Average plastic properties of friction stir-welded AA2024-T3 are obtained by coupling novel small punch beam testing with a neural network algorithm. The small punch beam test utilizes a cylindrical punch head and miniature rectangular beam specimens. The specimens may be manufactured by material removed from in-service components with minimal effect on mechanical performances. Specimen preparation, material model, and identifying procedure are systematically presented. Predicted load–displacement results agree well with the experimental results and the identified strain–stress relationship demonstrates useful agreement with tensile test. Since the load–displacement curve is insensitive to base material properties, knowledge of these properties is not required in the proposed method.
Fischer-CrippsAC. Use of combined elastic modulus in the analysis of depth-sensing indentation data. J Mater Res2001; 16: 3050–3052.
2.
OliverWCPharrGM. Review: Measurement of hardness and elastic modulus by instrumented indentation: Advances in understanding and refinements to methodology. J Mater Res2004; 19: 3–20.
3.
LeeJHKimTLeeH. A study on robust indentation techniques to evaluate elastic–plastic properties of metals. Int J Solids Struct2013; 47: 647–664.
4.
NayebiAAbdiREBartierO. New procedure to determine steel mechanical parameters from the spherical indentation technique. Mech Mater2002; 34: 243–254.
5.
JiangPZhangTHFengYH. Determination of plastic properties by instrumented spherical indentation: Expanding cavity model and similarity solution approach. J Mater Res2009; 24: 1045–1053.
6.
ManahanMPArgonASHarlingOK. The development of miniaturized disk bend test for the determination of post irradiation mechanical properties. J Nucl Mater1981; 104: 1545–1550.
7.
KrishnaKDKrishnaKPMukeshP. Influence of material parameters on small punch test using curved specimens. Arch Appl Sci Res2013; 2: 211–218.
8.
PanWBoyleJRamlanM. Material plastic properties characterization using a generic algorithm and finite element method modelling of the plane-strain small punch test. Metall J2013; LXIII: 174–179 (special issue).
9.
Sehgal DK, Husain A and Pandey RK. The rectangular shaped miniature specimen to study the mechanical behavior of materials. In: 2nd International conference on mechanical and electronics engineering (ICMEE), 2010, Kyoto, Japan, 1–3 August 2010, pp.196–199. New York: IEEE.
10.
Zhou X, Pan W and Mackenzie D. Material plastic properties characterization by coupling experimental and numerical analysis of small punch beam tests. Comput Struct DOI: 10.1016/j.compstruc.2012.07.002.
11.
AbendrothMKunaM. Determination of ductile material properties by means of the small punch test and neural networks. Adv Eng Mater2004; 6: 536–540.
12.
AbendrothMKunaM. Identification of ductile damage and fracture parameters from the small punch test using neural networks. Eng Fract Mech2006; 73: 710–725.
13.
AbendrothMKunaM. Determination of deformation and failure properties of ductile materials by means of the small punch test and neural networks. Comput Maters Sci2003; 28: 633–644.
14.
Mathworks. Documentation of MATLAB 2007b, neural network toolbox user's guide, September 2007, Cambridge, UK: MathWorks.
15.
MartinTHHowardBDBealeMark H. Neural network design, Boulder, CO: University of Colorado, 2002.
16.
RumelhartDEHintonGEWilliamsRJ. Learning representations by back-propagating errors. Nature 3231986; 6088: 533–536.
17.
Werbos PJ. Beyond regression: New tools for prediction and analysis in the behavioral sciences. PhD thesis, Harvard University, USA, 1974.
18.
Poppe T, et al. Estimating material properties for process optimization. In: S Gielen and B Kappen (eds). Proceedings of the international conference on artificial neural networks, Amsterdam, the Netherlands, 13–16 September 1993, pp.795–798. Heidelberg: Springer.
19.
CharalambousC. Conjugate gradient algorithm for efficient training of artificial neural networks. IET Circuits Devices Syst1992; 139: 301–310.
20.
HaganMTMenhajMB. Training feedforward networks with the Marquardt algorithm. IEEE Trans Neural Networks1994; 5(6): 989–993.
21.
Nazari J and Okan KE. Implementation of back-propagation neural networks with MatLab, docs.lib.purdue.edu/cgi/viewcontent.cgi?article=1279&context=ecetr (1992, accessed 6 April 2012).
22.
GB/T 228-2002: 2002. Metallic materials – Tensile testing at ambient temperature. General Administration of Quality Supervision, Inspection and Quarantine of the People's Republic of China.
