Home > Research > Publications & Outputs > Application of machine learning methods on dyna...

Research

Links

Text available via DOI:

Keywords

View graph of relations

Application of machine learning methods on dynamic strength analysis for additive manufactured polypropylene-based composites

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Application of machine learning methods on dynamic strength analysis for additive manufactured polypropylene-based composites. / Cai, R.; Wang, K.; Wen, W. et al.
In: Polymer Testing, Vol. 110, 107580, 30.06.2022.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Cai, R, Wang, K, Wen, W, Peng, Y, Baniassadi, M & Ahzi, S 2022, 'Application of machine learning methods on dynamic strength analysis for additive manufactured polypropylene-based composites', Polymer Testing, vol. 110, 107580. https://doi.org/10.1016/j.polymertesting.2022.107580

APA

Cai, R., Wang, K., Wen, W., Peng, Y., Baniassadi, M., & Ahzi, S. (2022). Application of machine learning methods on dynamic strength analysis for additive manufactured polypropylene-based composites. Polymer Testing, 110, Article 107580. https://doi.org/10.1016/j.polymertesting.2022.107580

Vancouver

Cai R, Wang K, Wen W, Peng Y, Baniassadi M, Ahzi S. Application of machine learning methods on dynamic strength analysis for additive manufactured polypropylene-based composites. Polymer Testing. 2022 Jun 30;110:107580. Epub 2022 Apr 12. doi: 10.1016/j.polymertesting.2022.107580

Author

Cai, R. ; Wang, K. ; Wen, W. et al. / Application of machine learning methods on dynamic strength analysis for additive manufactured polypropylene-based composites. In: Polymer Testing. 2022 ; Vol. 110.

Bibtex

@article{ecb47d5b6aca48eba79e0f6129eddd84,
title = "Application of machine learning methods on dynamic strength analysis for additive manufactured polypropylene-based composites",
abstract = "This study aimed at applying machine learning (ML) methods to analyze dynamic strength of 3D-printed polypropylene (PP)-based composites. The dynamic strength of additive manufactured PP-based composites with different fillers and printing parameters was investigated by split Hopkinson pressure bars. Based on experimental results, six machine learning approaches were applied to express the relationships between the dynamic strength and materials as well as printing parameters. The performance of the six machine learning algorithms with relatively small training datasets was evaluated. The comparison results showed that artificial neural network could achieve the highest prediction accuracy but with relatively low computational efficiency, whereas the support vector regression could provide satisfactory prediction with both good accuracy and efficiency. The extreme gradient boosting and random forest approaches were recommended if the importance of input was required. ",
keywords = "Additive manufacturing, Dynamic strength, Machine learning, Polypropylene-based composites, Prediction",
author = "R. Cai and K. Wang and W. Wen and Y. Peng and M. Baniassadi and S. Ahzi",
year = "2022",
month = jun,
day = "30",
doi = "10.1016/j.polymertesting.2022.107580",
language = "English",
volume = "110",
journal = "Polymer Testing",

}

RIS

TY - JOUR

T1 - Application of machine learning methods on dynamic strength analysis for additive manufactured polypropylene-based composites

AU - Cai, R.

AU - Wang, K.

AU - Wen, W.

AU - Peng, Y.

AU - Baniassadi, M.

AU - Ahzi, S.

PY - 2022/6/30

Y1 - 2022/6/30

N2 - This study aimed at applying machine learning (ML) methods to analyze dynamic strength of 3D-printed polypropylene (PP)-based composites. The dynamic strength of additive manufactured PP-based composites with different fillers and printing parameters was investigated by split Hopkinson pressure bars. Based on experimental results, six machine learning approaches were applied to express the relationships between the dynamic strength and materials as well as printing parameters. The performance of the six machine learning algorithms with relatively small training datasets was evaluated. The comparison results showed that artificial neural network could achieve the highest prediction accuracy but with relatively low computational efficiency, whereas the support vector regression could provide satisfactory prediction with both good accuracy and efficiency. The extreme gradient boosting and random forest approaches were recommended if the importance of input was required.

AB - This study aimed at applying machine learning (ML) methods to analyze dynamic strength of 3D-printed polypropylene (PP)-based composites. The dynamic strength of additive manufactured PP-based composites with different fillers and printing parameters was investigated by split Hopkinson pressure bars. Based on experimental results, six machine learning approaches were applied to express the relationships between the dynamic strength and materials as well as printing parameters. The performance of the six machine learning algorithms with relatively small training datasets was evaluated. The comparison results showed that artificial neural network could achieve the highest prediction accuracy but with relatively low computational efficiency, whereas the support vector regression could provide satisfactory prediction with both good accuracy and efficiency. The extreme gradient boosting and random forest approaches were recommended if the importance of input was required.

KW - Additive manufacturing

KW - Dynamic strength

KW - Machine learning

KW - Polypropylene-based composites

KW - Prediction

U2 - 10.1016/j.polymertesting.2022.107580

DO - 10.1016/j.polymertesting.2022.107580

M3 - Journal article

VL - 110

JO - Polymer Testing

JF - Polymer Testing

M1 - 107580

ER -