This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Design and Simulation of Fault Tolerant Flight Control Schemes Implemented on a Parallel and Distributed Computational Cluster
Technical Paper
2015-01-2528
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
In recent years, there has been an increase in the use of Unmanned Aerial Systems (UAS) in the civilian sector for various purposes. As these platforms are constrained in terms of payload and capacity, they are typically equipped with a minimal sensor suite and the use of redundant sensors is uncommon. This research effort describes the design and simulation of a Neural Network (NN) based fault tolerant flight control approach for sensor and actuator failures, implemented on a parallel and distributed computational architecture. The inter process communication is implemented using BSD sockets and Message Passing Interface (MPI). For the purpose of the sensor failure detection, identification and accommodation (SFDIA) task, it is assumed that the pitch, roll and yaw rate gyros onboard the aircraft are without physical redundancy. The SFDIA task is accomplished through the use of a set of four neural networks, named Main Neural Network (MNN) and a set of three De-Centralized Neural Networks (DNNs), providing analytical redundancy for the pitch, roll and yaw gyros. The purpose of the MNN is to detect any failure on the three sensors, while the purpose of the DNNs is to identify the failed sensor and subsequently to facilitate failure accommodation by providing estimates of the sensor measurements. The actuator failure detection, identification and accommodation (AFDIA) scheme also features the MNN, for detection of actuator failures, along with three Neural Network Controllers (NNCs) for providing the compensating control surface deflections to neutralize any failure induced pitching, rolling and yawing moments. All NNs continue to train online, on top of an offline trained baseline network structure, using the Extended Back-Propagation Algorithm (EBPA), with data from a pilot-in-the loop flight simulation. Experiments indicate that the distributed architecture is capable of learning the behavior of the sensors (roll, pitch and yaw gyros) and is able to detect and identify failures on them. Additionally, it has also been shown that the distributed architecture is able to provide compensating control surface deflections to recover from failures on the actuators of the aircraft.
Authors
Topic
Citation
Gururajan, S., "Design and Simulation of Fault Tolerant Flight Control Schemes Implemented on a Parallel and Distributed Computational Cluster," SAE Technical Paper 2015-01-2528, 2015, https://doi.org/10.4271/2015-01-2528.Also In
References
- Kerr , T. Decentralized Filtering and Redundancy Management/Failure Detection for Multisensor Integrated Navigation Systems IEEE Transactions on Information Theory 191 208 1986
- Willsky , A.S. A Survey of Design Methods for Failure Detection in Dynamic Systems Automatica 12 601 611 1976
- Willsky , A.S. Failure Detection in Dynamic Systems Agard LS-109, Neuilly sur Seine France 2.1 2.14 1980
- Guo T.-H. , Nurre J. Sensor Failure Detection and Recovery by Neural Networks Proceedings of the International Joint Conference on Neural Networks I-221 I-226 1991
- Jokinen Petri A. Comparison of Neural Network Models for Process Fault Detection and Diagnosis Problems Proceedings of the International Joint Conference on Neural Networks I-239 I-244 1991
- Sreedhar R. , Fernandez B. , Masada C.Y. A Neural Network Based Adaptive Fault Detection Scheme Proceedings of the American Control Conference 3259 3263 1995
- Narendra , K.S. , Partasarathy , K. Identification and Control of Dynamical Systems Using Neural Networks IEEE Transactions on Neural Networks 1 1 4 27 1990
- Levin , A.U. , Narendra , K.S. Control of Non-Linear Dynamical Systems Using Neural Networks: Controllability and Stabilization IEEE Transactions on Neural Networks 4 2 192 206 1993
- Polycarpou M.M. , Vemuri A.T. Learning Methodology for Failure Detection and Accommodation IEEE Control Systems 16 24 1995
- Polycarpou M.M. , Helmicki A.J. Automated Fault Detection and Accommodation: A Learning Systems Approach IEEE Transactions on Systems, Man, and Cybernetics 25 11 1447 1458 1995
- Kline-Schoder , R. , Rauch , H. , Youssef Fault Detection, Isolation, and Reconfiguration for Aircraft Using Neural Networks Proceedings of the AIAA Guidance, Navigation and Control Conference, AIAA Paper 93-3876 Monterey, Ca 1993
- Balakrishnan S.N. , Biega Victor Adaptive-Critic-Based Neural Networks for Aircraft Optimal Control Journal of Guidance, Control, and Dynamics 19 4 893 898 1996
- Huang , C. , Tylock , J. , Engel , S. , Whitson , J. , Eilbert , J. Failure-Accommodating Neural Network Flight Control Proceedings of the AIAA Guidance, Navigation and Control Conference, AIAA Paper 92-4394 Hilton Head, SC 1992
- Ha C.M. Neural Networks Approaches to AIAA Aircraft Control Design Challenge Journal of Guidance, Control, and Dynamics 18 4 731 739 1995
- Ha , C.M. , Wei , Y.P. , Bessolo , J.A. Reconfigurable Aircraft Flight Control System Via Neural Networks Proceedings of the 1992 Aerospace Design Conference, AIAA Paper 92-1075 Irvine, Ca 1992
- Chiang Chi-Yuan , Youssef H.M. Neural Network and Fuzzy Logic Approach to Aircraft Reconfigurable Control Design Proceedings of the American Control Conference 3505 3509 1995
- Kim B.S. , Calise A.J. Nonlinear Flight Control Using Neural Networks Journal of Guidance, Control, and Dynamics 20 1 26 33 1997
- Napolitano , M.R. , Chen , C.I. et. al. Aircraft Failure Detection and Identification Using Neural Networks Journal of Guidance, Control, and Dynamics 16 6 999 1009 1993
- Napolitano , M.R. , Casdorph , V. , Neppach , C. , Naylor , S On- line Learning Neural Architectures and Cross-Correlation Analysis for Actuator Failure Detection and Identification International Journal of Control 63 3 433 455 1996
- Napolitano , M.R. , Naylor Steve et. al. On-Line Learning Nonlinear Direct Neurocontrollers for Restructurable Systems Journal of Guidance, Control, and Dynamics 18 1 170 176 1995
- Mascarell , J. C. Design and Comparison of Neural Network and Fuzzy Logic Actuator Failure Schemes for Flight Control System Master Thesis Department of Mechanical and Aerospace Engineering, West Virginia University 1996
- Napolitano , M.R. , Neppach , C. et. al. Neural-Network-Based Scheme for Sensor Failure Detection, Identification, and Accommodation Journal of Guidance, Control, and Dynamics 18 6 1280 1286 1995
- Windon , D.A. Design and Comparison of Neural Network and Kalman Predictor Based Sensor Validation Schemes for Implementation on the NASA-Aurora Theseus Aircraft Master Thesis Department of Mechanical and Aerospace Engineering, West Virginia University 1996
- Napolitano , M.R. , Swaim , R.L. New Technique for Aircraft Flight Control Reconfiguration Journal of Guidance, Control, and Dynamics 14 1 184 190 1991
- Perhinschi , M.G , Lando , M , Massotti , L. , Campa , G. , Napolitano , M.R. , Fravolini , M.L. On-Line Parameter Estimation Issues for the NASA IFCS F-15Fault Tolerant Systems
- Brinkre , J. , & Wise , K. Flight testing of a reconfigurable flight control law on the X-36 tailless fighter aircraft AIAA GNC Conference 2000
- Air Force Research Laboratory First Flight Test Demonstration of Neural Network Software http://www.afrlhorizons.com/Briefs/0001/VA9904.html
- Dryden Flight Research Center X-36 Tailless Fighter Agility Research Aircraft in flight http://www.dfrc.nasa.gov/Gallery/Photo/X-36
- NASA Dryden Flight Research Center Intelligent Flight Control Systems http://www.dfrc.nasa.gov/Newsroom/FactSheets/FS-076-DFRC.html
- Perhinschi M. G. , Napolitano M.R. , Campa G. , Seanor B. , Gururajan S. Design of Intelligent Flight Control Laws for the WVU F-22 Model Aircraft Proceedings of the AIAA Intelligent Systems Technical Conference 2004 Chicago IL
- Perhinschi M. G. , Napolitano M.R. , Campa G. , Burke H. E. , Larson R. R. , Burken J. , Fravolini M. L. Design and Testing of a Safety Monitor Scheme on the NASA Gen_2 IFCS F-15 Flight Simulator Proceedings of the AIAA Intelligent Systems Technical Conference 2004 Chicago IL
- Perhinschi M. G. , Burken J. , Napolitano M.R. , Campa G. , Fravolini M. L. Performance Comparison of Different Neural Augmentation for the NASA Gen_2 IFCS F-15 Control Laws Proceedings of the American Control Conference 2004 Boston MA 3180 3184
- Perhinschi M. G. , Napolitano M.R. , Campa G. , Fravolini M. L. Integration of Fault Tolerant System for Sensor and Actuator Failures within the WVU NASA F-15 Simulator Proceedings of the AIAA Guidance, Navigation, and Control Conference August 2003 Austin, Texas
- Perhinschi M. G. , Napolitano M.R. , Stolarik B. , Hammaker S. , Campa G. , Rogers S. Design Of Safety Monitor Schemes for a Fault Tolerant Flight Control System Proceedings of the AIAA Guidance, Navigation, and Control Conference August 2003 Austin, Texas
- Battipede M. , Gili P. , Lando M , Napolitano M. R. , Perhinschi M. G. , Campa G. Comparative Analysis of Neural Control Systems Within the NASA IFCS F-15 WVU Simulator Proceedings of the AIAA Guidance, Navigation, and Control Conference August 2003 Austin, Texas
- Perhinschi M. G. , Napolitano M.R. , Campa G. , Fravolini M. L. , Massotti L. , Lando M. Augmentation of a Non Linear Dynamic Inversion Scheme Within the NASA IFCS F-15 WVU Simulator Proceedings of the American Control Conference 2003 June 4 6 2003 Denver CO, USA 1667 1672
- Perhinschi M. G. , Campa G. , Napolitano M.R. , Fravolini M. L. , Lando M. , Massotti L. Performance Comparison of Fault Tolerant Control Laws Within the NASA IFCS F-15 WVU Simulator Proceedings of the American Control Conference 2003 June 4 6 2003 Denver CO, USA 1661 1666
- Battipede M. , Gili P. , Napolitano M. R. , Perhinschi M. G. , Massotti L. , Lando M. Implementation of an Adaptive Predictor-Corrector Neural Controller within the NASA IFCS F-15 WVU Simulator Proceedings of the American Control Conference 2003 June 4 6 2003 Denver CO, USA 1302 1307
- Perhinschi M. G. , Lando M. , Massotti L. , Fravolini M. L. , Campa G. , Napolitano M.R. On-Line Parameter Estimation for Real Time Application for the NASA IFCS F-15 Fault Tolerant Systems Proceedings of the American Control Conference Anchorage, AK 2002 191 196
- Coetzee , L. Parallel approaches to training feedforward neural nets Ph.D. Thesis University of Pretoria 1996
- Torrensen , J. Parallelization of Backpropagation Training for Feed-Forward Neural Networks Ph.D. Thesis The Norwegian Institute of Technology 1996
- Haykin , S. Neural Networks: A comprehensive Foundation McMillan College Publishing Company, Inc. 1994
- VanderPlas Jake Statistics, Data Mining, and Machine Learning in Astronomy 2013
- Chen , C.L. , Nutter , R.S. An Extended Back-Propagation Learning by Using Heterogeneous Processing Units Proceedings of International Joint Conference on Neural Networks III-988 993 Baltimore, Maryland 1992
- AVDS User Manual, Version 1.2.1 Artificial Horizons Inc. October 1999
- Marc Snir , M. , Otto , S. , Huss-Lederman , S. , Walker , D. , Dongarra , J. MPI: The Complete Reference MIT press 1999