论文信息 - Performance comparison of different neural augmentation for the NASA Gen-2 IFCS F-15 control laws

Performance comparison of different neural augmentation for the NASA Gen-2 IFCS F-15 control laws

This paper describes the results of a study focused on comparing the performance of three different neural augmentations of the dynamic inversion-based control laws used for fault tolerant purposes on the NASA IFCS F-15 aircraft. The performance of the specific neural algorithms, the extended minimal resource allocating networks algorithm, the single hidden layer neural network, and the SigmaPi neural network have been compared. The comparison has been conducted in terms of specific parameters relative to the tracking of desirable handling qualities following the injection of simulated failures on the actuators of the right stabilator and the left canard of the NASA F-15 aircraft. The simulation results have shown that all three neural networks have promising performance with the extended minimal resource allocating networks algorithm slightly outperforming the other algorithms.

M.L. Fravolini | G. Campa | M.R. Napolitano | M.G. Perhinschi | J. Burken

[1] Anthony J. Calise,et al. Adaptive Autopilot Design for Guided Munitions , 1998 .

[2] Joydeep Ghosh,et al. The pi-sigma network: an efficient higher-order neural network for pattern classification and function approximation , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[3] M. L. Fravolini,et al. Comparison of different growing radial basis functions algorithms for control systems applications , 2002, Proceedings of the 2002 American Control Conference (IEEE Cat. No.CH37301).

[4] Joseph J. Totah,et al. GENERIC NEURAL FLIGHT CONTROL AND AUTOPILOT SYSTEM , 2000 .

[5] Seungjae Lee,et al. Direct adaptive reconfigurable control of a tailless fighter aircraft , 1998 .

[6] John Kaneshige,et al. INTEGRATED NEURAL FLIGHT AND PROPULSION CONTROL SYSTEM , 2001 .

[7] Yan Li,et al. Analysis of minimal radial basis function network algorithm for real-time identification of nonlinear dynamic systems , 2000 .

[8] Anthony J. Calise,et al. FAULT TOLERANT FLIGHT CONTROL VIA ADAPTIVE NEURAL NETWORK AUGMENTATION , 1998 .

[9] Mario G. Perhinschi,et al. A SIMULATION TOOL FOR ON-LINE REAL TIME PARAMETER IDENTIFICATION , 2002 .

[10] Marios M. Polycarpou. On-line approximators for nonlinear system identification: A unified approach , 1998 .

[11] Marcello R. Napolitano,et al. A library of adaptive neural networks for control purposes , 2002, Proceedings. IEEE International Symposium on Computer Aided Control System Design.