Data-driven diagnosis of multicopter thrust fault using supervised learning with inertial sensors

Simple item page
dc.contributor.authorKim, Taegyun
dc.contributor.authorKim, Seungkeun
dc.contributor.authorShin, Hyosang
dc.date.accessioned2023-11-16T15:46:46Z
dc.date.available2023-11-16T15:46:46Z
dc.date.issued2023-09-25
dc.description.abstractThis study proposes a data-driven fault diagnosis for multicopter unmanned aerial vehicles that uses the principal direction vector of inertial measurement unit (IMU) sensor signals calculated by principal component analysis. The main idea comes from the fact that a normal sphere-shaped distribution of the sensor data changes to a specific elliptical shape under a certain thrust fault situation. The fault diagnosis is based on classification and regression using supervised learning with the gyroscope and accelerometer datasets of an IMU. We analyze the performance of the proposed approach by depending on different learning algorithms. To verify the diagnostic performance, ground experiments with a hexacopter on the gimbaled jig are performed for various cases of damaged propellers. Then, the applicability of the proposed data-driven fault diagnosis is confirmed by analyzing the accuracy of the fault’s location and degree.en_UK
dc.identifier.citationKim T, Kim S, Shin H-S. (2023) Data-driven diagnosis of multicopter thrust fault using supervised learning with inertial sensors. Journal of Aerospace Information Systems, Volume 20, Number 11, November 2023, pp. 690-701en_UK
dc.identifier.issn2327-3097
dc.identifier.urihttps://doi.org/10.2514/1.I011256
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/20551
dc.language.isoenen_UK
dc.publisherAIAAen_UK
dc.rightsAttribution-NonCommercial 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/*
dc.subjectonboard sensorsen_UK
dc.subjectvibration measuring instrumentsen_UK
dc.subjectunmanned aerial vehicleen_UK
dc.subjectpropellersen_UK
dc.subjectartificial neural networken_UK
dc.subjectsupport vector machineen_UK
dc.subjectfault detection and diagnosisen_UK
dc.subjectinertial measurement uniten_UK
dc.subjectfault detectionen_UK
dc.subjectdata-driven system monitoringen_UK
dc.titleData-driven diagnosis of multicopter thrust fault using supervised learning with inertial sensorsen_UK
dc.typeArticleen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Data-driven_diagnosis_of_multicopter_thrust_fault-2023.pdf
Size:
3.48 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)