New Approach for the Identification and Validation of a Nonlinear F/A-18 Model by Use of Neural Networks

• Published in: IEEE transaction on neural networks and learning systems 2010-11, Vol.21 (11), p.1759-1765
• Main Authors: Boëly, Nicolas, Botez, R M
• Format: Article
• Language: English
• Subjects: Aeroservoelasticity; Aircraft; Aircraft - standards; aircraft validation and identification; Algorithms; Altitude; Applied sciences; Artificial Intelligence; Artificial neural networks; Atmospheric modeling; Aviation - methods; Computer science; control theory; systems; Control theory. Systems; Data models; Elasticity; Exact sciences and technology; flight flutter tests; Flutter; Fundamental areas of phenomenology (including applications); Measurement and testing methods; Military aircraft; Military planes; MIMO; Modelling and identification; neural network; Neural networks; Neural Networks (Computer); Neurons; Neurons - physiology; Nonlinear Dynamics; Optimization; Physics; Robustness; Software Validation; Solid mechanics; Stress, Mechanical; Structural and continuum mechanics; Vibration; Vibration, mechanical wave, dynamic stability (aeroelasticity, vibration control...)
• ISSN: 1045-9227; 2162-237X; 1941-0093; 2162-2388
• DOI: 10.1109/TNN.2010.2071398

This paper presents a new approach for identifying and validating the F/A-18 aeroservoelastic model, based on flight flutter tests. The neural network (NN), trained with five different flight flutter cases, is validated using 11 other flight flutter test (FFT) data. A total of 16 FFT cases were obtained for all three flight regimes (subsonic, transonic, and supersonic) at Mach numbers ranging between 0.85 and 1.30 and at altitudes of between 5000 and 25 000 ft. The results obtained highlight the efficiency of the multilayer perceptron NN in model identification. Optimization of the NN requires mixing of two proprieties: the hidden layer size reduction and four-layered NN performances. This paper shows that a four-layer NN with only 16 neurons is enough to create an accurate model. The fit coefficients were higher than 92% for both the identification and the validation test data, thus demonstrating accuracy of the NN.