Explainable MRF-BBAPM with self-learning for predicting compressive strength of oxidized pellet

The compressive strength of oxidized pellets is a key indicator for evaluating pellet quality and stability. Accurate prediction of its variation trend is essential for improving production efficiency and optimizing process parameters. However, due to the high dimensionality and strong nonlinearity of compressive strength prediction, existing models still face limitations in terms of reliability, applicability, and generalization. This study proposes the MRF-BBAPM model, which integrates metallurgical domain knowledge with random forest-based feature selection. The model further enhances predictive performance using a BiGRU network optimized via Bayesian tuning and equipped with an attention mechanism. In the feature selection stage, metallurgical mechanisms are combined with random forest algorithms to identify relevant input features. The parameters of the BiGRU network are optimized using Bayesian methods, and an attention mechanism is introduced to focus on key features. The SHAP method is introduced to quantify the contribution of each feature to the prediction results, revealing the model’s decision-making process and enhancing its interpretability and reliability. The model also incorporates a self-learning mechanism that automatically updates and optimizes itself based on weekly prediction errors. Experimental results show that the proposed model achieves a mean absolute error of 80.58 N/P and a root mean square error of 95.75 N/P in predicting pellet compressive strength, demonstrating strong stability and reliability in real-world applications. This method provides effective data support for accurate prediction of pellet compressive strength and informed decision-making in production.