Interpretable Machine Learning and Genetic Algorithm-Based Optimization of Ultimate Tensile Strength And Melting Completion In Alloys

Türkoğlu, Safa Enes; Uzunoğlu, Yusuf

doi:10.2478/adms-2025-0022

Abstract

In this study, we present a comprehensive machine learning-based approach for optimizing alloy compositions with the goal of simultaneously maximizing Ultimate Tensile Strength (UTS) and approaching a target Melting Completion temperature. Using a dataset comprising elemental compositions of various alloys and their corresponding mechanical properties, we developed predictive models based on the Random Forest Regressor algorithm. SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) were employed to interpret the feature contributions and determine the most influential elements on both UTS and melting behavior. The analysis revealed that elements such as Fe, Mn, Co, and Mo significantly contribute to optimal alloy performance, while elements like C and V play a critical role in enhancing UTS. A multi-objective optimization was conducted using a Genetic Algorithm (GA), yielding an optimal composition that achieved a predicted UTS of 1520.7 psi and a Melting Completion temperature of 1407.4°C, closely aligned with the target of 1460°C. Our approach demonstrates the potential of combining interpretable machine learning with evolutionary optimization to accelerate intelligent alloy design and discovery.

References

P. Wang and G. El-Fallah, “A Data-Driven Machine Learning Model for Radiation-Induced DBTT Shifts in RAFM Steels,” Journal of Nuclear Materials, vol. 584, 2025. DOI: 10.1016/j.jnucmat.2025.155984
Search in Google Scholar Back to article
D. Dey et al., “Developing new high-entropy alloys with enhanced hardness using a hybrid machine learning approach: integrating interpretability and NSGA-II optimization,” Journal of Materials Science, vol. 60, no. 15, 2025. DOI: 10.1007/s10853-025-10729-5
Search in Google Scholar Back to article
M. Hu, “Design of New Wrought Aluminium Alloys with Improved Performance Assisted by Machine Learning,” Ph.D. Thesis, The University of Queensland, 2024. [Online]. Available: https://espace.library.uq.edu.au/view/UQ:500ce4a
Search in Google Scholar Back to article
Y. Han, H. Wang, P. Xu, Q. Chen and R. Zhang, “Deep learning-based framework for efficient design of multicomponent high-hardness high-entropy alloys,” ACS Applied Materials & Interfaces, vol. 17 (13), p. 19952-19965, 2025. DOI: 10.1021/acsami.4c23010
Search in Google Scholar Back to article
T. Song, P. Cui, T. Xia, Y. Liu and J. Zhu, “Data-driven property-oriented composition design and feature analysis of lightweight high-entropy alloys,” Journal of Alloys and Compounds, vol. 1037, 2025. DOI: 10.1016/j.jallcom.2025.182197
Search in Google Scholar Back to article
H. Bian and C. Fang, “Improved random forest for titanium alloy milling force prediction based on finite element-driven features,” Journal of the Brazilian Society of Mechanical Sciences and Engineering, vol. 46, 2024. DOI: 10.1007/s40430-024-05241-x
Search in Google Scholar Back to article
X. Geng et al., “Data-driven and artificial intelligence accelerated steel material research and intelligent manufacturing technology,” Materials Genome Engineering Advances, vol. 1(1):e10, 2023. DOI: 10.1002/mgea.10
Search in Google Scholar Back to article
H. Liu, D. Wu, F. Ding, W. Wang, S. Pan and P. Chen, “Machine learning-enhanced laser cladding process for high-entropy alloy coatings with concurrent strength and ductility optimization,” Materials Science and Engineering: A, vol. 943, 148788, 2025. DOI: 10.1016/j.msea.2025.148788
Search in Google Scholar Back to article
A. G. Kusne et al., “On-the-fly machine-learning for high-throughput experiments: search for rare-earth-free permanent magnets,” Scientific Reports, vol. 4, 6367, 2014. DOI: 10.1038/srep06367
Search in Google Scholar Back to article
Ö. Özdilli et al., “Optimal design of flat plate fin heat sinks using a computational fluid dynamics (CFD) and deep learning (DL)-based ensemble approach with explainable artificial intelligence (XAI) integration,” Applied Thermal Engineering, vol. 279, 127547, Jul. 2025. DOI: 10.1016/j.applthermaleng.2025.127547.
Search in Google Scholar Back to article
K. Qian, “Automated Detection of Steel Defects via Machine Learning based on Real-Time Semantic Segmentation,” Proc. 3rd Int. Conf. Video and Image Processing (ICVIP ‘19), Shanghai, China, 2019, pp. 42–46, DOI: 10.1145/3376067.3376113
Search in Google Scholar Back to article
S. Umbare, “Alloy Dataset,” Kaggle, 2023. [Online]. Available: https://www.kaggle.com/datasets/sohamumbare/alloy-dataset
Search in Google Scholar Back to article
L. Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. DOI: 10.1023/A:1010933404324
Search in Google Scholar Back to article
T. Lookman et al., “Active learning in materials science with emphasis on adaptive sampling using uncertainties for targeted design,” npj Computational Materials, vol. 5, 2019. DOI: 10.1038/s41524-019-0153-8
Search in Google Scholar Back to article
J. Ling et al., “High-dimensional materials and process optimization using data-driven approaches,” JOM, vol. 69, pp. 768–776, 2017. DOI: 10.1007/s40192-017-0098-z
Search in Google Scholar Back to article
S. Lundberg and S.I. Lee, “A Unified Approach to Interpreting Model Predictions,” in Advances in Neural Information Processing Systems, vol. 30, 2017. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2017/hash/8a20a8621978632d76c43dfd28b67767-Abstract.html
Search in Google Scholar Back to article
M. T. Ribeiro, S. Singh, and C. Guestrin, “Why should I trust you?”: Explaining the predictions of any classifier,” in Proc. of the 22nd ACM SIGKDD, pp. 1135–1144, 2016. DOI: 10.1145/2939672.2939778
Search in Google Scholar Back to article
M. Wu, Z. Li, B. Gault, P. Munroe and I. Baker, “The effects of carbon on the phase stability and mechanical properties of heat-treated FeNiMnCrAl high entropy alloys,” Materials Science and Engineering: A, vol. 748, pp. 59-73, 2019. DOI: 10.1016/j.msea.2019.01.083.
Search in Google Scholar Back to article
F.A. Fortin et al., “DEAP: Evolutionary Algorithms Made Easy,” Journal of Machine Learning Research, vol. 13, pp. 2171–2175, 2012. [Online]. Available: https://www.jmlr.org/papers/volume13/fortin12a/fortin12a.pdf
Search in Google Scholar Back to article
Y. Cheng, L. Wang, Z. Dong, Z. Zheng, and Z. Xia, “RF-NSGA-II framework for inverse design of high-performance Mg-Gd-based magnesium alloys,” Journal of Materials Informatics, vol. 5, 53, 2025. DOI:10.20517/jmi.2025.61
Search in Google Scholar Back to article
R. Mukherjee and S. Datta, “Design of biodegradable magnesium alloy using bi-objective genetic programming and multi-objective genetic algorithm in tandem,” Journal of Materials Engineering and Performance, Springer, 2025. DOI: 10.1007/s11665-025-11885-0
Search in Google Scholar Back to article
K. AlHammad, M. Medraj, and M. Tembely, “Application of machine learning for predicting the incubation period of water droplet erosion in metals,” Discover Applied Sciences, vol. 7, 712, 2025. DOI: 10.1007/s42452-025-07268-8
Search in Google Scholar Back to article
M. Mahfouf, M. Jamei, and D. A. Linkens, “Optimal Design of Alloy Steels Using Multiobjective Genetic Algorithms,” Mater. Manuf. Process., vol. 20, no. 3, pp. 553–567, 2005, DOI:10.1081/AMP-200053580
Search in Google Scholar Back to article
C. Liu, X. Wang, W. Cai, J. Yang, and H. Su, “Optimal Design of the Austenitic Stainless-Steel Composition Based on Machine Learning and Genetic Algorithm,” Materials, vol. 16, no. 5633, 2023, DOI:10.3390/ma16165633
Search in Google Scholar Back to article
M. F. Kilicaslan, Y. Yilmaz, B. Akgul, H. Karatas and C. D. Vurdu, “Effect of Fe–Ni substitution in FeNiSiB soft magnetic alloys produced by melt spinning,” Advances in Materials Science, vol. 21, no. 4, pp. 80–86, 2021. DOI: 10.2478/adms-2021-0026.
Search in Google Scholar Back to article
M. Kul, Y. Yilmaz, K. O. Oskay and L. C. Kumruoglu, “Effect of chemical composition of boriding agent on the optimization of surface hardness and layer thickness on AISI 8620 steel by solid and liquid boriding processes,” Advances in Materials Science, vol. 22, no. 3, pp. 1–9, 2022. DOI: 10.2478/adms-2022-0010.
Search in Google Scholar Back to article
Y. Uzunoğlu et al., “High-Accuracy Prediction of Mechanical Properties of Ni-Cr-Fe Alloys Using Machine Learning”, ACS, vol. 2, no. 1, pp. 7–14, Jan. 2025, DOI: 10.69882/adba.cs.2025012.
Search in Google Scholar Back to article
B. Emin et al., “Investigation of the Impact of Alloying Elements on the Mechanical Properties of Superalloys Using Explainable Artificial Intelligence”, CHF, vol. 2, no. 1, pp. 20–27, Jan. 2025, DOI: 10.69882/adba.chf.2025014.
Search in Google Scholar Back to article
Y. Alaca et al., “Investigation of the Effect of Alloying Elements on the Density of Titanium-Based Biomedical Materials Using Explainable Artificial Intelligence”, CEM, vol. 2, no. 1, pp. 15–19, Jan. 2025, DOI: 10.69882/adba.cem.2025013.
Search in Google Scholar Back to article
Y. Uzunoğlu and Y. Alaca, “Inverse Prediction of the CALPHAD-Modeled Physical Properties of Superalloys Using Explainable Artificial Intelligence and Artificial Neural Networks”, Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, vol. 14, no. 1, pp. 331–347, 2025, DOI: 10.17798/bitlisfen.1586564.
Search in Google Scholar Back to article
Y. Uzunoǧlu and Y. Alaca, “High-accuracy prediction of the thermo-physical properties of 6xxx series aluminum alloys using explainable artificial intelligence”, International Journal of Computational Materials Science and Engineering, 2025, [Early Access]. DOI: 10.1142/S2047684125500101
Search in Google Scholar Back to article

Interpretable Machine Learning and Genetic Algorithm-Based Optimization of Ultimate Tensile Strength And Melting Completion In Alloys

Abstract

Paradigm

My account