Predicting the Mechanical Properties of Polyurethane Elastomers Using Machine Learning

Fang Ding; Lun-Yang Liu; Ting-Li Liu; Yun-Qi Li; Jun-Peng Li; Zhao-Yan Sun

doi:10.1007/s10118-022-2838-6

Your Location：

Home >

Browse articles >

Predicting the Mechanical Properties of Polyurethane Elastomers Using Machine Learning

RESEARCH ARTICLE | Updated：2023-01-18

- Predicting the Mechanical Properties of Polyurethane Elastomers Using Machine Learning
- Predicting the Mechanical Properties of Polyurethane Elastomers Using Machine Learning
- 高分子科学（英文版） 2023年41卷第3期页码：422-431
- Affiliations：
  
  a.State Key Laboratory of Polymer Physics and Chemistry, Changchun Institute of Applied Chemistry, Chinese Academy of Sciences, Changchun 130022, China
  b.School of Applied Chemistry and Engineering, University of Science and Technology of China, Hefei 230026, China
  c.Department of Polymer Materials and Engineering, College of Materials and Metallurgy, Guizhou University, Guiyang 550025, China
  d.State Key Laboratory of Advanced Technologies for Comprehensive Utilization of Platinum Metals, Sino-Platinum Metals Co. Ltd., Kunming 650106, China
- Author bio：
  
  yunqi@ciac.ac.cn (Y.Q.L.)
  lijunpeng@ipm.com.cn (J.P.L)
  zysun@ciac.ac.cn (Z.Y.S.)
- Funds：
  
  The work was financially supported by the National Natural Science Foundation of China (Nos. 51988102 and 22173094), CAS Key Research Program of Frontier Sciences (No. QYZDY-SSW-SLH027). We are grateful to Network and Computing Center, Changchun Institute of Applied Chemistry for essential support. The authors also appreciate the financial support of Major Science and Technology Project in Yunnan Province (No. 202002AB080001-1).;Electronic supplementary information (ESI) is available free of charge in the online version of this article at http://doi.org/10.1007/s10118-022-2838-6.
- DOI：10.1007/s10118-022-2838-6
  中图分类号：
- 收稿：2022-06-13，
  
  修回：2022-7-4，
  
  录用：2022-7-6，
  
  网络首发：2022-10-08，
  
  纸质出版：2023-03-01
- Accepted：
Scan QR Code
Ding, F.; Liu, L. Y.; Liu, T. L.; Li, Y. Q.; Li, J. P.; Sun, Z. Y. Predicting the mechanical properties of polyurethane elastomers using machine learning. Chinese J. Polym. Sci. 2023, 41, 422–431

Fang Ding, Lun-Yang Liu, Ting-Li Liu, et al. Predicting the Mechanical Properties of Polyurethane Elastomers Using Machine Learning[J]. Chinese Journal of Polymer Science, 2023, 41(3): 422-431.
Ding, F.; Liu, L. Y.; Liu, T. L.; Li, Y. Q.; Li, J. P.; Sun, Z. Y. Predicting the mechanical properties of polyurethane elastomers using machine learning. Chinese J. Polym. Sci. 2023, 41, 422–431 DOI： 10.1007/s10118-022-2838-6.

Fang Ding, Lun-Yang Liu, Ting-Li Liu, et al. Predicting the Mechanical Properties of Polyurethane Elastomers Using Machine Learning[J]. Chinese Journal of Polymer Science, 2023, 41(3): 422-431. DOI： 10.1007/s10118-022-2838-6.

摘要

Predict the mechanical properties of polyurethane elastomers and construct a benchmark dataset with conserved chemical structure-composition-processing-mechanical properties relationship.

Abstract

Bridging the gap between the computation of mechanical properties and the chemical structure of elastomers is a long-standing challenge. To fill the gap

we create a raw dataset and build predictive models for Young’s modulus

tensile strength

and elongation at break of polyurethane elastomers (PUEs). We then construct a benchmark dataset with 50.4% samples remained from the raw dataset which suffers from the intrinsic diversity problem

through a newly proposed recursive data elimination protocol. The coefficients of determination (

s) from predictions are improved from 0.73−0.78 to 0.85−0.91 based on the raw and the benchmark datasets. The fitting of stress-strain curves using the machine learning model shows a slightly better performance than that for one of the well-performed constitutive models (

e.g.

the Khiêm-Itskov model). It confirmed that the black-box machine learning models are feasible to bridge the gap between the mechanical properties of PUEs and multiple factors for their chemical structures

composition

processing

and measurement settings. While accurate prediction for these curves is still a challenge. We release the raw dataset and the most representative benchmark dataset so far to call for more attention to tackle the long-standing gap problem.

关键词

Keywords

references

Liu, T.; Liu, L.; Cui, F.; Ding, F.; Zhang, Q.; Li, Y . Predicting the performance of polyvinylidene fluoride, polyethersulfone and polysulfone filtration membranes using machine learning . J. Mater. Chem. A , 2020 . 8 21862 - 21871 . DOI: 10.1039/D0TA07607D http://doi.org/10.1039/D0TA07607D .

Liu, L.; Chen, W.; Li, Y . A statistical study of proton conduction in nafion®-based composite membranes: prediction, filler selection and fabrication methods . J. Membr. Sci. , 2018 . 549 393 - 402 . DOI: 10.1016/j.memsci.2017.12.025 http://doi.org/10.1016/j.memsci.2017.12.025 .

Liu, L.; Liu, T.; Ding, F.; Zhang, H.; Zheng, J.; Li, Y . Exploration of the polarization curve for proton-exchange membrane fuel cells . ACS Appl. Mater. Interfaces , 2021 . 13 58838 - 58847 . DOI: 10.1021/acsami.1c20289 http://doi.org/10.1021/acsami.1c20289 .

Jin, K.; Luo, H.; Wang, Z.; Wang, H.; Tao, J . Composition optimization of a high-performance epoxy resin based on molecular dynamics and machine learning . Mater. Des. , 2020 . 194 108932 DOI: 10.1016/j.matdes.2020.108932 http://doi.org/10.1016/j.matdes.2020.108932 .

Liu, L. Y.; Chen, W. D.; Liu, T. L.; Kong, X. X.; Zheng, J. F.; Li, Y. Q . Rational design of hydrocarbon-based sulfonated copolymers for proton exchange membranes . J. Mater. Chem. A , 2019 . 7 11847 - 11857 . DOI: 10.1039/C9TA00688E http://doi.org/10.1039/C9TA00688E .

Somarathna, H. M. C. C.; Raman, S. N.; Mohotti, D.; Mutalib, A. A.; Badri, K. H . The use of polyurethane for structural and infrastructural engineering applications: a state-of-the-art review . Constr. Build. Mater. , 2018 . 190 995 - 1014 . DOI: 10.1016/j.conbuildmat.2018.09.166 http://doi.org/10.1016/j.conbuildmat.2018.09.166 .

Opris, D. M . Polar elastomers as novel materials for electromechanical actuator applications . Adv. Mater. , 2018 . 30 1703678 DOI: 10.1002/adma.201703678 http://doi.org/10.1002/adma.201703678 .

Xiao, R.; Huang, W. M . Heating/solvent responsive shape-memory polymers for implant biomedical devices in minimally invasive surgery: current status and challenge . Macromol. Biosci. , 2020 . 20 e2000108 DOI: 10.1002/mabi.202000108 http://doi.org/10.1002/mabi.202000108 .

Shi, R.; Chen, D.; Liu, Q.; Wu, Y.; Xu, X.; Zhang, L.; Tian, W . Recent advances in synthetic bioelastomers . Int. J. Mol. Sci. , 2009 . 10 4223 - 4256 . DOI: 10.3390/ijms10104223 http://doi.org/10.3390/ijms10104223 .

Utrera-Barrios, S.; Verdejo, R.; Lopez-Manchado, M. A.; Santana, M. H . Evolution of self-healing elastomers, from extrinsic to combined intrinsic mechanisms: a review . Mater. Horizons , 2020 . 7 2882 - 2902 . DOI: 10.1039/D0MH00535E http://doi.org/10.1039/D0MH00535E .

Ma, Z. P.; Li, H.; Jing, X.; Liu, Y. J.; Mi, H. Y . Recent advancements in self-healing composite elastomers for flexible strain sensors: materials, healing systems, and features . Sensors Actuators A-Phys. , 2021 . 329 112800 DOI: 10.1016/j.sna.2021.112800 http://doi.org/10.1016/j.sna.2021.112800 .

Sui, T.; Baimpas, N.; Dolbnya, I. P.; Prisacariu, C.; Korsunsky, A. M . Multiple-length-scale deformation analysis in a thermoplastic polyurethane . Nat. Commun. , 2015 . 6 6583 DOI: 10.1038/ncomms7583 http://doi.org/10.1038/ncomms7583 .

Ding, F.; Liu, T.; Zhang, H.; Liu, L.; Li, Y . Stress-strain curves for polyurethane elastomers: a statistical assessment of constitutive models . J. Appl. Polym. Sci. , 2021 . 138 e51269 DOI: 10.1002/app.51269 http://doi.org/10.1002/app.51269 .

He, H.; Zhang, Q.; Zhang, Y.; Chen, J.; Zhang, L.; Li, F . A comparative study of 85 hyperelastic constitutive models for both unfilled rubber and highly filled rubber nanocomposite material . Nano Mater. Sci. , 2021 . 4 64 - 82 . .

Ma, R.; Luo, T . Pi1m: A benchmark database for polymer informatics . J. Chem. Inf. Model. , 2020 . 60 4684 - 4690 . DOI: 10.1021/acs.jcim.0c00726 http://doi.org/10.1021/acs.jcim.0c00726 .

Otsuka, S.; Kuwajima, I.; Hosoya, J.; Xu, Y.; Yamazaki, M . Polyinfo: Polymer database for polymeric materials design . Proceedings of the 2011 International Conference on Emerging Intelligent Data and Web Technologies , 2011 . 22 - 29 . .

Nozaki, S.; Masuda, S.; Kamitani, K.; Kojio, K.; Takahara, A.; Kuwarnura, G.; Hasegawa, D.; Moorthi, K.; Mita, K.; Yamasaki, S . Superior properties of polyurethane elastomers synthesized with aliphatic diisocyanate bearing a symmetric structure . Macromolecules , 2017 . 50 1008 - 1015 . DOI: 10.1021/acs.macromol.6b02044 http://doi.org/10.1021/acs.macromol.6b02044 .

Hu, J.; Mo, R.; Sheng, X.; Zhang, X . A self-healing polyurethane elastomer with excellent mechanical properties based on phase-locked dynamic imine bonds . Polym. Chem. , 2020 . 11 2585 - 2594 . DOI: 10.1039/D0PY00151A http://doi.org/10.1039/D0PY00151A .

Chen, T.; Guestrin, C . Xgboost: A scalable tree boosting system . Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , 2016 . 785 - 794 . DOI: 10.1145/2939672.2939785 http://doi.org/10.1145/2939672.2939785 .

Landrum, G. Rdkit: Open-source cheminformatics software. 2021 . https://rdkit.org/

Van Krevelen, D. W.; Te Nijenhuis, K., in Properties of polymers (fourth edition) , Elsevier. Amsterdam, 2009 , 189−227.

Fedors, R. F. A method for estimating both the solubility parameters and molar volumes of liquids . Supplement . Polym. Eng. Sci. , 1974 . 14 472 - 472 . DOI: 10.1002/pen.760140611 http://doi.org/10.1002/pen.760140611 .

Zhang, H.; Ding, F.; Liu, T. L.; Liu, L. Y.; Li, Y. Q . Additivity of the mechanical properties for acrylonitrile-butadiene-styrene resins . J. Appl. Polym. Sci. , 2022 . 139 e51923 DOI: 10.1002/app.51923 http://doi.org/10.1002/app.51923 .

Guyon, I.; Weston, J.; Barnhill, S.; Vapnik, V . Gene selection for cancer classification using support vector machines . Mach. Learn. , 2002 . 46 389 - 422 . DOI: 10.1023/A:1012487302797 http://doi.org/10.1023/A:1012487302797 .

Breiman, L . Random forests . Mach. Learn. , 2001 . 45 5 - 32 . DOI: 10.1023/A:1010933404324 http://doi.org/10.1023/A:1010933404324 .

Smola, A. J.; Scholkopf, B . A tutorial on support vector regression . Stat. Comput. , 2004 . 14 199 - 222 . DOI: 10.1023/B:STCO.0000035301.49549.88 http://doi.org/10.1023/B:STCO.0000035301.49549.88 .

Rumelhart, D. E.; Hinton, G. E.; Williams, R. J . Learning representations by back-propagating errors . Nature , 1986 . 323 533 - 536 . DOI: 10.1038/323533a0 http://doi.org/10.1038/323533a0 .

Fix, E.; Hodges, J. L . Discriminatory analysis-nonparametric discrimination - consistency properties . Int. Stat. Rev. , 1989 . 57 238 - 247 . DOI: 10.2307/1403797 http://doi.org/10.2307/1403797 .

Altman, N. S . An introduction to kernel and nearest-neighbor nonparametric regression . Am. Stat. , 1992 . 46 175 - 185 . .

Pugar, J. A.; Gang, C.; Huang, C.; Haider, K. W.; Washburn, N. R . Predicting young’s modulus of linear polyurethane and polyurethane–polyurea elastomers: bridging length scales with physicochemical modeling and machine learning . ACS Appl. Mater. Interfaces , 2022 . 14 16568 - 16581 . DOI: 10.1021/acsami.1c24715 http://doi.org/10.1021/acsami.1c24715 .

Ertem, S. P.; Yilgor, E.; Kosak, C.; Wilkes, G. L.; Zhang, M. Q.; Yilgor, I . Effect of soft segment molecular weight on tensile properties of poly(propylene oxide) based polyurethaneureas . Polymer , 2012 . 53 4614 - 4622 . DOI: 10.1016/j.polymer.2012.08.020 http://doi.org/10.1016/j.polymer.2012.08.020 .

Cordero, J . A.; He K.; Janya K.; Echigo S.; Itoh S. Predicting formation of haloacetic acids by chlorination of organic compounds using machine-learning-assisted quantitative structure-activity relationships . J. Hazard. Mater. , 2021 . 408 124466 DOI: 10.1016/j.jhazmat.2020.124466 http://doi.org/10.1016/j.jhazmat.2020.124466 .

Yang, S.; Wang, S.; Du, X.; Du, Z.; Cheng, X.; Wang, H . Mechanically robust self-healing and recyclable flame-retarded polyurethane elastomer based on thermoreversible crosslinking network and multiple hydrogen bonds . Chem. Eng. J. , 2020 . 391 123544 DOI: 10.1016/j.cej.2019.123544 http://doi.org/10.1016/j.cej.2019.123544 .

Prasanna, S.; Doerksen, R. J . Topological polar surface area: A useful descriptor in 2d-qsar . Curr. Med. Chem. , 2009 . 16 21 - 41 . DOI: 10.2174/092986709787002817 http://doi.org/10.2174/092986709787002817 .

Labute, P . A widely applicable set of descriptors . J. Mol. Graph. Model. , 2000 . 18 464 - 477 . DOI: 10.1016/S1093-3263(00)00068-1 http://doi.org/10.1016/S1093-3263(00)00068-1 .

Pugar, J. A.; Childs, C. M.; Huang, C.; Haider, K. W.; Washburn, N. R . Elucidating the physicochemical basis of the glass transition temperature in linear polyurethane elastomers with machine learning . J. Phys. Chem. B , 2020 . 124 9722 - 9733 . DOI: 10.1021/acs.jpcb.0c06439 http://doi.org/10.1021/acs.jpcb.0c06439 .

Menon, A.; Thompson-Colon, J. A.; Washburn, N. R . Hierarchical machine learning model for mechanical property predictions of polyurethane elastomers from small datasets . Front. Mater. , 2019 . 6 87 DOI: 10.3389/fmats.2019.00087 http://doi.org/10.3389/fmats.2019.00087 .

He, Y.; Xie, D.; Zhang, X . The structure, microphase-separated morphology, and property of polyurethanes and polyureas . J. Mater. Sci. , 2014 . 49 7339 - 7352 . DOI: 10.1007/s10853-014-8458-y http://doi.org/10.1007/s10853-014-8458-y .

Sonnenschein, M. F.; Guillaudeu, S. J.; Landes, B. G.; Wendt, B. L . Comparison of adipate and succinate polyesters in thermoplastic polyurethanes . Polymer , 2010 . 51 3685 - 3692 . DOI: 10.1016/j.polymer.2010.06.012 http://doi.org/10.1016/j.polymer.2010.06.012 .

Shin, J.; Matsushima, H.; Chan, J. W.; Hoyle, C. E . Segmented polythiourethane elastomers through sequential thiol-ene and thiol-isocyanate reactions . Macromolecules , 2009 . 42 3294 - 3301 . DOI: 10.1021/ma8026386 http://doi.org/10.1021/ma8026386 .

Falco, G.; Simonin, L.; Pensec, S.; Dalmas, F.; Chenal, J. M.; Bouteiller, L.; Chazeau, L . Linear and nonlinear viscoelastic properties of segmented silicone-urea copolymers: Influence of the hard segment structure . Polymer , 2020 . 186 122041 DOI: 10.1016/j.polymer.2019.122041 http://doi.org/10.1016/j.polymer.2019.122041 .

Rogulska, M.; Kultys, A.; Pikus, S. . Studies on thermoplastic polyurethanes based on new diphenylethane-derivative diols. Iii. The effect of molecular weight and structure of soft segment on some properties of segmented polyurethanes . J. Appl. Polym. Sci. , 2008 . 110 1677 - 1689 . DOI: 10.1002/app.28583 http://doi.org/10.1002/app.28583 .

Kim, H. D.; Lee, T. J.; Huh, J. H.; Lee, D. J . Preparation and properties of segmented thermoplastic polyurethane elastomers with two different soft segments . J. Appl. Polym. Sci. , 1999 . 73 345 - 352 . DOI: 10.1002/(SICI)1097-4628(19990718)73:3<345::AID-APP5>3.0.CO;2-T http://doi.org/10.1002/(SICI)1097-4628(19990718)73:3<345::AID-APP5>3.0.CO;2-T .

Liao, T.; Yang, X.; Zhao, X. T.; Tang, Y. J.; Jiang, Z. Y.; Men, Y. F . Gaussian and non-gaussian distributions of fracture properties in tensile stretching of high-density polyethylene . Macromolecules , 2021 . 54 8860 - 8874 . DOI: 10.1021/acs.macromol.1c00944 http://doi.org/10.1021/acs.macromol.1c00944 .

Tang, H.; Cui, F.; Liu, L.; Li, Y . Predictive models for tyrosinase inhibitors: challenges from heterogeneous activity data determined by different experimental protocols . Comput. Biol. Chem. , 2018 . 73 79 - 84 . DOI: 10.1016/j.compbiolchem.2018.02.007 http://doi.org/10.1016/j.compbiolchem.2018.02.007 .

Cereto-Massague, A.; Ojeda, M . J.; Valls C.; Mulero M.; Garcia-Vallve S.; Pujadas G. Molecular fingerprint similarity search in virtual screening . Methods , 2015 . 71 58 - 63 . DOI: 10.1016/j.ymeth.2014.08.005 http://doi.org/10.1016/j.ymeth.2014.08.005 .

Durant, J. L.; Leland, B. A.; Henry, D. R.; Nourse, J. G . Reoptimization of mdl keys for use in drug discovery . J. Chem. Inf. Comput. Sci. , 2002 . 42 1273 - 1280 . DOI: 10.1021/ci010132r http://doi.org/10.1021/ci010132r .

Zhang, H.; Ding, F.; Liu, T.; Liu, L.; Li, Y . Additivity of the mechanical properties for acrylonitrile-butadiene-styrene resins . J. Appl. Polym. Sci. , 2021 . 139 e51923 .

Kim, B. K.; Lee, S. Y.; Xu, M . Polyurethanes having shape memory effects . Polymer , 1996 . 37 5781 - 5793 . DOI: 10.1016/S0032-3861(96)00442-9 http://doi.org/10.1016/S0032-3861(96)00442-9 .

Rahmawati, R.; Nozaki, S.; Kojio, K.; Takahara, A.; Shinohara, N.; Yamasaki, S . Microphase-separated structure and mechanical properties of cycloaliphatic diisocyanate-based thiourethane elastomers . Polym. J. , 2018 . 51 265 - 273 . .

Oprea, S.; Timpu, D.; Oprea, V . Design-properties relationships of polyurethanes elastomers depending on different chain extenders structures . J. Polym. Res. , 2019 . 26 117 DOI: 10.1007/s10965-019-1777-6 http://doi.org/10.1007/s10965-019-1777-6 .

Khiem, V. N.; Itskov, M . Analytical network-averaging of the tube model: rubber elasticity . J. Mech. Phys. Solids , 2016 . 95 254 - 269 . DOI: 10.1016/j.jmps.2016.05.030 http://doi.org/10.1016/j.jmps.2016.05.030 .

浏览量

493

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Prediction of Stress-strain Behavior for Polyurethane Elastomers Based on Machine Learning

Data-Driven Exploration of Polymer Processing Effects on the Mechanical Properties in Carbon Black-Reinforced Rubber Composites

From Molecular Defect to Macroscopic Performance: Manipulating Dichroism and Mechanics in Iodine-doped Poly(vinyl alcohol) via Ethylene Incorporation

End-to-End Neuron-inspired Signal Transduction Using Organic Electrochemical Transistors

Silk Sericin-inspired Poly-β-homoserine for Protein Protection