Abstract
Principal component analysis and fuzzy c-means clustering algorithms were applied to slip-induced strain and geometric metric data in an attempt to discover unique microstructural configurations and their frequencies of occurrence in statistically representative instantiations of a titanium alloy microstructure. Grain-averaged fatigue indicator parameters were calculated for the same instantiation. The fatigue indicator parameters strongly correlated with the spatial location of the microstructural configurations in the principal components space. The fuzzy c-means clustering method identified clusters of data that varied in terms of their average fatigue indicator parameters. Furthermore, the number of points in each cluster was inversely correlated to the average fatigue indicator parameter. This analysis demonstrates that data-driven methods have significant potential for providing unbiased determination of unique microstructural configurations and their frequencies of occurrence in a given volume from the point of view of strain localization and fatigue crack initiation.
Similar content being viewed by others
References
J.M. Larsen, S.K. Jha, C.J. Szczepanski, M.J. Caton, R. John, A.H. Rosenberger, D.J. Buchanan, P.J. Golden, and J.R. Jira, Int. J. Fatigue 57, 103 (2013).
S.K. Jha, C.J. Szczepanski, R. John, and J.M. Larsen, Acta Mater. 82, 378 (2015).
S.K. Jha, C.J. Szczepanski, P.J. Golden, W.J. Porter, and R. John, Int. J. Fatigue 42, 248 (2012).
C.J. Szczepanski, S.K. Jha, J.M. Larsen, and J.W. Jones, Metall. Mater. Trans. A 39, 2841 (2008).
V. Sinha, A.L. Pilchak, S.K. Jha, W.J. Porter, III, R. John, and J.M. Larsen, Metall. Mater. Trans. A 49, 1061 (2018). https://doi.org/10.1007/s11661-017-4437-7.
F. Bridier, P. Villechaise, and J. Mendez, Acta Mater. 56, 3951 (2008).
M.W. Libbrecht and W.S. Noble, Nat. Rev. Genet. 16, 321 (2015).
D. Stavens and S. Thrun, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2010).
M. Collins and N. Duffy, Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (2004), p. 263–270.
S.R. Niezgoda, A.K. Kanjarla, and S.R. Kalidindi, Integr. Mater. Manuf. Innov. 2, 3 (2013).
B.L. DeCost and E.A. Holm, Comput. Mater. Sci. 110, 126 (2015).
M.A. Groeber and M.A. Jackson, Integr. Mater. Manuf. Innov. 3, 5 (2014).
I.T. Jolliffe, Principal Component Analysis, 2nd ed. (New York, NY: Springer, 2002), pp. 1–6.
A. Ben-Hur and I. Guyon, Functional Genomics: Methods and Protocols, ed. M.J. Brownstein and A. Kohodursky (Totowa: Humana Press, 2003), pp. 159–182.
J.C. Bezdek, R. Ehrlich, and W. Full, Comput. Geosci. 10, 191 (1984).
L. Méric, P. Poubanne, and G. Cailletaud, ASME J. Eng. Mater. Technol. 113, 162 (1991).
Abaqus User Subroutines Reference Guide, Version 14.5, Dassault Systemès Simulia, Providence, RI, 2014.
A. Fatemi and D.F. Socie, Fatigue Fract. Eng. Mater. Struct. 11, 149 (1988).
A. Manonukul and F.P.E. Dunne, Proc. R. Soc. Lond. Ser. A 460, 1881 (2004).
D.L. McDowell and F.P.E. Dunne, Int. J. Fatigue 32, 1521 (2010).
J.D. Hochhalter, D.J. Littlewood, M.G. Veilleux, J.E. Bozek, A.M. Maniatty, A.D. Rollett, and A.R. Ingraffea, Model. Simul. Mater. Sci. Eng. 19, 1 (2011).
C.P. Przybyla and D.L. McDowell, Int. J. Plast. 27, 1871 (2011).
B. Scholkopf, A. Smola, and K.R. Muller, Artificial Neural Networks—ICANN’97, p. 583–588, 2005
Q. Wang, Kernel Principal Component Analysis and its Application in Face Recognition and Active Shape Models. arXiv:1207.3538 [cs.CV], 2012.
MATLAB R2017a, Mathworks, Inc., Natick, MA, 2017.
J.A. Hartigan and M.A. Wong, Algorithm AS 136: A k-means clustering algorithm. J. R. Stat. Soc. Ser. C 28, 100 (1979).
C.A. Sugar and G.M. James, J. Am. Stat. Assoc. 98, 750 (2003).
L. Kaufman and P.J. Rousseeuw, Finding Groups in Data. An Introduction to Cluster Analysis (New York, NY: Wiley-Interscience, 1990).
R. Tibshirani, G. Walther, and T. Hastie, J. R. Stat. Soc. B 63, 411 (2001).
M. Yan and K. Ye, Biometrics 63, 1031 (2007).
G.W. Milligan and M.C. Cooper, Psychometrica 50, 159 (1985).
R. Jang and N. Hickey, Data Set Clustering Using Fuzzy C-Means Clustering, Matlab Central File Exchange, MathWorks Inc., 2002.
S.K. Jha, R.A. Brockman, R.M. Hoffman, V. Sinha, W.J. Porter, III, D.J. Buchanan, A.L. Pilchak, J.M. Larsen, and R. John, Air Force Research Laboratory, Wright-Patterson Air Force Base, OH, unpublished research, 2018.
D.T. Fullwood, S.R. Niezgoda, B.L. Adams, and S.R. Kalidindi, Prog. Mater Sci. 55, 477 (2010).
Acknowledgements
This work was performed at the Air Force Research Laboratory, Materials and Manufacturing Directorate, AFRL/RXCM, Wright-Patterson Air Force Base, OH. The financial support of the Air Force Office of Scientific Research with Dr. David Stargel and Mr. James Fillerup as Program Managers is gratefully acknowledged.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Jha, S.K., Brockman, R.A., Hoffman, R.M. et al. A Data Analytics Approach to Discovering Unique Microstructural Configurations Susceptible to Fatigue. JOM 70, 1147–1153 (2018). https://doi.org/10.1007/s11837-018-2881-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11837-018-2881-5