An optimized machine-learning model for mechanical properties prediction and domain knowledge clarification in quenched and tempered steels

Clarifying the relationship between compositions, heat treatment processes, and me-chanical properties of carbon steel, as the basis of material design, is challengeable, while machine learning (ML) makes this complex correlation explicit. In this work, three different mechanical properties (ultimate tensile strength, yield strength, and total elongation) were predicted based on the collected quenched and tempered (Q & T) steel dataset by six ML algorithms, in which the optimal Gaussian process regression (GPR) combined with the key descriptors by feature engineering to train an optimized ML model. Such a simplified ML model shows even better prediction accuracy. In the above training process, Bayesian optimization (BO) searches the hyperparameters efficiently. The newly collected data also achieve small prediction errors, showing good generalization capacity. To maximize the application value of the current ML model, the grid prediction of composition and process, and local interpretable model-agnostic explanations (LIME) were utilized to reveal some new insights about the quenched and tempered steels, which could shed light on the ongoing new material design. Besides, the overfitting tendency of the ML model was examined to ensure the rationality of prediction, and the influence of data amount on the prediction performance was discussed.& COPY; 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Automated summary

In this study, machine learning algorithms were used to predict three mechanical properties of carbon steel and an optimized model was trained using feature engineering, achieving high prediction accuracy. Furthermore, the application value of the model was maximized through Bayesian optimization, analysis of newly collected data, and discussion of the influence of data amount on prediction performance.