In modern industrial manufacturing, the mechanical properties of large bearing housing castings are critical to equipment reliability and lifespan. Traditional prediction methods relying on experimental testing and empirical formulas face challenges such as high costs, limited samples, and inadequate generalization capabilities. This study presents a machine learning approach for predicting mechanical properties of ZG270-500 cast steel, integrating multivariate data (chemical composition, process parameters) to establish an efficient predictive model. Utilizing real-world production data from a certain foundry and forging plant, the research implemented preprocessing steps including outlier handling, data balancing, and normalization. A systematic comparison was conducted on the performance of four algorithms: Backpropagation Neural Network (BPNN), Support Vector Regression (SVR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The results indicate that under small-sample conditions, the SVR model outperforms other models, achieving a coefficient of determination (R²) between 0.85 and 0.95 on the test set for mechanical properties. The root mean square errors (RMSE) for yield strength, tensile strength, elongation, reduction in area, and impact energy are 7.59 MPa, 7.52 MPa, 0.68%, 1.47%, and 5.51 J, respectively. Experimental validation confirmed relative errors between predicted and measured values below 4%. SHAP value analysis elucidated the influence mechanisms of key process parameters (e.g., pouring speed, normalization holding time) and elemental composition on mechanical properties. This research establishes an efficient data-driven approach for large casting performance prediction and provides a theoretical foundation for guiding process optimization, thereby addressing the research gap in performance prediction for large bearing housing castings.

Hardness, as a typical mechanical property of dispersion-strengthened tungsten alloy, is influenced by various coupled factors. This paper aims to identify the key factors affecting the hardness of the dispersion-strengthened tungsten alloys with different carbides and oxides as the reinforcement phase in order to enable the high-throughput prediction of hardness. A dataset was established with alloy hardness as the target variable, and the features included the content of reinforcement phase, the Vickers hardness of reinforcement phase, the melting point of the reinforcement phase, the valence electron number of the reinforcement phase, the sintering temperature, the sintering time, pressure, relative density, and grain size. Seven regression models were trained, and we selected random forest, support vector regression, and XGBoost regression machine learning models with better performance to construct a hardness prediction model of the dispersion-strengthened tungsten alloy. SHAP analysis, based on random forests, shows that the content of reinforcement phase, grain size, and relative density have the most significant impact on the hardness. A random forest model is the most suitable machine learning method for predicting the hardness of dispersion-strengthened tungsten alloys in this work. The R² values of the training and test sets are 0.93 and 0.80, and the MAE values of the training and test sets are 22.72 and 38.37. The influence of the most important features on the hardness was also discussed based on the random forest model. This study provides a data-driven approach for the accurate and efficient prediction of the hardness of dispersion-strengthened tungsten alloys, offering an important reference for the design and development of high-performance tungsten alloy materials.