SpringerLink
Log in

Prediction of Smoke Points of Kerosene Distillates Using Simple Laboratory Tests: Artificial Neural Network versus Conventional Correlations

  • Published:
Theoretical Foundations of Chemical Engineering Aims and scope Submit manuscript

Abstract

In the present study, an artificial neural network (ANN) model and three well-known correlations were used to predict the smoke points of 430 kerosene distillates from their specific gravities and distillation temperatures. The ANN model was developed in MATLAB software, it is a feedforward multilayer perceptron with a single hidden layer. The optimal number of neurons in the hidden layer as well as the best training algorithm and the best values of connection weights and biases were determined by trial and error using the nftool command. The early stop** technique by cross-validation was employed to avoid overfitting of the model. The developed model composed of 17 sigmoid hidden neurons and one linear output neuron was trained with the Levenberg-Marquardt backpropagation algorithm. This model allowed the prediction of smoke points with a coefficient of determination of 0.852, an average absolute deviation of 1.4 mm and an average absolute relative deviation of 6%. Statistical analysis of the results indicated that the prediction accuracy of the ANN model is higher than that of the conventional correlations. Indeed, in addition to its effectiveness, the proposed ANN method for the estimation of smoke points has the advantages of low-cost and easy implementation, as it relies on simple laboratory tests. Thus, the developed ANN model is a reliable tool that can be used in petroleum refineries for fast quality control of kerosene distillates.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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.

REFERENCES

  1. Speight, J.G., Kerosene, in Handbook of Petroleum Product Analysis, Vitha, M.F., Ed., Hoboken, NJ: Wiley, 2015, ch. 8, pp. 141–154. https://doi.org/10.1002/9781118986370.ch8

    Book  Google Scholar 

  2. GOST (State Standard) 33193-2014: Aviation turbine fuels and kerosine. Determination of smoke point, Moscow: Standartinform, 2018.

  3. ASTM D1322-97, Standard Test Method for Smoke Point of Kerosine and Aviation Turbine Fuel, 1997.

  4. Baird IV, C.T., Crude Oil Yields and Product Properties, 1981.

  5. Guibet, J.-C., Characteristics of petroleum products for energy use (motor fuels–heating fuels), in Petroleum Refining, vol. 1: Crude Oil, Petroleum Products, Process Flowsheets, Wauquier, J.-P., Ed., Paris: Editions Technip, 1995, 1, pp. 177–269.

  6. Riazi, M.R., Characterization of petroleum fractions, in Characterization and Properties of Petroleum Fractions, West Conshohocken, PA: ASTM Int., 2005, pp. 87–151. https://doi.org/10.1520/MNL11403M

    Book  Google Scholar 

  7. Jenkins, G.I. and Walsh, R.E., Quick measure of jet fuel properties, Hydrocarbon Process., 1968, vol. 47, no. 5, pp. 161–164.

    Google Scholar 

  8. Oliver, A.D., Korosines, in Modern Petroleum Technology, Evans, E.B., Ed., London: Inst. Pet., 1962, pp. 600–612.

    Google Scholar 

  9. Parkash, S., Product blending, in Refining Processes Handbook, Parkash, S., Ed., Burlington, MA: Elsevier, 2003, ch. 11, pp. 308–383. https://doi.org/10.1016/B978-075067721-9/50011-6

    Book  Google Scholar 

  10. Coker, A.K., Petroleum, complex-mixture fractionation, gas processing, dehydration, hydrocarbon absorption and strip**, in Ludwig’s Applied Process Design for Chemical and Petrochemical Plants, vol. 2: Distillation, Packed Towers, Petroleum Fractionation, Gas Processing and Dehydration, Burlington, MA: Elsevier, 2010, pp. 269–344. https://doi.org/10.1016/B978-0-7506-8366-1.10011-8

  11. Coker, A.K., Characterization of petroleum and petroleum fractions, in Petroleum Refining Design and Applications Handbook, Volume 1, Beverly, MA: Wiley–Scrivener 2018, vol. 1, pp. 31–62. https://doi.org/10.1002/9781119257110.ch3

  12. Cookson, D.J., Iliopoulos, P., and Smith, B.E., Composition-property relations for jet and diesel fuels of variable boiling range, Fuel, 1995, vol. 74, no. 1, pp. 70–78. https://doi.org/10.1016/0016-2361(94)P4333-W

    Article  CAS  Google Scholar 

  13. Cookson, D.J. and Smith, B.E., Calculation of jet and diesel fuel properties using carbon-13 NMR spectroscopy, Energy Fuels, 1990, vol. 4, no. 2, pp. 152–156. https://doi.org/10.1021/ef00020a004

    Article  CAS  Google Scholar 

  14. Cookson, D.J., Latten, J.L., Shaw, I.M., and Smith, B.E., Property–composition relationships for diesel and kerosene fuels, Fuel, 1985, vol. 64, no. 4, pp. 509–519. https://doi.org/10.1016/0016-2361(85)90086-9

    Article  CAS  Google Scholar 

  15. Cookson, D.J., Lloyd, C.P., and Smith, B.E., Investigation of the chemical basis of kerosene (jet fuel) specification properties, Energy Fuels, 1987, vol. 1, no. 5, pp. 438–447. https://doi.org/10.1021/ef00005a011

    Article  CAS  Google Scholar 

  16. Cookson, D.J. and Smith, B.E., Observed and predicted properties of jet and diesel fuels formulated from coal liquefaction and Fischer-Tropsch feedstocks, Energy Fuels, 1992, vol. 6, no. 5, pp. 581–585. https://doi.org/10.1021/ef00035a007

    Article  CAS  Google Scholar 

  17. Ramaswamy, V. and Singh, I.D., Determination of smoke point of kerosene fraction by proton n.m.r. spectrometry, Fuel, 1990, vol. 69, no. 1, pp. 122–123. https://doi.org/10.1016/0016-2361(90)90268-U

    Article  CAS  Google Scholar 

  18. CHEMCAD: Physical Properties Version 5.6 User Guide and Tutorial. Houston, TX: Chemstations, Inc. https://www.chemstations.com/content/documents/ Archive/CCFmanual56.pdf. Cited December 27, 2022.

  19. Zhmykhova, N.M., Calculation method for determining smoke point of kerosine distillates, Chem. Technol. Fuels Oils, 1973, vol. 9, no. 12, pp. 967–969. https://doi.org/10.1007/BF00718079

    Article  Google Scholar 

  20. Albahri, T.A., Riazi, M.R., and Alqattan, A.A., Analysis of quality of the petroleum fuels, Energy Fuels, 2003, vol. 17, no. 3, pp. 689–693. https://doi.org/10.1021/ef020250w

    Article  CAS  Google Scholar 

  21. Anisimov, D.I., The possibility of using artificial neural networks to predict the performance properties of petroleum products, Tr. 25 GosNII MO RF, 2018, no. 58, pp. 379–389.

  22. Liu, G., Wang, L., Qu, H., Shen, H., Zhang, X., Zhang, S., and Mi, Z., Artificial neural network approaches on composition–property relationships of jet fuels based on GC–MS, Fuel, 2007, vol. 86, no. 16, pp. 2551–2559. https://doi.org/10.1016/j.fuel.2007.02.023

    Article  CAS  Google Scholar 

  23. Driatskaya, Z.V., Mkhchiyan, M.A., Zmykhova, N.M., Pavlova, S.N., Zavershinskaya, S.V., Baranova, Z.N., Ivchenko, E.G., Vol’fson, I.S., Teleshova, M.N., Sheikh-Ali, G.A., and Stolypina, N.A., Oils of the northern regions of the European Part of the USSR and the Urals, in Crude Oils of the USSR (Handbook), Driatskaya, Z.V., Ivchenko, E.G., Mkhchiyan, M.A., and Zmykhova, N.M., Eds., Moscow: Khimiya, 1971, vol. 1.

    Google Scholar 

  24. Lazareva, I.S., Driatskaya, Z.V., Mkhchiyan, M.A., Zmykhova, N.M., Pavlova, S.N., Zavershinskaya, S.V., Barinova, Z.N., Oleinikova, A.P., and Shul’ga, L.P., Oils of the Middle and Lower Volga region, in Crude Oils of the USSR (Handbook), Driatskaya, Z.V., Mkhchiyan, M.A., Zmykhova, N.M., Lazareva, I.S., Oleinikova, A.P., Eds., Moscow: Khimiya, 1972, vol. 2.

    Google Scholar 

  25. Aleksandrova, R.P., Ashumov, G.G., Baranova, Z.N., Bryanskaya, E.K., Driatskaya, Z.V., Zhmykhova, N.M., Zhurba, A.S., Zavershinskaya, S.V., Levchenko, E.S., Mkhchiyan, M.A., Pavlova, S.N., Ponomareva, E.A., Sklyar, V.T., Usupova, L.G., Cherfas, S.I., and Eivazova, S.A., Oils of the Caucasus and Western Regions of the European Part of the USSR, in Crude Oils of the USSR (Handbook), Ashumov, G.G., Driatskaya, Z.V., Zhmykhova, N.M., Zhurba, A.S., Levchenko, E.S., and Mkhchiyan, M.A., Eds., Moscow: Khimiya, 1972, vol. 3.

    Google Scholar 

  26. Abidova, Z.Kh., Aleksandrova, R.P., Baranova, Z.N., Driatskaya, Z.V., Zhmykhova, N.M., Zavershinskaya, S.V., Levchenko, E.S., Moiseikov, S.F., Mkhchiyan, M.A., Pavlova, S.N., Ponomareva, E.A., Sagidova, F.Z., Sokol’nikova, M.D., Tolstenev, V.S., and Khod-zhaev, G.Kh., Oils of Central Asia, Kazakhstan, Siberia and Sakhalin Island, in Crude Oils of the USSR (Handbook), Driatskaya, Z.V., Zhmykhova, N.M., Mkhchiyan, M.A., and Khodzhaev, G.Kh., Eds., Moscow, Khimiya, 1974, vol. 4.

    Google Scholar 

  27. Pirdashti, M., Curteanu, S., Kamangar, M.H., Hassim, M.H., and Khatami, M.A., Artificial neural networks: Applications in chemical engineering, Rev. Chem. Eng., 2013, vol. 29, no. 4, pp. 205–239. https://doi.org/10.1515/revce-2013-0013

    Article  CAS  Google Scholar 

  28. Hornik, K., Stinchcombe, M., and White, H., Multilayer feedforward networks are universal approximators, Neural Networks, 1989, vol. 2, no. 5, pp. 359–366. https://doi.org/10.1016/0893-6080(89)90020-8

    Article  Google Scholar 

Download references

Funding

No funding was received for conducting this study.

Author information

Authors and Affiliations

  1. Department of Chemical and Pharmaceutical Process Engineering, Faculty of Hydrocarbons and Chemistry, M’Hamed Bougara University of Boumerdes, 35000, Boumerdes, Algeria

    Kahina Bedda

Authors
  1. Kahina Bedda
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kahina Bedda.

Ethics declarations

The author declares that he has no conflict of interest related to this article.

Additional information

Publisher’s Note.

Pleiades Publishing remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bedda, K. Prediction of Smoke Points of Kerosene Distillates Using Simple Laboratory Tests: Artificial Neural Network versus Conventional Correlations. Theor Found Chem Eng 57, 908–916 (2023). https://doi.org/10.1134/S0040579523050366

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S0040579523050366

Keywords:

Search

Navigation