Toward accurate machine learning-driven prediction of polymeric composites properties based on experimental data

Abstract

In response to climate change, there has been a focus on developing lightweight and environmentally friendly materials, with active research aimed at enhancing the energy efficiency of electric and hybrid vehicles. In this context, the development of polymer composites with superior thermal conductivity (TC) has been recognized as critical to meeting mechanical property requirements. This paper presents a machine learning model that utilized 1774 experimental data points to predict various properties of polymer composites, such as density, heat deflection temperature, flexural modulus, flexural strength, tensile yield strength, impact strength, and TC. Various data representation methods for composition data are employed, and the XGBoost model is trained, achieving high accuracy with an average R² score of 0.95. This machine learning model, informed by experimental data, is a useful tool for predicting and optimizing the properties of polymer composites.

Keywords

machine learning / polymer data representation / polymer property prediction / thermal conductive polymer composites

References

[1] Liu Z, Deng Z, Davis S, Ciais P. Monitoring global carbon emissions in 2022. Nat Rev Earth Environ. 2023; 4(4): 205-206.

[2] Chen L, Msigwa G, Yang M, et al. Strategies to Achieve a Carbon Neutral Society: A Review. Vol. 20. Springer International Publishing; 2022: 2277-2310.

[3] Nunes LJR. The rising threat of atmospheric CO₂: a review on the causes, impacts, and mitigation strategies. Environments. 2023; 10(4): 66.

[4] Bai S, Liu C. Overview of energy harvesting and emission reduction technologies in hybrid electric vehicles. Renew Sustain Energy Rev. 2021; 147:111188.

[5] Lee H, Jang Jun, Kim J, et al. True self-reinforced composites enabled by tuning of molecular structure for lightweight structural materials in future mobility. Chem Eng J. 2023; 465(6):142996.

[6] Gupta P, Toksha B, Patel B, Rushiya Y, Das P, Rahaman M. Recent developments and research avenues for polymers in electric vehicles. Chem Rec. 2022; 22(11):e202200186.

[7] Kopelias P, Demiridi E, Vogiatzis K, Skabardonis A, Zafiropoulou V. Connected & autonomous vehicles – environmental impacts – a review. Sci Total Environ. 2020; 712:135237.

[8] Hawkins TR, Gausen OM, Strømman AH. Environmental impacts of hybrid and electric vehicles-a review. Int J Life Cycle Assess. 2012; 17(8): 997-1014.

[9] Al Haddad C, Chaniotakis E, Straubinger A, Plötner K, Antoniou C. Factors affecting the adoption and use of urban air mobility. Transp Res Part A Policy Pract. 2020; 132(November 2019): 696-712.

[10] Harper G, Sommerville R, Kendrick E, et al. Recycling lithium-ion batteries from electric vehicles. Nature. 2019; 575(7781): 75-86.

[11] Garole DJ, Hossain R, Garole VJ, Sahajwalla V, Nerkar J, Dubal DP. Recycle, recover and repurpose strategy of spent Li-ion batteries and catalysts: current status and future opportunities. ChemSusChem. 2020; 13(12): 3079-3100.

[12] Or T, Gourley SWD, Kaliyappan K, Yu A, Chen Z. Recycling of mixed cathode lithium-ion batteries for electric vehicles: current status and future outlook. Carbon Energy. 2020; 2(1): 6-43.

[13] Masias A, Marcicki J, Paxton WA. Opportunities and challenges of lithium ion batteries in automotive applications. ACS Energy Lett. 2021; 6(2): 621-630.

[14] Tete PR, Gupta MM, Joshi SS. Developments in battery thermal management systems for electric vehicles: a technical review. J Energy Storage. 2021; 35:102255.

[15] Lyu MY, Choi TG. Research trends in polymer materials for use in lightweight vehicles. Int J Precis Eng Manuf. 2015; 16(1): 213-220.

[16] Yoon Y-S, Jang M-H, Moon D-J, Jang E, Oh M-H, Park J-I. Thermally conductive polymer composites for electric vehicle battery housing. J Korea Converg Soc. 2022; 13(4): 331-337.

[17] Huang C, Qian X, Yang R. Thermal conductivity of polymers and polymer nanocomposites. Mater Sci Eng R Rep. 2018; 132: 1-22.

[18] Gogoi R, Manik G. Development of thermally conductive and high-specific strength polypropylene composites for thermal management applications in automotive. Polym Compos. 2021; 42(4): 1945-1960.

[19] Frketic J, Dickens T, Ramakrishnan S. Automated manufacturing and processing of fiber-reinforced polymer (FRP) composites: an additive review of contemporary and modern techniques for advanced materials manufacturing. Addit Manuf. 2017; 14: 69-86.

[20] Sanada K, Tada Y, Shindo Y. Thermal conductivity of polymer composites with close-packed structure of nano and micro fillers. Compos Part A Appl Sci Manuf. 2009; 40(6-7): 724-730.

[21] Lee GW, Park M, Kim J, Lee JI, Yoon HG. Enhanced thermal conductivity of polymer composites filled with hybrid filler. Compos Part A Appl Sci Manuf. 2006; 37(5): 727-734.

[22] Han Z, Fina A. Thermal conductivity of carbon nanotubes and their polymer nanocomposites: a review. Prog Polym Sci. 2011; 36(7): 914-944.

[23] Mazov IN, Ilinykh IA, Kuznetsov VL, et al. Thermal conductivity of polypropylene-based composites with multiwall carbon nanotubes with different diameter and morphology. J Alloys Compd. 2014; 586: S440-S442.

[24] Tan X, Yuan Q, Qiu M, et al. Rational design of graphene/polymer composites with excellent electromagnetic interference shielding effectiveness and high thermal conductivity: a mini review. J Mater Sci Technol. 2022; 117: 238-250.

[25] Kim C, Chandrasekaran A, Huan TD, Das D, Ramprasad R. Polymer genome: a data-powered polymer informatics platform for property predictions. J Phys Chem C. 2018; 122(31): 17575-17585.

[26] Wu S, Kondo Y, aki KM, et al. Machine-learning-assisted discovery of polymers with high thermal conductivity using a molecular design algorithm. npj Comput Mater. 2019; 5(1):66.

[27] Tao L, Varshney V, Li Y. Benchmarking machine learning models for polymer informatics: an example of glass transition temperature. J Chem Inf Model. 2021; 61(11): 5395-5413.

[28] Yamada H, Liu C, Wu S, et al. Predicting materials properties with little data using shotgun transfer learning. ACS Cent Sci. 2019; 5(10): 1717-1730.

[29] Han S, Kang Y, Park H, Yi J, Park G, Kim J. Multimodal transformer for property prediction in polymers. ACS Appl Mater Interfaces. 2024; 16(13): 16853-16860.

[30] Liu B, Vu-Bac N, Zhuang X, Fu X, Rabczuk T. Stochastic integrated machine learning based multiscale approach for the prediction of the thermal conductivity in carbon nanotube reinforced polymeric composites. Compos Sci Technol. 2022; 224:109425.

[31] Mohit H, Sanjay MR, Siengchin S, et al. Machine learning-based prediction of mechanical and thermal properties of nickel/cobalt/ferrous and dried leaves fiber-reinforced polymer hybrid composites. Polym Compos. 2024; 45(1): 489-506.

[32] Chen CT, Gu GX. Machine learning for composite materials. MRS Commun. 2019; 9(2): 556-566.

[33] Yue D, Feng Y, Liu XX, et al. Prediction of energy storage performance in polymer composites using high-throughput stochastic breakdown simulation and machine learning. Adv Sci. 2022; 9(17): 1-12.

[34] Joo C, Park H, Kwon H, et al. Machine learning approach to predict physical properties of polypropylene composites: application of MLR, DNN, and random forest to industrial data. Polymers (Basel). 2022; 14(17):3500.

[35] Fang J, Xie M, He X, et al. Machine learning accelerates the materials discovery. Mater Today Commun. 2022; 33:104900.

[36] Sharma A, Mukhopadhyay T, Rangappa SM, Siengchin S, Kushvaha V. Advances in computational intelligence of polymer composite materials: machine learning assisted modeling, analysis and design. Arch Comput Methods Eng. 2022; 29(5): 3341-3385.

[37] Hamidi YK, Berrado A, Altan MC. Machine learning applications in polymer composites. AIP Conf Proc. 2020; 2205:020031.

[38] Miccio LA, Schwartz GA. From chemical structure to quantitative polymer properties prediction through convolutional neural networks. Polymer (Guildf). 2020; 193:122341.

[39] Park J, Shim Y, Lee F, et al. Prediction and interpretation of polymer properties using the graph convolutional network. ACS Polym Au. 2022; 2(4): 213-222.

[40] Liu Y, Zheng W, Ai H, et al. Application of machine learning in predicting the thermal conductivity of single-filler polymer composites. Mater Today Commun. 2024; 39:109116.

[41] Domingos P. A few useful things to know about machine learning. Commun ACM. 2012; 55(10): 78-87.

[42] Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: machine learning in python. J Mach Learn Res. 2011; 12: 2825-2830.

[43] Chang CC, Lin CJ. LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol. 2011; 2(3): 1-40.

[44] Breiman L. Random forests. Mach Learn. 2001; 45(1): 5-32.

[45] Geurts P, Ernst D, Wehenkel L. Extremely randomized trees. Mach Learn. 2006; 63(1): 3-42.

[46] Friedman JH. Greedy function approximation: a gradient boosting machine. Ann Stat. 2001; 29(5): 1189-1232.

[47] Chen T, Guestrin C. XGBoost: a scalable tree boosting system. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery; 2016: 785-794.

[48] Akiba T, Sano S, Yanase T, Ohta T, Koyama M. Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining; 2019: 1-10.

[49] Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2012; 16(3): 426-430.

[50] Kaur H, Nori H, Jenkins S, et al. Interpreting interpretability: understanding data scientists’ use of interpretability tools for machine learning. In: Conference on Human Factors in Computing Systems - Proceedings; 2020: 1-14. Published online.

[51] Rodríguez-Pérez R, Bajorath J. Interpretation of machine learning models using shapley values: application to compound potency and multi-target activity predictions. J Comput Aided Mol Des. 2020; 34(10): 1013-1026.

[52] Suvarna M, Araújo TP, Pérez-Ramírez J. A generalized machine learning framework to predict the space-time yield of methanol from thermocatalytic CO₂ hydrogenation. Appl Catal B Environ. 2022; 315:121530.

RIGHTS & PERMISSIONS

2025 The Author(s). Materials Genome Engineering Advances published by Wiley-VCH GmbH on behalf of University of Science and Technology Beijing.