锻压技术

基于Arrhenius方程和机器学习的GH4742高温合金本构关系对比

英文标题：Comparison on constitutive relationship of superalloy GH4742 based on Arrhenius equation and machine learning

作者：冯彦成1 王松辉1 2 3 黎汝栋1 奚晓1 王文珂4 徐东1 苏海1 葛金锋1

单位：1. 贵州安大航空锻造有限责任公司 2. 贵州科学院 3. 中国科学院金属研究所 4. 哈尔滨工业大学材料科学与工程学院

关键词：GH4742高温合金热变形行为 Arrhenius模型支持向量机 GWO-BP网络

分类号：TG306

出版年,卷(期):页码：2025,50(1):260-271

摘要：

基于GH4742高温合金在应变速率为0.001~1 s-1、变形温度为950~1160 ℃及高度压下率为60%条件下的等温恒应变速率压缩试验，分析其流动应力行为，并分别构建了合金的Arrhenius方程、支持向量机和GWO-BP网络本构模型。研究结果表明，GH4742高温合金的流动应力曲线在高应变速率、低变形温度下呈现明显的软化现象；随着应变速率的降低和变形温度的升高，流动应力曲线逐渐呈现稳态流动特征。峰值应力和应变补偿Arrhenius模型的相关系数分别为0.993和0.991，平均绝对相对误差分别为8.986%和9.813%。测试样本支持向量机模型的相关系数为0.997，平均绝对相对误差为5.626%；测试样本GWO-BP模型的相关系数为0.997，平均绝对相对误差为5.471%。支持向量机和GWO-BP模型具有更高的预测精度，能更好地描述GH4742高温合金的高温流动行为。

Based on the isothermal constant strain rate compression tests of superalloy GH4742 at strain rates of 0.001-1 s-1, deformation temperatures of 950-1160 ℃, and high reduction rate of 60%, its rheological stress behavior was analyzed, and Arrhenius equation, support vector machine and GWO-BP network constitutive models of the alloy were constructed respectively. The results show that the rheological stress curve of superalloy GH4742 presents a significant softening phenomenon at high strain rates and low deformation temperatures. As the strain rate decreases and the deformation temperature increases, the rheological stress curve gradually shows steady-state flow characteristics. The correlation coefficients of the peak stress and strain compensation Arrhenius models are 0.993 and 0.991, respectively, and the average absolute relative errors are 8.986% and 9.813%, respectively. The correlation coefficient of the test sample support vector machine model is 0.997, and the average absolute relative error is 5.626%. While the correlation coefficient of the test sample GWO-BP model is 0.997, and the average absolute relative error is 5.471%. Thus, support vector machine and GWO-BP models have higher prediction accuracy and can better describe the high-temperature rheological behavior of GH4742 superalloy.

基金项目：

国家重点研发计划资助项目（2022YFB3706904）；国家科技重大专项资助项目(2024ZD0600100);贵州省高层次创新型人才项目（GCC[2023]098）；贵州省科技计划项目（ZZSG[2024]016）；安顺市科技计划项目（安市科工[2023]1号）

作者简介：冯彦成（1976-），男，硕士，高级工程师 E-mail：fengyancheng@126.com 通信作者：王松辉（1991-），男，博士，工程师 E-mail：wangsonghui91@126.com

参考文献：

[1] Zhang M X, Zhang B J, Jiao X Y, et al. Hot deformation behaviors and microstructure evolution of a supersaturated nickel-based superalloy[J]. Materials Characterization, 2024, 211: 113915.

[2] 张北江, 赵光普, 胥国华, 等. GH742合金热变形行为与微观组织演化[J]. 金属学报, 2005, 41(11): 1207-1214.

Zhang B J, Zhao G P, Xu G H, et al. Hot deformation behavior and microstructure evolution of superalloy GH742[J]. Acta Metallurgica Sinica, 2005, 41(11): 1207-1214.

[3] Zhang W W, Liu X G, Du Q, et al. Microstructure evolution in GH4742 superalloy by combining hot deformation and heat treatment[J]. Journal of Materials Research and Technology, 2023, 23: 13-35.

[4] 秦鹤勇, 李振团, 赵光普, 等. 固溶温度对GH4742合金力学性能及γ′相的影响[J]. 材料研究学报, 2023, 37(7): 502-510.

Qin H Y, Li Z T, Zhao G P, et al. Effect of solution temperature on mechanical properties and γ′ phase of GH4742 superalloy[J]. Chinese Journal of Materials Research, 2023, 37(7): 502-510.

[5] Xu H, Yang S F, Wang E H, et al. Cognition on oxidation behavior of Ni-based superalloy GH4742 when exposed to water vapor[J]. Journal of Materials Science and Technology, 2024, 174: 15-22.

[6] Kong W W, Yuan C, Zhang B N, et al. Investigation on low-cycle fatigue behaviors of wrought superalloy GH4742 at room-temperature and 700 ℃[J]. Materials Science and Engineering A, 2019, 751: 226-236.

[7] Lin Y C, Chen X M. A critical review of experimental results and constitutive descriptions for metals and alloys in hot working[J]. Materials and Design, 2011, 32(4): 1733-1759.

[8] 贡宣洋, 张海燕, 赵忠. GH4169合金DP工艺中的热变形行为及应变补偿本构模型[J]. 兵器材料科学与工程, 2024, 47(3): 1-7.

Gong X Y, Zhang H Y, Zhao Z. Thermal deformation behavior and strain compensation constitutive model of GH4169 alloy during DP[J]. Ordnance Material Science and Engineering, 2024, 47(3): 1-7.

[9] 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.

[10]Fu C Z, Tao C C, Huang H J, et al. Exploring microstructure evolution and machine-learning methods based on SCAT-CIWOA-BP-DMM theory during hot deformation of 56Ni-32Ti-12Hf alloy[J]. Intermetallics, 2024, 171: 108342.

[11]He D G, Lin Y C, Chen J, et al. Microstructural evolution and support vector regression model for an aged Ni-based superalloy during two-stage hot forming with stepped strain rates[J]. Materials and Design, 2018, 154: 51-62.

[12]唐江凌, 蔡从中, 皇思洁, 等. Al-Cu-Mg-Ag合金强度性能的支持向量回归预测[J]. 航空材料学报, 2012, 32(5): 92-96.

Tang J L, Cai C Z, Huang S J, et al. Strength prediction for Al-Cu-Mg-Ag alloy based on support vector regression[J]. Journal of Aeronautical Materials, 2012, 32(5): 92-96.

[13]Desu R K, Guntuku S C, Aditya B, et al. Support vector regression based flow stress prediction in austenitic stainless steel 304[J]. Procedia Materials Science, 2014, 6: 368-375.

[14]Limbadri K, Pankaj W, Suresh K, et al. Flow stress modeling of tube and slab route sheets of zircaloy-4 using machine learning techniques and Arrhenius type constitutive equations[J]. Journal of Materials Engineering and Performance, 2022, 32(2): 462-474.

[15]Ding F J, Jia X D, Hong T J, et al. Prediction model on flow stress of 6061 aluminum alloy sheet based on GA-BP and PSO-BP neural networks[J]. Rare Metal Materials and Engineering, 2020, 49(6): 1840-1853.

[16]Tian Y, Yu J Q, Zhao A J. Predictive model of energy consumption for office building by using improved GWO-BP[J]. Energy Reports, 2020, 6: 620-627.

[17]Ding G P, Hou S J. CFRP drive shaft damage identification and localization based on FBG sensing network and GWO-BP neural networks[J]. Optical Fiber Technology, 2024, 82: 103631.

[18]郭萃, 石云波, 温晓杰, 等. 基于GWO-BP方法的加速度计动态模型研究[J]. 测控技术, 2023, 42(8): 50-55.

Guo C, Shi Y B, Wen X J, et al. Dynamic model of accelerometer based on GWO-BP method[J]. Measurement and Control Technology, 2023, 42(8): 50-55.

[19]梁强, 张贤明, 李平, 等. 改进Zerilli-Armstrong、Arrhenius和GWO-BPNN模型对HAl61-4-3-1合金高温流变应力的预测[J]. 材料热处理学报, 2022, 43(9): 193-204.

Liang Q, Zhang X M, Li P, et al. Prediction of high temperature flow stress of HAl61-4-3-1 alloy by modified Zerilli-Armstrong, Arrhenius and GWO-BPNN models[J]. Transactions of Materials and Heat Treatment, 2022, 43(9): 193-204.

[20]Gai Y C, Zhang R, Zhou Z J, et al. Effect of C content on microstructure and hot deformation behavior of a Ni-based superalloy[J]. Journal of Alloys and Compounds, 2023, 965: 171453.

[21]刘晓燕, 张习祎, 陈秀全, 等. 热挤压态FGH96合金热变形行为及变形机制研究[J]. 稀有金属, 2024, 48(8): 1108-1119.

Liu X Y, Zhang X Y, Chen X Q, et al. Hot deformation behavior and deformation mechanism of hot extruded FGH96 superalloy[J]. Chinese Journal of Rare Metals, 2024, 48(8): 1108-1119.

[22]张明赫, 冯运莉, 田志伟, 等. V-Nb微合金化Q420B大规格角钢高温流变应力研究[J]. 锻压技术, 2024, 49(4): 226-234.

Zhang M H, Feng Y L, Tian Z W, et al. Study on high temperature flow stress of V-Nb microalloying Q420B angle steel with large size[J]. Forging & Stamping Technology, 2024, 49(4): 226-234.

[23]Sellars C M, McTegart W J. On the mechanism of hot deformation[J]. Acta Metallurgica, 1966, 14(9): 1136-1138.

[24]Lu C Y, Wang J, Zhang P. Flow behavior analysis and flow stress modeling of Ti17 alloy in β forging process[J]. Journal of Materials Engineering and Performance, 2021, 30(10): 7668-7681.

[25]陈由红, 兰博, 李金栋, 等. 挤压态GH710合金本构模型研究及应用验证[J]. 稀有金属, 2023, 47(7): 986-994.

Chen Y H, Lan B, Li J D, et al. Material characterization and validation for constitutive model of as-extruded GH710 alloy [J]. Chinese Journal of Rare Metals, 2023, 47(7): 986-994.

[26]Jiang Y Q, Guo Y W, Wang M B, et al. Hot deformation and constitutive modeling of a Ti-Al-Sn-Zr-Mo-Cr-Nb alloy[J]. Materials Today Communications, 2024, 40: 110037.

[27]Cortes C, Vapnik V. Support-vector networks[J]. Machine Learning, 1995, 20: 273-297.

[28]Li H Y, Wang X J, Song Y H, et al. Physical metallurgy guided machine learning to predict hot deformation mechanism of stainless steel[J]. Materials Today Communications, 2023, 36: 106779.

[29]Suykens J, Vandewalle J. Least squares support vector machine classifiers[J]. Neural Processing Letters, 1999, 9: 293-300.

[30]李航. 统计学习方法[M]. 北京: 清华大学出版社, 2012.

Li H. Statistical Learning Methods[M]. Beijing: Tsinghua University Press, 2012.

[31]Wu Z D, Wang X C, Yang Q, et al. Deformation resistance prediction of tandem cold rolling based on grey wolf optimization and support vector regression[J]. Journal of Iron and Steel Research International, 2023, 30: 1803-1820.

[32]Hatta N M, Zain A M, Sallehuddin R, et al. Recent studies on optimisation method of grey wolf optimiser (GWO): A review (2014-2017) [J]. Artificial Intelligence Review, 2019, 52: 2651-2683.

[33]Mirjalili S, Mirjalili S M, Lewis A. Grey wolf optimizer[J]. Advances in Engineering Software, 2014, 69: 46-61.

[34]Ghalambaz M, Yengejeh R J, Davami A H. Building energy optimization using grey wolf optimizer (GWO) [J]. Case Studies in Thermal Engineering, 2021, 27: 101250.

[35]Amitava R, Mohammad A, Satyabrata D, et al. Constitutive modeling for predicting high-temperature flow behavior in aluminum 5083+10wt pct SiCp composite[J]. Metallurgical and Materials Transactions B, 2019, 50: 1061-1076.

服务与反馈：

【文章下载】【加入收藏】