Empowering materials processing and performance from data and AI

Research output: Journal contributionsOther (editorial matter etc.)Research

Standard

Empowering materials processing and performance from data and AI. / Chinesta, Francisco; Cueto, Elias; Klusemann, Benjamin.
In: Materials, Vol. 14, No. 16, 4409, 06.08.2021.

Research output: Journal contributionsOther (editorial matter etc.)Research

Harvard

APA

Vancouver

Chinesta F, Cueto E, Klusemann B. Empowering materials processing and performance from data and AI. Materials. 2021 Aug 6;14(16):4409. doi: 10.3390/ma14164409

Bibtex

@article{2f93e8c4b65049fe98ea7e5fa8340bae,
title = "Empowering materials processing and performance from data and AI",
abstract = "Third millennium engineering is addressing new challenges in materials sciencesand engineering. In particular, the advances in materials engineering, combined with the advances in data acquisition, processing and mining as well as artificial intelligence, allow new ways of thinking in designing new materials and products. Additionally, this gives rise to new paradigms in bridging raw material data and processing to the induced properties and performance. On the one hand, the linkage can be done purely on a data-driven basis, i.e., models are created from scratch based on the obtained experimental data alone, forinstance with statistical methods or advanced methods of machine learning. Particularly obvious advantages of such kinds of models are that no simplification or assumptions need to be incorporated a priori, and that it allows real-time prediction, leading to a so-called digital twin of the specific material/process. However, such approaches typically face somegeneral challenges, such as the necessity of (maybe unnecessarily) large and comprehensive datasets, because they rely only on the data themselves and allow prediction only within the investigated/trained dataspace. Another way of addressing the challenge of predicting the complex processing–structure–property relationships in materials is the enhancement of already existing physics-based models via data and machine learning tools, i.e., combininga physics-based model (often called virtual twin) and a data-based model, leading to a so-called hybrid twin [1]. In this regard, possible deviations of the physics-based model, which rely on a number of simplifications and assumptions, can be healed by correcting the model based on a data-driven approach, i.e., combining the advantages of both models.",
keywords = "Engineering",
author = "Francisco Chinesta and Elias Cueto and Benjamin Klusemann",
year = "2021",
month = aug,
day = "6",
doi = "10.3390/ma14164409",
language = "English",
volume = "14",
journal = "Materials",
issn = "1996-1944",
publisher = "MDPI AG",
number = "16",

}

RIS

TY - JOUR

T1 - Empowering materials processing and performance from data and AI

AU - Chinesta, Francisco

AU - Cueto, Elias

AU - Klusemann, Benjamin

PY - 2021/8/6

Y1 - 2021/8/6

N2 - Third millennium engineering is addressing new challenges in materials sciencesand engineering. In particular, the advances in materials engineering, combined with the advances in data acquisition, processing and mining as well as artificial intelligence, allow new ways of thinking in designing new materials and products. Additionally, this gives rise to new paradigms in bridging raw material data and processing to the induced properties and performance. On the one hand, the linkage can be done purely on a data-driven basis, i.e., models are created from scratch based on the obtained experimental data alone, forinstance with statistical methods or advanced methods of machine learning. Particularly obvious advantages of such kinds of models are that no simplification or assumptions need to be incorporated a priori, and that it allows real-time prediction, leading to a so-called digital twin of the specific material/process. However, such approaches typically face somegeneral challenges, such as the necessity of (maybe unnecessarily) large and comprehensive datasets, because they rely only on the data themselves and allow prediction only within the investigated/trained dataspace. Another way of addressing the challenge of predicting the complex processing–structure–property relationships in materials is the enhancement of already existing physics-based models via data and machine learning tools, i.e., combininga physics-based model (often called virtual twin) and a data-based model, leading to a so-called hybrid twin [1]. In this regard, possible deviations of the physics-based model, which rely on a number of simplifications and assumptions, can be healed by correcting the model based on a data-driven approach, i.e., combining the advantages of both models.

AB - Third millennium engineering is addressing new challenges in materials sciencesand engineering. In particular, the advances in materials engineering, combined with the advances in data acquisition, processing and mining as well as artificial intelligence, allow new ways of thinking in designing new materials and products. Additionally, this gives rise to new paradigms in bridging raw material data and processing to the induced properties and performance. On the one hand, the linkage can be done purely on a data-driven basis, i.e., models are created from scratch based on the obtained experimental data alone, forinstance with statistical methods or advanced methods of machine learning. Particularly obvious advantages of such kinds of models are that no simplification or assumptions need to be incorporated a priori, and that it allows real-time prediction, leading to a so-called digital twin of the specific material/process. However, such approaches typically face somegeneral challenges, such as the necessity of (maybe unnecessarily) large and comprehensive datasets, because they rely only on the data themselves and allow prediction only within the investigated/trained dataspace. Another way of addressing the challenge of predicting the complex processing–structure–property relationships in materials is the enhancement of already existing physics-based models via data and machine learning tools, i.e., combininga physics-based model (often called virtual twin) and a data-based model, leading to a so-called hybrid twin [1]. In this regard, possible deviations of the physics-based model, which rely on a number of simplifications and assumptions, can be healed by correcting the model based on a data-driven approach, i.e., combining the advantages of both models.

KW - Engineering

UR - http://www.scopus.com/inward/record.url?scp=85112284614&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/8253a036-5593-38d4-bb10-582b4bc9dae6/

U2 - 10.3390/ma14164409

DO - 10.3390/ma14164409

M3 - Other (editorial matter etc.)

C2 - 34442931

AN - SCOPUS:85112284614

VL - 14

JO - Materials

JF - Materials

SN - 1996-1944

IS - 16

M1 - 4409

ER -

Documents

DOI