A physics-based neural network for flight dynamics modelling and simulation
Authors:
Open Access
- 4 July 2022
- journal article
- research article
- Published by Springer Nature in Advanced Modeling and Simulation in Engineering Sciences
- Vol. 9 (1) , 1-20
Abstract
The authors have developed a novel physics-based nonlinear autoregressive exogeneous neural network model architecture for flight modelling across the entire flight envelope, calledFlyNet. When using traditional parameter estimation and output-error methods, aircraft models are captured about a single point in the flight envelope using a first-order Taylor series to approximate forces and moments. To enable analysis throughout the entire operational envelope, the traditional models can be extended by interpolating or stitching between a number of these single-condition models. This paper completes the evolutionary next step in aircraft modelling to consider all second-order Taylor series terms instead of a subset of those and by exploiting the ability of neural networks to capture more complex and nonlinear behaviour for the efficient development of a continuous flight simulation model valid across the entire envelope. This method is valid for fixed- and rotary-wing aircraft. The behaviour of a conventional model is compared to FlyNet using flight test data collected from the National Research Council of Canada’s Bell 412HP in forward flight.Keywords
All Related Versions
This publication has 35 references indexed in Scilit:
- Deep learning helicopter dynamics models2015
- Identification of nonlinear aerodynamic derivatives using classical and extended local model networksAerospace Science and Technology, 2011
- A Multidimensional Spline-Based Global Nonlinear Aerodynamic Model for the Cessna Citation II2010
- Online Aerodynamic Model Structure Selection and Parameter Estimation for Fault Tolerant ControlJournal of Guidance, Control, and Dynamics, 2010
- Aircraft parameter estimation using output-error methodsInverse Problems in Science and Engineering, 2006
- Feedforward neural network based non‐linear dynamic modelling of a TRMS using RPROP algorithmAircraft Engineering and Aerospace Technology, 2005
- Advances in Real-Time Aerodynamic Model IdentificationJournal of Aircraft, 2005
- A trust region method based on interior point techniques for nonlinear programmingMathematical Programming, 2000
- Global nonlinear aerodynamic modeling using multivariate orthogonal functionsJournal of Aircraft, 1995
- Partitioning of flight data for aerodynamic modeling of aircraft at high angles of attackJournal of Aircraft, 1989