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

Publikation: Beiträge in ZeitschriftenÜbersichtsarbeitenForschung

Authors

  • Frederic E. Bock
  • Roland C. Aydin
  • Christian C. Cyron
  • Norbert Huber
  • Surya R. Kalidindi
  • Benjamin Klusemann
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.
OriginalspracheEnglisch
Aufsatznummer110
ZeitschriftFrontiers in Materials
Jahrgang6
Anzahl der Seiten23
ISSN2296-8016
DOIs
PublikationsstatusErschienen - 15.05.2019

Bibliographische Notiz

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.

    Fachgebiete

  • Ingenieurwissenschaften - machine learning, materials mechanics, data mining, process-structure-property-performance relationship, knowledge discovery

Dokumente

DOI

Zuletzt angesehen

Publikationen

  1. Determination of 10 particle-associated multiclass polar and semi-polar pesticides from small streams using accelerated solvent extraction
  2. Training effects of two different unstable shoe constructions on postural control in static and dynamic testing situations
  3. Intraspecific trait variation patterns along a precipitation gradient in Mongolian rangelands
  4. Artificial Intelligence in Foreign Language Learning and Teaching
  5. Unraveling Privacy Concerns in Complex Data Ecosystems with Architectural Thinking
  6. A survey of empirical studies using transaction level data on exports and imports
  7. Governing Objects from a Distance
  8. An Outcome-Oriented, Social-Ecological Framework for Assessing Protected Area Effectiveness
  9. Aspect-oriented software development
  10. Web-Based Drills in Maths Using a Computer Algebra System
  11. Effectiveness of a Web-Based Cognitive Behavioural Intervention for Subthreshold Depression
  12. Machine Learning and Data Mining for Sports Analytics
  13. E-stability and stability of adaptive learning in models with private information
  14. Action rate models for predicting actions in soccer
  15. Time Use Research and Time Use Data
  16. Failing and the perception of failure in student-driven transdisciplinary projects
  17. Computational history of knowledge
  18. Increased auditor independence by external rotation and separating audit and non audit duties?
  19. Lost-customers approximation of semi-open queueing networks with backordering
  20. Pushing the Envelope: Creating Public Value in the Labor Market
  21. An Interactive Layers Model of Self-Regulated Learning and Cognitive Load
  22. Knowledge transfer during the integration of knowledge-intensive acquisitions
  23. Deciding between the Covariance Analytical Approach and the Change-Score Approach in Two Wave Panel Data
  24. Dynamic efficiency and path dependencies in venture capital markets
  25. Machine Learning Applications in Convective Turbulence
  26. Anomalous Results in G-Factor Models
  27. Teachers’ temporary support and worked-out examples as elements of scaffolding in mathematical modeling
  28. Timing matters: Distinct effects of nitrogen and phosphorus fertilizer application timing on root system architecture responses
  29. Study of Single Filament Dielectric Barrier Discharge in Argon