Abstract
Online aerodynamic parameter estimation plays an important role in compensating control system of aircraft under parameter uncertainties and unknown disturbance. In this paper, stability and control derivatives of aircraft are estimated online via support vector regression-numerical differential(SVR-ND) method. Small-sample real-time flight data reflecting real-time aerodynamic characteristics of aircraft is processed as training samples. For the small-size training samples, SVR technique is used for aerodynamic modeling. To pursue good performance in both computation efficiency and estimation accuracy, offline parameter estimation simulations are performed to select training sample size. It is observed that parameter estimation accuracy is related to the number of training samples and the noise level of samples. After that, an empirical formula is proposed to select training sample size according to results of simulations. To adapt the variation of samples, empirical formulas to tune hyper-parameters of SVR are presented based on the estimation of noise variance of samples. Finally, aerodynamic parameters are obtained by numerical differential in real-time. In a simulated maneuver, the proposed method is applied to online aerodynamic parameter estimation, and a Monte Carlo simulation is carried out to validate the robustness of SVR-ND method. Results indicate that the proposed method could realize accurate and robust estimation of aerodynamic parameters online.
Highlights
Wind tunnel tests and computational method are always performed before parameter estimation to establish an aerodynamic model and obtain aerodynamic parameters
Extracting the stability and control derivatives from flight data is defined as aerodynamic parameter estimation, which has become a routine step in aircraft design and system performance evaluation [3]
SVR-ND method begins with real-time flight data processing to obtain training samples
Summary
Three approaches have been developed to obtain accurate aerodynamic characteristic of an aircraft, including wind tunnel tests, computational method and parameter estimation method. With the improvement of flight capability, the flight envelope of aircraft is becoming larger and the environment of flight gets more complex In this situation, high performance autopilot depends more on accurate and real-time aerodynamic parameters and the support of online estimation techniques is increasingly needed. The proposed method can estimate aerodynamic parameter online accurately and robustly with a low time overhead It has a good scalability and can be used as an offline method, and an online method to provide support for online flight ability prediction based on aerodynamic prediction capability of SVR model
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have