Prediction of the flash points of alkanes by group bond contribution method using artificial neural networks

Abstract

A group bond contribution model using artificial neural networks, which had the high ability of nonlinear of prediction, was established to predict the flash points of alkanes. This model contained not only the information of group property but also connectivity in molecules. A set of 16 group bonds were used as input parameters of neural networks to study the correlation of molecular structures with flash points of 44 alkanes. The results showed that the predicted flash points were in good agreement with the experimental data that the absolute mean absolute error was 6.9 K and the absolute mean relative error was 2.29%, which were superior to those of traditional group contribution methods. The method can be used not only to reveal the quantitative correlation between flash points and molecular structures of alkanes but also to predict the flash points of organic compounds for chemical engineering.

This is a preview of subscription content, access via your institution.

References

  1. 1.

    Liaw H J, Lee Y H, Tang C L, Hsu H H, Liu J H. A mathematical model for predicting the flash point of binary solutions. J Loss Prevent Proc, 2002, 15: 429–438

    Article  Google Scholar 

  2. 2.

    Lyman W J, Reehl W F, Rosenblatt D H. Handbook of Chemical Property Estimation Methods. New York: McGraw-Hill, 1982, 751–752

    Google Scholar 

  3. 3.

    Guo Z H. Calculation of boiling points of alkanes using molecule structure topological indices. Chem Eng (China), 1994, 3: 63–65 (in Chinese)

    Google Scholar 

  4. 4.

    Hall L H, Story C T. Boiling point and critical temperature of a heterogeneous data set: QSAR with atom type electrotopological state indices using artificial neural networks. J Chem Inf Comput Sci, 1996, (36): 1,004–1,014

  5. 5.

    Zhokhova N I, Baskin I I, Palyulin V A, Zefirov A N, Zefirov N S. Fragmental descriptors in QSPR: Flash point calculations. Russ Chem B, 2003, 52(9): 1,885–1,892

    CAS  Google Scholar 

  6. 6.

    Albahri T A. Flammability characteristics of pure hydrocarbons. Chem Eng Sci, 2003, 58: 3,629–3,641

    CAS  Google Scholar 

  7. 7.

    Tetteh J, Suzuki T, Metcalfe E, Howells S. Quantitative structure-property relationships for the estimation of boiling point and flash point using a radial basis function neural network. J Chem Inf Comput Sci, 1999, 39: 491–507

    Article  CAS  Google Scholar 

  8. 8.

    Wang K Q, Du Z X, Wang J. A new method for predicting the flash points of organic compounds from the information of molecular component. Bull Sci Technol, 2002, 18(3): 235–239 (in Chinese)

    Google Scholar 

  9. 9.

    Wang K Q. A new method for predicting the densities of alkanes from the information of molecular structure-group bond contribution method. Chin J Org Chem, 1999, 19: 304–308 (in Chinese)

    CAS  Google Scholar 

  10. 10.

    Wang K Q, Wang J. A new group contribution method for calculating the boiling point of alkane. Chin J Org Chem, 2001, 21: 751–754 (in Chinese)

    CAS  Google Scholar 

  11. 11.

    Wang L S, Han S K. Molecule Structure, Property and Activity. Beijing: Chemical Industry Press, 1997, 195–238 (in Chinese)

    Google Scholar 

  12. 12.

    Pan Y, Jiang J C, Zhao J B, Wang R. QSPR Studies for Predicting Flash Points of Alcohols Using Group Bond Contribution Method with Back-propagation Neural Networks. In: Jing G X, Zhou A T, Gao J L, eds. Progress in Mining Science and Safety Technology. Beijing: Science Press, 2007, 1,237–1,244

    Google Scholar 

  13. 13.

    Dean J. Lange’s Handbook of Chemistry, 15th ed. Beijing: World Book Press, 1999, 176–1,343

    Google Scholar 

  14. 14.

    Pan Y, Jiang J C. Quantitative Structure-property Relationship Study for Estimating Flash Points of Organic Compounds Using Back-propagation Artificial Neural Networks. In: Huang P, Wang Y J, Li S C, et al, eds. Progress in Safety Science and Technology. Vol. VI. Beijing: Science Press, 2006, 1,462–1,465

    Google Scholar 

  15. 15.

    Ma Z F, Yin X. Engineering Application of Mathematics Calculation Method and Software. Beijing: Chemical Industry Press, 2002, 247–248 (in Chinese)

    Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Juncheng Jiang.

Additional information

__________

Translated from Chemical Engineering (China), 2007, 35(4): 38–41 [译自: 化学工程]

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Pan, Y., Jiang, J. & Wang, Z. Prediction of the flash points of alkanes by group bond contribution method using artificial neural networks. Front. Chem. Eng. China 1, 390–394 (2007). https://doi.org/10.1007/s11705-007-0071-z

Download citation

Keywords

  • artificial neural networks
  • flash point
  • group bond contribution
  • alkane