Cemented filling technology is an effective approach to solving tailings accumulation and goaf, with rheological properties serving as key indicators of slurry fluidity. Since slurry rheology is influenced by multiple factors, accurate prediction of its parameters is essential for optimizing filling design. In this study, we developed a model to predict static and dynamic yield stress using the extreme gradient boosting (XGBoost) algorithm, trained on 140 experimental samples (105 for training and 35 for validation, split 75:25). For comparison, adaptive boosting tree (ADBT), gradient boosting decision tree (GBDT), and random forest (RF) algorithms were also applied. Model performance was evaluated using four metrics: coefficient of determination (R2), mean absolute error (MAE), root mean square error (RMSE), and explained variance score (EVS). The Shapley additive explanation (SHAP) method was employed to interpret model outputs. The results show that XGBoost achieved superior predictive accuracy for slurry yield stress compared with other models. Analysis of importance revealed that underflow concentration had the strongest influence on predictions, followed by the binder-to-tailings ratio, while the fine-to-coarse tailings ratio contributed least. These findings highlight the potential of machine learning as a powerful tool for modeling the rheological parameters of filling slurry, offering valuable guidance for engineering applications.
The stability of internal dumps in open-pit coal mines is critical for the safe production and economic performance of the entire mine. To further enhance slope stability and ensure safe production, a new method for constructing trenches (referred to as an anti-sliding trench) on the sloped basal bed of the dump slope in open-pit mines was proposed to improve slope stability. The internal dump slope at the Luzigou anticline of the Anjialing Open-Pit Mine was studied. The slope failure modes of the dumping steps were studied experimentally and by numerical simulations at different widths of anti-slide trenches at the slope’s toe in a staged loading state. Without anti-slide trenches, shear-layer and along-layer failure modes occurred, while the failure modes with anti-slide trenches included shear-layer, along-layer, and squeeze-out failure. Based on the limit equilibrium theory and the determined failure modes, the preset anti-slide trenches at the toe of the dumping steps were theoretically analyzed. The relationships between the slope stability coefficient and the width and depth of anti-slide trenches, as well as the physical and mechanical parameters of the slope body, were derived. Given the physical and mechanical parameters of the slope body and targeted improvement in the slope stability coefficient, the size parameters of anti-slide trenches were designed and optimized through the derived relationships. At the Anjialing Coal Mine, presetting anti-slide trenches with a depth of 1.5 m and a width of 22.68 m at the toe of the dumping steps increased the slope stability coefficient from 1.3095 to 1.6. The proposed method provides a guiding reference for designing similar internal dump slopes in open-pit coal mines and for disaster prevention.