Full
Outline
To address the insufficient prediction accuracy of the compressive strength of fiber reinforced cemented tailings backfill (FRCTB), an improved Stacking ensemble learning model based on a weighted residual mechanism was proposed, utilizing 364 sets of experimental data collected from the literature. The model constructed an ensemble framework with six heterogeneous base learners and four meta-learners, and employed the Hippopotamus Optimization Algorithm (HOA) for global optimization of the base learner parameters. The prediction results of the base learners were obtained through 5-fold cross-validation, and adaptive weights were assigned to each base learner according to their prediction errors. Residual features were extracted as inputs for the meta-learner. Six single models were set as benchmarks for horizontal prediction accuracy comparison. Finally, interpretability analysis was introduced to explore the key influencing factors. The results show that among the single models, the light gradient boosting machine achieves the best comprehensive performance, with a coefficient of determination of 0.887 0. The HOA-R-Stacking model with Support Vector Regression (SVR) as the meta-learner performs the best, achieving a coefficient of determination of 0.947 0, and its mean absolute error and root mean square error are reduced by 34.53% and 33.94%, respectively, compared with the best single model. The interpretability analysis indicates that fiber content is one of the key factors affecting the compressive strength of FRCTB. The research results provide an effective technical means for predicting the compressive strength of FRCTB, which helps to improve backfill stability and reduce the cost of mine filling.
58
9
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
