Using Fuzzy Knowledge Base to Evaluate a Classical Potential Barrier of Liquid Phase Reactions of Tert-Butyloxyl Radicals with Hydrocarbons

  • Vladimir E. TumanovEmail author
  • Elena S. Amosova
  • Andrei I. Prokhorov
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 521)


A classical potential barrier of liquid phase reactions of tert-Butyloxyl radical with hydrocarbons has been approximated using fuzzy knowledge base built from the experimental sample. The predicted values of the classical potential barrier have been compared with the experimental values on the testing sample. Experimental and calculated values are in good agreement within the error. Weak dependence of activation energy of such reactions on the solvent type is discovered. A feedforward artificial neural network has been developed to approximate the classical potential barrier of studied reactions and the obtained results have been compared with the results obtained from the fuzzy knowledge base. Using fuzzy knowledge base produces more precise prediction of the classical potential barrier of given reactions.


Knowledge discovery Fuzzy knowledge base Feedforward artificial neural network Radical abstraction reaction 


  1. 1.
    Brereton, R.G.: Applied Chemometrics for Scientists. Wiley, West Sussex (2007) Google Scholar
  2. 2.
    Banville D.L.: Chemical Information Mining, Facilitating Literature-Based Discovery. CRC Press, Taylor & Francis Group, Boca Raton (2009)Google Scholar
  3. 3.
    Gasteiger, J., Engel, T.: Chemoinformatics: A Texbook. Wiley-VCH GmbH & Co. KGaA, Weinheim (2003)Google Scholar
  4. 4.
    Rouvray, D.H.: Fuzzy Logic in Chemistry. Academic Press, New York (1997)Google Scholar
  5. 5.
    Tumanov, V., Gaifullin, B.: Subject-oriented science intelligent system on physical chemistry of radical reactions. In: Ding, W., Jiang, H., Ali, M., Li, M. (eds.) Modern Advances in Intelligent Systems and Tools, SCI, vol. 431, pp. 121–126, Springer, Heidelberg (2012)Google Scholar
  6. 6.
    Tumanov, V.E.: Knowledge extraction from the problem-oriented data warehouses on chemical kinetics and thermochemistry. WSEAS Trans. Comput. 15(9), 93–102 (2016)Google Scholar
  7. 7.
    Denisov, E.T., Tumanov, V.E.: Transition-state model as the result of 2 morse terms crossing applied to atomic-hydrogen reactions. Zurnal fiziceskoj himii 68(4), 719–725 (1994)Google Scholar
  8. 8.
    Denisov, E.T.: New empirical models of radical abstraction reactions. Russ. Chem. Rev. 66(10), 953–971 (1997)CrossRefGoogle Scholar
  9. 9.
    Semenov, N.N.: Some problems in chemical kinetics and reactivity. Academy of Sciences of the USSR, Moscow (1958)Google Scholar
  10. 10.
    Larose D.T., Data mining methods and models. Wiley, New Jersey (2006)Google Scholar
  11. 11.
    Luo, Y.-R.: Comprehensive Handbook of Chemical Bond Energies. CRC Press, Boca Raton, London, New York (2007)CrossRefGoogle Scholar
  12. 12.
    Tumanov, V.E.: Hybrid algorithm of application of artificial neuronets for an evaluation of rate constants of radical bimolecular reactions. In: Balicski, J. (ed) Advances in neural networks, fuzzy systems and artificial intelligence. Recent Advances in Computer Engineering Series, vol. 21, pp. 58–61, WSEAS Press, Gdansk, Poland (2014)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Vladimir E. Tumanov
    • 1
    Email author
  • Elena S. Amosova
    • 1
  • Andrei I. Prokhorov
    • 1
  1. 1.Department of Computing and Information ResourcesInstitute of Problems of Chemical Physics RASMoscowRussian Federation

Personalised recommendations