A Shape-Constrained Neural Data Fusion Network for Health Index Construction and Residual Life Prediction

Simple item page
dc.contributor.authorLi, Zhenen
dc.contributor.authorWu, Jianguoen
dc.contributor.authorYue, Xiaoweien
dc.date.accessioned2021-12-10T19:49:58Zen
dc.date.available2021-12-10T19:49:58Zen
dc.date.issued2021-11-01en
dc.date.updated2021-12-10T19:49:56Zen
dc.description.abstractWith the rapid development of sensor technologies, multisensor signals are now readily available for health condition monitoring and remaining useful life (RUL) prediction. To fully utilize these signals for a better health condition assessment and RUL prediction, health indices are often constructed through various data fusion techniques. Nevertheless, most of the existing methods fuse signals linearly, which may not be sufficient to characterize the health status for RUL prediction. To address this issue and improve the predictability, this article proposes a novel nonlinear data fusion approach, namely, a shape-constrained neural data fusion network for health index construction. Especially, a neural network-based structure is employed, and a novel loss function is formulated by simultaneously considering the monotonicity and curvature of the constructed health index and its variability at the failure time. A tailored adaptive moment estimation algorithm (Adam) is proposed for model parameter estimation. The effectiveness of the proposed method is demonstrated and compared through a case study using the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) data set.en
dc.description.versionAccepted versionen
dc.format.extentPages 5022-5033en
dc.format.extent12 page(s)en
dc.format.mimetypeapplication/pdfen
dc.identifier.doihttps://doi.org/10.1109/TNNLS.2020.3026644en
dc.identifier.eissn2162-2388en
dc.identifier.issn2162-237Xen
dc.identifier.issue11en
dc.identifier.pmid33027006en
dc.identifier.urihttp://hdl.handle.net/10919/106927en
dc.identifier.volume32en
dc.language.isoenen
dc.publisherIEEEen
dc.relation.urihttp://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000711638200024&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=930d57c9ac61a043676db62af60056c1en
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectTechnologyen
dc.subjectComputer Science, Artificial Intelligenceen
dc.subjectComputer Science, Hardware & Architectureen
dc.subjectComputer Science, Theory & Methodsen
dc.subjectEngineering, Electrical & Electronicen
dc.subjectComputer Scienceen
dc.subjectEngineeringen
dc.subjectIndexesen
dc.subjectDegradationen
dc.subjectData integrationen
dc.subjectNeural networksen
dc.subjectCondition monitoringen
dc.subjectEnginesen
dc.subjectAtmospheric modelingen
dc.subjecthealth indexen
dc.subjectneural data fusion networken
dc.subjectremaining useful life (RUL) predictionen
dc.subjectshape constraineden
dc.subjectDEGRADATION SIGNALen
dc.subjectPROGNOSTICSen
dc.subjectSUBJECTen
dc.subjectMODELen
dc.subjectArtificial Intelligence & Image Processingen
dc.titleA Shape-Constrained Neural Data Fusion Network for Health Index Construction and Residual Life Predictionen
dc.title.serialIEEE Transactions on Neural Networks and Learning Systemsen
dc.typeArticle - Refereeden
dc.type.dcmitypeTexten
dc.type.otherArticleen
dc.type.otherJournalen
pubs.organisational-group/Virginia Techen
pubs.organisational-group/Virginia Tech/Engineeringen
pubs.organisational-group/Virginia Tech/Engineering/Industrial and Systems Engineeringen
pubs.organisational-group/Virginia Tech/All T&R Facultyen
pubs.organisational-group/Virginia Tech/Engineering/COE T&R Facultyen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
P16-A Shape Constained Neural Data Fusion Network.pdf
Size:
1.63 MB
Format:
Adobe Portable Document Format
Description:
Accepted version
Download

Collections

All Faculty Deposits
Scholarly Works, Industrial and Systems Engineering