Citation: Lan, B.; Lin, Y.-J.; Lai, Y.-H.;
Tang, C.-H.; Yang, J.-T. A Neural
Network Approach to Estimate
Transient Aerodynamic Properties of
a Flapping Wing System. Drones 2022,
6, 210. https://doi.org/10.3390/
drones6080210
Academic Editors: Andrzej
Łukaszewicz, Wojciech Giernacki,
Zbigniew Kulesza, Jaroslaw Pytka,
Andriy Holovatyy and Abdessattar
Abdelkefi
Received: 11 July 2022
Accepted: 12 August 2022
Published: 17 August 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
A Neural Network Approach to Estimate Transient
Aerodynamic Properties of a Flapping Wing System
Bluest Lan
1,2,
* , You-Jun Lin
1
, Yu-Hsiang Lai
1,3
, Chia-Hung Tang
1
and Jing-Tang Yang
1,
*
1
Department of Mechanical Engineering, National Taiwan University, Taipei 10617, Taiwan
2
Department of Mechanical Engineering, National Chung Hsing University, Taichung 40227, Taiwan
3
Department of Mechanical and Aerospace Engineering, Chung Cheng Institute of Technology,
National Defense University, Taoyuan 33551, Taiwan
* Correspondence: bluest@engineer.com (B.L.); jtyang@ntu.edu.tw (J.-T.Y.)
Abstract:
Understanding the causal impacts among various parameters is essential for designing
micro aerial vehicles (MAVs). The simulation of computational fluid dynamics (CFD) provides us
with a technique to calculate aerodynamic forces precisely. However, even a single result regularly
takes considerable computational time. Machine learning, due to the advance in computer hardware,
shows another approach that can speed up the analysis process. In this study, we introduce an
artificial neural network (ANN) framework to predict the transient aerodynamic forces and the
corresponding energy consumption. Instead of considering the whole transient changes of each
parameter as inputs, we utilised the technique of Fourier transform to simplify the ANN structure
for minimising the computation cost. Furthermore, two typical activation functions, rectified linear
unit (ReLU) and sigmoid, were attempted to build the network. The validity of the method was
further examined by comparing it with CFD simulation. The result shows that both functions are able
to provide highly accurate estimations that can be implemented for model construction under this
framework. Consequently, this novel approach makes it possible to reduce the complexity of analysis,
study the flapping wing aerodynamics and enable a more efficient way to optimise parameters.
Keywords: micro aerial vehicle; flapping wing; neural network; aerodynamics
1. Introduction
While a human can fly into the sky with a machine, the mechanism of insect flight
remains yet a mystery of sorts. Unlike conventional artificial aircraft, an insect exhibits
its fascinating aerial manoeuvrability by repeatedly flapping its wings. This particular
mechanism has recently been extensively investigated to develop an improved micro aerial
vehicle (MAV). Furthermore, aerodynamics at a small Reynolds number provides a more
efficient flight [
1
], which allows a MAV to cruise at a low speed to execute examination
tasks [2]
. As MAVs can overcome terrain constraints, they are expected to search for victims
in narrow buildings or explore dangerous environments by employing various
sensors [3,4]
.
However, as the flapping wing system is a relatively novel concept compared with other
aircraft, its mechanism has not been fully revealed yet. Considerable time is therefore
required to examine the impact of various variables.
Among various methods, some studies have reported their findings through biological
observations. Ellington [
5
] claimed that wing paths had no consistent patterns among
numerous insects. Wakeling and Ellington [
6
] displayed exceptional steady-state aerody-
namic property of dragonfly wings and utilised it to predict the parasite drag. Josephson
and Stevenson [
7
] measured the oxygen consumption from insects to evaluate the energy
efficiency of various flight patterns; Dial et al. [
8
] also presented the measured power con-
sumption of birds that flew at different speeds by examining the electromyograms (EMGs).
As it is tough to reproduce the same experiment due to the individual differences
and the uncontrolled environmental variables, some studies consequently built flapping
Drones 2022, 6, 210. https://doi.org/10.3390/drones6080210 https://www.mdpi.com/journal/drones
