Direct adaptive flight envelope protection

---

Tezin Türü: Doktora

Tezin Yürütüldüğü Kurum: Orta Doğu Teknik Üniversitesi, Mühendislik Fakültesi, Havacılık ve Uzay Mühendisliği Bölümü, Türkiye

Tezin Onay Tarihi: 2016

Öğrenci: GÖNENÇ GÜRSOY

Danışman: İLKAY YAVRUCUK

Özet:

In this thesis, two vital signals to enable flight envelope protection, namely the onset to the flight envelope, i.e. limit margin, and the available control travel to reach the limit boundary, i.e. control margin, are estimated using adaptive neural-network-based approximate models. An adaptive learning method, known as concurrent learning, is used to update the adaptive weights online with guaranteed signal bounds. Current and previously recorded data are used concurrently in the weight update. Minimum singular value maximization method is used to record necessary data online for concurrent learning. Results showed better convergence properties of the network weights compared with results in the literature in which only the current data is used for network weight updates. New methodologies are introduced to calculate limit and control margins from approximate online models. None of the introduced methods require online iterations and therefore remove a previously introduced assumption related to iteration convergence. Nonlinear fixed wing and rotary wing aircraft models are used to show the effectiveness in simulation for estimating limit and control margins and avoiding the limit through artificial control saturation.