Predicting Austenite Yield Strength in Steels by using Artificial Intelligence

NOVEMBER 2-4, 2025 NANJING, JIANGSU PROVINCE, CHINA THE 9th INTERNATIONAL CONFERENCE ON HIGH STRENGTH LOW ALLOY STEELS PROCEEDINGS HSLA Steels 2025 Organized by The Chinese Society for Metals (CSM) Co-organized by Nanjing Iron & Steel Co., Ltd. Supported by CBMM | Niobium Vanitec-CISRI Vanadium Technology Center The Vanadium International Technical Committee (VANITEC) CITIC Metal Co., Ltd. State Key Laboratory of Metallic Materials for Marine Equipment and Applications Committees Organized by The Chinese Society for Metals (CSM) Co-organized by Nanjing Iron & Steel Co., Ltd. Supported by CBMM | Niobium Vanitec-CISRI Vanadium Technology Center The Vanadium International Technical Committee (VANITEC) CITIC Metal Co., Ltd. State Key Laboratory of Metallic Materials for Marine Equipment and Applications Conference Structure Honorary Chairman Yuqing Weng, The Chinese Society for Metals Conference Chairman Xiaogang Zhang, The Chinese Society for Metals Conference Vice Chairmen Zhiling Tian, The Chinese Society for Metals Chengjia Shang, University of Science & Technology Beijing International Advisory Board Harry Bhadeshia, University of Cambridge, UK Wolfgang Bleck, RWTH Aachen University of Technology, Germany Julie Cairney, The University of Sydney, Australia Tadashi Furuhara, Tohoku University, Japan Junyan Fu, CITIC Metal Co., Ltd., China Robert (Bob) Glodowski, RJG Metallurgical LLC, USA Xinping Mao, University of Science & Technology Beijing, China Rafael Mesquita, CBMM | Niobium, Brazil John Speer, Colorado School of Mines, USA Fumitaka Tsukihashi, The University of Tokyo, Japan Guodong Wang, Northeast University, China Fucheng Zhang, North China University of Science and Technology, China International Scientific Committee Chairmen: Aimin Guo, CITIC Metal Co., Ltd., China Caifu Yang, Central Iron & Steel Research Institute Company Limited, China Members: Frank John Barbaro, University of Wollongong, Australia Shaohui Chen, Jiangsu Shagang Group, China David Crowther, Vanitec Ltd., UK Haiwen Luo, University of Science & Technology Beijing, China Mingxin Huang, The University of Hong Kong (HKU), HK, China Hardy Mohrbacher, NiobelCon bvba, Belgium Jitendra Patel, International Metallurgy Ltd., UK Elena Pereloma, University of Wollongong, Australia Mingliang Qiao, Nanjing Iron & Steel Co., Ltd., China Jose-Maria Rodriguez-Ibabe, CEIT, Spain Qingyun Sha, Ansteel Group, China Colin Scott, CanmetMATERIALS, Canada Dong-Woo Suh, POSTECH, Korea Jing Wang, Hunan Iron & Steel Group Co., Ltd., China Guosen Zhu, Shougang Group Co., Ltd., China Li Wang, China Baowu Group, China Kaiming Wu, Wuhan University of Science and Technology, China Wei Xu, Northeast University, China Jian Yang, Shanghai University, China Zhigang Yang, Tsinghua University, China Guo Yuan, Northeast University, China Hongliang Yi, Northeast University, China Caidong Zhang, HBIS Group Co., Ltd., China Secretary-General Xinjiang Wang, The Chinese Society for Metals Deputy Secretary-General Zhongzhu Liu, CITIC Metal Co., Ltd., China Xuehui Chen, Central Iron & Steel Research Institute Company Limited, China Preface This is a collection of papers presented at the 9th International Conference on High Strength Low Alloy Steels (HSLA Steels 2025). HSLA Steels 2025 is organized by The Chinese Society for Metals, co-organized by Nanjing Iron & Steel Co., Ltd. and supported by CBMM | Niobium, CITIC Metal Co., Ltd., Vanitec-CISRI Vanadium Technology Center, Vanitec Ltd. and State Key Laboratory of Metallic Materials for Marine Equipment and Applications. The HSLA Steels conference series has been successfully organized by The Chinese Society for Metals in Beijing (1985, 1990, 1995, 2011, 2022), Xi’an (2000), Sanya (2005) and Hangzhou (2015) since 1985 and grown into the leading platform for scientific and technological exchange in HSLA Steels. With an initial submission of more than 150 abstracts from 12 countries for HSLA Steels 2025, after peer review process there are 50 papers published in these proceedings, which cover the following fields: (1) Physical Metallurgy (2) Products for Automotive, Infrastructure and Maritime Industry (3) Performance, Safety and Application (4) Process Technologies for High Quality Products. We would like to express our sincere gratitude to the International Advisory Board and Scientific Committee for their valuable suggestions and support. We are very grateful to Mr. Xin Zhao and Ms. Fang Liu from CSM, Dr. Zhongzhu Liu, Dr. Guodong Zhang and Dr. Yongqing Zhang from CITIC Metal, Dr. Tao Pan, Dr. Xuehui Chen from CISRI, Dr. Zhenjia Xie from USTB, Dr. Linheng Chen, Dr. Yi Fan and Ms. Xiaohui Wu from Nanjing Iron & Steel Co., Ltd. for their contributions to the conference planning and management. We also thank Metallurgical Industry Press for preparing the proceedings. Finally, we acknowledge the financial support from Nanjing Iron & Steel Co., Ltd., CBMM | Niobium, CITIC Metal Co., Ltd., Vanitec-CISRI Vanadium Technology Center and Vanitec Ltd. to the publication. Prof. Zhiling Tian Prof. Chengjia Shang Executive Chairmen of HSLA Steels 2025 Beijing, October, 2025 ·III· Contents Contents Plenary Lecture 003 Niobium-Driven Innovations in Advanced Steels Rafael Mesquita, Jose Bacalhau, Caio Pisano, Roney Lino, Wenjun Wang 010 Vanadium in Modern Steels: A Versatile Microalloying Element for Enhanced Strength, Toughness, and Wear Resistance Yu Li, David N. Crowther Physical Metallurgy for Innovation 019 Dual-Phase Steel Strengthened by Interphase-Precipitated TiC Nanocarbides Jer-Ren Yang 025 Modelling Microstructure Evolution in Line Pipe Steels M. Militzer, W. J. Poole, M.Y. Tseng, J. Swan, S. Roy, R. Birch, S. Patel, M. Gaudet 026 Reduced Operational Costs and Lower Embodied Carbon for Commodity Grade Steels Using Ultra Low Niobium (ULNb) Alloying Solution Dr Jitendra Patel Eng.D, MBA, C.Eng., FIMMM 032 Microstructural Understanding in Low-Carbon Bainitic Steels D. de Castro, F. G. Caballero, D. San Martín, C. Capdevila 035 Microstructure Characterization of SM570 Steel Plate and Exploration of Its Mechanical Property Improvement by Adding Appropriate Amounts of Alloying Elements Changching Ho, Shinghoa Wang, Jerren Yang, Pohan Chiu, Tzuching Tsao 038 Strengthening Scenarios in Heavy-Gaged Plate Steel Using Niobium, Molybdenum, Nickel and Boron Alloying Hardy Mohrbacher 043 Impact of Nb and V on Nanoprecipitate Formation in Novel Advanced Ferritic-Martensitic Steels Javier Vivas, David San-Martín, David De-Castro, Eberhard Altstadt, Martin Houska, Esteban Urones-Garrote, Francisca G. Caballero, Marta Serrano, Rebeca Hernández, Carlos Capdevila 046 Effect of Cooling Temperature on Strength and Microstructure of Hot Rolled S760 Steel for Industrial Applications D. Sidorenko, M.Y. Rekha, B. Lin, B. Ehrhardt, E. Poliak 049 Effective Improvement in Mechanical Properties of Medium Mn Steel by Warm Rolling Yan Zhang, Yu Yan ·IV· Contents 051 Study on the Influence of Residual Elements on HC420LA Yuqiao Zhao, Pengfei Gao, Xin Xu, Xuming Liu, Shengrui Su, Bingquan Ai, Junsheng Wang 055 Effect of Electrochemical Hydrogen Charging on Precipitation in 6061 Aluminum Alloy Myeongjin Lee, Junyoung Chae, Siwhan Lee, Heungnam Han 058 Achieving High Strength and High Ductility of Dual-Phase Steel via Alternating Lamellar Microstructure Gang Niu, Chao Ding, Mengjie Wamg, Aicheng Liu, Huibin Wu 062 Devlopment of GPa Grade Galvanized Multi-phase Steel Bearing Nb Bingquan Ai, Xuming Liu, Pengfei Gao, Zhiyu Geng, Jingjing Wang 066 Elucidation of the Mechanism Governing Electrochemically-Induced Martensitic Transformation Junyoung Chae, Guihyung Lee, Hyukjae Lee, Yeonggeun Cho, Dameul Jeong, Young-Kyun Kwon, In-Ho Jung, Sung-Joon Kim, Heung Nam Han 069 Metallurgical Functionalities of Microalloys during Annealing of Cold Rolled Automotive Steel Hardy Mohrbacher and Caio Pisano 074 Effect of Thermomechanical Processing Parameters on the Microstructure of High Strength Low Alloyed Steel Gholam Ali Baqeri, Chris Killmore, Elena Pereloma 075 Study on Improving Vanadium Precipitation Rate for Vanadium Microalloyed Power Angle Steel Fu Han, Junhua Qiu, Hui Wen, Wei Deng 081 Research on the Continuous Cooling Phase Transformation Behavior of Medium Manganese Steel Yu Du , Tao Liu , Yuwei Zhou , Xiuhua Gao , Hongyan Wu , Linxiu Du 084 The Performance and Microstructure of 11MnNiMoDR Steel Plate for Low-temperature Pressure Vessels Lianyun Xi, Zhanglong Xie, Jie Yin, Junzhou Ji, Zhengyang Wu 090 Effect of Ni on the Transformation Behavior of Undercooled Austenite in Si-Mn-Cr-B System High-Strength Spring Steel Hongwei Zheng, Wei Deng, Ye Jiang, Yang Wang 094 Microstructure and Performance of Ti Deoxidized Low Carbon Steel Zhu Yan, Chao Wang, Guo Yuan 096 Effect of Microalloying System and Hot Rolling Parameters on the Strength of Low Carbon Steels Dagman A.I., Koldaev A.V., Naumenko V.V., Arutyunyan N.A., Matrossov M.Yu. 097 Microstructure and Mechanical Properties of Cu-bearing Medium Mn Steel Via Intercritical Quenching and Tempering Process Yunzi Yan, YunBo Xu, Jiayu Li, Hao Hu 102 Analysis of Surface Crack of High Strength Austenitic Stainless Steel Continuous Casting Billet Kunyu Wang, Yu Zhang, Xiangyu Zhang, Dong Pan ·V· Contents Performance, Safety and Application 109 Development of a Prototype Steel for a New Type of Ultra-high Strength Austenitic Non-magnetic Stainless Steel Dong Pan, Yu Zhang, Xiangyu Zhang, Kunyu Wang 112 Low Temperature Mechanical Properties of 460MPa Polar Ship Steel and Its Welded Joints Wang Chaoyi, Yan Lin, LI Wenbing, Zhang Ning 119 Microstructure and Mechanical Properties of 1000MPa Low-carbon Bainite-martensitic Steel Welded Joints Xingjian Ma, Zhenyu Fei, Jingjie Wang, Yi Fan, Wei Li 121 Influence of Cr Content on Corrosion Resistance of Supercritical CO2 Pipeline Steel Ba Li, Qilin Ma, Shujun Jia, Bing Wang, Qingyou Liu, Chengjia Shang 123 Mechanism of Cementite Morphology in Enhancing Plasticity of EH 40 Hull-Structural Steel Zhongran Shi, Qiang Wang, Zuoning Chen, Qing Yu, Zhongwen Wu, Zhen Wang Process Technologies for High Quality 133 Effects of Heat Treatment Processing on Microstructure and Properties of 410S+Q345R Clad Plate Shan Jiang, Zhouyu Zeng, FeilongWang 136 Predicting Austenite Yield Strength in Steels by using Artificial Intelligence Isaac Toda-Caraballo, Carlos Garcia-Mateo 139 Multi-scale Simulation and Machine Learning-Based Toughness Prediction of HSLA Weld CGHAZ Zhixing Wang 142 Effect of Intercritical Annealing on Tensile Properties of Cr Alloying Medium-Mn Steel Shengrui Su, Pengfei Gao, JingjingWang, Bingquan Ai, Yuqiao zhao 146 Physics-Informed Machine Learning for Predicting Strength and Flow Behavior of Steels Shasha Zhang, Changqing Shu, Guojin Xiang, Zhengjun Yao 150 Influence of Nb, V and Ti Microalloying on Microstructure and Mechanical Properties of Hot Stamping Steel Zhang Xiangyu, Qin Zhe, Zhang Yu, Pan Dong Wang Kunyu, Li Zhihui 156 Research on Key Technologies for Optimizing Processes and Enhancing Production Capacity of Thin Plates Heat Treatment An Jiale Process Technologies for High Quality 2025 ·136· Process Technologies for High Quality Predicting Austenite Yield Strength in Steels by using Artificial Intelligence Isaac Toda-Caraballo, Carlos Garcia-Mateo (Materalia Group, Centro Nacional de Investigaciones Metalúrgicas (CENIM), Consejo Superior de Investigaciones Científicas (CSIC), Avda. Gregorio del Amo 8, 28040 Madrid, Spain) Abstract: The accurate control of austenite hot deformation requires reliable prediction of yield strength in order to design thermomechanical treatments to optimize the final properties of steels. This has motivated extensive efforts to develop predictive models in the past. Such models have demonstrated good accuracy, but their applicability has been limited to narrow compositional ranges or inaccurate evolution with temperature, largely constrained by the scope of the databases used for calibration. Therefore, when tested against broader datasets encompassing wider temperature and compositional variations, these models exhibit significant deviations. Moreover, strain rate—an influential factor in mechanical behavior—has often been overlooked in earlier approaches. In this study, we present a more comprehensive and robust model that incorporates strain rate effects and extends the compositional and temperature ranges. By integrating physical based methods and artificial intelligence architectures, the model presented significantly enhances the accuracy of yield strength prediction. Key words: yield strength, austenite, machine learning, mechanical properties 1 Introduction The accurate prediction of austenite yield strength is essential for optimizing thermomechanical treatments in steel manufacturing. Traditional models have often been limited by narrow compositional ranges and have neglected the influence of strain rate, which significantly affects mechanical behavior. This work presents a comprehensive and integrated model that accounts for composition, temperature, and strain rate, aiming to improve the prediction accuracy of austenite yield strength across a wide range of lean steels. 2 Database and Review of Existing Models A robust database comprising 845 yield strength measurements from 80 different steels was compiled. These measurements were primarily obtained from compression tests using dilatometers, ensuring consistent methodology. The dataset spans a wide range of temperatures (200–1100℃), strain rates (0.003–11s–1), and chemical compositions, making it suitable for developing a generalized model[1]. Several existing models were evaluated, including those by Irvine[2], Young et al.[3], Azuma, and van Bohemen[4]. While these models incorporate composition and temperature effects, they lack generalizability and do not account for strain rate. Modified versions of Young and van Bohemen’s models were tested, but they still showed limitations, especially at high temperatures and strain rates. 3 Computational Development of the Proposed Model The authors developed two new formulations based on established flow behavior models: Johnson-Cook ·137· Predicting Austenite Yield Strength in Steels by using Artificial Intelligence (JC)[5,6] and Modified Zerilli-Armstrong (MZA)[7]. These were adapted to predict yield strength without considering plastic strain, focusing solely on temperature and strain rate effects. The two considered expressions are fitted by using Machine Learning techniques from the database considered are: 0.658 (52.3 47 31.3 1 1 31.3 1.3 10.7 3.8 16.8 15.2 53( 34)) 1 0.001 1 0.001 1487 25 Y JC c Si Mn Cr Mo Ni V Al Vu Ti r XXXX XX XX X X T ln                            (1) 5 (52.6 50.7 34.1 0.9 0.6 4.1 2.3 12.3 6.5 19.1 17.4 53( 34)) 0.0014? (0.0111 2.2 10 )ln 0.001 Y MZA c Si Mn Cr Mo Ni V Al Vu Ti r r XXX XX X XX X XexpT T                         (2) Where XY represents the at.% content of element Y, Tr is the temperature increase with respect to room temperature and   is the strain rate. The performance of each model can be seen in Figure 1, where the experimental vs. the calculated σY are depicted. Four groups (denoted 1, 2, 3 and 4) are identified based on the different compositional ranges, where the main differences arise by the C content. Group 1 contains low C around 1wt.%, group 2 and 3 contains C around 1-2wt.% with low Si and high Si respectively, and group 4 represents steels with high C content. Figure 1 Experimental vs. calculated σY calculated according to Eqs. (1) and (2). To make the plot clearer, the whole dataset has not been plotted. Instead, the data of steels whose composition is extremely close (close enough not to obtain significant variations of yield strength according to the model) has been averaged, with the horizontal lines representing the confidence interval (Experimental Standard Error). The color of each point represents εHP which represents the confidence interval associated with the grain boundaries strengthening Using K-Fold Cross-Validation (K=10), the JC-based model (Eq. 18) showed superior predictive performance with lower mean squared error and relative error. The model was further validated using unseen experimental data, confirming its robustness across different steels and conditions. In order to have in insight about the model physical meaning of the approach, the model’s coefficients were compared models predicting the solid solution strengthening from previous approaches[8]. This suggests that the model not only fits the data well but also aligns with metallurgical principles. 4 Conclusion The integrated model proposed in this study significantly improves the prediction of austenite yield strength by incorporating strain rate effects, covering a wide compositional and temperature range and demonstrating physical consistency and generalizability. Equation (1), based on the JC model, is recommended for practical applications due to its lower prediction error and broader applicability ·138· Process Technologies for High Quality Acknowledgement The authors gratefully acknowledge the support of the European Research Fund for Coal and Steel under the Contract RFCS-02-2022-RPJ No 101112425. Isaac TodaCaraballo would like to thank to the DIGImeTAL project (Ref: TED2021-132214B-I00), from the Proyectos Estratégicos Orientados a la Transición Ecológica y a la Transición Digital 2021, funded by the Plan de Recuperación, Transformación y Resiliencia, Spanish Ministerio de Ciencia, Innovación y Universidades. The authors are also grateful to the Digital Laboratory of Metallurgy from CENIM-CSIC and the access to the high-performing server facilities. References [1] Adriana Eres-Castellanos, An integrated-model for austenite yield strength considering the influence of temperature and strain rate in lean steels, Mat. Design 188 (2020) 108435 [2] K. Irvine, The strength of austenitic stainless steels, J. Iron Steel Inst. 207 (1969),1017–1028. [3] S. van Bohemen, Exploring the correlation between the austenite yield strength and the bainite lath thickness, Mater. Sci. Eng. A 731 (2018) 119–123. [4] M. Azuma, N. Fujita, M. Takahashi, T. Senuma, D. Quidort, T. Lung, Modelling upper and lower bainite trasformation in steels, ISIJ Int. 45(2) (2005) 221–228. [5] G.R. Johnson, A constitutive model and data for materials subjected to large strains, high strain rates, and high temperatures, Proc. 7th Inf. Sympo. Ballistics 1983, pp. 541–547. [6] G.R. Johnson, W.H. Cook, Fracture characteristics of three metals subjected to various strains, strain rates, temperatures and pressures, Eng. Fract. Mech. 21(1) (1985) 31–48. [7] F.J. Zerilli, R.W. Armstrong, Dislocation-mechanics-based constitutive relations for material dynamics calculations, J. Appl. Phys. 61 (5) (1987) 1816–1825. [8] I. Toda-Caraballo, A general formulation for solid solution hardening effect in multicomponent alloys, Scr. Mater. 127 (2017) 113–117. Products for the Automotive, Energy, Infrastructure and Maritime Industry, etc. 2025 ·213· Author Index Author Index A Aicheng Liu ········································ 058 An Jiale ············································· 156 Arutyunyan N.A. ·································· 096 B B. Ehrhardt ········································· 046 B. Lin ··············································· 046 Ba Li ·········································· 121, 194 Bangming Qin ····································· 162 Bing Wang ··································· 121, 194 Bingquan Ai ··························· 051, 062, 142 C C. Capdevila ······································· 032 C.Eng. ··············································· 026 Caio Pisano ·································· 003, 069 Carlos Capdevila ·································· 043 Carlos Garcia-Mateo ·················· 136, 196, 200 Changching Ho ···································· 035 Changqing Shu ···································· 146 Chao Ding ·········································· 058 Chao Wang ········································· 094 Chengjia Shang ···································· 121 Chris Killmore ····································· 074 Chunxia Tang ······································ 186 D D. de Castro ······································· 032 D. San Martín ····································· 032 D. Sidorenko ······································ 046 Dagman A.I. ······································· 096 Dameul Jeong ····································· 066 Dan Guo ··········································· 159 David De-Castro ·································· 043 David N. Crowther ······························· 010 David San-Martín ································· 043 Deunbom Chung ·································· 181 Dong Pan ···································· 102, 109 Dr Jitendra Patel Eng.D ·························· 026 E E. Poliak ··········································· 046 Eberhard Altstadt ································· 043 Elena Pereloma ··································· 074 Esteban Urones-Garrote ························· 043 F F. G. Caballero ···································· 032 FeilongWang ······································ 133 FIMMM ············································ 026 Francisca G. Caballero ··························· 043 Fu Han·············································· 075 ·220· Subject Index refining ············································ 162 residual elements ································· 051 retained austenite ································ 081 retransformation ·································· 069 run-out table cooling ···························· 046 S SHCCT diagram ································· 119 Si-Mn-Cr-B ······································· 090 SM570 steel ······································ 035 spheroidization ··································· 123 spray height ······································· 159 SSRT ·············································· 194 steel for large diameter pipes ··················· 172 steel ················································ 026 steels ··············································· 146 strength ············································ 146 strength-ductility synergy ······················· 058 supercritical CO2 pipeline steel ················ 121 surface defect ····································· 159 sustainability ······································ 003 T tempering temperature ·························· 123 tempering ········································· 038 tensile properties ································· 097 tensile strength ··································· 051 thermal simulation ······························· 139 thermo-mechanical processing ················· 074 Ti-Oxide ·········································· 094 TMCP ··············································112 transformation behavior of undercooled austenite ·················································· 090 transformation kinetics ·························· 066 transformation ···································· 038 transmission electron microscope ············· 035 transmission electron microscopy ············· 019 U ULNb ·············································· 026 Ultra grade R6 steel ····························· 189 Ultrafine compound carbides ··················· 189 uniform elongation ······························ 172 V V microalloyed ··································· 075 vanadium microalloying ························ 010 W wear resistance ··································· 010 weld toughness ··································· 010 weldability ········································ 003 welding thermal cycle ····························119 Y Yield ratio controllable chain ·················· 189 yield strength ······························· 136, 142