Towards machine learning approaches for predicting the self-healing efficiency of materials

Wenjun Wang, Nicolette G. Moreau, Yingfang Yuan, Paul R. Race, Wei Pang (Corresponding Author)

Research output: Contribution to journalArticle

Abstract

Self-healing materials with an inherent repair mechanism have been widely studied. However, the self-healing efficiencies of most materials can only be measured by laboratory-based experiments, which can be time consuming and expensive. Inspired by modern machine learning approaches, we are interested in predicting the self-healing efficiency of new bio-hybrid materials, as part of our ongoing EPSRC funded ’Manufacturing Immortality’ project. By modelling existing experimental data, predictive models can be built to forecast self-healing efficiency. This has the potential to reduce the time input required by laboratory experiments, guide material and component selection, and inform hypotheses, thereby facilitating the design of novel self-healing materials. In this position paper, we first present preliminary knowledge and quantitative definitions of the self-healing efficiency of materials. We then demonstrate several widely used machine learning approaches and review an experimental case of predictive modelling based on neural networks. Furthermore, and aiming to expedite self-healing material development, we propose an on-line ensemble learning framework as the whole system model for the optimization of predictive computational models. Finally, the rationality of our on-line ensemble learning framework is experimentally studied and validated.
Original languageEnglish
Pages (from-to)180-187
Number of pages8
JournalComputational Materials Science
Volume168
Early online date19 Jun 2019
DOIs
Publication statusPublished - Oct 2019

Fingerprint

machine learning
Self-healing materials
healing
Learning systems
Machine Learning
Ensemble Learning
Predictive Model
Hybrid materials
learning
Repair
Predictive Modeling
Experiments
materials selection
Neural networks
Rationality
forecasting
Computational Model
Experiment
Forecast
manufacturing

Keywords

  • self-healing efficiency
  • predictive model
  • regression and classification
  • artificial neural networks
  • online ensemble learning framework

ASJC Scopus subject areas

  • Computer Science(all)
  • Chemistry(all)
  • Materials Science(all)
  • Mechanics of Materials
  • Physics and Astronomy(all)
  • Computational Mathematics

Cite this

Towards machine learning approaches for predicting the self-healing efficiency of materials. / Wang, Wenjun; Moreau, Nicolette G.; Yuan, Yingfang; Race, Paul R.; Pang, Wei (Corresponding Author).

In: Computational Materials Science, Vol. 168, 10.2019, p. 180-187.

Research output: Contribution to journalArticle

@article{67afc94ec5084329b05eeb570fb08705,
title = "Towards machine learning approaches for predicting the self-healing efficiency of materials",
abstract = "Self-healing materials with an inherent repair mechanism have been widely studied. However, the self-healing efficiencies of most materials can only be measured by laboratory-based experiments, which can be time consuming and expensive. Inspired by modern machine learning approaches, we are interested in predicting the self-healing efficiency of new bio-hybrid materials, as part of our ongoing EPSRC funded ’Manufacturing Immortality’ project. By modelling existing experimental data, predictive models can be built to forecast self-healing efficiency. This has the potential to reduce the time input required by laboratory experiments, guide material and component selection, and inform hypotheses, thereby facilitating the design of novel self-healing materials. In this position paper, we first present preliminary knowledge and quantitative definitions of the self-healing efficiency of materials. We then demonstrate several widely used machine learning approaches and review an experimental case of predictive modelling based on neural networks. Furthermore, and aiming to expedite self-healing material development, we propose an on-line ensemble learning framework as the whole system model for the optimization of predictive computational models. Finally, the rationality of our on-line ensemble learning framework is experimentally studied and validated.",
keywords = "self-healing efficiency, predictive model, regression and classification, artificial neural networks, online ensemble learning framework",
author = "Wenjun Wang and Moreau, {Nicolette G.} and Yingfang Yuan and Race, {Paul R.} and Wei Pang",
note = "Acknowledgement This research is supported by the Engineering and Physical Sciences Research Council (EPSRC) funded Project on New Industrial Systems: Manufacturing Immortality (EP/R020957/1). The authors are also grateful to the Manufacturing Immortality consortium.",
year = "2019",
month = "10",
doi = "10.1016/j.commatsci.2019.05.050",
language = "English",
volume = "168",
pages = "180--187",
journal = "Computational Materials Science",
issn = "0927-0256",
publisher = "Elsevier",

}

TY - JOUR

T1 - Towards machine learning approaches for predicting the self-healing efficiency of materials

AU - Wang, Wenjun

AU - Moreau, Nicolette G.

AU - Yuan, Yingfang

AU - Race, Paul R.

AU - Pang, Wei

N1 - Acknowledgement This research is supported by the Engineering and Physical Sciences Research Council (EPSRC) funded Project on New Industrial Systems: Manufacturing Immortality (EP/R020957/1). The authors are also grateful to the Manufacturing Immortality consortium.

PY - 2019/10

Y1 - 2019/10

N2 - Self-healing materials with an inherent repair mechanism have been widely studied. However, the self-healing efficiencies of most materials can only be measured by laboratory-based experiments, which can be time consuming and expensive. Inspired by modern machine learning approaches, we are interested in predicting the self-healing efficiency of new bio-hybrid materials, as part of our ongoing EPSRC funded ’Manufacturing Immortality’ project. By modelling existing experimental data, predictive models can be built to forecast self-healing efficiency. This has the potential to reduce the time input required by laboratory experiments, guide material and component selection, and inform hypotheses, thereby facilitating the design of novel self-healing materials. In this position paper, we first present preliminary knowledge and quantitative definitions of the self-healing efficiency of materials. We then demonstrate several widely used machine learning approaches and review an experimental case of predictive modelling based on neural networks. Furthermore, and aiming to expedite self-healing material development, we propose an on-line ensemble learning framework as the whole system model for the optimization of predictive computational models. Finally, the rationality of our on-line ensemble learning framework is experimentally studied and validated.

AB - Self-healing materials with an inherent repair mechanism have been widely studied. However, the self-healing efficiencies of most materials can only be measured by laboratory-based experiments, which can be time consuming and expensive. Inspired by modern machine learning approaches, we are interested in predicting the self-healing efficiency of new bio-hybrid materials, as part of our ongoing EPSRC funded ’Manufacturing Immortality’ project. By modelling existing experimental data, predictive models can be built to forecast self-healing efficiency. This has the potential to reduce the time input required by laboratory experiments, guide material and component selection, and inform hypotheses, thereby facilitating the design of novel self-healing materials. In this position paper, we first present preliminary knowledge and quantitative definitions of the self-healing efficiency of materials. We then demonstrate several widely used machine learning approaches and review an experimental case of predictive modelling based on neural networks. Furthermore, and aiming to expedite self-healing material development, we propose an on-line ensemble learning framework as the whole system model for the optimization of predictive computational models. Finally, the rationality of our on-line ensemble learning framework is experimentally studied and validated.

KW - self-healing efficiency

KW - predictive model

KW - regression and classification

KW - artificial neural networks

KW - online ensemble learning framework

UR - http://www.mendeley.com/research/towards-machine-learning-approaches-predicting-selfhealing-efficiency-materials

U2 - 10.1016/j.commatsci.2019.05.050

DO - 10.1016/j.commatsci.2019.05.050

M3 - Article

VL - 168

SP - 180

EP - 187

JO - Computational Materials Science

JF - Computational Materials Science

SN - 0927-0256

ER -