Prediction of Glass Transition Temperature of Polymer by Support Vector Regression

Abstract:

. Based on two quantum chemical descriptors (the thermal energy Ethermal and the total energy of the whole system EHF) calculated from the structures of the repeat units of polyacrylamides by density functional theory (DFT), the support vector regression (SVR) approach combined with particle swarm optimization (PSO), is proposed to establish a model for prediction of the glass transition temperature (Tg) of polyacrylamides. The prediction performance of SVR was compared with that of multivariate linear regression (MLR). The results show that the mean absolute error (MAE=4.65K), mean absolute percentage error (MAPE=1.28%) and correlation coefficient (R2=0.9818) calculated by leave-one–out cross validation (LOOCV) via SVR models are superior to those achieved by QSPR (MAE=14.25K, MAPE=4.39% and R2=0.9211) and QSPR-LOO (MAE=17.01K, MAPE=5.66% and R2=0.8823) models for the identical samples, respectively. The prediction results strongly demonstrate that the modeling and generalization abilities of SVR model consistently surpass those of QSPR and QSPR-LOO models. It is revealed that the established SVR model is more suitable to be used for prediction of the Tg values for unknown polymers possessing similar structure than the conventional MLR approach. These suggest that SVR is a promising and practical methodology to predict the glass transition temperature of polyacrylamides.

• Periodical: Advanced Materials Research (Volumes 455-456)
• Pages: 436-442
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.455-456.436
• Online since: January 2012
• Authors: J.F. Pei, C.Z. Cai, X.J. Zhu, G.L. Wang, B. Yan
• Keywords: Glass Transition Temperature, Polymer, Prediction, Regression Analysis, Support Vector Regression (SVR)

References

[1] S.H. Lin and K. Argasinski, Fluoropolymer alloys: performance optimization of PVDF alloys. in Fluopolymers 2: Properties, G. Hougham, P.E. Cassidy, K. Johns and T. Davison (editors), New York: Plenum Press, vol. 122, (1999).

[2] S. Krause, J.J. Gormley, N. Roman, J.A. Shetter and W.H. Wantanade, Glass temperatures of some acrylic polymers, J. Polym. Sci., Part A: Polym. Chem., vol. 10, no. 3, pp.3573-3586, (1965).

DOI: 10.1002/pol.1965.100031020

[3] A. Majumdar, J.P. Carrejo and J. Lai, Thermal imaging using the atomic force microscope, Appl. Phys. Lett., Vol. 20, no. 62, pp.2501-2503, (1993).

DOI: 10.1063/1.109335

[4] H.M. Pollock and A. Hammiche, Micro-thermal analysis: techniques and applications, J. Phys. D: Appl. Phys., Vol. 9, no. 34, pp.23-53, (2001).

[5] R.F. Boyres, in: H.F. Mark, N.M. Bikales. Suppl. vol. II, New York: Wiley, 1997, p.745.

[6] M. Kunaver, J. Zadnik, O. Planinsek and S. Srcie, Inverse gas chromatography - A different approach to characterization of solids and liquids, Acta. Chim. Slov., vol. 3, no. 51, pp.373-394, (2004).

[7] M.S. Gaur, P. Shukla, R.K. Tiwari, A. Tanwar and S.P. Singh, New approach for the measurement of glass transition temperature of polymer, Indian. J. of Pure & Applied Phys., vol. 8, no. 45, pp.535-539, (2008).

[8] W.P. Winfree, F.R. Parker, and M.C. Wu, Acoustic measurement of glass transition temperature in polymers, IEEE 1986 Ultrasonics Symposium, pp.1009-1012, (1986).

DOI: 10.1109/ultsym.1986.198889

[9] T. Miyazaki, R. Inoue, K. Nishida and T. Kanaya, X-ray reflectivity studies on glass transition of free standing polystyrene thin films, Eur. Phys. J. Special Topics, vol. 141, pp.203-206, (2007).

DOI: 10.1140/epjst/e2007-00041-y

[10] L. Banks and B. Ellis, The glass transition temperature of an epoxy resin and the effect of absorbed water, Polym. Bulletin, vol. 1, pp.377-382, (1979).

DOI: 10.1007/bf00284406

[11] A.R. Katrizky, P. Pachwal, K.W. Law, M. Karelson, and V.S. Lobanov, Prediction of polymer glass transition temperature using a general quantitative structure-property relationship treatment, J. Chem. Inf. Comput. Sci., vol. 36, pp.879-884, (1996).

DOI: 10.1021/ci950156w

[12] J. Bicerano, Prediction of polymers properties, 2nd ed., New York: Marcel Dekker, (1996).

[13] P. Camelio, C.C. Cypcar, V. lazzeri and B. Waegell, A novel approach toward the prediction of the glass transition temperature: application of the EVM model, a designer QSPR equation for the prediction of acrylate and methacrylate polymers, J. Polym. Sci. Part A: Polym. Chem., vol. 35, pp.2579-2591, (1997).

DOI: 10.1002/(sici)1099-0518(19970930)35:13<2579::aid-pola5>3.0.co;2-m

[14] J. Schut, D. Bolikal, I.J. Khan, A. Pesnell, A. Rege, R. Rojas and L. Sheihet, Glass transition temperature prediction of polymers through the mass-per-flexible-bond principle, Polymer, vol. 48, pp.6115-6124, (2007).

DOI: 10.1016/j.polymer.2007.07.048

[15] A.R. Katritzky, S. Sild, V. Lobanov and M. Karelson, Quantitative structure- property relationship (QSPR) Correlation of glass transition temperature of high molecular weight polymers, J. Chem. Inf. Comput. Sci., vol. 38, pp.300-304, (1998).

DOI: 10.1021/ci9700687

[16] S.J. Joyce and D.J. Osguthorpe, Neural network prediction of glass- transition temperatures from monomer structure, J. Chem. Soc., Faraday Trans., vol. 91, pp.2491-2496, (1995).

DOI: 10.1039/ft9959102491

[17] B.E. Mattioni and P.C. Jurs, Prediction of glass transition temperature from monomer and repeat unit structure using computation neural networks, J. Chem. Inf. Comput. Sci., vol. 42, pp.232-240, (2002).

DOI: 10.1021/ci010062o

[18] X.L. Yu and B. Yi, X.Y. Wang, Z.M. Xie, Correlation between the glass transition temperatures and multipole moments for polymers, Chem. Phys., vol. 332, pp.115-118, (2007).

DOI: 10.1016/j.chemphys.2006.11.029

[19] A.L. Liu, X.Y. Wang, L. Wang, H.L. Wang and H.L. Wang, Prediction of dielectric constants and glass transition temperatures of polymers by quantitative structure property relationships, Eur. Polym. J., vol. 43, pp.989-995, (2007).

DOI: 10.1016/j.eurpolymj.2006.12.029

[20] V. Vapnik, The natural of statistical learning theory, New York: Springer, (1995).

[21] C.Z. Cai, X.J. Zhu, Y.F. Wen, J.F. Pei and G.L. Wang, Predicting the superconducting transition temperature Tc of BiPbSrCaCuOF superconductors by using support vector regression, J. Supercond. Nov. Magn., vol. 23, pp.737-740, (2010).

DOI: 10.1007/s10948-010-0732-x

[22] D.O. Whiteson, and N.A. Naumann, Support vector regression as a signal discriminator in high energy physics, Neurocomputing, vol. 55, pp.251-264, (2003).

DOI: 10.1016/s0925-2312(03)00366-7

[23] Z. Yuan and B.X. Huang, Prediction of protein accessible surface areas by support vector regression, Proteins, vol. 57, pp.558-564, (2004).

DOI: 10.1002/prot.20234

[24] C.Z. Cai, W.L. Wang, L.Z. Sun and Y.Z. Chen, Protei function classification via support vector machine approach, Mathematical Biosciences, vol. 2, no. 185, pp.111-122, (2003).

DOI: 10.1016/s0025-5564(03)00096-8

[25] C.Z. Cai, L.Y. Han, Z.L. Ji, X. Chen, Y.Z. Chen. SVM-Prot: web-based support vector machine software for functional classification of a protein from its primary sequence, Nucleic. Acids. Res., vol. 31, pp.3692-3697, (2003).

DOI: 10.1093/nar/gkg600

[26] C.Z. Cai, W.L. Wang, Y.Z. Chen, Support vector machine classification of physical and biological datasets, Int. J. of Mod. Phys. C, vol. 14, pp.575-585, (2003).

DOI: 10.1142/s0129183103004759

[27] J. Song and K. Burrage, Predicting residue-wise contact orders in proteins by support vector regression, BMC Bioinformatics, vol. 7, p.425, (2006).

DOI: 10.1186/1471-2105-7-425

[28] Y.F. Wen, C.Z. Cai, X.H. Liu, J.F. Pei, X.J. Zhu and T.T. Xiao, Corrosion rate prediction of 3C steel under different seawater environment by using support vector regression, Corrosion Science, vol. 51, pp.349-355, (2009).

DOI: 10.1016/j.corsci.2008.10.038

[29] National Institute for Materials Science, Polymer Database: http: /polymer. nims. go. jp/PoLyInfo.

[30] J. Brandrup, E.H. Immergut and E.A. Grulke, Polymer handbook. 4th ed., New York: John and Sons Inc., (1999).

[31] J. Kennedy and R. Eberhart, Particle swarm optimization, Proceedings of IEEE International Conference on Neural Networks, vol. 4, pp.1942-1948, (1995).

[32] P.J. Achorn and R.G. Ferrillo, Comparison of thermal techniques for glass transition measurements of polystyrene and cross-linked acrylic polyurethane films, J. Appl . Polym. Sci., vol. 54, pp.2033-2034, (1994).

DOI: 10.1002/app.1994.070541305

[33] R.G. Ferrillo and P.J. Achorn, Comparison of thermal techniques for glass transition assignment, J. Appl. Polym. Sci., vol. 64, pp.191-196, (1997).

DOI: 10.1002/(sici)1097-4628(19970404)64:1<191::aid-app17>3.0.co;2-7

[34] R. Hagen, L. Salmen, H. Lavebratt and B. Stenberg, Comparison of dynamic mechanical measurements and Tg determinations with two dirrerent instruments, Polymer Testing, vol. 13, pp.113-128, (1994).

DOI: 10.1016/0142-9418(94)90020-5