Publication:
Remaining useful life estimation of turbofan engines with deep learning using change-point detection based labeling and feature engineering

dc.contributor.buuauthorEnsarioğlu, Kıymet
dc.contributor.buuauthorEmel, Erdal
dc.contributor.buuauthorEMEL, ERDAL
dc.contributor.buuauthorİnkaya, Tülin
dc.contributor.buuauthorİNKAYA, TÜLİN
dc.contributor.departmentBursa Uludağ Üniversitesi/Mühendislik Fakültesi.
dc.contributor.orcid0000-0002-6260-0162
dc.contributor.orcid0000-0002-9220-7353
dc.contributor.researcheridJNT-1214-2023
dc.contributor.researcheridN-8691-2014
dc.date.accessioned2024-10-25T05:32:56Z
dc.date.available2024-10-25T05:32:56Z
dc.date.issued2023-11-01
dc.description.abstractAccurate remaining useful life (RUL) prediction is one of the most challenging problems in the prognostics of turbofan engines. Recently, RUL prediction methods for turbofan engines mainly involve data-driven models. Preprocessing the sensor data is essential for the performance of the prognostic models. Most studies on turbofan engines use piecewise linear (PwL) labeling, which starts with a constant initial RUL value in normal/healthy operating time. In this study, we designed a prognostic procedure that includes difference-based feature construction, change-point-detection-based PwL labeling, and a 1D-CNN-LSTM (one-dimensional-convolutional neural network-long short-term memory) hybrid neural network model for RUL prediction. The procedure was evaluated on the subset FD001 of the C-MAPSS dataset. The proposed procedure was compared with machine learning and deep learning models with and without the new difference feature. Also, the results were compared with the studies that used similar labeling approaches. Our analysis of the numerical results underscores the clear superiority of the proposed 1D-CNN-LSTM model with the difference feature in RUL prediction, with a score of 437.2 and an RMSE value of 16.1. This result illustrates the superior predictive capability of the 1D-CNN-LSTM model, which outperformed traditional machine learning methods and one of the earliest deep learning methods. These findings emphasize the superior predictive capability of the 1D-CNN-LSTM model and underline the potential of the feature engineering process for more accurate and robust RUL prediction in the context of turbofan engine prognostics.
dc.identifier.doi10.3390/app132111893
dc.identifier.issue21
dc.identifier.urihttps://doi.org/10.3390/app132111893
dc.identifier.urihttps://hdl.handle.net/11452/47056
dc.identifier.volume13
dc.identifier.wos001100428600001
dc.indexed.wosWOS.SCI
dc.language.isoen
dc.publisherMdpi
dc.relation.journalApplied Sciences-basel
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectPrediction
dc.subjectNetwork
dc.subjectRemaining useful life
dc.subjectPrognostics and health management
dc.subjectFeature engineering
dc.subjectTurbofan engines
dc.subjectChange point detection
dc.subjectConvolutional neural network
dc.subjectLong short-term memory network
dc.subjectScience & technology
dc.subjectPhysical sciences
dc.subjectTechnology
dc.subjectChemistry, multidisciplinary
dc.subjectEngineering, multidisciplinary
dc.subjectMaterials science, multidisciplinary
dc.subjectPhysics, applied
dc.subjectChemistry
dc.subjectEngineering
dc.subjectMaterials science
dc.subjectPhysics
dc.titleRemaining useful life estimation of turbofan engines with deep learning using change-point detection based labeling and feature engineering
dc.typeArticle
dspace.entity.typePublication
relation.isAuthorOfPublication758ceefe-22fa-474e-8207-c551b8f5f98a
relation.isAuthorOfPublication50789246-3e56-4752-a821-3ae9957be346
relation.isAuthorOfPublication.latestForDiscovery758ceefe-22fa-474e-8207-c551b8f5f98a

Files

Collections