Citation: Bondyra, A.; Kołodziejczak,
M.; Kulikowski, R.; Giernacki, W.
An Acoustic Fault Detection and
Isolation System for Multirotor UAV.
Energies 2022, 15, 3955. https://
doi.org/10.3390/en15113955
Academic Editor: Francisco
Manzano Agugliaro
Received: 6 May 2022
Accepted: 24 May 2022
Published: 27 May 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
An Acoustic Fault Detection and Isolation System for
Multirotor UAV
Adam Bondyra * , Marek Kołodziejczak, Radosław Kulikowski and Wojciech Giernacki
Faculty of Automatic Control, Robotics and Electrical Engineering, Institute of Robotics and Machine Intelligence,
Poznan University of Technology, ul. Piotrowo 3a, 60-965 Poznan, Poland;
marek.s.kolodziejczak@student.put.poznan.pl (M.K.); radoslaw.kulikowski@student.put.poznan.pl (R.K.);
wojciech.giernacki@put.poznan.pl (W.G.)
* Correspondence: adam.bondyra@put.poznan.pl
Abstract:
With the rising popularity of unmanned aerial vehicles (UAVs) and increasing variety of
their applications, the task of providing reliable and robust control systems becomes significant. An
active fault-tolerant control (FTC) scheme requires an effective fault detection and isolation (FDI)
algorithm to provide information about the fault’s occurrence and its location. This work aims to
present a prototype of a diagnostic system intended to recognize and identify broken blades of rotary
wing UAVs. The solution is based on an analysis of acoustic emission recorded with an onboard
microphone array paired with a lightweight yet powerful single-board computer. The standalone
hardware of the FDI system was utilized to collect a wide and publicly available dataset of recordings
in real-world experiments. The detection algorithm itself is a data-driven approach that makes use of
an artificial neural network to classify characteristic features of acoustic signals. Fault signature is
based on Mel Frequency Spectrum Coefficients. Furthermore, in the paper an extensive evaluation of
the model’s parameters was performed. As a result, a highly accurate fault classifier was developed.
The best models allow not only a detection of fault occurrence, but thanks to multichannel data
provided with a microphone array, the location of the impaired rotor is reported, as well.
Keywords: UAV; fault detection; rotor; data-driven; acoustic
1. Introduction
1.1. Background
The increasing number and variety of applications of unmanned aerial vehicles raise
the question of operational safety and reliability [
1
,
2
]. Few recent studies have pointed
out the key causes of drone accidents in flight, with actuator faults being one of the major
issues, both in military and commercial UAVs [
3
,
4
]. This challenge is often addressed with
fault-tolerant control systems, which provide minimal performance for the aerial vehicle
in the occurrence of faults [
5
]. FTC strategies are typically divided into two categories.
Passive approaches aim to provide robustness of control algorithms and utilize hardware
redundancy. On the other hand, active systems are based on the fault detection algorithm
and real-time adjustment of the control laws [
6
]. The fault diagnosis stage itself is frequently
divided into the basic detection of the fault followed by its isolation, which is defined as
the determination of the exact location of the faulty component [
7
]. It is believed that
precise fault detection and isolation systems, as crucial components of FTC control schemes,
will significantly increase the safety of operating UAVs and, as a result, accelerate their
introduction to practical applications [8].
1.2. Research Motivation
In this article, a new approach to the problem addressed in a couple of our previous
works [
9
,
10
] is presented. The main focus was placed on the problem of efficient fault
detection and isolation of damaged propellers of multirotor UAV. The initial approaches
Energies 2022, 15, 3955. https://doi.org/10.3390/en15113955 https://www.mdpi.com/journal/energies
