REAL-TIME AUTOMATIC TUNING OF AN AIRCRAFT SIDESLIP ESTIMATOR
暂无分享,去创建一个
Abstract The problem presented in this paper is that of finding a method that would allow engineers to tune a “grey-box” sideslip estimator of a new aircraft, known only by a wind-tunnel model, using flight test data. The method that is proposed here, makes a combined use of local learning and real-time parameter estimation techniques. The presented results are obtained using a Simulink-based estimator, stimulated by flight test data.
[1] Roderick Murray-Smith,et al. Local model networks and local learning , 1994 .
[2] Miroslav Kárný,et al. Tracking of Slowly Varying Parameters by Directional Forgetting , 1984 .
[3] Andrew W. Moore,et al. Locally Weighted Learning , 1997, Artificial Intelligence Review.