Machine learning-based extraction of mechanical properties from multi-fidelity small punch test data

Abstract

The extraction of mechanical properties plays a crucial role in understanding material behavior and predicting performance in various applications. However, the traditional methods for determining these properties often involve complex and time-consuming tests, which may not be practical in certain situations. To address this challenge, we developed a novel machine learning methodology that leveraged multi-fidelity datasets obtained from small punch test (SPT) experiments. SPT is a simple technique in which a localized load is applied to a small specimen, and the resulting deformation is measured. By analyzing the load-displacement data obtained from the SPT, valuable insights into the mechanical properties of the material can be obtained. In this study, we developed a multi-fidelity model capable of predicting the mechanical properties of steel and aluminum alloys. The proposed model considers variations in the material thickness and can effectively predict the mechanical properties of materials with different thicknesses, accommodating practical scenarios in which material samples exhibit varying thicknesses owing to different applications or manufacturing processes. In constructing our model, we synergistically incorporated low-fidelity finite element method (FEM) data and high-fidelity experimental data to predict the material properties. This integration enabled us to optimize and bolster the accuracy of our predictions, thereby facilitating a comprehensive and dependable characterization of the mechanical behavior of the material. By leveraging the advantages of SPT and incorporating multi-fidelity modeling techniques, our approach offers a practical and efficient solution for extracting mechanical properties. The ability to predict the properties of steel and aluminum alloys and materials with varying thicknesses enhances the versatility and applicability of our model in real-world scenarios.

Keywords

Transfer learning / Multi-fidelity / Mechanical properties / Small punch test (SPT)

References

[1] ManahanMP, ArgonAS, HarlingOK. The development of a miniaturized disk bend test for the determination of postirradiation mechanical properties. J Nucl Mater, 1981, 104: 1545-1550.

[2] JančaA, SieglJ, HaušildP. Small punch test evaluation methods for material characterisation. J Nucl Mater, 2016, 481: 201-213.

[3] KlevtsovI, NeshumaevD, DedovA. A method of using miniature samples for determining mechanical properties of metal of power-generating equipment at thermal power stations in Estonia. Therm Eng, 2009, 56: 426-431.

[4] ChicaJC, DíezPMB, CalzadaMP. Development of an improved prediction method for the yield strength of steel alloys in the small punch test. Mater Des, 2018, 148: 153-166.

[5] LiM, LiuZ, HuangL. A new multi-fidelity surrogate modelling method for engineering design based on neural network and transfer learning. Eng Comput, 2022, 39(6): 2209-2230.

[6] LiuZ, XuH, ZhuP. An adaptive multi-fidelity approach for design optimization of mesostructure-structure systems. Struct Multidiscip Optim, 2020, 62: 375-386.

[7] LiM, LiuZ, HuangL, et al.. Multi-fidelity data-driven optimization design framework for self-piercing riveting process parameters. J Manuf Process, 2023, 99: 812-824.

[8] WeissK, KhoshgoftaarTM, WangD. A survey of transfer learning. J Big data, 2016, 3(1): 1-40.

[9] XueY, YangR, ChenX, et al.. A novel local binary temporal convolutional neural network for bearing fault diagnosis. IEEE Trans Instrum Meas, 2023, 723525013.

[10] ChenX, YangR, XueY, et al.. Deep transfer learning for bearing fault diagnosis: a systematic review since 2016. IEEE Trans Instrum Mea, 2023, 723508221.

[11] LiH, WangZ, LanC, et al.. A novel dynamic multiobjective optimization algorithm with non-inductive transfer learning based on multi-strategy adaptive selection. IEEE Trans Neural Netw Learn Syst, 2023, 35(11): 16533-16547.

[12] JiaoL, HuangZ, LiuX, et al.. Brain-inspired remote sensing interpretation: a comprehensive survey. IEEE J Sel Top Appl Earth Obs Remote Sens, 2023, 16: 2992-3033.

[13] PanSJ, YangQ. A survey on transfer learning. IEEE Trans Knowl Data Eng, 2009, 22(10): 1345-1359.

[14] ChenS, YangR, ZhongM. Graph-based semi-supervised random forest for rotating machinery gearbox fault diagnosis. Control Eng Pract, 2021, 117. 104952

[15] LuQ, YangR, ZhongM, et al.. An improved fault diagnosis method of rotating machinery using sensitive features and RLS-BP neural network. IEEE Trans Instrum Meas, 2019, 69(4): 1585-1593.

[16] ChenS, YangR, ZhongM, et al.. A random forest and modelbased hybrid method of fault diagnosis for satellite attitude control systems. IEEE Trans Instrum Meas, 2023, 72: 1-13

[17] LucasG. Review of small specimen test techniques for irradiation testing. Metall Trans A, 1990, 21: 1105-1119.

[18] LucasG, OkadaA, KiritaniM. Parametric analysis of the disc bend test. J Nucl Mater, 1986, 141: 532-535.

[19] HuberN, KonstantinidisA, TsakmakisC. Determination of poisson’s ratio by spherical indentation using neural networks—part I: theory. J Appl Mech, 2001, 68(2): 218-223.

[20] TyulyukovskiyE, HuberN. Identification of viscoplastic material parameters from spherical indentation data: Part I. neural networks. J Mater Res, 2006, 21(3): 664-676.

[21] AbendrothM, KunaM. Determination of deformation and failure properties of ductile materials by means of the small punch test and neural networks. Comput Mater Sci, 2003, 28(3/4): 633-644.

[22] MaoX, TakahashiH. Development of a further-miniaturized specimen of 3 mm diameter for tem disk (3 mm) small punch tests. J Nucl Mater, 1987, 150(1): 42-52.

[23] CahoonJ, BroughtonW, KutzakA. The determination of yield strength from hardness measurements. Metall Trans, 1971, 2: 1979-1983.

[24] JunC, LiFG, SunZK, et al.. Tensile stress-strain behavior of metallic alloys. Trans Nonferrous Met Soc China, 2017, 27(11): 2443-2453.

[25] BowenA, PartridgeP. Limitations of the hollomon strain-hardening equation. J Phys D Appl Phys, 1974, 77969.

[26] Zhou Z, Shin J, Zhang L (2017) Fine-tuning convolutional neural networks for biomedical image analysis: actively and incrementally. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu, pp 7340–7351

[27] SunB, FengJ, SaenkoKCorrelation alignment for unsupervised domain adaptation, 2017, Cham. Springer. 153171

[28] Gopalan R, Ruonan Li, Chellappa R (2011) Domain adaptation for object recognition: an unsupervised approach. In: 2011 international conference on computer vision, IEEE, Barcelona, pp 999–1006

[29] Gong B, Shi Y, Sha F et al (2012) Geodesic flow kernel for unsupervised domain adaptation. In: 2012 IEEE conference on computer vision and pattern recognition, IEEE, RI, pp 2066–2073

[30] Fernando B, Habrard A, Sebban M et al (2013) Unsupervised visual domain adaptation using subspace alignment. In: 2013 IEEE international conference on computer vision, IEEE, Sydeny, pp 2960–2967

Funding

National Natural Science Foundation(52205377)

National Key Research and Development Program(2022YFB4601804)

Key Basic Research Project of Suzhou(#SJC2022031)

RIGHTS & PERMISSIONS

Shanghai University and Periodicals Agency of Shanghai University and Springer-Verlag GmbH Germany, part of Springer Nature