@Article{cmes.2025.068211,
AUTHOR = {Yingui Qiu, Enming Li, Pablo Segarra, Bin Xi, Jian Zhou},
TITLE = {Developing Hybrid XGBoost Model to Predict the Strength of Polypropylene and Straw Fibers Reinforced Cemented Paste Backfill and Interpretability Insights},
JOURNAL = {Computer Modeling in Engineering \& Sciences},
VOLUME = {144},
YEAR = {2025},
NUMBER = {2},
PAGES = {1607--1629},
URL = {http://www.techscience.com/CMES/v144n2/63723},
ISSN = {1526-1506},
ABSTRACT = {With the growing demand for sustainable development in the mining industry, cemented paste backfill (CPB) materials, primarily composed of tailings, play a crucial role in mine backfilling and underground support systems. To enhance the mechanical properties of CPB materials, fiber reinforcement technology has gradually gained attention, though challenges remain in predicting its performance. This study develops a hybrid model based on the adaptive equilibrium optimizer (adap-EO)-enhanced XGBoost method for accurately predicting the uniaxial compressive strength of fiber-reinforced CPB. Through systematic comparison with various other machine learning methods, results demonstrate that the proposed hybrid model exhibits excellent predictive performance on the test set, achieving a coefficient of determination (R<sup>2</sup>) of 0.9675, root mean square error (RMSE) of 0.6084, and mean absolute error (MAE) of 0.4620. Input importance analysis reveals that cement-tailings ratio, curing time, and concentration are the three most critical factors affecting material strength, with cement-tailings ratio showing a positive correlation with strength, concentrations above 70% significantly improving material strength, and curing periods beyond 28 days being essential for strength development. Fiber parameters contribute secondarily but notably to material strength, with fiber length exhibiting an optimal range of approximately 12 mm. This study not only provides a high-precision strength prediction model but also reveals the inherent correlations between various parameters and material performance, offering scientific basis for mixture optimization and engineering applications of fiber-reinforced CPB materials.},
DOI = {10.32604/cmes.2025.068211}
}