF-15B Intelligent Flight Control System (IFCS) Project with Adaptation to a Simulated Stabilator Failure

Flight Results of the NF-15B Intelligent Flight Control System (IFCS) Aircraft with Adaptation to a Longitudinally Destabilized Plant

Contact Info

Product

Resources

About