Physics-Informed Network Models: a Data Science Approach to Metal Design

  • Amit K. Verma
  • Roger H. French
  • Jennifer L. W. CarterEmail author
Technical Article


Functional graded materials (FGM) allow for reconciliation of conflicting design constraints at different locations in the material. This optimization requires a priori knowledge of how different architectural measures are interdependent and combine to control material performance. In this work, an aluminum FGM was used as a model system to present a new network modeling approach that captures the relationship between design parameters and allows an easy interpretation. The approach, in an un-biased manner, successfully captured the expected relationships and was capable of predicting the hardness as a function of composition.


Metal design Network models Optimization Functional gradient materials 



The material for this study was provided by the Alcoa/Arconic Alloy Technology Division. This work was funded by the Army Research Office Short Term Innovative Research program: W911NF-14-0549. The data and R-analytics code utilized for the paper can be found at


  1. 1.
    (2011) Materials genome initiative for global competitiveness. Tech. rep.
  2. 2.
    Arnold SM, Holland F, Gabb TP, Nathal M, Wong TT (2013) American institute of aeronautics and astronautics.
  3. 3.
    Arnold SM, Holland F, Bednarcyk BA (2014) American institute of aeronautics and astronautics.
  4. 4.
  5. 5.
    Lingerfelt EJ, Belianinov A, Endeve E, Ovchinnikov O, Somnath S, Borreguero JM, Grodowitz N, Park B, Archibald RK, Symons CT, Kalinin SV, Messer OEB, Shankar M, Jesse S (2016) Procedia computer science 80(Supplement C):2276.
  6. 6.
    Kalidindi SR, De Graef M (2015) Materials Data Science: Current Status and Future Outlook. Annu Rev Mater Res 45(1):171–193. Scholar
  7. 7.
    Jacobsen MD, Benedict MD, Foster BJ, Ward CH, Foster BJ, Jacobsen MD, Benedict MD (2015). In: Proceedings of the 3rd world congress on integrated computational materials engineering (ICME 2015). Springer, Cham, pp 285–292.
  8. 8.
    Jacobsen MD, Fourman JR, Porter KM, Wirrig EA, Benedict MD, Foster BJ, Ward CH, Jacobsen MD, Foster BJ, Fourman JR, Benedict MD, Porter KM, Wirrig EA (2016) Creating an integrated collaborative environment for materials research. Integr Mater Manuf Innov 5(1):12. Scholar
  9. 9.
    Havlin S, Kenett DY, Ben-Jacob E, Bunde A, Cohen R, Hermann H, Kantelhardt JW, Kertész J, Kirkpatrick S, Kurths J, Portugali J, Solomon S (2012) The European Physical Journal Special Topics 214(1):273. Scholar
  10. 10.
    Nibbe RK, Koyutürk M, Chance MR (2010) PLOs Comput Biol 6(1):e1000639. Scholar
  11. 11.
    Steinhaeuser K, Chawla NV, Ganguly AR (2011) Statistical Analysis and Data Mining 4(5):497.
  12. 12.
    Bhadeshia HKDH (1999) ISIJ Int 39(10):966.
  13. 13.
    Bhadeshia HKDH (2009) Neural Networks and Information in Materials Science. Statistical Analy Data Mining 1(5):296–305. CrossRefGoogle Scholar
  14. 14.
  15. 15.
    Hoyle RH (2012) Handbook of structural equation modeling, 1st edn. The Guilford Press, New YorkGoogle Scholar
  16. 16.
    French RH, Podgornik R, Peshek TJ, Bruckman LS, Xu Y, Wheeler NR, Gok A, Hu Y, Hossain MA, Gordon DA, Zhao P, Sun J, Zhang G-Q (2015) Curr Opinion Solid State Mater Sci 19(4):212. Scholar
  17. 17.
    Faraway JJ (2004) Linear models with R, 1st edn. Chapman and Hall/CRC, Boca RatonGoogle Scholar
  18. 18.
    Wheeler N, Xu Y, Du W, Gok A, Ma J, Bruckman L, Elsaeiti M, Sun J, French R (2013) Semi-supervised generalized structural equation modeling.
  19. 19.
    Mitchell TM (1997) Machine learning, 1st edn. McGraw-Hill Education, New YorkGoogle Scholar
  20. 20.
    White H, Gallant AR, Hornik K, Stinchcombe M, Wooldridge J (1992) Artificial neural networks: approximation and learning theory, illustrated edition edition edn. Blackwell Pub, OxfordGoogle Scholar
  21. 21.
    Skinner AJ, Broughton JQ (1995) Model Simul Mater Sci Eng 3(3):371. Scholar
  22. 22.
    Rioja RJ, Sawtell RR, Chu MG, Karabin M, Cassada WA, Karabin M (2012) Functional Gradient Products Enabled by Planar Solidification Technologies. Springer, Pittsburgh, pp 1383–1388. Scholar
  23. 23.
    Chu M, Giron A, Cassada W (2012) The Minerals, Metals and Materials Society, Pittsburgh, pp 1367–1375Google Scholar
  24. 24.
    Chu MG, Yu H, Giron A, Kallaher K (2007) Method of unidirectional solidification of castings and associated apparatus. U.S. Classification 164/122.1, 164/133, 164/337; International Classification B22D35/04, B22D27/04, B22D37/00, B22D35/00; Cooperative Classification B22D27/045, B22D7/00; European Classification B22D27/04A
  25. 25.
    (2015) International alloy designations and chemical composition limits for wrought aluminum and wrought aluminum alloys. The Alumninum Association, Arlington, pp 38.
  26. 26.
  27. 27.
    Balderach DC, Hamilton JA, Leung E, Cristina Tejeda M, Qiao J, Taleff EM (2003) Mater Sci Eng A 339(1–2):194. Scholar
  28. 28.
  29. 29.
  30. 30.
    Orowan E (1948) Institute of metals, London, pp 451–453Google Scholar
  31. 31.
    Guo Z, Sha W (2002) Mater Trans 43(No. 6):1273CrossRefGoogle Scholar
  32. 32.
  33. 33.
    Petch NJ (1953) J Iron Steel Inst Jpn 174:25Google Scholar
  34. 34.
  35. 35.
    R Core Team (2015) R: a language and environment for statistical computing, R Foundation for Statistical Computin, Vienna.
  36. 36.
    RPubs - Predictive R-squared according to Tom Hopper.
  37. 37.
  38. 38.
    Schmid E, Boas W (1968) Plasticity of crystals with special reference to metals. Chapman & Hall, LondonGoogle Scholar
  39. 39.
    Bruckman LS, Wheeler NR, Ma J, Wang E, Wang CK, Chou I, Sun J, French RH (2013) IEEE Access 1:384. Scholar

Copyright information

© The Minerals, Metals & Materials Society 2017

Authors and Affiliations

  1. 1.Department of Materials Science and EngineeringCase Western Reserve UniversityClevelandUSA
  2. 2.SDLE Research CenterCase Western Research UniversityClevelandUSA

Personalised recommendations