Autenrieb, Johannes (Cranfield University), Shin, Hyo-Sang (Cranfield University), Bacic, Marko (University Of Oxford)

Development of a Neural Network-Based Adaptive Nonlinear Dynamic Inversion Controller for a Tilt-Wing VTOL Aircraft

Scheduled for presentation during the Regular Session "Control Architectures I" (MoD12T2), Monday, November 25, 2019, 10:50−11:10, Room T2

2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS), November 25-27, 2019, Cranfield University, Cranfield, UK

This information is tentative and subject to change. Compiled on April 25, 2024

Abstract

This paper presents an adaptive control strategy for a tilt-wing vertical take-off and landing (VTOL) aircraft system. To solve the highly nonlinear control problem, a time-scale separated nonlinear dynamic inversion (NDI) control scheme is proposed to regulate a VTOL aircraft system. In order to handle the existing model uncertainties, an adaptive neural network (ANN) is additionally introduced to the flight control strategy. Due to the fact that the tilt-wing aircraft is able to operate in a conventional take-off and landing (CTOL) mode as well as in a multi-copter VTOL mode, two distinct flight control systems for each mode have been implemented. In order to ensure a safe transition between both modes, a tilt angle-depending linear control mixing approach is applied. The performance of the suggested control approach is investigated by utilising a high fidelity nonlinear flight dynamics model of the tilt-wing system. The results presented demonstrate that the proposed approach provides significant benefits for the robust control of the tilt-wing system.