000144824 001__ 144824
000144824 005__ 20250210083428.0
000144824 0247_ $$2doi$$a10.1177/10812865241257850
000144824 0248_ $$2sideral$$a139695
000144824 037__ $$aART-2025-139695
000144824 041__ $$aeng
000144824 100__ $$0(orcid)0000-0003-2564-6038$$aAyensa-Jiménez, Jacobo
000144824 245__ $$aPredicting and explaining nonlinear material response using deep physically guided neural networks with internal variables
000144824 260__ $$c2025
000144824 5060_ $$aAccess copy available to the general public$$fUnrestricted
000144824 5203_ $$aNonlinear materials are often difficult to model with classical state model theory because they have a complex and sometimes inaccurate physical and mathematical description, or we simply do not know how to describe such materials in terms of relations between external and internal variables. In many disciplines, neural network methods have emerged as powerful tools to identify very complex and nonlinear correlations. In this work, we use the very recently developed concept of physically guided neural networks with internal variables (PGNNIVs) to discover constitutive laws using a model-free approach and training solely with measured force–displacement data. PGNNIVs make a particular use of the physics of the problem to enforce constraints on specific hidden layers and are able to make predictions without internal variable data. We demonstrate that PGNNIVs are capable of predicting both internal and external variables under unseen loading scenarios, regardless of the nature of the material considered (linear, with hardening or softening behavior and hyperelastic), unravelling the constitutive law of the material hence explaining its nature altogether, endowing the method with some explanatory character that distances it from the traditional black box approach.
000144824 540__ $$9info:eu-repo/semantics/closedAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/
000144824 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000144824 700__ $$aOrera-Echeverría, Javier$$uUniversidad de Zaragoza
000144824 700__ $$0(orcid)0000-0001-8741-6452$$aDoblare, Manuel$$uUniversidad de Zaragoza
000144824 7102_ $$15008$$2800$$aUniversidad de Zaragoza$$bDpto. Ingeniería Electrón.Com.$$cÁrea Teoría Señal y Comunicac.
000144824 7102_ $$15004$$2605$$aUniversidad de Zaragoza$$bDpto. Ingeniería Mecánica$$cÁrea Mec.Med.Cont. y Teor.Est.
000144824 773__ $$g30, 2 (2025), 573-598$$pMath. mech. solids$$tMATHEMATICS AND MECHANICS OF SOLIDS$$x1081-2865
000144824 8564_ $$s1940338$$uhttps://zaguan.unizar.es/record/144824/files/texto_completo.pdf$$yVersión publicada
000144824 8564_ $$s1774085$$uhttps://zaguan.unizar.es/record/144824/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000144824 909CO $$ooai:zaguan.unizar.es:144824$$particulos$$pdriver
000144824 951__ $$a2025-02-10-08:31:25
000144824 980__ $$aARTICLE