A Review of the Application of Machine Learning and Data Mining Approaches in Continuum Materials Mechanics

Research output: Journal contributionsScientific review articlesResearch

Standard

A Review of the Application of Machine Learning and Data Mining Approaches in Continuum Materials Mechanics. / Bock, Frederic E.; Aydin, Roland C.; Cyron, Christian C. et al.

In: Frontiers in Materials, Vol. 6, 110, 15.05.2019.

Research output: Journal contributionsScientific review articlesResearch

Harvard

APA

Vancouver

Bock FE, Aydin RC, Cyron CC, Huber N, Kalidindi SR, Klusemann B. A Review of the Application of Machine Learning and Data Mining Approaches in Continuum Materials Mechanics. Frontiers in Materials. 2019 May 15;6:110. doi: 10.3389/fmats.2019.00110

Bibtex

@article{32d5835b5f31401a997ef65b3f528e00,
title = "A Review of the Application of Machine Learning and Data Mining Approaches in Continuum Materials Mechanics",
abstract = "Machine learning tools represent key enablers for empowering material scientists and engineers to accelerate the development of novel materials, processes and techniques. One of the aims of using such approaches in the field of materials science is to achieve high-throughput identification and quantification of essential features along the process-structure-property-performance chain. In this contribution, machine learning and statistical learning approaches are reviewed in terms of their successful application to specific problems in the field of continuum materials mechanics. They are categorized with respect to their type of task designated to be either descriptive, predictive or prescriptive; thus to ultimately achieve identification, prediction or even optimization of essential characteristics. The respective choice of the most appropriate machine learning approach highly depends on the specific use-case, type of material, kind of data involved, spatial and temporal scales, formats, and desired knowledge gain as well as affordable computational costs. Different examples are reviewed involving case-by-case dependent application of different types of artificial neural networks and other data-driven approaches such as support vector machines, decision trees and random forests as well as Bayesian learning, and model order reduction procedures such as principal component analysis, among others. These techniques are applied to accelerate the identification of material parameters or salient features for materials characterization, to support rapid design and optimization of novel materials or manufacturing methods, to improve and correct complex measurement devices, or to better understand and predict fatigue behavior, among other examples. Besides experimentally obtained datasets, numerous studies draw required information from simulation-based data mining. Altogether, it is shown that experiment- and simulation-based data mining in combination with machine leaning tools provide exceptional opportunities to enable highly reliant identification of fundamental interrelations within materials for characterization and optimization in a scale-bridging manner. Potentials of further utilizing applied machine learning in materials science and empowering significant acceleration of knowledge output are pointed out.",
keywords = "Engineering, machine learning, materials mechanics, data mining, process-structure-property-performance relationship, knowledge discovery, machine learning, materials mechanics, data mining, process-structure-property-performance relationship, knowledge discovery",
author = "Bock, {Frederic E.} and Aydin, {Roland C.} and Cyron, {Christian C.} and Norbert Huber and Kalidindi, {Surya R.} and Benjamin Klusemann",
note = "Funding Information: FB and BK acknowledge support from the Helmholtz-Association via an ERC-Recognition-Award under contract number ERC-RA-0022. From CC and NH, support from Deutsche Forschungsgemeinschaft (DFG, German Research Foundation)—Projektnummer 192346071—SFB 986 is acknowledged. SK acknowledges support from NIST 70NANB18H039. Publisher Copyright: {\textcopyright} 2019 Bock, Aydin, Cyron, Huber, Kalidindi and Klusemann.",
year = "2019",
month = may,
day = "15",
doi = "10.3389/fmats.2019.00110",
language = "English",
volume = "6",
journal = "Frontiers in Materials",
issn = "2296-8016",
publisher = "Frontiers Research Foundation",

}

RIS

TY - JOUR

T1 - A Review of the Application of Machine Learning and Data Mining Approaches in Continuum Materials Mechanics

AU - Bock, Frederic E.

AU - Aydin, Roland C.

AU - Cyron, Christian C.

AU - Huber, Norbert

AU - Kalidindi, Surya R.

AU - Klusemann, Benjamin

N1 - Funding Information: FB and BK acknowledge support from the Helmholtz-Association via an ERC-Recognition-Award under contract number ERC-RA-0022. From CC and NH, support from Deutsche Forschungsgemeinschaft (DFG, German Research Foundation)—Projektnummer 192346071—SFB 986 is acknowledged. SK acknowledges support from NIST 70NANB18H039. Publisher Copyright: © 2019 Bock, Aydin, Cyron, Huber, Kalidindi and Klusemann.

PY - 2019/5/15

Y1 - 2019/5/15

N2 - Machine learning tools represent key enablers for empowering material scientists and engineers to accelerate the development of novel materials, processes and techniques. One of the aims of using such approaches in the field of materials science is to achieve high-throughput identification and quantification of essential features along the process-structure-property-performance chain. In this contribution, machine learning and statistical learning approaches are reviewed in terms of their successful application to specific problems in the field of continuum materials mechanics. They are categorized with respect to their type of task designated to be either descriptive, predictive or prescriptive; thus to ultimately achieve identification, prediction or even optimization of essential characteristics. The respective choice of the most appropriate machine learning approach highly depends on the specific use-case, type of material, kind of data involved, spatial and temporal scales, formats, and desired knowledge gain as well as affordable computational costs. Different examples are reviewed involving case-by-case dependent application of different types of artificial neural networks and other data-driven approaches such as support vector machines, decision trees and random forests as well as Bayesian learning, and model order reduction procedures such as principal component analysis, among others. These techniques are applied to accelerate the identification of material parameters or salient features for materials characterization, to support rapid design and optimization of novel materials or manufacturing methods, to improve and correct complex measurement devices, or to better understand and predict fatigue behavior, among other examples. Besides experimentally obtained datasets, numerous studies draw required information from simulation-based data mining. Altogether, it is shown that experiment- and simulation-based data mining in combination with machine leaning tools provide exceptional opportunities to enable highly reliant identification of fundamental interrelations within materials for characterization and optimization in a scale-bridging manner. Potentials of further utilizing applied machine learning in materials science and empowering significant acceleration of knowledge output are pointed out.

AB - Machine learning tools represent key enablers for empowering material scientists and engineers to accelerate the development of novel materials, processes and techniques. One of the aims of using such approaches in the field of materials science is to achieve high-throughput identification and quantification of essential features along the process-structure-property-performance chain. In this contribution, machine learning and statistical learning approaches are reviewed in terms of their successful application to specific problems in the field of continuum materials mechanics. They are categorized with respect to their type of task designated to be either descriptive, predictive or prescriptive; thus to ultimately achieve identification, prediction or even optimization of essential characteristics. The respective choice of the most appropriate machine learning approach highly depends on the specific use-case, type of material, kind of data involved, spatial and temporal scales, formats, and desired knowledge gain as well as affordable computational costs. Different examples are reviewed involving case-by-case dependent application of different types of artificial neural networks and other data-driven approaches such as support vector machines, decision trees and random forests as well as Bayesian learning, and model order reduction procedures such as principal component analysis, among others. These techniques are applied to accelerate the identification of material parameters or salient features for materials characterization, to support rapid design and optimization of novel materials or manufacturing methods, to improve and correct complex measurement devices, or to better understand and predict fatigue behavior, among other examples. Besides experimentally obtained datasets, numerous studies draw required information from simulation-based data mining. Altogether, it is shown that experiment- and simulation-based data mining in combination with machine leaning tools provide exceptional opportunities to enable highly reliant identification of fundamental interrelations within materials for characterization and optimization in a scale-bridging manner. Potentials of further utilizing applied machine learning in materials science and empowering significant acceleration of knowledge output are pointed out.

KW - Engineering

KW - machine learning

KW - materials mechanics

KW - data mining

KW - process-structure-property-performance relationship

KW - knowledge discovery

KW - machine learning

KW - materials mechanics

KW - data mining

KW - process-structure-property-performance relationship

KW - knowledge discovery

UR - http://www.scopus.com/inward/record.url?scp=85067394950&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/83157c73-372e-36e1-b362-a06d59d07c6c/

U2 - 10.3389/fmats.2019.00110

DO - 10.3389/fmats.2019.00110

M3 - Scientific review articles

VL - 6

JO - Frontiers in Materials

JF - Frontiers in Materials

SN - 2296-8016

M1 - 110

ER -

Documents

DOI