Aeroelasticity & Structural Dynamics in a Fast Changing World
17 – 21 June 2024, The Hague, The Netherlands
Home Program Author Index Search

Nonlinear aeroelastic analysis of a regional airliner wing via a neural-network based reduced order model for aerodynamics


Go-down ifasd2024 Tracking Number 161

Presentation:
Session: Data driven methods 2
Room: Room 1.1
Session start: 11:00 Thu 20 Jun 2024

Nicolò Laureti   nicolo.laureti@uniroma1.it
Affifliation: Sapienza University of Rome
Luca Pustina   luca.pustina@uniroma1.it
Affifliation: Sapienza University of Rome
Marco Pizzoli   marco.pizzoli@uniroma1.it
Affifliation: Sapienza University of Rome
Francesco Saltari   francesco.saltari@uniroma1.it
Affifliation: Sapienza University of Rome
Franco Mastroddi   franco.mastroddi@uniroma1.it
Affifliation: Sapienza University of Rome

Topics: - Steady/Unsteady Aerodynamics (High and low fidelity (un)coupled analysis methods:), - Computational Aeroelasticity (High and low fidelity (un)coupled analysis methods:), - Highly Flexible Aircraft Structures (High and low fidelity (un)coupled analysis methods:), - Reduced Order Modeling (High and low fidelity (un)coupled analysis methods:), - Aeroelasticity in Conceptual Aircraft Design (Vehicle analysis/design using model-based and data driven models)

Abstract:

This paper investigates the use of a neural network based reduced order model to solve the nonlinear gust response of a regional aircraft wing characterised by high angle of attack and gust intensity. Dynamic aerodynamic stall is generally able to provide a natural load mitigation, which is generally not considered in aircraft design. The neural network is combined with strip theory, thus requiring the training of a single airfoil model. Given the difficulties in obtaining CFD based aerodynamic data due to the excessive time consuming simulations, the approach has started the training phase with data obtained from the Beddoes-Leishman unsteady aerodynamic model. The wing response is then evaluated by a reduced-order model implemented in the Simulink environment, based on Nastran structural data and strip theory, enhanced by a number of neural networks in parallel describing the nonlinear transient behavior.