Cryogenic Mechanical Properties and Machine Learning Prediction Model of Ti6554 Titanium Alloy

LIU Chuankun; QU Zhoude; WU Chuan

doi:10.3969/j.issn.1674-6457.2026.04.002

PDF(13704 KB)

Journal of Netshape Forming Engineering ›› 2026, Vol. 18 ›› Issue (4) : 11-23. DOI: 10.3969/j.issn.1674-6457.2026.04.002

Light Alloy Forming

Cryogenic Mechanical Properties and Machine Learning Prediction Model of Ti6554 Titanium Alloy

LIU Chuankun, QU Zhoude^*, WU Chuan

Author information +

History +

Abstract

The work aims to study the mechanical behavior and microstructural evolution of Ti-6554 titanium alloy subject to cryogenic conditions, elucidating the underlying mechanisms governing temperature-dependent property variations. Load-displacement curves were captured via a liquid nitrogen-integrated tensile testing apparatus, while temperature-dependent mechanisms governing mechanical properties were probed through comprehensive analysis of true stress-strain curves, fractographic observations, work hardening rate quantification, and electron backscatter diffraction (EBSD) characterization. Based on these findings, a Support Vector Regression optimized by Particle Swarm Algorithm (PSO-SVR) and an Error Back-Propagation neural network model (EBP) were formulated. Experimental outcomes revealed that progressive temperature reduction induced significant flow stress elevation of Ti-6554 titanium alloy, where twin-dislocation interactions were found to enhance yield strength yet diminish elongation. Crucially, a fracture mode transition from ductile to ductile-brittle mixed failure was documented across the 0 ℃ to -180 ℃ regime. Model validation demonstrated optimal R² values of 0.94 and 0.98 for PSO-SVR and EBP respectively, with corresponding mean RMSE of 11.12 MPa and 4.01 MPa, and mean MAE of 9.024 MPa and 2.067 MPa, conclusively establishing the superior predictive capability of the EBP framework. Cryogenic temperatures substantially enhance both the yield strength and ultimate tensile strength of the material. This strengthening is fundamentally attributed to increased interatomic bonding forces, which elevates the lattice friction resistance that dislocation slip must overcome, coupled with the diminished thermal activation energy available for dislocations to surmount obstacles. However, this strengthening is accompanied by degradation in plasticity, manifested as reduced elongation. As the tensile temperature decreases from 0 ℃ to -180 ℃, the alloy's dominant fracture mechanism shifts from ductile fracture to a ductile-brittle mixed fracture. The developed EBP neural network prediction model demonstrates significantly superior predictive accuracy compared to the PSO-SVR model.

Key words

cryogenic titanium alloys / mechanical properties / support vector regression (SVR) / error back propagation neural network (EBP)

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

LIU Chuankun, QU Zhoude, WU Chuan. Cryogenic Mechanical Properties and Machine Learning Prediction Model of Ti6554 Titanium Alloy[J]. Journal of Netshape Forming Engineering. 2026, 18(4): 11-23 https://doi.org/10.3969/j.issn.1674-6457.2026.04.002

References

[1] LI C M, LUO H J, WEI M G, et al.Research on Hot Workability and Deformation Mechanism of As-Extruded Ti-6554 Alloy over a Broad Temperature Range[J]. Journal of Alloys and Compounds, 2025, 1010: 177055.
[2] 孟亚飞, 王庆敏, 武川, 等. Ti6554钛合金连续孔型轧制过程微观组织演化和力学性能研究[J]. 精密成形工程, 2025, 17(8): 12-24.
MENG Y F, WANG Q M, WU C, et al.Microstructure Evolution and Mechanical Properties of the Ti6554 Titanium Alloy during Continuous Hole Rolling Process[J]. Journal of Netshape Forming Engineering, 2025, 17(8): 12-24.
[3] 彭志伟, 武川, 王圆圆, 等. Ti6554钛合金β相区动态再结晶元胞自动机模拟[J]. 塑性工程学报, 2025, 32(2): 163-171.
PENG Z W, WU C, WANG Y Y, et al.Cellular Automaton Simulation of Dynamic Recrystallization in β Phase Region of Ti6554 Titanium Alloy[J]. Journal of Plasticity Engineering, 2025, 32(2): 163-171.
[4] LU Z C, ZHANG X H, JI W, et al.Investigation on the Deformation Mechanism of Ti-5Al-2.5Sn ELI Titanium Alloy at Cryogenic and Room Temperatures[J]. Materials Science and Engineering: A, 2021, 818: 141380.
[5] ZANG M C, NIU H Z, YU J S, et al.Cryogenic Tensile Properties and Deformation Behavior of a Fine-Grained near Alpha Titanium Alloy with an Equiaxed Microstructure[J]. Materials Science and Engineering: A, 2022, 840: 142952.
[6] HAO F, XIAO J F, FENG Y, et al.Tensile Deformation Behavior of a Near-α Titanium Alloy Ti-6Al-2Zr-1Mo-1V under a Wide Temperature Range[J]. Journal of Materials Research and Technology, 2020, 9(3): 2818-2831.
[7] XU Y L, ZHANG B B.Effects of Hydrogen as a Solid Solution Element on the Deformation Behavior of a Near-Alpha Titanium Alloy[J]. Materials Science and Engineering: A, 2021, 815: 141269.
[8] YAO K, XIN S W, YANG Y, et al.Ultrahigh Cryogenic Strength and Exceptional Ductility at 20 K in a TWIP Ti-15Mo Alloy[J]. Scripta Materialia, 2022, 213: 114595.
[9] DI I S, BRIOTTET L, RAUCH E F, et al.Plastic Deformation, Damage and Rupture of PM Ti-6Al-4V at 20 K under Monotonic Loading[J]. Acta Materialia, 2007, 55(1): 105-118.
[10] ZANG M C, NIU H Z, ZHANG H R, et al.Cryogenic Tensile Properties and Deformation Behavior of a Superhigh Strength Metastable Beta Titanium Alloy Ti-15Mo-2Al[J]. Materials Science and Engineering: A, 2021, 817: 141344.
[11] HUANG Z W, JIN S B, ZHOU H, et al.Evolution of Twinning Systems and Variants during Sequential Twinning in Cryo-Rolled Titanium[J]. International Journal of Plasticity, 2019, 112: 52-67.
[12] HUANG S X, ZHAO Q Y, ZHAO Y Q, et al.Toughening Effects of Mo and Nb Addition on Impact Toughness and Crack Resistance of Titanium Alloys[J]. Journal of Materials Science & Technology, 2021, 79: 147-164.
[13] 戴进财, 闵小华, 辛社伟, 等. 间隙元素O对β型Ti-15Mo合金超低温力学性能的影响[J]. 金属学报, 2025, 61(2): 243-252.
DAI J C, MIN X H, XIN S W, et al.Effect of Interstitial Element O on Cryogenic Mechanical Properties in β-Type Ti-15Mo Alloy[J]. Acta Metallurgica Sinica, 2025, 61(2): 243-252.
[14] 郑壮壮, 陆子川, 杨建辉, 等. CT1400低温钛合金的显微组织与力学性能[J]. 材料工程, 2024, 52(11): 125-132.
ZHENG Z Z, LU Z C, YANG J H, et al.Microstructure and Mechanical Properties of CT1400 Cryogenic Titanium Alloy[J]. Journal of Materials Engineering, 2024, 52(11): 125-132.
[15] 夏天, 高志玉, 赵斐, 等. 金属材料塑性本构模型建立研究进展[J]. 塑性工程学报, 2024, 31(9): 23-35.
XIA T, GAO Z Y, ZHAO F, et al.Research Progress on Establishing of Plastic Constitutive Models for Metal Materials[J]. Journal of Plasticity Engineering, 2024, 31(9): 23-35.
[16] 施文鹏, 孙岑花, 李佳俊, 等. 基于人工神经网络智能算法的9310钢本构模型优化[J]. 精密成形工程, 2024, 16(3): 171-180.
SHI W P, SUN C H, LI J J, et al.9310 Steel Constitutive Model Optimization Based on Artificial Neural Network Intelligent Algorithm[J]. Journal of Netshape Forming Engineering, 2024, 16(3): 171-180.
[17] 周潼, 程军, 王克鲁, 等. Ti₂AlNb基合金热变形行为及加工图研究[J]. 中国机械工程, 2025, 36(11): 2757-2765.
ZHOU T, CHENG J, WANG K L, et al.Hot Deformation Behavior and Processing Maps of Ti₂AlNb-Based Alloys[J]. China Mechanical Engineering, 2025, 36(11): 2757-2765.
[18] 王新云, 唐学峰, 余国卿, 等. 基于深度学习的塑性变形理论建模研究进展[J]. 塑性工程学报, 2024, 31(4): 92-116.
WANG X Y, TANG X F, YU G Q, et al.Research Progress on Theoretical Modeling of Plastic Deformation Based on Deep Learning[J]. Journal of Plasticity Engineering, 2024, 31(4): 92-116.
[19] 唐学峰, 王志洲, 冯仪, 等. 基于机器学习的TC18钛合金起落架锻造成形工艺智能优化[J]. 塑性工程学报, 2024, 31(4): 254-266.
TANG X F, WANG Z Z, FENG Y, et al.Intelligent Optimization of Forging Forming Process of TC18 Titanium Alloy Landing Gear Based on Machine Learning[J]. Journal of Plasticity Engineering, 2024, 31(4): 254-266.
[20] 赵德望, 刘汉杰, 赵延广, 等. 基于数理与机器学习的ZTC钛合金塑性本构模型[J]. 中国有色金属学报, 2025, 35(10): 3539-3551.
ZHAO D W, LIU H J, ZHAO Y G, et al.Plastic Constitutive Model of ZTC4 Titanium Alloy Based on Theoretical Modeling and Machine Learning[J]. The Chinese Journal of Nonferrous Metals, 2025, 35(10): 3539-3551.
[21] PENG Z S, JI H C, PEI W C, et al.Constitutive Relationship of TC4 Titanium Alloy Based on Back Propagating (BP) Neural Network (NN)[J]. Metalurgija, 2021, 60(3/4): 277-280.
[22] 武鹏飞, 肖旭彤, 娄燕山, 等. 不同温度下Mg-Gd-Y稀土镁合金的变形行为表征[J]. 塑性工程学报, 2022, 29(6): 134-140.
WU P F, XIAO X T, LOU Y S, et al.Characterization of Deformation Behavior of Mg-Gd-Y Rare Earth Magnesium Alloy at Different Temperatures[J]. Journal of Plasticity Engineering, 2022, 29(6): 134-140.
[23] LI S J, CHEN W N, BHANDARI K S, et al.Flow Behavior of AA5005 Alloy at High Temperature and Low Strain Rate Based on Arrhenius-Type Equation and back Propagation Artificial Neural Network (BP-ANN) Model[J]. Materials, 2022, 15(11): 3788.
[24] 赵文娟, 丁桦, 周舸, 等. TC21合金超塑性本构关系的BP人工神经网络模型[J]. 锻压技术, 2009, 34(4): 138-142.
ZHAO W J, DING H, ZHOU G, et al.Constitutive Relationship Model of TC21 Alloy during Superplastic Deformation Based on BP Artificial Neural Network[J]. Forging & Stamping Technology, 2009, 34(4): 138-142.
[25] SONG S H.A Comparison Study of Constitutive Equation, Neural Networks, and Support Vector Regression for Modeling Hot Deformation of 316L Stainless Steel[J]. Materials, 2020, 13(17): 3766.
[26] HUSSAIN A, SAKHAEI A H, SHAFIEE M.Machine Learning-Based Constitutive Modelling for Material Non-Linearity: A Review[J]. Mechanics of Advanced Materials and Structures, 2024: 1-19.
[27] LIU Y F, FENG Y D, LIU Q B, et al.Prediction of Flow Stress in Mg-3Dy Alloy Based on Constitutive Equation and PSO-SVR Model[J]. Materials Research Express, 2024, 11(5): 056513.
[28] JANG D P, FAZILY P, YOON J W.Machine Learning-Based Constitutive Model for J2-Plasticity[J]. International Journal of Plasticity, 2021, 138: 102919.
[29] QIAO L, DENG Y, WANG Y, et al.A Comparative Study on Arrhenius Equations and BP Neural Network Models to Predict Hot Deformation Behaviors of a Hypereutectoid Steel[J]. IEEE Access, 2020, 8: 68083-68090.
[30] 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 Y H, LUO S M, DONG X J, 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.
[31] 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.
[32] CAI Z M, JI H C, PEI W C, et al.Constitutive Model of 3Cr23Ni8Mn3N Heat-Resistant Steel Based on back Propagation (BP) Neural Network (NN)[J]. Metalurgija, 2019, 58: 191-195.
[33] LIU J T, CHANG H B, HSU T Y, et al.Prediction of the Flow Stress of High-Speed Steel during Hot Deformation Using a BP Artificial Neural Network[J]. Journal of Materials Processing Technology, 2000, 103(2): 200-205.
[34] 于清波, 李建明, 杨月冰, 等. TA15钛合金低温力学性能及J-C本构模型的研究[J]. 工具技术, 2024, 58(4): 77-83.
YU Q B, LI J M, YANG Y B, et al.Study on Cryogenic Mechanical Properties and J-C Constitutive Model of TA15 Titanium Alloy[J]. Tool Engineering, 2024, 58(4): 77-83.
[35] 张云波. 典型钛合金极低温下的变形机理研究[D]. 西安: 西安理工大学, 2024.
ZHANG Y B.Study on Deformation Mechanism of Typical Titanium Alloy at Extremely Low Temperature[D]. Xi’an: Xi’an University of Technology, 2024.
[36] 李佳怡. 双相钛合金超低温塑性变形行为与机理研究[D]. 北京: 北方工业大学, 2024.
LI J Y.Study on Ultra-Low Temperature Plastic Deformation Behavior and Mechanism of Dual-Phase Titanium Alloy[D]. Beijing: North China University of Technology, 2024.
[37] HU J W, CHEN X, WANG Y S, et al.Mechanical Properties and Flow Stress Constitutive Relationship of Ti-6Al-4V Alloy with Equiaxed Microstructure at Cryogenic Temperatures[J]. Chinese Journal of Aeronautics, 2025, 38(1): 103238.
[38] ZHU Y T, LIAO X Z, WU X L.Deformation Twinning in Nanocrystalline Materials[J]. Progress in Materials Science, 2012, 57(1): 1-62.
[39] NIU H Z, LIU S, ZANG M C, et al.Anomalous Strain Rate Dependence of Ultra-Low Temperature Strength and Ductility of an Electron Beam Additively Manufactured near Alpha Titanium Alloy[J]. Journal of Materials Science & Technology, 2024, 198: 44-55.
[40] NAYAN N, SINGH G, ANTONY P T, et al.Cryogenic Mechanical Properties of Warm Multi-Pass Caliber-Rolled Fine-Grained Titanium Alloys: Ti-6Al-4V (Normal and ELI Grades) and VT14[J]. Metallurgical and Materials Transactions A, 2018, 49(1): 128-146.
[41] SHIN S, ZHU C Y, VECCHIO K S.Observations on {332} Twinning-Induced Softening in Ti-Nb Gum Metal[J]. Materials Science and Engineering: A, 2018, 724: 189-198.
[42] LEI L, ZHU Q W, ZHAO Q Y, et al.Low-Temperature Impact Toughness and Deformation Mechanism of CT20 Titanium Alloy[J]. Materials Characterization, 2023, 195: 112504.
[43] 赵玥滔. TC4钛合金低温变形组织与性能研究[D]. 哈尔滨: 哈尔滨理工大学, 2023.
ZHAO Y T.Study on Microstructure and Properties of TC4 Titanium Alloy Deformed at Low Temperature[D]. Harbin: Harbin University of Science and Technology, 2023.
[44] GUO M Q, ZHANG Y, ZHOU C, et al.The Transition from Strain Rate Insensitivity to Sensitivity of Ti-6Al-4V Alloys Deformed at Cryogenic Temperature[J]. Materials Science and Engineering: A, 2024, 902: 146627.
[45] 梁强, 张贤明, 李平, 等. 基于修正Arrhenius模型和SVR-PSO模型的HNi55-7-4-2合金高温本构模型的对比[J]. 材料热处理学报, 2020, 41(8): 157-165.
LIANG Q, ZHANG X M, LI P, et al.Comparative of High-Temperature Constitutive Model of HNi55-7-4-2 Alloy Based on Modified Arrhenius Model and SVR-PSO Model[J]. Transactions of Materials and Heat Treatment, 2020, 41(8): 157-165.
[46] 梁强, 张贤明, 李平, 等. 基于修正Arrhenius模型和SVR-PSO模型的HNi55-7-4-2合金高温本构模型的对比[J]. 材料热处理学报, 2020, 41(8): 157-165.
LIANG Q, ZHANG X M, LI P, et al.Comparative of High-Temperature Constitutive Model of HNi55-7-4-2 Alloy Based on Modified Arrhenius Model and SVR-PSO Model[J]. Transactions of Materials and Heat Treatment, 2020, 41(8): 157-165.
[47] 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 P, FENG W.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.
[48] 娄淑梅, 李一明, 李鑫, 等. 基于BP神经网络和Arrhenius本构模型的石墨烯/7075复合材料热变形行为[J]. 吉林大学学报(工学版), 2024, 54(5): 1237-1245.
LOU S M, LI Y M, LI X, et al.Thermal Deformation Behavior of Graphene Nanosheets Reinforced 7075Al Based on BP Neural Network and Arrhenius Constitutive Equation[J]. Journal of Jilin University (Engineering and Technology Edition), 2024, 54(5): 1237-1245.

Funding

National Natural Science Foundation of China (52475394, 52075386); Tianjin Natural Science Foundation of China-Multi-input Key Projects (22JCZDJC00650)