基于机器学习的Monel K-500合金热变形行为及本构关系研究

张振; 朱明渝; 付绪楷; 何川; 朱玉亮; 万亚昌; 张开铭

doi:10.3969/j.issn.1674-6457.2025.11.023

PDF(897 KB)

精密成形工程 ›› 2025, Vol. 17 ›› Issue (11) : 242-251. DOI: 10.3969/j.issn.1674-6457.2025.11.023

高温合金成形

基于机器学习的Monel K-500合金热变形行为及本构关系研究

张振¹, 朱明渝¹, 付绪楷¹, 何川¹, 朱玉亮², 万亚昌^3,*, 张开铭⁴

作者信息 +

Hot Deformation Behavior and Constitutive Relationship of Monel K-500 Alloy Based on Machine Learning

ZHANG Zhen¹, ZHU Mingyu¹, FU Xukai¹, HE Chuan¹, ZHU Yuliang², WAN Yachang^3,*, ZHANG Kaiming⁴

Author information +

文章历史 +

摘要

目的为合理制定Monel K-500合金热变形工艺参数,探索其塑性加工能力,以热压缩实验为基础,探究Monel K-500合金的高温流变行为,并建立本构模型。方法采用Gleeble-3800热模拟实验机在变形温度为900~1 100 ℃、应变速率为0.001~1 s^-1条件下进行了变形量为50%的热压缩实验。分析了Monel K-500合金的热变形行为,并建立了应变补偿Arrhenius本构模型、极限学习机（ELM）本构模型以及支持向量机（SVM）本构模型。结果 Monel K-500合金的应力随变形温度的降低和应变速率的增加而增大;应变补偿Arrhenius本构模型的相关系数R²和相对误差分别为0.993、5.7%,ELM本构模型测试集的相关系数R²和相对误差分别为0.997、1.8%,SVM本构模型测试集的相关系数R²和相对误差分别为0.988、4.8%,ELM本构模型的精度最高,在对Monel K-500合金的流动应力进行预测时,可优先选用机器学习的方法替代计算复杂的传统本构模型,以实现对流动应力的高精度预测。

Abstract

The work aims to reasonably formulate the hot deformation process parameters of Monel K-500 alloy, explore its plastic processing ability, investigate the high temperature flow behavior of Monel K-500 alloy and establish a constitutive model based on the hot compression experiment. The hot compression experiment of 50% deformation was carried out by Gleeble-3800 hot simulation test machine at the deformation temperature of 900-1 100 ℃ and the strain rate of 0.001-1 s^‒1. The hot deformation behavior of Monel K-500 alloy was investigated. A strain-compensated Arrhenius constitutive model, an extreme Learning Machine (ELM) constitutive model, and a Support Vector Machine (SVM) constitutive model for the alloy were established. The results indicated that the stress of Monel K-500 alloy increased with the decrease of deformation temperature and the increase of strain rate. The R² and AARE of the strain-compensated Arrhenius constitutive model were 0.993 and 5.7%, respectively. For the ELM constitutive model, the R² and AARE of the test set were 0.997 and 1.8%, respectively. The R² and AARE of the SVM constitutive model's test set were 0.988 and 4.8%, respectively. The ELM constitutive model demonstrated the highest accuracy and was preferred for predicting the flow stress of Monel K-500 alloy. The application of machine learning methods could effectively replace traditional constitutive models with complex calculations, achieving high-precision predictions of flow stress.

导出引用

张振, 朱明渝, 付绪楷, 何川, 朱玉亮, 万亚昌, 张开铭. 基于机器学习的Monel K-500合金热变形行为及本构关系研究[J]. 精密成形工程. 2025, 17(11): 242-251 https://doi.org/10.3969/j.issn.1674-6457.2025.11.023

ZHANG Zhen, ZHU Mingyu, FU Xukai, HE Chuan, ZHU Yuliang, WAN Yachang, ZHANG Kaiming. Hot Deformation Behavior and Constitutive Relationship of Monel K-500 Alloy Based on Machine Learning[J]. Journal of Netshape Forming Engineering. 2025, 17(11): 242-251 https://doi.org/10.3969/j.issn.1674-6457.2025.11.023

中图分类号： TG142.1

参考文献

[1] LIU F, ZHANG C H, HOU X H, et al.Deformation Behavior at Fatigue Crack Tip in Nickel-Based Alloy[J]. Vacuum, 2024, 228: 113491.
[2] 徐超, 吴畏, 吴勇, 等. 镍基高温合金极薄带精密轧制技术研究进展[J]. 精密成形工程, 2025, 17(7): 206-218.
XU C, WU W, WU Y, et al.Research Progress on Precision Rolling Technology of Nickel Based High-Temperature Alloy Ultra-Thin Strip[J]. Journal of Netshape Forming Engineering, 2025, 17(7): 206-218.
[3] ZHU Y H, WANG J Z, LIU H, et al.The Tribocorrosion Behavior of Monel 400 Alloy in Seawater at Different Temperatures[J]. Tribology International, 2023, 189: 108975.
[4] 王成, 巨少华, 荀淑玲, 等. 镍基耐蚀合金研究进展[J]. 材料导报, 2009, 23(3): 71-76.
WANG C, JU S H, XUN S L, et al.Progress in Research on Nickel-Based Corrosion Resistant Alloys[J]. Materials Review, 2009, 23(3): 71-76.
[5] AL-SAADI S, RAMAN R K, ANISUR M R, et al.Graphene Coating on a Nickel-Copper Alloy (Monel 400) for Microbial Corrosion Resistance: Electrochemical and Surface Characterizations[J]. Corrosion Science, 2021, 182: 109299.
[6] HE Z B, QIN Z B, GAO Z M, et al.Synergistic Effect between Cavitation Erosion and Corrosion of Monel K500 Alloy in 3.5wt% NaCl Solution[J]. Materials Characterization, 2023, 205: 113340.
[7] TÜRKMEN İ, KEDDAM M. Boronizing of Monel K500 Alloy: Microstructural Characterization and Modeling of Boron Diffusion[J]. Materials Characterization, 2024, 213: 113995.
[8] 秦明花, 郑文杰, 张雪冰, 等. Monel K-500合金的研究现状[J]. 热加工工艺, 2021, 50(11): 5-8.
QIN M H, ZHENG W J, ZHANG X B, et al.Research Status of Monel K-500 Alloy[J]. Hot Working Technology, 2021, 50(11): 5-8.
[9] CHEN Z, WANG C C, TANG C, et al.Microstructure and Mechanical Properties of a Monel K-500 Alloy Fabricated by Directed Energy Deposition[J]. Materials Science and Engineering: A, 2022, 857: 144113.
[10] 朱玉亮, 郑文杰, 宋志刚, 等. 析出相对Monel K-500合金冲击韧性的影响[J]. 钢铁研究学报, 2015, 27(10): 67-74.
ZHU Y L, ZHENG W J, SONG Z G, et al.Effect of Precipitates on Impact Toughness of Monel K-500 Alloy[J]. Journal of Iron and Steel Research, 2015, 27(10): 67-74.
[11] 杨明辉, 李星吾, 孙崇昊, 等. 定向凝固与固态相变双联协控下Monel K-500合金的组织和力学性能[J]. 金属学报, 2025, 61(4): 561-571.
YANG M H, LI X W, SUN C H, et al.Microstructure and Mechanical Properties of Monel K-500 Alloy in Synergetic Modulation of Directional Solidification and Thermal Processing[J]. Acta Metallurgica Sinica, 2025, 61(4): 561-571.
[12] 朱玉亮, 王哲, 郑文杰, 等. Monel K-500合金高温流变特性及其本构方程[J]. 钢铁研究学报, 2017, 29(11): 933-938.
ZHU Y L, WANG Z, ZHENG W J, et al.Characteristics of High Temperature Flow Behavior and Constitutive Equation of Monel K-500 Alloy[J]. Journal of Iron and Steel Research, 2017, 29(11): 933-938.
[13] 俞年年, 项金钟, 郑文杰. Monel K-500合金的热变形行为及热加工图[J]. 热加工工艺, 2018, 47(7): 172-176.
YU N N, XIANG J Z, ZHENG W J.Hot Deformation Behavior and Hot Processing Map of Monel K-500 Alloy[J]. Hot Working Technology, 2018, 47(7): 172-176.
[14] HU M W, TAN Q Y, KNIBBE R, et al.Recent Applications of Machine Learning in Alloy Design: A Review[J]. Materials Science and Engineering: R: Reports, 2023, 155: 100746.
[15] GERASHI E, POURBAGHI M, DUAN X L, et al.Machine Learning-Aided Phase and Mechanical Properties Prediction in Multi-Principal Element Alloys[J]. Computational Materials Science, 2024, 243: 113114.
[16] 杨剑锋, 乔佩蕊, 李永梅, 等. 机器学习分类问题及算法研究综述[J]. 统计与决策, 2019, 35(6): 36-40.
YANG J F, QIAO P R, LI Y M, et al.A Review of Machine-Learning Classification and Algorithms[J]. Statistics & Decision, 2019, 35(6): 36-40.
[17] 王海伟, 叶波, 冯晶, 等. 机器学习在钢铁材料研究中的应用综述[J]. 中国材料进展, 2023, 42(10): 806-813.
WANG H W, YE B, FENG J, et al.Application of Machine Learning in Steel Materials: A Survey[J]. Materials China, 2023, 42(10): 806-813.
[18] 周岳钰, 高静, 汪燕, 等. 机器学习在材料科学中的应用进展[J]. 信息记录材料, 2022, 23(6): 8-12.
ZHOU Y Y, GAO J, WANG Y, et al.Applications of Machine Learning in Material Science[J]. Information Recording Materials, 2022, 23(6): 8-12.
[19] 冯伟, 刘忠翰, 谢臻轩, 等. F316奥氏体不锈钢热变形行为与动态再结晶机制[J]. 钢铁研究学报, 2024, 36(8): 1060-1070.
FENG W, LIU Z H, XIE Z X, et al.Hot Deformation Behavior and Dynamic Recrystallization Mechanism of F316 Austenitic Stainless Steel[J]. Journal of Iron and Steel Research, 2024, 36(8): 1060-1070.
[20] 张开铭, 鲁世强, 江丰建聪, 等. Laves相NbCr₂/Nb两相合金的应变补偿物理本构关系研究[J]. 稀有金属材料与工程, 2023, 52(8): 2835-2843.
ZHANG K M, LU S Q, JIANG F J C, et al. Strain-Compensated Physical Constitutive Relation of Laves Phase NbCr₂/Nb Dual-Phase Alloy[J]. Rare Metal Materials and Engineering, 2023, 52(8): 2835-2843.
[21] 张开铭, 王克鲁, 鲁世强, 等. 基于物理参数和响应面法的S280超高强度不锈钢本构模型[J]. 塑性工程学报, 2023, 30(5): 105-115.
ZHANG K M, WANG K L, LU S Q, et al.Constitutive Model of S280 Ultra-High Strength Stainless Steel Based on Physical Parameters and Response Surface Method[J]. Journal of Plasticity Engineering, 2023, 30(5): 105-115.
[22] 张开铭. S280超高强度不锈钢动态再结晶行为及工艺参数优化研究[D]. 南昌: 南昌航空大学, 2023.
ZHANG K M.Study on Dynamic Recrystallization Behavior and Process Parameter Optimization of S280 Ultra-high Strength Stainless Steel[D]. Nanchang: Nanchang Hangkong University, 2023.
[23] YE L Y, ZHAI Y W, ZHOU L Y, et al.The Hot Deformation Behavior and 3D Processing Maps of 25Cr2Ni4MoV Steel for a Super-Large Nuclear-Power Rotor[J]. Journal of Manufacturing Processes, 2020, 59: 535-544.
[24] BABU K, PRITHIV T S, GUPTA A, et al.Modeling and Simulation of Dynamic Recrystallization in Super Austenitic Stainless Steel Employing Combined Cellular Automaton, Artificial Neural Network and Finite Element Method[J]. Computational Materials Science, 2021, 195: 110482.
[25] LU C Y, SHI J, WANG J.Physically Based Constitutive Modeling for Ti17 Alloy with Original Basketweave Microstructure in β Forging: A Comparison of Three Approaches[J]. Materials Characterization, 2021, 181: 111455.
[26] ZHAO Z W, LI J X, WANG X T, et al.Thermal Deformation Behavior of a Ni-Cr-Fe Superalloy and Its Effect on Corrosion Resistance: A Comprehensive Analysis of Strain Rate and Temperature Effects[J]. Journal of Alloys and Compounds, 2024, 1006: 176370.
[27] ZENER C, HOLLOMON J H.Effect of Strain Rate Upon Plastic Flow of Steel[J]. Journal of Applied Physics, 1944, 15(1): 22-32.
[28] HUANG G B, ZHU Q Y, SIEW C K.Extreme Learning Machine: Theory and Applications[J]. Neurocomputing, 2006, 70(1/2/3): 489-501.
[29] 陆思源, 陆志海, 王水花, 等. 极限学习机综述[J]. 测控技术, 2018, 37(10): 3-9.
LU S Y, LU Z H, WANG S H, et al.Review of Extreme Learning Machine[J]. Measurement & Control Technology, 2018, 37(10): 3-9.
[30] ELDABAH N M, SHOUKRY A, KHAIR-ELDEEN W, et al.Design and Characterization of Low Young's Modulus Ti-Zr-Nb-Based Medium Entropy Alloys Assisted by Extreme Learning Machine for Biomedical Applications[J]. Journal of Alloys and Compounds, 2023, 968: 171755.
[31] 甘露. 极限学习机的研究与应用[D]. 西安: 西安电子科技大学, 2014.
GAN L.Research and Application of Extreme Learning Machine[D]. Xi'an: Xidian University, 2014.
[32] 徐睿, 梁循, 齐金山, 等. 极限学习机前沿进展与趋势[J]. 计算机学报, 2019, 42(7): 1640-1670.
XU R, LIANG X, QI J S, et al.Advances and Trends in Extreme Learning Machine[J]. Chinese Journal of Computers, 2019, 42(7): 1640-1670.
[33] 张开铭, 温余远, 王克鲁, 等. Ti-22Al-24Nb合金热变形行为及本构关系[J]. 塑性工程学报, 2022, 29(10): 208-215.
ZHANG K M, WEN Y Y, WANG K L, et al.Hot Deformation Behavior and Constitutive Relation of Ti-22Al-24Nb Alloy[J]. Journal of Plasticity Engineering, 2022, 29(10): 208-215.
[34] ZHANG W, LI P Y, WANG L, et al.Explaining of Prediction Accuracy on Phase Selection of Amorphous Alloys and High Entropy Alloys Using Support Vector Machines in Machine Learning[J]. Materials Today Communications, 2023, 35: 105694.
[35] ALSHAIJI A, ALBINMOUSA J, PERON M, et al.Analyzing Quasi-Static Fracture of Notched Magnesium ZK60 Using Notch Fracture Toughness and Support Vector Machine[J]. Theoretical and Applied Fracture Mechanics, 2022, 121: 103463.
[36] 李海生. 支持向量机回归算法与应用研究[D]. 广州: 华南理工大学, 2005.
LI H S.Algorithm and Application Research of Support Vector Machine Regression[D]. Guangzhou: South China University of Technology, 2005.
[37] 孙德山. 支持向量机分类与回归方法研究[D]. 长沙: 中南大学, 2004.
SUN D S.The Researches on Support Vector Machine Classification and Regression Methods[D]. Changsha: Central South University, 2004.
[38] 张学工. 关于统计学习理论与支持向量机[J]. 自动化学报, 2000, 26(1): 32-42.
ZHANG X G.Introduction to Statistical Learning Theory and Support Vector Machines[J]. Acta Automatica Sinica, 2000, 26(1): 32-42.