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

doi:10.1007/s40436-024-00540-x

Advances in Manufacturing ›› 2025, Vol. 13 ›› Issue (3): 511-524.doi: 10.1007/s40436-024-00540-x

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

Zheng-Ni Yang^1,2,3, Jie Zou^3,4, Li Huang^2,3, Rui Yang^1,5, Jing-Yi Zhang³, Chao Tong³, Jing-Yu Kong³, Zhen-Fei Zhan⁴, Qing Liu^2,3

1. School of Advanced Technology, Xi'an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, People's Republic of China;
2. Key Laboratory for Light-weight Materials, Nanjing Tech University, Nanjing, 210009, People's Republic of China;
3. Materials Bigdata and Applications Division, Materials Academy Jitri, Suzhou, 215131, Jiangsu, People's Republic of China;
4. School of Mechatronics and Vehicle Engineering, Chongqing Jiaotong University, Chongqing, 400074, People's Republic of China;
5. Research Institute of Big Data Analytics, Xi'an Jiaotong-Liverpool University, Suzhou, 215131, Jiangsu, People's Republic of China

收稿日期:2023-11-24 修回日期:2023-12-07 发布日期:2025-09-19
通讯作者: Li Huang,E-mail:hli@jitri-amrd.com;Rui Yang,E-mail:r.yang@xjtlu.edu.cn;Zhen-Fei Zhan,E-mail:zhenfei_zhan@163.com E-mail:hli@jitri-amrd.com;r.yang@xjtlu.edu.cn;zhenfei_zhan@163.com
作者简介:Zheng-Ni Yang is PhD student of Xi’an Jiaotong Liverpool University. He received his bachelor’s degree at Nanjing Forestry University in Mechanical Engineering and earned MSc from the Xi’an Jiaotong Liverpool University in applied informatics. Now, his research for PhD program is “Research in the Constitutive Law Establishment of Advanced High Strength Steel based on Machine Learning” and focuses on AI for engineering (AI4E-Material/Constitutive Law Establishment).
Jie Zou is master student of Chongqing Jiaotong University. He received his bachelor’s degree in mechanical engineering from Henan Polytechnic University. Now, his master’s program research is “Machine Learning-based Process Design and Optimization of Automotive Body Connections”.
Li Huang is doctor, vice director of Materials Data Department at Materials Academy JITRI and guest professor at Nanjing Tech University. His research interests include AI algorithms & engineering applications (AI for engineering), integrated computational materials engineering (ICME), digital design of material manufacturing and joining process, and material fatigue & fracture.
Rui Yang received both Ph.D. degree and B.Eng degree from National University of Singapore (NUS). His main research areas are transfer learning (TL), deep learning (DL), fault diagnosis (FD), brain-computer interface (BCI) and human-computer interaction (HCI). He is also the associate editor (AE) of Neurocomputing (JCR Q1, IF=6.0) and international journal of network dynamics and intelligence. He is the founding director of centre for intelligent control and optimization (CICO).
Jing-Yi Zhang is CAE engineer. He graduated in 2016 with a master’s degree in Mechanical Engineering from South China University. He is currently employed at the materials bigdata and applications division, delta advanced materials research institute, Suzhou.
Chao Tong is Machine Learning engineer. He graduated in 2018 with a master’s degree in Material Science and Engineering from Soochow University. He is currently employed at the Material Academy JITRI, Suzhou.
Jing-Yu Kong is Machine Learning Application engineer at Materials Academy JITRI, responsible for developing and applying machine learning and deep learning methods to solve complex computational problems in materials science.
Zhen-Fei Zhan is doctor, professor at the School of Mechatronics and Vehicle Engineering, Chongqing Jiaotong University. He graduated from Shanghai Jiao Tong University with a bachelor’s degree and a doctorate degree in mechanical engineering. His research interests include automotive digital design, automotive intelligent safety, and automotive big data analytics.
Qing Liu is the director of Material Academy, JITRI, Suzhou and the director of the Lightweight Materials Center at Nanjing Tech University. His research interests include electron microscopy techniques for characterizing the microstructure of deformed metals, micromechanisms and mechanical behaviors of metal deformation, formation mechanisms.
基金资助:
This research was supported by the National Natural Science Foundation (Grant No. 52205377), National Key Research and Development Program (Grant No. 2022YFB4601804), and Key Basic Research Project of Suzhou (Grant Nos. #SJC2022031, #SJC2022029).

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

Zheng-Ni Yang^1,2,3, Jie Zou^3,4, Li Huang^2,3, Rui Yang^1,5, Jing-Yi Zhang³, Chao Tong³, Jing-Yu Kong³, Zhen-Fei Zhan⁴, Qing Liu^2,3

1. School of Advanced Technology, Xi'an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, People's Republic of China;
2. Key Laboratory for Light-weight Materials, Nanjing Tech University, Nanjing, 210009, People's Republic of China;
3. Materials Bigdata and Applications Division, Materials Academy Jitri, Suzhou, 215131, Jiangsu, People's Republic of China;
4. School of Mechatronics and Vehicle Engineering, Chongqing Jiaotong University, Chongqing, 400074, People's Republic of China;
5. Research Institute of Big Data Analytics, Xi'an Jiaotong-Liverpool University, Suzhou, 215131, Jiangsu, People's Republic of China

Received:2023-11-24 Revised:2023-12-07 Published:2025-09-19
Supported by:
This research was supported by the National Natural Science Foundation (Grant No. 52205377), National Key Research and Development Program (Grant No. 2022YFB4601804), and Key Basic Research Project of Suzhou (Grant Nos. #SJC2022031, #SJC2022029).

摘要/Abstract

摘要： 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.

The full text can be downloaded at https://link.springer.com/article/10.1007/s40436-024-00540-x

关键词: Transfer learning, Multi-fidelity, Mechanical properties, Small punch test (SPT)

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.

The full text can be downloaded at https://link.springer.com/article/10.1007/s40436-024-00540-x

Key words: Transfer learning, Multi-fidelity, Mechanical properties, Small punch test (SPT)

Zheng-Ni Yang, Jie Zou, Li Huang, Rui Yang, Jing-Yi Zhang, Chao Tong, Jing-Yu Kong, Zhen-Fei Zhan, Qing Liu. Machine learning-based extraction of mechanical properties from multi-fidelity small punch test data[J]. Advances in Manufacturing, 2025, 13(3): 511-524.

参考文献

[1] Manahan MP, Argon AS, Harling OK (1981) The development of a miniaturized disk bend test for the determination of postirradiation mechanical properties. J Nucl Mater 104:1545-1550
[2] Janča A, Siegl J, Haušild P (2016) Small punch test evaluation methods for material characterisation. J Nucl Mater 481:201-213
[3] Klevtsov I, Neshumaev D, Dedov A (2009) A method of using miniature samples for determining mechanical properties of metal of power-generating equipment at thermal power stations in Estonia. Therm Eng 56:426-431
[4] Chica JC, Díez PMB, Calzada MP (2018) Development of an improved prediction method for the yield strength of steel alloys in the small punch test. Mater Des 148:153-166
[5] Li M, Liu Z, Huang L (2022) A new multi-fidelity surrogate modelling method for engineering design based on neural network and transfer learning. Eng Comput 39(6):2209-2230
[6] Liu Z, Xu H, Zhu P (2020) An adaptive multi-fidelity approach for design optimization of mesostructure-structure systems. Struct Multidiscip Optim 62:375-386
[7] Li M, Liu Z, Huang L et al (2023) Multi-fidelity data-driven optimization design framework for self-piercing riveting process parameters. J Manuf Process 99:812-824
[8] Weiss K, Khoshgoftaar TM, Wang D (2016) A survey of transfer learning. J Big data 3(1):1-40
[9] Xue Y, Yang R, Chen X et al (2023) A novel local binary temporal convolutional neural network for bearing fault diagnosis. IEEE Trans Instrum Meas 72:3525013. https://doi.org/10.1109/TIM.2023.3298653
[10] Chen X, Yang R, Xue Y et al (2023) Deep transfer learning for bearing fault diagnosis: a systematic review since 2016. IEEE Trans Instrum Mea 72:3508221. https://doi.org/10.1109/TIM.2023.3244237
[11] Li H, Wang Z, Lan C et al (2023) A novel dynamic multiobjective optimization algorithm with non-inductive transfer learning based on multi-strategy adaptive selection. IEEE Trans Neural Netw Learn Syst 35(11):16533-16547
[12] Jiao L, Huang Z, Liu X et al (2023) Brain-inspired remote sensing interpretation: a comprehensive survey. IEEE J Sel Top Appl Earth Obs Remote Sens 16:2992-3033
[13] Pan SJ, Yang Q (2009) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345-1359
[14] Chen S, Yang R, Zhong M (2021) Graph-based semi-supervised random forest for rotating machinery gearbox fault diagnosis. Control Eng Pract 117:104952. https://doi.org/10.1016/j.conengprac.2021.104952
[15] Lu Q, Yang R, Zhong M et al (2019) An improved fault diagnosis method of rotating machinery using sensitive features and RLS-BP neural network. IEEE Trans Instrum Meas 69(4):1585-1593
[16] Chen S, Yang R, Zhong M et al (2023) A random forest and modelbased hybrid method of fault diagnosis for satellite attitude control systems. IEEE Trans Instrum Meas 72:1-13
[17] Lucas G (1990) Review of small specimen test techniques for irradiation testing. Metall Trans A 21:1105-1119
[18] Lucas G, Okada A, Kiritani M (1986) Parametric analysis of the disc bend test. J Nucl Mater 141:532-535
[19] Huber N, Konstantinidis A, Tsakmakis C (2001) Determination of poisson’s ratio by spherical indentation using neural networks—part I: theory. J Appl Mech 68(2):218-223
[20] Tyulyukovskiy E, Huber N (2006) Identification of viscoplastic material parameters from spherical indentation data: Part I. neural networks. J Mater Res 21(3):664-676
[21] Abendroth M, Kuna M (2003) Determination of deformation and failure properties of ductile materials by means of the small punch test and neural networks. Comput Mater Sci 28(3/4):633-644
[22] Mao X, Takahashi H (1987) Development of a further-miniaturized specimen of 3 mm diameter for tem disk (3 mm) small punch tests. J Nucl Mater 150(1):42-52
[23] Cahoon J, Broughton W, Kutzak A (1971) The determination of yield strength from hardness measurements. Metall Trans 2:1979-1983
[24] Jun C, Li FG, Sun ZK et al (2017) Tensile stress-strain behavior of metallic alloys. Trans Nonferrous Met Soc China 27(11):2443-2453
[25] Bowen A, Partridge P (1974) Limitations of the hollomon strain-hardening equation. J Phys D Appl Phys 7(7):969. https://doi.org/10.1088/0022-3727/7/7/305
[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] Sun B, Feng J, Saenko K (2017) Correlation alignment for unsupervised domain adaptation. Springer, Cham, pp 153-171
[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

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

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

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 12

编辑推荐

Metrics

本文评价

[1]	Si-Geng Li, Qiu-Ren Chen, Li Huang, Min Chen, Chen-Di Wei, Zhong-Jie Yue, Ru-Xue Liu, Chao Tong, Qing Liu. Data-driven approach to predict the fatigue properties of ferrous metal materials using the cGAN and machine-learning algorithms[J]. Advances in Manufacturing, 2024, 12(3): 447-464.
[2]	Zhong-Jie Yue, Qiu-Ren Chen, Zu-Guo Bao, Li Huang, Guo-Bi Tan, Ze-Hong Hou, Mu-Shi Li, Shi-Yao Huang, Hai-Long Zhao, Jing-Yu Kong, Jia Wang, Qing Liu. Improving RSW nugget diameter prediction method: unleashing the power of multi-fidelity neural networks and transfer learning[J]. Advances in Manufacturing, 2024, 12(3): 409-427.
[3]	Bo-Hao Li, Li-Ping Zhao, Yi-Yong Yao. Multiconditional machining process quality prediction using deep transfer learning network[J]. Advances in Manufacturing, 2023, 11(2): 329-341.
[4]	Qi-Dong Sun, Jie Sun, Kai Guo, Saad Waqar, Jiang-Wei Liu, Lei-Shuo Wang. Influences of processing parameters and heat treatment on microstructure and mechanical behavior of Ti-6Al-4V fabricated using selective laser melting[J]. Advances in Manufacturing, 2022, 10(4): 520-540.
[5]	Lin-Ju Wen, Xiao-Gang Hu, Zhong Li, Zhan-Hua Wang, Ji-Kai Wu, Qiang Zhu. Anisotropy in tensile properties and fracture behaviour of 316L stainless steel parts manufactured by fused deposition modelling and sintering[J]. Advances in Manufacturing, 2022, 10(3): 345-355.
[6]	Omar Ahmed Mohamed, Syed Hasan Masood, Wei Xu. Nickel-titanium shape memory alloys made by selective laser melting:a review on process optimisation[J]. Advances in Manufacturing, 2022, 10(1): 24-58.
[7]	Xing-Sheng Yu, Chuan Wu, Ru-Xing Shi, Ya-Sha Yuan. Microstructural evolution and mechanical properties of 55NiCrMoV7 hot-work die steel during quenching and tempering treatments[J]. Advances in Manufacturing, 2021, 9(4): 520-537.
[8]	E. Virgillito, A. Aversa, F. Calignano, M. Lombardi, D. Manfredi, D. Ugues, P. Fino. Failure mode analysis on compression of lattice structures with internal cooling channels produced by laser powder bed fusion[J]. Advances in Manufacturing, 2021, 9(3): 403-413.
[9]	Behrouz Bagheri, Mahmoud Abbasi. Development of AZ91/SiC surface composite by FSP: effect of vibration and process parameters on microstructure and mechanical characteristics[J]. Advances in Manufacturing, 2020, 8(1): 82-96.
[10]	Prakash KumarSahu, Kanchan Kumari, Sukhomay Pal, Surjya K. Pal. Hybrid fuzzy-grey-Taguchi based multi weld quality optimization of Al/Cu dissimilar friction stir welded joints[J]. Advances in Manufacturing, 2016, 4(3): 237-247.
[11]	Omar A. Mohamed, Syed H. Masood, Jahar L. Bhowmik. Optimization of fused deposition modeling process parameters: a review of current research and future prospects[J]. Advances in Manufacturing, 2015, 3(1): 42-53.
[12]	Min Jiang,Li-Na Chen,Jin He,Guang-Yao Chen,Chong-He Li,Xiong-Gang Lu. Effect of controlled rolling/controlled cooling parameters on microstructure and mechanical properties of the novel pipeline steel[J]. Advances in Manufacturing, 2014, 2(3): 265-274.