Abstract—Identification of material properties involves
physical experimentation followed by modeling, simulation and
manual optimization. However, the last step tends to be
computational expensive. This paper investigates an artificial
neural network (ANN) surrogate model for identifying material
parameters. The proposed approach is illustrated with a case
study based on a nano-indentation test.
Index Terms—Surrogate models, optimization,
metal-mechanic properties, infill sampling, inverse analysis.
Gutierrez L., Li H. Kobayashi M., and Batres R. are with the Department
of Mechanical Engineering, Toyohashi University of Technology,
Toyohashi, Aichi 441-8580, Japan (e-mail: {Leonardo, lihan, m-kobayashi}
@ise.me.tut.ac.jp).
Toda H. is with the Department of Mechanical Engineering, Kyushu
University, Fukuoka 819-0395, Japan (e-mail: toda@mech.kyushu-u.ac.jp).
Kuwazuru O. is with the Department of Nuclear Power & Energy Safety,
University of Fukui, Fukui 910-8507, Japan (e-mail: kuwa@u-fukui.ac.jp).
[PDF]
Cite:Leonardo Gutierrez, Han Li, Hiroyuki Toda, Masakazu Kobayashi, Osamu Kuwazuru, and Rafael Batres, "A Method for the Identification of Mechanical Properties Using Surrogate Models," International Journal of Computer Theory and Engineering vol. 6, no. 3, pp. 234-239, 2014.