A Compound Fault Labeling and Diagnosis Method Based on Flight Data and BIT Record of UAV
In the process of Unmanned Aerial Vehicle (UAV) flight testing, plenty of compound faults exist, which could be composed of concurrent single faults or over-limit states alarmed by Built-In-Test (BIT) equipment. At present, there still lacks a suitable automatic labeling approach for UAV flight data...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-06-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/11/12/5410 |
id |
doaj-9d72b4305aba40958bd35ec41724ed68 |
---|---|
record_format |
Article |
spelling |
doaj-9d72b4305aba40958bd35ec41724ed682021-06-30T23:51:59ZengMDPI AGApplied Sciences2076-34172021-06-01115410541010.3390/app11125410A Compound Fault Labeling and Diagnosis Method Based on Flight Data and BIT Record of UAVKe Zheng0Guozhu Jia1Linchao Yang2Jiaqing Wang3School of Economics and Management, Beihang University, Beijing 100191, ChinaSchool of Economics and Management, Beihang University, Beijing 100191, ChinaSchool of Economics and Management, Beihang University, Beijing 100191, ChinaSchool of Business, Stevens Institute of Technology, Hoboken, NJ 07030, USAIn the process of Unmanned Aerial Vehicle (UAV) flight testing, plenty of compound faults exist, which could be composed of concurrent single faults or over-limit states alarmed by Built-In-Test (BIT) equipment. At present, there still lacks a suitable automatic labeling approach for UAV flight data, effectively utilizing the information of the BIT record. The performance of the originally employed flight data-driven fault diagnosis models based on machine learning needs to be improved as well. A compound fault labeling and diagnosis method based on actual flight data and the BIT record of the UAV during flight test phase is proposed, through labeling the flight data with compound fault modes corresponding to concurrent single faults recorded by the BIT system, and upgrading the original diagnosis model based on Gradient Boosting Decision Tree (GBDT) and Fully Convolutional Network (FCNN), to eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM) and modified Convolutional Neural Network (CNN). The experimental results based on actual test flight data show that the proposed method could effectively label the flight data and obtain a significant improvement in diagnostic performance, appearing to be practical in the UAV test flight process.https://www.mdpi.com/2076-3417/11/12/5410fault diagnosisdata labelingUAVflight data and BIT recordmachine learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ke Zheng Guozhu Jia Linchao Yang Jiaqing Wang |
spellingShingle |
Ke Zheng Guozhu Jia Linchao Yang Jiaqing Wang A Compound Fault Labeling and Diagnosis Method Based on Flight Data and BIT Record of UAV Applied Sciences fault diagnosis data labeling UAV flight data and BIT record machine learning |
author_facet |
Ke Zheng Guozhu Jia Linchao Yang Jiaqing Wang |
author_sort |
Ke Zheng |
title |
A Compound Fault Labeling and Diagnosis Method Based on Flight Data and BIT Record of UAV |
title_short |
A Compound Fault Labeling and Diagnosis Method Based on Flight Data and BIT Record of UAV |
title_full |
A Compound Fault Labeling and Diagnosis Method Based on Flight Data and BIT Record of UAV |
title_fullStr |
A Compound Fault Labeling and Diagnosis Method Based on Flight Data and BIT Record of UAV |
title_full_unstemmed |
A Compound Fault Labeling and Diagnosis Method Based on Flight Data and BIT Record of UAV |
title_sort |
compound fault labeling and diagnosis method based on flight data and bit record of uav |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2021-06-01 |
description |
In the process of Unmanned Aerial Vehicle (UAV) flight testing, plenty of compound faults exist, which could be composed of concurrent single faults or over-limit states alarmed by Built-In-Test (BIT) equipment. At present, there still lacks a suitable automatic labeling approach for UAV flight data, effectively utilizing the information of the BIT record. The performance of the originally employed flight data-driven fault diagnosis models based on machine learning needs to be improved as well. A compound fault labeling and diagnosis method based on actual flight data and the BIT record of the UAV during flight test phase is proposed, through labeling the flight data with compound fault modes corresponding to concurrent single faults recorded by the BIT system, and upgrading the original diagnosis model based on Gradient Boosting Decision Tree (GBDT) and Fully Convolutional Network (FCNN), to eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM) and modified Convolutional Neural Network (CNN). The experimental results based on actual test flight data show that the proposed method could effectively label the flight data and obtain a significant improvement in diagnostic performance, appearing to be practical in the UAV test flight process. |
topic |
fault diagnosis data labeling UAV flight data and BIT record machine learning |
url |
https://www.mdpi.com/2076-3417/11/12/5410 |
work_keys_str_mv |
AT kezheng acompoundfaultlabelinganddiagnosismethodbasedonflightdataandbitrecordofuav AT guozhujia acompoundfaultlabelinganddiagnosismethodbasedonflightdataandbitrecordofuav AT linchaoyang acompoundfaultlabelinganddiagnosismethodbasedonflightdataandbitrecordofuav AT jiaqingwang acompoundfaultlabelinganddiagnosismethodbasedonflightdataandbitrecordofuav AT kezheng compoundfaultlabelinganddiagnosismethodbasedonflightdataandbitrecordofuav AT guozhujia compoundfaultlabelinganddiagnosismethodbasedonflightdataandbitrecordofuav AT linchaoyang compoundfaultlabelinganddiagnosismethodbasedonflightdataandbitrecordofuav AT jiaqingwang compoundfaultlabelinganddiagnosismethodbasedonflightdataandbitrecordofuav |
_version_ |
1721350236493840384 |