Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Remaining Useful Battery Life Prediction for UAVs based on Machine Learning
Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.ORCID-id: 0000-0001-7631-002X
Laboratory of Knowledge and Intelligent Computing, Department of Computer Engineering, Technological Educational Institute of Epirus.
Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.ORCID-id: 0000-0001-9701-4203
Luleå tekniska universitet, Institutionen för system- och rymdteknik, Signaler och system.ORCID-id: 0000-0003-0126-1897
2017 (Engelska)Ingår i: IFAC-PapersOnLine, ISSN 1045-0823, E-ISSN 1797-318X, Vol. 50, nr 1, s. 4727-4732Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

Unmanned Aerial Vehicles are becoming part of many industrial applications. The advancements in battery technologies played a crucial part for this trend. However, no matter what the advancements are, all batteries have a fixed capacity and after some time drain out. In order to extend the flying time window, the prediction of the time that the battery will no longer be able to support a flying condition is crucial. This in fact can be cast as a standard Remaining Useful Life prognostic problem, similarly encountered in many fields. In this article, the problem of Remaining Useful Life estimation of a battery, under different flight conditions, is tackled using four machine learning techniques: a linear sparse model, a variant of support vector regression, a multilayer perceptron and an advanced tree based algorithm. The efficiency of the overall proposed machine learning techniques, in the field of batteries prognostics, is evaluated based on multiple experimental data from different flight conditions.

Ort, förlag, år, upplaga, sidor
Elsevier, 2017. Vol. 50, nr 1, s. 4727-4732
Nationell ämneskategori
Reglerteknik
Forskningsämne
Reglerteknik
Identifikatorer
URN: urn:nbn:se:ltu:diva-66196DOI: 10.1016/j.ifacol.2017.08.863Scopus ID: 2-s2.0-85031802665OAI: oai:DiVA.org:ltu-66196DiVA, id: diva2:1150694
Konferens
20th IFAC World Congress, Toulouse, France, 9-14 July 2017
Projekt
Collaborative Aerial Robotic Workers, AEROWORKSIntegrated Process Control based on Distributed In-Situ Sensors into Raw Material and Energy Feedstock, DISIRE
Forskningsfinansiär
EU, Horisont 2020, 644128EU, Horisont 2020, 636834
Anmärkning

Konferensartikel i tidskrift

Tillgänglig från: 2017-10-19 Skapad: 2017-10-19 Senast uppdaterad: 2018-05-29Bibliografiskt granskad
Ingår i avhandling
1. On Visual Area Coverage Using Micro Aerial Vehicles
Öppna denna publikation i ny flik eller fönster >>On Visual Area Coverage Using Micro Aerial Vehicles
2018 (Engelska)Licentiatavhandling, sammanläggning (Övrigt vetenskapligt)
Abstract [en]

The aim of this Licentiate is to advance the field of cooperative visual coverage path planners for multiple Micro Aerial Vehicles (MAVs), while aiming for their real life adoption towards the tasks of aerial infrastructure inspection. The fields that will be addressed are focusing in: a) the collaborative perception of the environment, b) the collaborative visual inspection, and c) the optimization of the aerial missions based on the remaining flying battery, camera constraints, coverage constraints and other real life mission induced constraints.

Towards this envisioned aim, this Licentiate will present the following main theoretical contributions: a) centralized and distributed Model Predictive Control (MPC) schemes for the cooperative motion control of MAVs focusing in the establishing of a formation control architecture to enable a dynamic visual sensor from monocular cameras towards a reconfigurable environmental perception, b) revisiting the Cooperative Coverage Path Planning (C-CPP) problem for the inspection of complex infrastructures, c) developing a holistic approach to the problems of 2-D area coverage with MAVs for polygon areas, while considering the camera footprint, and d) designing of a scheme to estimate the Remaining Useful Life (RUL) of the battery during a flight mission, a fact that directly effects the flying capabilities of the MAVs. The theoretical contributions of this thesis have been extensively evaluated in simulation and real life large scale field trials, a direction that adds another contribution of the suggested framework towards the massive insertion of the aerial platforms as aerial tools in the close future.

In the first part of this Licentiate, the vision, motivation, open challenges, contributions, and future works are discussed, while in the second part the full articles connected to the presented contributions in this Licentiate are presented in the annex.

Ort, förlag, år, upplaga, sidor
Luleå: Luleå tekniska universitet, 2018
Serie
Licentiate thesis / Luleå University of Technology, ISSN 1402-1757
Nationell ämneskategori
Reglerteknik
Forskningsämne
Reglerteknik
Identifikatorer
urn:nbn:se:ltu:diva-68666 (URN)978-91-7790-140-2 (ISBN)978-91-7790-141-9 (ISBN)
Presentation
2018-06-15, A1547, Luleå tekniska universitet, Luleå, 13:00 (Engelska)
Opponent
Handledare
Tillgänglig från: 2018-05-07 Skapad: 2018-05-07 Senast uppdaterad: 2018-06-08Bibliografiskt granskad

Open Access i DiVA

fulltext(388 kB)2 nedladdningar
Filinformation
Filnamn FULLTEXT01.pdfFilstorlek 388 kBChecksumma SHA-512
ab2444d8bd4d502b60f83bc084261c4f2df44dafb81368066ff1e6bdcc775e8c4850b176cb557d7f5c0070e3e0c9ae3e588cac2959f9214b5071926dc45badc5
Typ fulltextMimetyp application/pdf

Övriga länkar

Förlagets fulltextScopus

Personposter BETA

Mansouri, Sina SharifGeorgoulas, GeorgiosNikolakopoulos, George

Sök vidare i DiVA

Av författaren/redaktören
Mansouri, Sina SharifGeorgoulas, GeorgiosNikolakopoulos, George
Av organisationen
Signaler och system
I samma tidskrift
IFAC-PapersOnLine
Reglerteknik

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 2 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 36 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf