Inversion Method Based on Machine Learning for Johnson-Cook Constitutive Parameters of GH4169 Alloy

QIAN Dixin; WANG Liren; XIA Chunming

doi:10.11973/jxgccl230581

Materials and Mechanical Engineering > 2024 > 48(12): 100-105. > DOI: 10.11973/jxgccl230581

QIAN Dixin, WANG Liren, XIA Chunming. Inversion Method Based on Machine Learning for Johnson-Cook Constitutive Parameters of GH4169 Alloy[J]. Materials and Mechanical Engineering, 2024, 48(12): 100-105. DOI: 10.11973/jxgccl230581

Citation:

PDF (822 KB)

Inversion Method Based on Machine Learning for Johnson-Cook Constitutive Parameters of GH4169 Alloy

1.
School of Mechanical and Power Engineering, East China University of Technology, Shanghai 200237, China
2.
Guohan (Shanghai) Intelligent Technology Co., Ltd., Shanghai 201306, China
3.
School of Mechanical and Automotive Engineering, Shanghai University of Engineering and Technology, Shanghai 201620, China

More Information

Received Date: December 06, 2023
Revised Date: September 17, 2024

Graphical Abstract

Abstract

Abstract

The Latin hypercube sampling method was used to uniformly sample the Johnson-Cook (J-C) constitutive parameter space for GH4169 alloy from literatures. The stress-strain curve corresponding to the parameter combination was output by finite element simulation. With the simulated stress-strain curve data as input and J-C constitutive parameters as output, the forward neural network (FNN) model, random forest (RF) model and recurrent neural network (RNN) model were used for training, and Bayesian hyperparameter optimization was conducted on the models. The parameter inversion ability of the three models was compared by the determination coefficient R² of the test set. With the stress-strain curve data obtained by testing as input, the corresponding J-C constitutive parameters were output by the trained machine learning model, and then the stress-strain curve was generated by finite element simulation and compared with the test results. The results show that the R² of FNN model, RF model and RNN model on the test set was 0.847, 0.499, 0.741, respectively; FNN model had the best performance, while RF model had the worst performance and was not suitable for the inversion of material constitutive parameters. The compressive stress-strain curves of GH4169 alloy at 850–1 050 ℃ predicted with FNN model inversion J-C constitutive parameters were more consistent with the test curves, and the average relative error was about 11.9% and 2.1% lower than that of the predicted curves obtained with RNN model inversion J-C constitutive parameters and test curve fitting constitutive parameters, respectively, which verified the effectiveness of the machine learning method in the inversion of J-C constitutive parameters of GH4169 alloy.
- superalloy,
- constitutive parameter inversion,
- finite element simulation,
- machine learning,
- neural network

FullText(HTML)

References (23)

References

[1]	WU Y Q ,ZHANG C B ,ZHOU J ,et al. Analysis of the microstructure and mechanical properties during inertia friction welding of the near-α TA19 titanium alloy[J]. Chinese Journal of Mechanical Engineering,2020,33（6）：215-227.
[2]	耿培皓,秦国梁. 惯性摩擦焊接技术及其在航空工业领域的应用[J]. 精密成形工程,2017,9（5）：73-82. GENG P H ,QIN G L. Inertia friction welding technology and its application in aviation industry field[J]. Journal of Netshape Forming Engineering,2017,9（5）：73-82.
[3]	秦静筠,杜春晖. 惯性摩擦焊研究与应用现状[J]. 内燃机与配件,2018（18）：116-117. QIN J Y ,DU C H. Research and application status of inertia friction welding[J]. Internal Combustion Engine & Parts,2018（18）：116-117.
[4]	鹿安理,史清宇,赵海燕,等. 焊接过程仿真领域的若干关键技术问题及其初步研究[J]. 中国机械工程,2000,11（1）：201-205. LU A L ,SHI Q Y ,ZHAO H Y ,et al. Key techniques and some tentative research of welding process simulation[J]. China Mechanical Engineering,2000,11（1）：201-205.
[5]	JOHNSON G R ,COOK W H. A constitutive model and data for metals subjected to large strains,high strain rates and high temperatures[J]. Engineering Fracture Mechanics,1983,21：541-548.
[6]	王强,王建军,张晓琼,等. 金属热黏塑性本构关系的研究进展[J]. 爆炸与冲击,2022,42（9）：38-65. WANG Q ,WANG J J ,ZHANG X Q ,et al. Research progress on the thermal viscoplastic constitutive relationship of metals[J]. Explosion and Shock Waves,2022,42（9）：38-65.
[7]	许磊,雷旭升. GH4169高温合金材料的力学性能实验研究[J]. 机械制造与自动化,2021,50（5）：32-34. XU L ,LEI X S. Experimental study on mechanical properties of GH4169 superalloy[J]. Machine Building & Automation,2021,50（5）：32-34.
[8]	古愉川基于遗传算法与神经网络的高温高应变率下GH4169本构模型研究重庆重庆理工大学2022古愉川. 基于遗传算法与神经网络的高温高应变率下GH4169本构模型研究[D]. 重庆：重庆理工大学,2022. GU Y CStudy on GH4169 constitutive model under high temperature and high strain rate based on genetic algorithm and neural networkChongqingChongqing University of Technology2022GU Y C. Study on GH4169 constitutive model under high temperature and high strain rate based on genetic algorithm and neural network[D]. Chongqing: Chongqing University of Technology,2022.
[9]	尹海清,徐斌,姜雪,等. 镍基高温合金材料数据集[J/OL]. 中国科学数据,2019,4（1）.[2019-02-14]. DOI：10.11922/csdata.2018.0060.zh. YIN H Q ,XU B ,JIANG X ,et al. Dataset of nickel-based high temperature alloy materials[J/OL]. China Scientific Data,2019,4（1）.[2019-02-14]. DOI：10.11922/csdata.2018.0060.zh.
[10]	GENG P H ,QIN G L ,ZHOU J ,et al. Hot deformation behavior and constitutive model of GH4169 superalloy for linear friction welding process[J]. Journal of Manufacturing Processes,2018,32：469-481.
[11]	李洋,桑建兵,敖日汗,等. 基于仿真和智能算法骨骼肌超弹性本构参数的反演方法研究[J]. 力学学报,2021,53（5）：1449-1456. LI Y ,SANG J B ,AO R H ,et al. Research on inversion method of hyperelastic constitutive parameters of skeletal muscles based on simulation and intelligent algorithm[J]. Chinese Journal of Theoretical and Applied Mechanics,2021,53（5）：1449-1456.
[12]	MUKHAMEDOV B O ,KARAVAEV K V ,ABRIKOSOV I A. Machine learning prediction of thermodynamic and mechanical properties of multicomponent Fe-Cr-based alloys[J]. Physical Review Materials,2021,5（10）：104407.
[13]	DABIRI Y ,VAN DER VELDEN A ,SACK K L ,et al. Prediction of left ventricular mechanics using machine learning[J]. Frontiers in Physics,2019,7：117.
[14]	LIU S L ,SANG J B ,ZHANG Y ,et al. An inverse procedure for characterization of material parameters of passive skeletal muscle using FEM and experimental data[J]. Journal of Theoretical and Applied Mechanics,2020,58（1）：247-259.
[15]	魏新宇,桑建兵,张睿琳,等. 基于机器学习软骨细胞的时间依赖性力学行为及本构参数反演[J]. 力学学报,2022,54（11）：3125-3222. WEI X Y ,SANG J B ,ZHANG R L ,et al. Time-dependent mechanical behavior and constitutive parameter identification of chondrocytes based on machine learning[J]. Chinese Journal of Theoretical and Applied Mechanics,2022,54（11）：3125-3222.
[16]	张晓迪镍基高温合金动态断裂性能的数值模拟与Hopkinson杆冲击实验研究重庆重庆理工大学2018张晓迪. 镍基高温合金动态断裂性能的数值模拟与Hopkinson杆冲击实验研究[D]. 重庆：重庆理工大学,2018. ZHANG X DNumerical simulation of dynamic fracture performance of nickel base superalloy and study of Hopkinson bar impact testChongqingChongqing University of Technology2018ZHANG X D. Numerical simulation of dynamic fracture performance of nickel base superalloy and study of Hopkinson bar impact test[D]. Chongqing：Chongqing University of Technology,2018.
[17]	邹品GH4169高温动态本构模型与高速冲击性能研究南京南京航空航天大学2018邹品. GH4169高温动态本构模型与高速冲击性能研究[D]. 南京：南京航空航天大学,2018. ZOU PResearch on dynamic constitutive model at high temperature and high speed impact performance of GH4169NanjingNanjing University of Aeronautics and Astronautics2018ZOU P. Research on dynamic constitutive model at high temperature and high speed impact performance of GH4169[D]. Nanjing：Nanjing University of Aeronautics and Astronautics,2018.
[18]	刘晓,闫欢松,孔祖开,等. GH4169高温合金的动态力学行为及其本构关系[J]. 机械工程材料,2019,43（1）：75-81. LIU X ,YAN H S ,KONG Z K ,et al. Dynamic mechanical behavior and constitutive relationship of superalloy GH4169[J]. Materials for Mechanical Engineering,2019,43（1）：75-81.
[19]	胡伟基于SHPB高应变率冲击加载下的GH4169合金动态力学性能实验与仿真重庆重庆理工大学2021胡伟. 基于SHPB高应变率冲击加载下的GH4169合金动态力学性能实验与仿真[D]. 重庆：重庆理工大学,2021. HU WExperiment and simulation of dynamic mechanical properties of GH4169 alloy under high strain rate impact loading based on SHPBChongqingChongqing University of Technology2021HU W. Experiment and simulation of dynamic mechanical properties of GH4169 alloy under high strain rate impact loading based on SHPB[D]. Chongqing：Chongqing University of Technology,2021.
[20]	SHEIKHOLESLAMI R ,RAZAVI S. Progressive Latin hypercube sampling：An efficient approach for robust sampling-based analysis of environmental models[J]. Environmental Modelling & Software,2017,93：109-126.
[21]	BREIMAN L. Random forests[J]. Machine Learning,2001,45：5-32.
[22]	JEUNG M ,BAEK S ,BEOM J ,et al. Evaluation of random forest and regression tree methods for estimation of mass first flush ratio in urban catchments[J]. Journal of Hydrology,2019,575：1099-1110.
[23]	BISCHL B,BINDER M,LANG M,et alHyperparameter optimization：Foundations,algorithms,best practices and open challenges2023-11-11 https://ar5iv.org/abs/2107.0584BISCHL" target="_blank"> https://ar5iv.org/abs/2107.0584BISCHL B ,BINDER M ,LANG M ,et al. Hyperparameter optimization：Foundations,algorithms,best practices and open challenges[EB/OL].[2023-11-11]. https://ar5iv.org/abs/2107.0584

Cited By

Get Citation

PDF

XML

Article views (50) PDF downloads (12)

Turn off MathJax

Article Contents

Abstract

References

Inversion Method Based on Machine Learning for Johnson-Cook Constitutive Parameters of GH4169 Alloy

Abstract

References

Catalog

Export File

Citation

Format

Content