An unsupervised data completion method for physically-based data-driven models
Resumen: Data-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.
Idioma: Inglés
DOI: 10.1016/j.cma.2018.09.035
Año: 2019
Publicado en: Computer Methods in Applied Mechanics and Engineering 344 (2019), 120-143
ISSN: 0045-7825

Factor impacto JCR: 5.763 (2019)
Categ. JCR: MECHANICS rank: 7 / 136 = 0.051 (2019) - Q1 - T1
Categ. JCR: MATHEMATICS, INTERDISCIPLINARY APPLICATIONS rank: 2 / 106 = 0.019 (2019) - Q1 - T1
Categ. JCR: ENGINEERING, MULTIDISCIPLINARY rank: 6 / 91 = 0.066 (2019) - Q1 - T1

Factor impacto SCIMAGO: 2.786 - Computational Mechanics (Q1) - Computer Science Applications (Q1) - Physics and Astronomy (miscellaneous) (Q1) - Mechanics of Materials (Q1) - Mechanical Engineering (Q1)

Financiación: info:eu-repo/grantAgreement/ES/DGA/T24-17R
Financiación: info:eu-repo/grantAgreement/ES/MINECO/MAT2016-76039-C4-4-R
Tipo y forma: Artículo (PostPrint)
Área (Departamento): Área Mec.Med.Cont. y Teor.Est. (Dpto. Ingeniería Mecánica)

Creative Commons Debe reconocer adecuadamente la autoría, proporcionar un enlace a la licencia e indicar si se han realizado cambios. Puede hacerlo de cualquier manera razonable, pero no de una manera que sugiera que tiene el apoyo del licenciador o lo recibe por el uso que hace. No puede utilizar el material para una finalidad comercial. Si remezcla, transforma o crea a partir del material, no puede difundir el material modificado.


Exportado de SIDERAL (2022-10-03-13:16:43)


Visitas y descargas

Este artículo se encuentra en las siguientes colecciones:
Artículos



 Registro creado el 2019-10-25, última modificación el 2022-10-04


Postprint:
 PDF
Valore este documento:

Rate this document:
1
2
3
 
(Sin ninguna reseña)