Neural networks-based sensor validation for the flight control system of a B777 research model
Proceedings of the American Control Conference - Tập 1 - Trang 412-417 vol.1
Tóm tắt
Shows the results of the analysis of a scheme for sensor failure, detection, identification and accommodation (SFDIA) using experimental flight data of a research aircraft model. Conventional approaches to the problem are based on observers and Kalman filters while more recent methods are based on neural approximators. The work described in the paper is based on the use of neural networks (NNs) as online learning nonlinear approximators. The performances of two different neural architectures are compared. The first architecture is based on a multi layer perceptron NN trained with the extended backpropagation algorithm. The second architecture is based on a radial basis function (RBF) NN trained with the extended minimal resource allocating networks (EMRAN) algorithms. The experimental data for this study are acquired from the flight-testing of a 1/24th semi-scale B777 research model designed, built, and flown at West Virginia University.
Từ khóa
#Neural networks #Sensor systems #Aerospace control #Redundancy #Aircraft #Resource management #Fault tolerant systems #Fault detection #Mechanical sensors #Aerospace engineeringTài liệu tham khảo
10.1162/neco.1991.3.2.213
stevens, 1987, Aircraft Control and Simulation
10.2514/6.1992-4394
10.1080/00207179608921851
10.2514/3.21120
leger, 1998, Fault detection and diagnosis using statistical control charts and artificial neural networks, Artificial Intelligence in Engineering, 12, 35, 10.1016/S0954-1810(96)00039-8
10.1016/S0967-0661(97)00053-1
ha, 0, Reconfigurable aircraft flight control system via neural networks, Proceedings of Aerospace Design Conference 1992
10.1016/S0959-1524(97)00016-4
blanke, 2000, Fault-tolerant control of complex systems, Control of Complex Systems
napolitano, 1999, Design of the B777 model flight control system
patton, 0, Robust model based fault diagnosis: The state of the art, Proceedings of the IFAC International Conference on Fault Detection Supervision and Safety for Technical Processes Espoo Finland 1994
10.1023/A:1026571426761
10.1109/TIT.1982.1056529
lu, 0, Analysis of minimal radial basis function network algorithm for real-time identification of non-linear dynamic systems, IEEE Proceedings on Control Theory and Application 2000, 4, 476
10.2514/3.20242
patton, 1989, Fault diagnosis in dynamic systems: Theory and applications
10.1109/70.681254
fu, 1994, Neural Networks in Computer Intelligence
10.1016/S1369-8869(00)00009-4
10.1016/0005-1098(92)90053-I
10.2514/3.21542
10.1016/S1874-5946(98)80085-0
powell, 1987, Radial basis function for multivariable interpolation: A review, Algorithms for Approximation, 143