000084191 001__ 84191
000084191 005__ 20221004075831.0
000084191 0247_ $$2doi$$a10.1016/j.cma.2018.09.035
000084191 0248_ $$2sideral$$a108743
000084191 037__ $$aART-2019-108743
000084191 041__ $$aeng
000084191 100__ $$0(orcid)0000-0003-2564-6038$$aAyensa-Jiménez, J.$$uUniversidad de Zaragoza
000084191 245__ $$aAn unsupervised data completion method for physically-based data-driven models
000084191 260__ $$c2019
000084191 5060_ $$aAccess copy available to the general public$$fUnrestricted
000084191 5203_ $$aData-driven methods are an innovative model-free approach for engineering and sciences, still in process of maturation. The idea behind is the combination of data analytics techniques, to handle the huge amount of data derived from continuous monitoring or experimental measurements, and of the constraints imposed by universal physical laws, particular to the field in hands. A well-known problem in the former corresponds to the quality and completeness of the available data that, sometimes, are so poor that make the predictions useless. In data-driven simulation-based engineering and sciences (DDSBES), the intrinsic physical constraints may help in completing the missing data in a more precise manner, by forcing them to remain in the manifold defined by the physical laws. In this work, a suitable imputation method to complete incomplete data that preserves the data context-dependent structure is presented. This is accomplished by enforcing the data to fulfill the set of physical constraints, specific to the problem. For this purpose, a generalization of the weighted mean concept is proposed, where the distance to the admissible points (in a physical sense) is used as a weighting function to get the optimal candidate. The method is evaluated in a classical regression problem, where it is compared with other standard methods, showing better results. Then, its application is illustrated in two data-driven problems, where no filling data procedure has been yet proposed, showing good predictive capability, provided that the data are close enough to the actual system state.
000084191 536__ $$9info:eu-repo/grantAgreement/ES/DGA/T24-17R$$9info:eu-repo/grantAgreement/ES/MINECO/MAT2016-76039-C4-4-R
000084191 540__ $$9info:eu-repo/semantics/openAccess$$aby-nc-nd$$uhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
000084191 590__ $$a5.763$$b2019
000084191 592__ $$a2.786$$b2019
000084191 591__ $$aMECHANICS$$b7 / 136 = 0.051$$c2019$$dQ1$$eT1
000084191 593__ $$aComputational Mechanics$$c2019$$dQ1
000084191 591__ $$aMATHEMATICS, INTERDISCIPLINARY APPLICATIONS$$b2 / 106 = 0.019$$c2019$$dQ1$$eT1
000084191 593__ $$aComputer Science Applications$$c2019$$dQ1
000084191 591__ $$aENGINEERING, MULTIDISCIPLINARY$$b6 / 91 = 0.066$$c2019$$dQ1$$eT1
000084191 593__ $$aPhysics and Astronomy (miscellaneous)$$c2019$$dQ1
000084191 593__ $$aMechanics of Materials$$c2019$$dQ1
000084191 593__ $$aMechanical Engineering$$c2019$$dQ1
000084191 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion
000084191 700__ $$0(orcid)0000-0003-0088-7222$$aHamdy Doweidar, M.$$uUniversidad de Zaragoza
000084191 700__ $$aSanz-Herrera, J.A.
000084191 700__ $$0(orcid)0000-0001-8741-6452$$aDoblaré, M.$$uUniversidad de Zaragoza
000084191 7102_ $$15004$$2605$$aUniversidad de Zaragoza$$bDpto. Ingeniería Mecánica$$cÁrea Mec.Med.Cont. y Teor.Est.
000084191 773__ $$g344 (2019), 120-143$$pComput. methods appl. mech. eng.$$tComputer Methods in Applied Mechanics and Engineering$$x0045-7825
000084191 8564_ $$s933192$$uhttps://zaguan.unizar.es/record/84191/files/texto_completo.pdf$$yPostprint
000084191 8564_ $$s146993$$uhttps://zaguan.unizar.es/record/84191/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint
000084191 909CO $$ooai:zaguan.unizar.es:84191$$particulos$$pdriver
000084191 951__ $$a2022-10-03-13:16:43
000084191 980__ $$aARTICLE