Skip to main content
SpringerLink
Log in

The neural network and multivariate linear regression approach for observing phase transitions of polymers with the differential thermal analysis method

  • Published:
Journal of Thermal Analysis and Calorimetry Aims and scope Submit manuscript

Abstract

The aim of this study was to correlate the results of experimental data using DTA method and predictions of artificial neural network (ANN) and multivariate linear regression (MLR). Thermal decomposition of polymers was analyzed by simultaneous DTA method, and kinetic parameters (critical points, the change of enthalpy and entropy) of polymers were investigated. A computer model based on multilayer feed forwarding back propagation and multilayer linear regression model were used for the prediction of critical points, phase transitions of low-density polyethylene (LDPE) and mid-density polyethylene. As a result of our study, we concluded that ANN model is more suitable than MLR about prediction of experimental data.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

References

  1. Sebastiao RCO, Braga JP, Yoshida MI. Competition between kinetic models in thermal decomposition analysis by artificial neural network. Thermochim Acta. 2004. doi:10.1016/j.tca.2003.09.009.

  2. Tomaszewicz E, Kotfica M. Application of neural networks in analysis of thermal decomposition of CoSO 4. J Therm Anal Calorim. 2003. doi:10.1023/B:JTAN.0000005197.33066.f5.

  3. Ayhan-Sarac B. Neural network methodology for heat transfer enhancement data. Int J Numer Methods Heat Fluid Flow. 2007. doi:10.1108/0961530710825774.

  4. Ayhan T, Karlik B, Tandiroglu A. Flow geometry optimization of channels with baffels using neural networks and second-low of thermodynamics. Comput Mech. 2004. doi:10.1007/s00466-003-0509-1.

  5. Browna ME, Maciejewskib M, Vyazovkinc S, Nomend R, Sempered J, Burnhame A, Opfermannf J, Streyg R, Andersong HL, Kemmlerg A, Keuleersh R, Janssensh J, Desseynh HO, Lii CR, Tangi TB, Roduitj B, Malekk J, Mitsuhashil T. Computational aspects of kinetic analysis part A: the ICTAC kinetics project-data, methods and results. Thermochim Acta. 2000. doi:10.1016/S0040-6031(00)00443-3.

  6. Beken M. Developing differential thermal analysis device under high pressure. PhD Thesis, Yildiz Technical University; 2002.

  7. Bundy FP. Effect of pressure on emf of thermocouples. J Appl Phys. 1960. doi:10.1063/1.1708993.

  8. Michalik K, Drzazga Z, Michnik A, Kaszuba M. Differential scanning microcalorimetry study of thermal stability of nevirapine and azidothymidine mixture. J Therm Anal Calorim. 2006. doi:10.1007/s10973-005-7171-0.

  9. Richter PW, Clarke JB. Asymmetrical friction in a piston-cylinder device and the effect on the melting curves of indium and bismuth. Rev Sci Instrum. 1980. doi:10.1063/1.1136354.

  10. Sozen A, Arcaklioglu E, Ozalp M. A new approach to thermodynamic analysis of ejectorabsorption cycle: artificial neural networks. Appl Therm Eng. 2003. doi:10.1016/S1359-4311(03)00034-6.

  11. Haykin S. Neural networks: A comprehensive foundation, 2–3. Englewood Cliffs: Macmillan College Publishing Company; 1994.

    Google Scholar 

  12. Caballero JA, Conesa JA, Font R, Marcilla A. Pyrolysis kinetics of almond shells and olive stones considering their organic fractions. J Anal Appl Pyrol. 1997. doi:10.1016/S0165-2370(97)00015-6.

  13. Karlik B. Myoeletric control of multifunction prothesis using neural networks. PhD Thesis, Yildiz Technical University; 1994.

  14. Maimon OZ, Rokach L. Data mining and knowledge discovery handbook. New York: Springer; 2005.

    Book  Google Scholar 

  15. Brillinger DR. The identification of a particular nonlinear time series system. Biometrika. 1977. doi:10.1093/biomet/64.3.509.

Download references

Acknowledgements

The author wishes to thank Dr. Reha Basaran for the support of experimental studies and Ozlem Ilgun for neural network studies and Derya Kosucuoglu for the support of MLR studies. Also the author wishes to thank Emirhan Emre for his technical support.

Author information

Authors and Affiliations

  1. Applied Mathematics Department, Halic University, Bomonti, Istanbul, Turkey

    Murat Beken

Authors
  1. Murat Beken
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Murat Beken.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Beken, M. The neural network and multivariate linear regression approach for observing phase transitions of polymers with the differential thermal analysis method. J Therm Anal Calorim 101, 339–347 (2010). https://doi.org/10.1007/s10973-010-0749-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10973-010-0749-1

Keywords

Search

Navigation