A comparison of state-of-the-art machine learning algorithms on fault indication and remaining useful life determination by telemetry data

Simple item page
buir.contributor.authorÜnal, Aras Fırat
buir.contributor.authorKaleli, Ali Yücel
dc.citation.epage85en_US
dc.citation.spage79en_US
dc.contributor.authorÜnal, Aras Fırat
dc.contributor.authorKaleli, Ali Yücel
dc.contributor.authorUmmak, Emre
dc.contributor.authorAlbayrak, Özlem
dc.contributor.editorYounas, M.
dc.contributor.editorAwan, I.
dc.contributor.editorUnal, P.
dc.coverage.spatialRome, Italyen_US
dc.date.accessioned2022-01-28T13:07:04Z
dc.date.available2022-01-28T13:07:04Z
dc.date.issued2021-11-15
dc.departmentComputer Engineeringen_US
dc.departmentComputer Technology and Information Systems
dc.descriptionConference Name: International Conference on Future Internet of Things and Cloud, FiCloud 2021en_US
dc.descriptionDate of Conference: 23-25 August 2021en_US
dc.description.abstractContemporary trends in the diffusion of artificial intelligence technologies has increased the number of studies on predictive maintenance, a recent focus of interest in many industrial domains. Despite the increased interest in the use of machine learning for predictive maintenance, few studies involve thorough comparisons of machine learning algorithms' performance on predictive maintenance applications. This work aims to predict the remaining useful life and machine failures and compares five different algorithms: Random Forest, Gradient Boosted Tree, K-Nearest Neighbors, Multilayer Perceptron and LightGBM. Our results suggest better performances for binary classification using Random Forest, and for regression using LightGRM comnared to other selected algorithms.en_US
dc.identifier.doi10.1109/FiCloud49777.2021.00019en_US
dc.identifier.eisbn978-1-6654-2574-2
dc.identifier.isbn978-1-6654-2575-9
dc.identifier.isbn978-1-6654-2575-9en_US
dc.identifier.urihttp://hdl.handle.net/11693/76884
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttps://dx.doi.org/10.1109/FiCloud49777.2021.00019en_US
dc.source.titleInternational Conference on Future Internet of Things and Cloud (FiCloud)en_US
dc.subjectFailure detectionen_US
dc.subjectRemaining useful life determinationen_US
dc.subjectArtificial intelligenceen_US
dc.subjectPredictive maintenanceen_US
dc.subjectLinear regressionen_US
dc.titleA comparison of state-of-the-art machine learning algorithms on fault indication and remaining useful life determination by telemetry dataen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
A_Comparison_of_State-of-the-Art_Machine_Learning_Algorithms_on_Fault_Indication_and_Remaining_Useful_Life_Determination_by_Telemetry_Data.pdf
Size:
403.93 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.69 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Department of Computer Engineering