Metaheuristics in Physical Processes Optimization

  • Tomasz RybotyckiEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 945)


The subject of this work is applying the artificial neural network (ANN) taught using two metaheuristics - the firefly algorithm (FA) and properly prepared evolutionary algorithm (EA) - to find the approximate solution of the Wessinger’s equation, which is a nonlinear, first order, ordinary differential equation. Both methods were compared as an ANN training tool. Then, application of this method in selected physical processes is discussed.


Evolutionary algorithm Firefly algorithm Neural network Wessinger’s equation 



This work was supported by the Systems Research Institute of the Polish Academy of Sciences and is extended version of paper presented at 3rd Conference on Information Technology, Systems Research and Computational Physics, 2–5 July 2018, Cracow, Poland [21].


  1. 1.
    Malek, A., Beidokhti, R.S.: Numerical solution for high order differential equations using a hybrid neural network-optimization method. Appl. Math. Comput. 183, 260 (2006)MathSciNetzbMATHGoogle Scholar
  2. 2.
    Caetano, C., Reis Jr., J.L., Amorim, J., Lemes, M.R., Dalpino Jr., A.: Using neural networks to solve nonlinear differential equations in atomic and molecular physics. Int. J. Quantum Chem. 111, 2732–2740 (2011)CrossRefGoogle Scholar
  3. 3.
    Lagaris, I.E., Likas, A., Fotiadis, D.I.: Artificial neural networks for solving ordinary and partial differential equations. IEEE Trans. Neural Networks 9, 987–1000 (1998)CrossRefGoogle Scholar
  4. 4.
    Press, W.H., Teukolski, S.A., Vetterling, W.T., Flannery, B.P.: Numerical Recipes in C. The Art of Scientific Computing, 2nd edn. Press Syndicate of the University Press, Cambridge (1992)zbMATHGoogle Scholar
  5. 5.
    Brajevic, I., Tuba, M.: Training feed-forward neural networks using firefly algorithms. In: Proceedings of the 12th International Conference on Artificial Intelligence, Knowledge Engineering and Data Bases, p. 156 (2013)Google Scholar
  6. 6.
    Acheson, D.J.: Elementary Fluid Dynamics. Oxford Applied Mathematics and Computing Sciences Series. Oxford University Press, Oxford (1990)Google Scholar
  7. 7.
    Kennedy, J., Eberhart, R.: Particle swarm optimization. In: Proceedings of IEEE International Conference on Neural Networks (1942)Google Scholar
  8. 8.
    Khan, J., Raja, M., Qureshi, I.: Swarm intelligence for the problems of non-linear ordinary differential equations and it’s application to well known Wessinger’s equation. Eur. J. Sci. Res. 34, 514–525 (2009)Google Scholar
  9. 9.
    Montana, D.J.: Neural network weight selection using genetic algorithms. Intell. Hybrid Syst. (1995)Google Scholar
  10. 10.
    Montana, D.J., Davis, L.: Training feedforward neural networks using genetic algorithm. In: Proceedings of the International Joint Conference on Artificial Intelligence, pp. 762–767 (1989)Google Scholar
  11. 11.
    Hornick, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Networks 2(5), 359–366 (1989)CrossRefGoogle Scholar
  12. 12.
    Fausett, L.: Fundamentals of Neural Networks: Architectures, Algorithms and Applications. Prentice-Hall Inc., Upper Saddle River (1994)zbMATHGoogle Scholar
  13. 13.
    Biglari, M., Ghoddosian, A., Poultangari, I., Assareh, E., Nedaei, M.: Using evolutionary algorithms for solving a differential equation. Global J. Sci. Eng. Technol. 14, 25–32 (2013)Google Scholar
  14. 14.
    Bojarski, M., Del Testa, D., Dworakowski, D., Bernhard, F., Flepp, B., Goyal, P., Jackel, L.D., Monfort, M., Mullar, U., Zhang, J., Zhang, X., Zhao, J., Zieba, K.: End to end learning for self-driving cars (2016)Google Scholar
  15. 15.
    Chiaramonte, M.M., Kiener, M.: Solving differential equations using neural networks (2013).
  16. 16.
    Ghalambaz, M., Noghrehabdi, A.R., Behrang, M.A., Assareh, E., Ghanbarzadeh, A., Hedayat, N.: A hybrid neural network and gravitational search algorithm (HNNGSA) method to solve well known Wessinger’s equation. Int. J. Mech. Aerosp Ind. Mechatron. Manuf. Eng. (2011)Google Scholar
  17. 17.
    Gori, M., Tesi, A.: On the problem of local minima in backpropagation. IEEE Trans. Pattern Anal. Mach. Intell. 14, 76–86 (1992)CrossRefGoogle Scholar
  18. 18.
    Engelbrecht, A.P.: Computational Intelligence: An Introduction, 2nd edn. Wiley, Chichester (2007)CrossRefGoogle Scholar
  19. 19.
    McGurn, A.R.: Nonlinear Optics of Photonic Crystals and Meta-Materials. Morgan & Claypool Publishers, San Rafael (2016)Google Scholar
  20. 20.
    Lippman, R.P.: An introduction to computing with neural nets. IEEE ASSP Mag. 4, 4–22 (1987)CrossRefGoogle Scholar
  21. 21.
    Rybotycki, T.: Metaheuristics in physical processes optimization. In: Kulczycki, P., Kowalski, P.A., Lukasik, S. (eds.) Contemporary Computational Science, p. 205. AGH-UST Press (2018)Google Scholar
  22. 22.
    McCulloch, W.S., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 5, 115–133 (1943)MathSciNetCrossRefGoogle Scholar
  23. 23.
    Phan, D.T., Liu, X.: Neural Networks for Identification, Prediction and Control. Springer, London (1995)CrossRefGoogle Scholar
  24. 24.
    Rybotycki, T.: Nowoczesne metaheurystyki w optymalizacji procesów fizycznych. Master’s Thesis, University of Silesia, Sosnowiec (2016)Google Scholar
  25. 25.
    Yang, X.: Nature-inspired Metaheuristic Algorithms, 2nd edn. Luniver Press, Frome (2010)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Centre of Information Technology for Data Analysis MethodsSystems Research Institute, Polish Academy of SciencesWarsawPoland

Personalised recommendations