• Proposes the MRF-BBAPM model integrating metallurgical mechanisms, random forest feature selection, Bayesian optimization, BiGRU, and attention mechanism for accurate compressive strength prediction.
• Achieves high prediction accuracy with a mean absolute error of 80.58 N (2.77% of the mean) and root mean square error of 95.75 N (3.29% of the mean).
• Incorporates SHAP explainability to quantify feature contributions, enhancing model interpretability and reliability for industrial adoption.
• Features a self-learning mechanism that updates based on weekly prediction errors, ensuring sustained performance in real-world production environments.