Application of self-organizing map on flight data analysis for quadcopter health diagnosis system

De Li Cheng, Wei Hsiang Lai

Research output: Contribution to journalConference article

Abstract

The UAS fault problem has led to many potential risk factors behind its rapid development in recent years. Therefore, the diagnosis of UAS health status is still an important issue. This study adopted the SOM machine learning method which is an unsupervised clustering method to establish a model for diagnosing the health status of quadcopter. Take the vibration features of three flight states (undamaged, motor mount loose, unbalanced broken propeller). Through those training data the model can cluster different vibration pattern of fault situation. It not only can classify the failure status with 99% accuracy but also can provide pre-failure indicators.

Original languageEnglish
Pages (from-to)241-246
Number of pages6
JournalInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
Volume42
Issue number2/W13
DOIs
Publication statusPublished - 2019 Jun 4
Event4th ISPRS Geospatial Week 2019 - Enschede, Netherlands
Duration: 2019 Jun 102019 Jun 14

Fingerprint

Self organizing maps
health status
flight
vibration
data analysis
Health
Propellers
learning method
health
risk factor
Learning systems
method
indicator
machine learning

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Geography, Planning and Development

Cite this

@article{565e75ef931c43779a3e8a1017395328,
title = "Application of self-organizing map on flight data analysis for quadcopter health diagnosis system",
abstract = "The UAS fault problem has led to many potential risk factors behind its rapid development in recent years. Therefore, the diagnosis of UAS health status is still an important issue. This study adopted the SOM machine learning method which is an unsupervised clustering method to establish a model for diagnosing the health status of quadcopter. Take the vibration features of three flight states (undamaged, motor mount loose, unbalanced broken propeller). Through those training data the model can cluster different vibration pattern of fault situation. It not only can classify the failure status with 99{\%} accuracy but also can provide pre-failure indicators.",
author = "Cheng, {De Li} and Lai, {Wei Hsiang}",
year = "2019",
month = "6",
day = "4",
doi = "10.5194/isprs-archives-XLII-2-W13-241-2019",
language = "English",
volume = "42",
pages = "241--246",
journal = "International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives",
issn = "1682-1750",
number = "2/W13",

}

TY - JOUR

T1 - Application of self-organizing map on flight data analysis for quadcopter health diagnosis system

AU - Cheng, De Li

AU - Lai, Wei Hsiang

PY - 2019/6/4

Y1 - 2019/6/4

N2 - The UAS fault problem has led to many potential risk factors behind its rapid development in recent years. Therefore, the diagnosis of UAS health status is still an important issue. This study adopted the SOM machine learning method which is an unsupervised clustering method to establish a model for diagnosing the health status of quadcopter. Take the vibration features of three flight states (undamaged, motor mount loose, unbalanced broken propeller). Through those training data the model can cluster different vibration pattern of fault situation. It not only can classify the failure status with 99% accuracy but also can provide pre-failure indicators.

AB - The UAS fault problem has led to many potential risk factors behind its rapid development in recent years. Therefore, the diagnosis of UAS health status is still an important issue. This study adopted the SOM machine learning method which is an unsupervised clustering method to establish a model for diagnosing the health status of quadcopter. Take the vibration features of three flight states (undamaged, motor mount loose, unbalanced broken propeller). Through those training data the model can cluster different vibration pattern of fault situation. It not only can classify the failure status with 99% accuracy but also can provide pre-failure indicators.

UR - http://www.scopus.com/inward/record.url?scp=85067474892&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067474892&partnerID=8YFLogxK

U2 - 10.5194/isprs-archives-XLII-2-W13-241-2019

DO - 10.5194/isprs-archives-XLII-2-W13-241-2019

M3 - Conference article

AN - SCOPUS:85067474892

VL - 42

SP - 241

EP - 246

JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

SN - 1682-1750

IS - 2/W13

ER -