Using Multiple Deep Neural Networks Platform to Detect Different Types of Potential Faults in Unmanned Aerial Vehicles

Detalhes bibliográficos
Autor(a) principal: Alos,Ahmad
Data de Publicação: 2021
Outros Autores: Dahrouj,Zouhair
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Journal of Aerospace Technology and Management (Online)
Texto Completo: http://old.scielo.br/scielo.php?script=sci_arttext&pid=S2175-91462021000100309
Resumo: ABSTRACT Many researchers developed new algorithms to predict the faults of unmanned aerial vehicles (UAV). These algorithms detect anomalies in the streamed data of the UAV and label them as potential faults. Most of these algorithms consider neither the complex relationships among the UAV variables nor the temporal patterns of the previous instances, which leaves a potential opportunity for new ideas. A new method for analyzing the relationships and the temporal patterns of every two variables to detect the potentially defected sensors. The proposed method depends on a new platform, which is composed of multiple deep neural networks. The method starts by building and training this platform. The training step requires reshaping the dataset into a set of subdatasets. Each new subdataset is used to train one deep neural network. In the testing phase, the method reads new instances of the UAV testing dataset. The output of the algorithm is the predicted potential faults. The proposed approach is evaluated and compared it with other well-known algorithms. The proposed approach showed promising results in predicting different kinds of faults.
id DCTA-1_1b550fa0b6bfbde1cfc06ef4154759d0
oai_identifier_str oai:scielo:S2175-91462021000100309
network_acronym_str DCTA-1
network_name_str Journal of Aerospace Technology and Management (Online)
repository_id_str
spelling Using Multiple Deep Neural Networks Platform to Detect Different Types of Potential Faults in Unmanned Aerial VehiclesUAVDeep neural networkAnomaly detectionAbnormalFaultABSTRACT Many researchers developed new algorithms to predict the faults of unmanned aerial vehicles (UAV). These algorithms detect anomalies in the streamed data of the UAV and label them as potential faults. Most of these algorithms consider neither the complex relationships among the UAV variables nor the temporal patterns of the previous instances, which leaves a potential opportunity for new ideas. A new method for analyzing the relationships and the temporal patterns of every two variables to detect the potentially defected sensors. The proposed method depends on a new platform, which is composed of multiple deep neural networks. The method starts by building and training this platform. The training step requires reshaping the dataset into a set of subdatasets. Each new subdataset is used to train one deep neural network. In the testing phase, the method reads new instances of the UAV testing dataset. The output of the algorithm is the predicted potential faults. The proposed approach is evaluated and compared it with other well-known algorithms. The proposed approach showed promising results in predicting different kinds of faults.Departamento de Ciência e Tecnologia Aeroespacial2021-01-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S2175-91462021000100309Journal of Aerospace Technology and Management v.13 2021reponame:Journal of Aerospace Technology and Management (Online)instname:Departamento de Ciência e Tecnologia Aeroespacial (DCTA)instacron:DCTA10.1590/jatm.v13.1186info:eu-repo/semantics/openAccessAlos,AhmadDahrouj,Zouhaireng2021-02-11T00:00:00Zoai:scielo:S2175-91462021000100309Revistahttp://www.jatm.com.br/ONGhttps://old.scielo.br/oai/scielo-oai.php||secretary@jatm.com.br2175-91461984-9648opendoar:2021-02-11T00:00Journal of Aerospace Technology and Management (Online) - Departamento de Ciência e Tecnologia Aeroespacial (DCTA)false
dc.title.none.fl_str_mv Using Multiple Deep Neural Networks Platform to Detect Different Types of Potential Faults in Unmanned Aerial Vehicles
title Using Multiple Deep Neural Networks Platform to Detect Different Types of Potential Faults in Unmanned Aerial Vehicles
spellingShingle Using Multiple Deep Neural Networks Platform to Detect Different Types of Potential Faults in Unmanned Aerial Vehicles
Alos,Ahmad
UAV
Deep neural network
Anomaly detection
Abnormal
Fault
title_short Using Multiple Deep Neural Networks Platform to Detect Different Types of Potential Faults in Unmanned Aerial Vehicles
title_full Using Multiple Deep Neural Networks Platform to Detect Different Types of Potential Faults in Unmanned Aerial Vehicles
title_fullStr Using Multiple Deep Neural Networks Platform to Detect Different Types of Potential Faults in Unmanned Aerial Vehicles
title_full_unstemmed Using Multiple Deep Neural Networks Platform to Detect Different Types of Potential Faults in Unmanned Aerial Vehicles
title_sort Using Multiple Deep Neural Networks Platform to Detect Different Types of Potential Faults in Unmanned Aerial Vehicles
author Alos,Ahmad
author_facet Alos,Ahmad
Dahrouj,Zouhair
author_role author
author2 Dahrouj,Zouhair
author2_role author
dc.contributor.author.fl_str_mv Alos,Ahmad
Dahrouj,Zouhair
dc.subject.por.fl_str_mv UAV
Deep neural network
Anomaly detection
Abnormal
Fault
topic UAV
Deep neural network
Anomaly detection
Abnormal
Fault
description ABSTRACT Many researchers developed new algorithms to predict the faults of unmanned aerial vehicles (UAV). These algorithms detect anomalies in the streamed data of the UAV and label them as potential faults. Most of these algorithms consider neither the complex relationships among the UAV variables nor the temporal patterns of the previous instances, which leaves a potential opportunity for new ideas. A new method for analyzing the relationships and the temporal patterns of every two variables to detect the potentially defected sensors. The proposed method depends on a new platform, which is composed of multiple deep neural networks. The method starts by building and training this platform. The training step requires reshaping the dataset into a set of subdatasets. Each new subdataset is used to train one deep neural network. In the testing phase, the method reads new instances of the UAV testing dataset. The output of the algorithm is the predicted potential faults. The proposed approach is evaluated and compared it with other well-known algorithms. The proposed approach showed promising results in predicting different kinds of faults.
publishDate 2021
dc.date.none.fl_str_mv 2021-01-01
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://old.scielo.br/scielo.php?script=sci_arttext&pid=S2175-91462021000100309
url http://old.scielo.br/scielo.php?script=sci_arttext&pid=S2175-91462021000100309
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 10.1590/jatm.v13.1186
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv text/html
dc.publisher.none.fl_str_mv Departamento de Ciência e Tecnologia Aeroespacial
publisher.none.fl_str_mv Departamento de Ciência e Tecnologia Aeroespacial
dc.source.none.fl_str_mv Journal of Aerospace Technology and Management v.13 2021
reponame:Journal of Aerospace Technology and Management (Online)
instname:Departamento de Ciência e Tecnologia Aeroespacial (DCTA)
instacron:DCTA
instname_str Departamento de Ciência e Tecnologia Aeroespacial (DCTA)
instacron_str DCTA
institution DCTA
reponame_str Journal of Aerospace Technology and Management (Online)
collection Journal of Aerospace Technology and Management (Online)
repository.name.fl_str_mv Journal of Aerospace Technology and Management (Online) - Departamento de Ciência e Tecnologia Aeroespacial (DCTA)
repository.mail.fl_str_mv ||secretary@jatm.com.br
_version_ 1754732532367097856