Advertisement

Development of an Evolutionary Deep Neural Net for Materials Research

  • Swagata Roy
  • Nirupam ChakrabortiEmail author
Conference paper
  • 597 Downloads
Part of the The Minerals, Metals & Materials Series book series (MMMS)

Abstract

Modeling and optimization in many materials related problems routinely involve noisy, non-linear data from diverse sources. This novel algorithm, now tested on several problems, eliminates noise and extracts the meaningful trends from such data, using some multi-objective evolutionary algorithms, instead of the existing training methods. Some small neural nets with flexible topology and architecture are fed with random subsets of the problem variables, ensuring that each variable is used at least once. They evolve through a tradeoff between two conflicting requirements that they should be of maximum accuracy and at the same time of minimum complexity, defined through the number of parameters used. Mathematically, this leads to a Pareto-optimal problem, and the evolutionary algorithms that are used to train them are geared to handle that. These subnets are then assembled using a number of hidden layers; a linear least square algorithm is used for the optimization of the associated weights. Some applications in the metallurgical and materials domain are also discussed.

Keywords

Multi-objective optimization Evolutionary computation Neural net Genetic programming Reference vector Deep neural network Metamodeling Materials application 

References

  1. 1.
    CoelloCoello CA, Becerra RL (2009) Evolutionary multiobjective optimization in materials science and engineering. Mater Manuf Process 24(2):119–129CrossRefGoogle Scholar
  2. 2.
    Wilson B (2014) The machine learning dictionary. http://www.cse.unsw.edu.au/~billw/mldict.html
  3. 3.
    Poli R, Langdon WB, McPhee NF (2008) A field guide to genetic programming. http://www.gp-field-guide.org.uk
  4. 4.
    Pettersson F, Chakraborti N, Saxén H (2007)A genetic algorithms based multi-objective neural net applied to noisy blast furnace data. Appl Soft Comput 7(1):387–397Google Scholar
  5. 5.
    Pettersson F, Biswas A, Sen PK, Saxén H, Chakraborti N (2009) Analyzing leaching data for low-grade manganese ore using neural nets and multiobjective genetic algorithms. Mater Manuf Process 24(3):320–330CrossRefGoogle Scholar
  6. 6.
    Giri BK, Hakanen J, Miettinen K, Chakraborti N (2013) Genetic programming through bi-objective genetic algorithms with a study of a simulated moving bed process involving multiple objectives. Appl Soft Comput 13(5):2613–2623CrossRefGoogle Scholar
  7. 7.
    Wason R (2018) Deep learning: evolution and expansion. Cogn Syst Res 52:701–708CrossRefGoogle Scholar
  8. 8.
    Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958Google Scholar
  9. 9.
    Deb K, Thiele L, Laumanns M, Zitzler E (2002) Scalable multi-objective optimization test problems. In: Proceedings of the 2002 congress on evolutionary computation, CEC’02 (Cat. No. 02TH8600), vol 1. IEEE, pp 825–830Google Scholar
  10. 10.
    Zitzler E, Deb K, Thiele L (2000) Comparison of multiobjective evolutionary algorithms: empirical results. Evol Comput 8(2):173–195CrossRefGoogle Scholar
  11. 11.
    Cheng R, Jin Y, Olhofer M, Sendhoff BA (2016) Reference vector guided evolutionary algorithm for many-objective optimization. IEEE Trans Evol Comput 20(5):773–791CrossRefGoogle Scholar
  12. 12.
    Mahanta BK, Chakraborti N (2019) Tri-objective optimization of noisy dataset in blast furnace iron-making process using evolutionary algorithms. Mater Manuf Process.  https://doi.org/10.1080/10426914.2019.1643472
  13. 13.
    Mahanta BK, Chakraborti N (2018) Evolutionary data driven modeling and multi objective optimization of noisy data set in blast furnace iron making process. Steel Res Int 89:1–11CrossRefGoogle Scholar
  14. 14.
    Mondal DN, Sarangi K, Pettersson F, Sen PK, Saxén H, Chakraborti N (2011) Cu-Zn separation by supported liquid membrane analyzed through multi-objective genetic algorithms. Hydrometallurgy 107(3–4):112–123CrossRefGoogle Scholar
  15. 15.
    Laumanns M, Rudolph G, Schwefel HP (1998) A spatial predator-prey approach to multi-objective optimization: a preliminary study. Presented in international conference on parallel problem solving from nature, pp 241–249Google Scholar
  16. 16.
    Akaike H, Akaike’s information criterion. Int Encycl Stat Sci, 25 (Springer, Berlin, Heidelberg)Google Scholar
  17. 17.
    McKay MD, Beckman RJ, Conover WJ (1979) Comparison of three methods for selecting values of input variables in the analysis of output from a computer code. Technometrics 21(2):239–245Google Scholar
  18. 18.
    Lagneborg R, Siwecki T, Zajac S, Hutchinson B (1999) The role of vanadium in microalloyed steels. Scand J Met 28(5):186–241Google Scholar
  19. 19.
    Li Y, Wilson JA, Craven AJ, Mitchell PS, Crowther DN, Baker TN (2007) Dispersion strengthening in vanadium microalloyed steels processed by simulated thin slab casting and direct charging part 1-processing parameters, mechanical properties and microstructure. Mater Sci Technol 23(5):509–518CrossRefGoogle Scholar
  20. 20.
    Petch NJ (1986) The influence of grain boundary carbide and grain size on the cleavage strength and impact transition temperature of steel. Acta Metall 34(7):1387–1393CrossRefGoogle Scholar
  21. 21.
    Chen MY, Linkens DA (2005) Hybrid neural-fuzzy modeling for impact toughness prediction of alloy steels. Presented in ICSC congress on computational intelligence methods and applicationsGoogle Scholar
  22. 22.
    Roy S, Saini BS, Chakrabarti D, Chakraborti N (2019) A new deep evolutionary neural network algorithm employed in the study of mechanical properties of micro-alloyed steel. Mater Manuf Process.  https://doi.org/10.1080/10426914.2019.1660786
  23. 23.
    Garcia-Mateo C, Caballero FG (2005) Ultra-high-strength bainitic steels. ISIJ Int 45(11):1736–1740CrossRefGoogle Scholar
  24. 24.
    Pickering FB (1980) Some aspects of the relationships between the mechanical properties of steels and their microstructures. Tisco 27(1):105–132Google Scholar
  25. 25.
    Baskes MI, Nelson JS, Wright AF (1989) Semiempirical modified embedded-atom potentials for silicon and germanium. Phys Rev B 40:6085CrossRefGoogle Scholar
  26. 26.
    Voter AF, Chen SP, Siegel RW, Weertman JR, Sinclair R (1987) Characterization of defects in materials. In: Presented in MRS symposia proceedings vol 82, pp 175Google Scholar
  27. 27.
    Omori M (ed) (1987) Blast furnace phenomena and modelling. Elsevier, LondonGoogle Scholar

Copyright information

© The Minerals, Metals & Materials Society 2020

Authors and Affiliations

  1. 1.Department of Metallurgical and Materials EngineeringIndian Institute of TechnologyKharagpurIndia

Personalised recommendations