| 67 | 0 | 38 |
| 下载次数 | 被引频次 | 阅读次数 |
采用Gleeble-3500热模拟试验机，在变形温度为970～1060℃、应变速率为0.001～10 s-1及60%变形量下对Ti_2AlNb基合金进行热压缩实验。通过分析应力-应变曲线发现，不同变形参数下的Ti_2AlNb基合金流动应力-应变曲线呈现高度非线性关系。为准确预测其流动行为，分别构建了应变补偿的Arrhenius模型、优化的Zerilli-Armstrong模型以及粒子群算法优化的极限学习机(PSO-ELM)模型。上述模型的预测精度分别为0.989、0.985和0.999,而平均绝对相对误差依次为8.69%、9.59%和4.74%。上述结果表明，提出的PSO-ELM模型能够更为准确地描述Ti_2AlNb基合金的热变形行为。
Abstract：Hot compression experiments of Ti_2AlNb-based alloy were conducted on Gleeble-3500 thermal simulator at deformation temperatures of 970-1060 ℃, strain rates of 0.001-10 s-1 and deformation amount of 60%. By analyzing the stress-strain curves, it is found that the flow stress-strain curves of Ti_2AlNb-based alloy with different deformation parameters exhibit highly nonlinear relationship. To accurately predict its flow behavior, a strain-compensated Arrhenius model, an optimized Zerilli-Armstrong model and a particle swarm optimization-based extreme learning machine(PSO-ELM) model were constructed, respectively. The prediction accuracies of these models are 0.989, 0.985 and 0.999, respectively; while the mean absolute relative errors are 8.69%, 9.59% and 4.74%, respectively. The above results demonstrate that the proposed PSO-ELM model can more accurately describe the hot deformation behaviors of Ti_2AlNb-based alloy.
[1] GOYAL K,SARDANA N.Mechanical properties of the Ti2AlNb intermetallic:A review[J].Transactions of the Indian Institute of Metals,2021,74(8):1839-1853.
[2] ZHAO Q,LÜ M,CUI Z.Investigation on transformation-related recrystallization behavior of Ti2AlNb-based alloy[J].Intermetallics,2021,138:107302.
[3] ZHANG Q,CHEN M,WANG H,et al.Thermal deformation behavior and mechanism of intermetallic alloy Ti2AlNb[J].Transactions of the Nonferrous Metals Society of China,2016,26(3):722-728.
[4] ZHANG H,YAN N,LIANG H,et al.Phase transformation and microstructure control of Ti2AlNb-based alloys:A review[J].Journal of Materials Science and Technology,2021,80:203-216.
[5] 文超，孙前江，徐浩，等.基于Arrhenius模型和修正Johnson-Cook模型的TC21钛合金流动应力预测[J].塑性工程学报，2023,30(11):82-90.WEN Chao,SUN Qianjiang,XU Hao,et al.Flow stress prediction of TC21 titanium alloy based on Arrhenius model and modified Johnson-Cook model [J].Journal of Plasticity Engineering,2023,30 (11):82-90.
[6] 郭士琦，黄亮，刘可卓.铸态钛合金热变形行为及其弹黏塑性本构模型[J].材料开发与应用，2025,40(2):20-30,39.GUO Shiqi,HUANG Liang,LIU Kezhuo.Hot deformation behavior and elastic-viscoplastic constitutive model of as-cast titanium alloy[J].Development and Application of Materials,2025,40(2):20-30,39.
[7] 沈建成，贾海深，张继林，等.基于Z-A本构模型TC4钛合金高温流变行为的预测[J].钢铁钒钛，2024,45(4):76-83.SHEN Jiancheng,JIA Haishen,ZHANG Jilin,et al.Prediction of high-temperature rheological behavior of TC4 titanium alloy based on Z-A constitutive model[J].Iron Steel Vanadium Titanium,2024,45(4):76-83.
[8] 苏志毅，陈学文，杨圳，等.δ相时效态GH4169合金Zerilli-Armstrong本构模型及其参数反求方法[J].塑性工程学报，2024,31(8):133-139.SU Zhiyi,CHEN Xuewen,YANG Zhen,et al.Zerilli-Armstrong constitutive model of δ phase-aged GH4169 alloy and its parameters inversion method[J].Journal of Plasticity Engineering,2024,31(8):133-139.
[9] ZHANG M,CHEN D,LIU H,et al.Research on hot deformation behavior of Cu-Ti alloy based on machine learning algorithms and microalloying[J].Materials Today Communications,2024,39:108783.
[10] 朱鹏，冯玮.基于BP神经网络的15Cr14Co12Mo5Ni2齿轮钢本构模型建立及热加工图研究[J].塑性工程学报，2025,32(8):177-186.ZHU Peng,FENG Wei.Research on establishment of constitutive model and hot processing map of 15Cr14Co12Mo5Ni2 gear steel based on BP neural network[J].Journal of Plasticity Engineering,2025,32 (8):177-186.
[11] SELLARS C M,MCTEGART W J.On the mechanism of hot deformation[J].Acta Metallurgica,1966,14(9):1136-1138.
[12] SAMANTARAY D,MANDAL S,BHADURI A K.A comparative study on Johnson Cook,modified Zerilli-Armstrong and Arrhenius-type constitutive models to predict elevated temperature flow behavior in modified 9Cr-1Mo steel[J].Computational Materials Science,2009,47(2):568-576.
[13] SHOKRY A.Modified Fields-Backofen and Zerilli-Armstrong constitutive models to predict the hot deformation behavior in titanium-based alloys[J].Scientific Reports,2024,14(1).DOI:10.1038/s41598-024-58568-9.
[14] HUANG C,JIA X,ZHANG Z.A modified back propagation artificial neural network model based on genetic algorithm to predict the flow behavior of 5754 aluminum alloy[J].Materials,2018,11(5):855.
[15] ZHU Y,CAO Y,LIU C,et al.Dynamic behavior and modified artificial neural network model for predicting flow stress during hot deformation of alloy 925[J].Materials Today Communications,2020,25:101329.
[16] 孙岑花，施文鹏，王津，等.基于Arrhenius与机器学习的TC21钛合金本构模型研究[J].精密成形工程，2024,16(8):102-110.SUN Cenhua,SHI Wenpeng,WANG Jin,et al.Constitutive model of TC21 titanium alloy based on Arrhenius equation and machine learning[J].Journal of Netshape Forming Engineering,2024,16(8):102-110.
[17] LI X W,LIU Y,LUAN S,et al.Investigation of deformation behavior of Mg-2Ho alloy based on hyperbolic sine constitutive equation and PSO-BP neural network[J].Materials Today Communications,2024,38:107613.
[18] 冯彦成，王松辉，黎汝栋，等.基于Arrhenius方程和机器学习的GH4742高温合金本构关系对比[J].锻压技术，2025,50(1):260-271.FENG Yancheng,WANG Songhui,LI Rudong,et al.Comparison of constitutive relationships of GH4742 superalloy at high temperatures based on Arrhenius equation and machine learning[J].Forging & Stamping Technology,2025,50(1):260-271.
[19] 李全，金朝阳.采用改进和优化的Zerilli-Armstrong本构模型预测AZ80镁合金的高温流动应力[J].中国有色金属学报，2021,31(8):2091-2100.LI Quan,JIN Zhaoyang.Prediction of high temperature flow stress of AZ80 magnesium alloy by using modified and optimized Zerilli-Armstrong constitutive models [J].The Chinese Journal of Nonferrous Metals,2021,31(8):2091-2100.
[20] HUANG G B,ZHU Q Y,SIEW C K.Extreme learning machine:Theory and applications[J].Neurocomputing,2006,70(1-3):489-501.
[21] 穆晨光，陈曦，邬冠华，等.基于PSO-SVR的巴克豪森效应特征信号预测环轧件残余应力[J].南昌航空大学学报(自然科学版),2024,38(2):1-9.MU Chenguang,CHEN Xi,WU Guanhua,et al.Prediction of residual stress in ring-rolled parts using barkhausen effect characteristic signals based on PSO-SVR[J].Journal of Nanchang Hangkong University (Natural Science Edition),2024,38(2):1-9.
[22] 王宇航，罗拴谋，董显娟，等.基于物理参数和BP神经网络的9310钢本构模型研究[J].塑性工程学报，2024,31(8):117-124.WANG Yuhang,LUO Shuanmou,DONG Xianjuan,et al.Research on constitutive model of 9310 steel based on physical parameters and BP neural network[J].Journal of Plasticity Engineering,2024,31 (8):117-124.
[23] ZHAO M,JIANG L,ZHAO C,et al.Data-driven prediction of flow behavior and microstructure characteristics in ultra-high-strength steel during elevated temperature tensile deformation[J].Steel Research International,2025:2500402.
[24] ZHAO M,LI C,JIANG L,et al.Hot workability of a typical ultrahigh strength steel during the isothermal forging process[J].Metals and Materials International,2024,30(4):1055-1071.
基本信息:
中图分类号:TG146.23
引用信息:
[1]唐明浩,赵明杰,陈卫平,等.Ti_2AlNb基合金热变形行为及本构建模[J].塑性工程学报,2026,33(08):270-279.
基金信息:
国家自然科学基金资助项目(52564058); 江西省自然科学基金资助项目(20252BAC240335); 江西省研究生创新专项基金资助项目(YC2025-S625)
2026-08-21
2026-08-21
2026-08-21