Machine Learning-Based Prediction of Impact Toughness in AISI 430–AISI 304 Friction-Welded Joints

Jagadesh Kumar Jatavallabhula; Vasudeva Rao Veeredhi; Gundeti Sreeram  Reddy; Ravinder Reddy Baridula; Vaddi Venkata Satyanarayana

doi:10.15282/ijame.22.1.2025.13.0930

Authors

Jagadesh Kumar Jatavallabhula Department of Mechanical, Bioresources and Biomedical Engineering, College of Science, Engineering and Technology, University of South Africa, Florida Campus, Johannesburg, South Africa
Vasudeva Rao Veeredhi Department of Mechanical, Bioresources and Biomedical Engineering, College of Science, Engineering and Technology, University of South Africa, Florida Campus, Johannesburg, South Africa
Gundeti Sreeram Reddy Department of Mechanical Engineering, Vidya Jyothi Institute of Technology, Aziznagar, Hyderabad, India
Ravinder Reddy Baridula Department of Mechanical Engineering, Vidya Jyothi Institute of Technology, Aziznagar, Hyderabad, India
Vaddi Venkata Satyanarayana Department of Mechanical Engineering, Vidya Jyothi Institute of Technology, Aziznagar, Hyderabad, India

DOI:

https://doi.org/10.15282/ijame.22.1.2025.13.0930

Keywords:

Friction welding, Impact toughness, Machine learning, Random forest, Taguchi analysis

Abstract

Friction welding is a solid-state joining technique widely used for dissimilar materials due to its efficiency and cost-effectiveness. However, welding AISI 430 ferritic and AISI 304 austenitic stainless steels poses challenges due to their differences in chemical composition and mechanical properties, particularly in achieving optimal impact toughness. Existing studies focus on optimizing process parameters but lack predictive modeling for impact toughness using machine learning (ML). This study aims to bridge this gap by experimentally evaluating the impact toughness of friction-welded AISI 430–AISI 304 joints and developing ML models for accurate prediction. Experiments were designed using a Taguchi L32 orthogonal array, varying friction force, forge force, and burn-off. Charpy impact tests were performed to assess toughness, and the results were used to train Decision Tree, Random Forest, and Gradient Boosting regression models. Random Forest regression outperformed others with an R² value of 0.98 and a mean squared error of 0.29. The predicted impact toughness (15.8 J) closely matched the value from the confirmation experiment (16 J) with only a 1.25% deviation. The findings demonstrate that ML can significantly enhance process optimization, reducing reliance on costly experimental runs. Future research should explore additional welding parameters and deep learning models for further improvements.

References

[1] Guo G, Shen Y, “Microstructure and mechanical properties of friction stir welded austenitic-ferritic stainless steels using staggered joint configuration,” Journal of Materials Engineering and Performance, vol. 29, pp. 5263-5272, 2020.

[2] Byeong-heon Kim, Ki-hwan Kim, Young-jin Kang, Sung-shin Kim, Hee-je Kim, “Hastelloy C276/AISI SS304 dissimilar metal welding: A comparative review of the effective application of laser and Micro-GTAW,” Journal of Materials Research and Technology, vol. 32, pp. 621-633, 2024.

[3] H. T. Serindağ and G. Çam, “Microstructure and mechanical properties of gas metal arc welded AISI 430/AISI 304 dissimilar stainless steels butt joints,” Journal of Physics: Conference Series, vol. 1777, no. 1, p. 012047, 2021.

[4] S. Emami, S. Sadeghi-Kanani, T. Saeid, and F. Khan, “Dissimilar friction stir welding of AISI 430 ferritic and AISI 304L austenitic stainless steels,” Archives of Civil and Mechanical Engineering, vol. 20, no. 131, pp. 1-16, 2020.

[5] G. M. Reddy and K. S. Rao, “Microstructure and mechanical properties of similar and dissimilar stainless steel electron beam and friction welds,” Int. J. Adv. Manuf. Technol., vol. 45, pp. 875-888, 2009.

[6] Y. I. Karlina, R. V. Kononenko, V. V. Ivancivskiy, M. A. Popov, F. F. Deryugin, and V. E. Byankin, “Overview of modern requirements for welding of high-strength low-alloy pipe steels,” Processing of Metals, vol. 25, no. 4, pp. 36-60, 2023.

[7] A. Zambrano, “A review on the effect of impact toughness and fracture toughness on impact-abrasion wear,” Journal of Materials Engineering and Performance, vol. 30, no. 10, pp. 7101-7116, 2021.

[8] K. Kim, M. Park, J. Jang, H. C. Kim, H.-S. Moon, D.-H. Lim, J. B. Jeon, S.-H. Kwon, H. Kim, and B. J. Kim, “Improvement of strength and impact toughness for cold-worked austenitic stainless steels using a surface-cracking technique,” Metals, vol. 8, no. 11, p. 932, 2018.

[9] Z. L. Hou, H. Q. Guo, J. J. Wang, Z. Y. Huang, Z. A. Wang, D. S. Fang, and J. Qiao, “Research on the low-temperature impact toughness of a new 100-mm ultra-thick offshore steel fabricated using the narrow-gap laser wire filling welding process,” Materials, vol. 17, no. 6, p. 1363, 2024.

[10] P. Luo, W. Feng, G. Zu, L. Luo, and J. Xiao, “Microstructure and impact toughness of laser-arc hybrid welded joint of medium-thick tc4 titanium alloy,” Coatings, vol. 14, no. 4, p. 395, 2024.

[11] O. Tunçel, “Optimization of charpy impact strength of tough pla samples produced by 3D printing using the taguchi method,” Polymers, vol. 16, no. 4, p. 459, 2024.

[12] S. S. Abdelhady, R. E. Elbadawi, and S. H. Zoalfakar, “Multi-objective optimization of FSW variables on joint properties of AA5754 aluminum alloy using Taguchi approach and grey relational analysis,” The International Journal of Advanced Manufacturing Technology, vol. 130, pp. 4235-4250, 2024.

[13] W. Safeen, S. Hussain, A. Wasim, M. Jahanzaib, H. Aziz, and H. Abdalla, “Predicting the tensile strength, impact toughness, and hardness of friction stir-welded AA6061-T6 using response surface methodology,” International Journal of Advanced Manufacturing Technology, vol. 87, pp. 1765-1781, 2016.

[14] Devaraj, Jeyaganesh, Aiman Ziout, Jaber E. Abu Qudeiri, Rashfa A Baalfaqih, Nasmah Baalfaqh, Kanna Alahbabi, Maitha Alnaqbi, Noura Alhosan, “Using machine learning models to predict weld sequence giving minimum distortion,” Advances in Science and Engineering Technology International Conferences (ASET), Dubai, UAE, pp. 1-6, 2022.

[15] G. Chen, B. Sheng, R. Luo, and P. Jia, “A parallel strategy for predicting the quality of welded joints in automotive bodies based on machine learning,” Journal of Manufacturing Systems, vol. 62, pp. 636–649, 2022.

[16] Y. Chen et al., “Identifying facile material descriptors for Charpy impact toughness in low-alloy steel via machine learning,” Journal of Materials Science and Technology, vol. 132, pp. 213-222, 2023.

[17] S. Wei Wu, J. Yang, and G. Ming Cao, “Prediction of the Charpy V-notch impact energy of low carbon steel using a shallow neural network and deep learning,” International Journal of Minerals, Metallurgy and Materials, vol. 28, no. 8, pp. 1309-1320, 2021.

[18] Y. Diao, L. Yan, and K. Gao, “A strategy assisted machine learning to process multi-objective optimization for improving mechanical properties of carbon steels,” Journal of Materials Science and Technology, vol. 109, pp. 86-93, 2022.

[19] M. Shaban, M. F. Alsharekh, F. N. Alsunaydih, A.I. Alateyah, M.O. Alawad et al., “Investigation of the effect of ECAP parameters on hardness, tensile properties, impact toughness, and electrical conductivity of pure cu through machine learning predictive models,” Materials, vol. 15, no. 24, p. 9032, 2022.

[20] J. Pak, J. Jang, H. K. D. H. Bhadeshia, and L. Karlsson, “Optimization of neural network for charpy toughness of steel welds,” Materials and Manufacturing Processes, vol. 24, no. 1, pp. 16-21, 2009.

[21] J.F. Durodola, “Machine learning for design, phase transformation and mechanical properties of alloys,” Progress in Materials Science, vol. 123, p. 100797, 2022.

[22] A. Stoll and P. Benner, “Machine learning for material characterization with an application for predicting mechanical properties,” GAMM - Mitteilungen, vol. 44, p. e202100003, 2021.

[23] K. Guo, Z. Yang, C.-H. Yu, and M. J. Buehler, “Artificial intelligence and machine learning in design of mechanical materials,” Materials Horizons, vol. 8, no. 4, pp. 1153-1172, 2021.

[24] M. Smyrnov, F. Funcke, and E. Kabliman, “Prediction of material toughness using ensemble learning and data augmentation,” Philosophical Magazine Letters, vol. 104, no. 1, p. 2372497, 2024.

[25] G. Xu, X. Zhang, and J. Xu, “Data augmentation of micrographs and prediction of impact toughness for cast austenitic steel by machine learning,” Metals, vol. 13, no. 1, p. 107, 2023.

[26] Z. Sabouri, N. Gherabi, and M. Amnai, “Comparative study of supervised regression algorithms in machine learning,” in Advances in Intelligent System and Smart Technologies, N. Gherabi, A. I. Awad, A. Nayyar, and M. Bahaj, Eds. Cham, Switzerland: Springer, vol. 826, pp. 365-374, 2024, Lecture Notes in Networks and Systems.

[27] Costa, V.G., Pedreira, C.E., “Recent advances in decision trees: an updated survey,” Artificial Intelligence Review, vol. 56, pp. 4765-4800, 2023.

[28] Iranzad, R., Liu, X., “A review of random forest-based feature selection methods for data science education and applications,” International Journal of Data Science and Analytics, vol. 2024, pp. 1-15, 2024.

[29] Bentéjac C, Csörgő A, Martínez-Muñoz G, “A comparative analysis of gradient boosting algorithms,” Artificial Intelligence Review, vol. 54, pp. 1937-1967, 2021.

[30] Hosseinpoor S, Sheikhmohammadi A, Rasoulzadeh H, Saadani M, Ghasemi SM, Alipour MR, Hadei M, Zarch SM, “Comparison of modeling, optimization, and prediction of important parameters in the adsorption of cefixime onto sol-gel derived carbon aerogel and modified with nickel using ANN, RSM, GA, and SOLVER methods,” Chemosphere, vol. 353, p. 141547, 2024.

[31] Jian Gao, “R-Squared (R2) – How much variation is explained?” Research Methods in Medicine & Health Sciences, vol. 5, no. 4, pp. 104-109, 2024.

[32] Prateek, S., Garg, R., Kumar Saxena, K., Srivastav, V. K., Vasudev, H., Kumar, N., “Data-driven materials science: application of ML for predicting band gap,” Advances in Materials and Processing Technologies, vol. 10, no. 2, pp. 708-717, 2023.

[33] Chu, T.K., Ho, C.Y., “Thermal conductivity and electrical resistivity of eight selected AISI stainless steels,” Thermal Conductivity 15, pp. 79-104, Springer, 1978.

[34] V. Ajay, N. Kishore Babu, M. Ashfaq, T. Mahesh Kumar, K. Vamsi Krishna, “A review on rotary and linear friction welding of inconel alloys,” Transactions of the Indian Institute of Metals, vol. 74, pp. 2583-2598, 2021.

[35] A. Atamashkin, E. Priymak, E. Tulibaev, Y. Syomka, and V. Trushov, “Influence of force parameters of rotary friction welding on the microstructure and mechanical properties of welded joints of high-strength drill pipes,” International Journal on Interactive Design and Manufacturing (IJIDeM), vol. 15, no. 6, pp. 1-13, 2024.