Model and system learners, optimal process constructors and kinetic theory-based goal-oriented design: a new paradigm in materials and processes informatics

Abisset-Chavanne, E. ; Duval, J.L. ; Cueto, E. (Universidad de Zaragoza) ; Chinesta, F.

Resumen: Traditionally, Simulation-Based Engineering Sciences (SBES) has relied on the use of static data inputs (model parameters, initial or boundary conditions, ... obtained from adequate experiments) to perform simulations. A new paradigm in the field of Applied Sciences and Engineering has emerged in the last decade. Dynamic Data-Driven Application Systems [9, 10, 11, 12, 22] allow the linkage of simulation tools with measurement devices for real-time control of simulations and applications, entailing the ability to dynamically incorporate additional data into an executing application, and in reverse, the ability of an application to dynamically steer the measurement process. It is in that context that traditional "digital-twins" are giving raise to a new generation of goal-oriented data-driven application systems, also known as "hybrid-twins", embracing models based on physics and models exclusively based on data adequately collected and assimilated for filling the gap between usual model predictions and measurements. Within this framework new methodologies based on model learners, machine learning and kinetic goal-oriented design are defining a new paradigm in materials, processes and systems engineering.

Idioma: Inglés

DOI: 10.1063/1.5034930

Año: 2018

Publicado en: AIP Conference Proceedings 1960 (2018), 090004 [6 pp.]
ISSN: 0094-243X

Factor impacto SCIMAGO: 0.182 - Physics and Astronomy (miscellaneous)

Tipo y forma: Artículo (Versión definitiva)

Área (Departamento): Área Mec.Med.Cont. y Teor.Est. (Dpto. Ingeniería Mecánica)