This chapter outlines a methodology for computation of aerodynamic derivatives directly from flight data using radial basis function network (RBFN). The delta method using RBFN is first applied to simulated data with added measurement and state noise. The delta method is an artificial neural network (ANN)‐based approach for parameter estimation. The derivative calculated using this method considers all the data points, thus smoothing noisy data. All presented results are obtained using the RBFN‐based delta method. The chapter discusses rotorcraft parameter estimation based on the RBFN‐based delta method. This technique is model‐free and is suitable for rotorcraft unmanned air vehicles (UAVs) and micro air vehicles (MAVs). The method is first evaluated on simulated data generated by a nonlinear simulation model. The helicopter can be mathematically modeled by considering it as a number of subsystems: the main rotor, fuselage, powerplant, empennage, tail rotor and flight control systems. The helicopter dynamics are assessed about its center of gravity.
Aerodynamic Derivative Calculation Using Radial Basis Function Neural Networks
2017-04-03
25 pages
Article/Chapter (Book)
Electronic Resource
English
Unsteady aerodynamic modeling based on fuzzy scalar radial basis function neural networks
SAGE Publications | 2019
|Aerodynamic Parameters Estimation Using Radial Basis Function Neural Partial Differentiation Method
BASE | 2018
|Vehicle tracking using radial basis function neural networks
Automotive engineering | 1996
|Vehicle Tracking using Radial Basis Function Neural Networks
British Library Conference Proceedings | 1996
|