000875308 001__ 875308
000875308 005__ 20240711092241.0
000875308 0247_ $$2doi$$a10.1016/j.commatsci.2019.109488
000875308 0247_ $$2ISSN$$a0927-0256
000875308 0247_ $$2ISSN$$a1879-0801
000875308 0247_ $$2WOS$$aWOS:000519572500007
000875308 037__ $$aFZJ-2020-01939
000875308 082__ $$a530
000875308 1001_ $$0P:(DE-Juel1)169125$$aHüter, Claas$$b0$$eCorresponding author$$ufzj
000875308 245__ $$aA pragmatic dataset augmentation approach for transformation temperature prediction in steels
000875308 260__ $$aAmsterdam [u.a.]$$bElsevier Science$$c2020
000875308 3367_ $$2DRIVER$$aarticle
000875308 3367_ $$2DataCite$$aOutput Types/Journal article
000875308 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1714570898_3667
000875308 3367_ $$2BibTeX$$aARTICLE
000875308 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000875308 3367_ $$00$$2EndNote$$aJournal Article
000875308 520__ $$aWe introduce an augmentation approach for the prediction of phase transformation temperatures that combines thermodynamic considerations and thermodynamic databases. Using the example of the bainitic start temperature, , we demonstrate the improvement of prediction accuracy that this augmentation scheme can provide. The training and testing dataset available from already published experimental measurements provides a varying set of alloying elements and measured bainitic start temperatures. In terms of a minimalistic thermodynamic model, we explain the benefit of augmenting the presented data set by the chemical potential of carbon in the ferritic phase at an estimated start temperature. To evaluate this augmentation scheme, we determine the prediction accuracy of sets of artificial neural networks (ANNs) for the unaugmented dataset, for the – only a posteriori accessible – dataset which is augmented with the chemical potential at the measured bainitic start temperature, and the prediction accuracy for the dataset augmented by an estimated , approximated with two different approaches. While the dataset which is augmented with the chemical potential at the measured bainitic start temperatures would not be practically usable for the prediction of a not yet measured bainitic start temperature, it provides theoretical limits of the achievable accuracy gain due to the augmentation. The developed approximation schemes for at are usable to predict for a given composition. We distinguish two levels of computational expense, which provide a mean absolute error of either about 14 °C or about 4 °C, thus reaching the regime of experimental measurement accuracy.
000875308 536__ $$0G:(DE-HGF)POF3-113$$a113 - Methods and Concepts for Material Development (POF3-113)$$cPOF3-113$$fPOF III$$x0
000875308 588__ $$aDataset connected to CrossRef
000875308 7001_ $$0P:(DE-Juel1)166023$$aYin, X.$$b1$$ufzj
000875308 7001_ $$0P:(DE-Juel1)177065$$aVo, T.$$b2$$ufzj
000875308 7001_ $$0P:(DE-Juel1)129290$$aBraun, Silvia$$b3$$ufzj
000875308 773__ $$0PERI:(DE-600)2014722-3$$a10.1016/j.commatsci.2019.109488$$gVol. 176, p. 109488 -$$p109488 -$$tComputational materials science$$v176$$x0927-0256$$y2020
000875308 8564_ $$uhttps://juser.fz-juelich.de/record/875308/files/CMS_ANN.pdf$$yRestricted
000875308 8564_ $$uhttps://juser.fz-juelich.de/record/875308/files/CMS_ANN.pdf?subformat=pdfa$$xpdfa$$yRestricted
000875308 909CO $$ooai:juser.fz-juelich.de:875308$$pVDB
000875308 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)169125$$aForschungszentrum Jülich$$b0$$kFZJ
000875308 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)166023$$aForschungszentrum Jülich$$b1$$kFZJ
000875308 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)177065$$aForschungszentrum Jülich$$b2$$kFZJ
000875308 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)129290$$aForschungszentrum Jülich$$b3$$kFZJ
000875308 9131_ $$0G:(DE-HGF)POF3-113$$1G:(DE-HGF)POF3-110$$2G:(DE-HGF)POF3-100$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bEnergie$$lEnergieeffizienz, Materialien und Ressourcen$$vMethods and Concepts for Material Development$$x0
000875308 9141_ $$y2020
000875308 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bCOMP MATER SCI : 2017
000875308 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS
000875308 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline
000875308 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search
000875308 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC
000875308 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List
000875308 915__ $$0StatID:(DE-HGF)0110$$2StatID$$aWoS$$bScience Citation Index
000875308 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection
000875308 915__ $$0StatID:(DE-HGF)0111$$2StatID$$aWoS$$bScience Citation Index Expanded
000875308 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences
000875308 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5
000875308 9201_ $$0I:(DE-Juel1)IEK-2-20101013$$kIEK-2$$lWerkstoffstruktur und -eigenschaften$$x0
000875308 9201_ $$0I:(DE-Juel1)IBG-2-3-TA-20110204$$kIBG-2-3-TA$$lBiotechnologie Technische und administrative Infrastruktur IBG-2 und 3$$x1
000875308 980__ $$ajournal
000875308 980__ $$aVDB
000875308 980__ $$aI:(DE-Juel1)IEK-2-20101013
000875308 980__ $$aI:(DE-Juel1)IBG-2-3-TA-20110204
000875308 980__ $$aUNRESTRICTED
000875308 981__ $$aI:(DE-Juel1)IMD-1-20101013