journal article·2026-07-30

Prediction of Backfill Slurry Shrinkage Rate and Optimization of Roof-Contact Backfilling Based on an Optimized Neural Network Approach

Haoliang Han, Hongjiao Li, Xu Huang, Yuye Tan, Jiazhao Chen, Yuchao Deng

Applied Sciences· Volume 16· Issue 15
Publisher page

Abstract

In backfill mining of metal mines, the sedimentation and shrinkage of backfill slurry critically affect roof-contact quality and stope stability. This study investigates these characteristics for unsorted tailings backfill slurry from the Daye Iron Mine through laboratory experiments and develops a prediction model for the shrinkage rate. Tests examined the effects of cement-to-tailings ratio (1:4 to 1:20) and slurry concentration (65% to 71%) on shrinkage rate over curing time. A crested porcupine optimizer-backpropagation (CPO-BP) neural network model was developed to predict the shrinkage rate and compared with the traditional BP model. The robustness and generalization capability of the model were further verified by repeated five-fold cross-validation and by comparison with the GA-BP, PSO-BP, random forest, support vector regression, and XGBoost models. Results show that shrinkage predominantly occurs within the first 8 h and stabilizes after 24 h; high-concentration slurries stabilize earlier. At a fixed concentration, the shrinkage rate increases with decreasing cement-to-tailings ratio; at a fixed ratio, it decreases with increasing concentration. The CPO-BP model significantly outperforms the BP model, achieving a mean squared error (MSE) of 3.0767 × 10−6, a mean absolute error (MAE) of 1.4528 × 10−3, and a coefficient of determination (R2) of 0.94946 on the test set. For the Daye Iron Mine, a slurry concentration of 69–71% reduces shrinkage height and improves roof-contact rate. This study reveals the evolution of shrinkage rate with curing time, cement-to-tailings ratio, and concentration, demonstrates the effectiveness of the CPO-BP model, and optimizes the backfilling scheme, providing a theoretical basis for roof-contact quality control in practice.
Source: crossref · Quality: baseline

Affiliations

Information Research Institute of the Ministry of Emergency Management, Beijing 100029, China

Key Laboratory of the Ministry of Education for High-Efficiency Mining and Safety in Metal Mines, University of Science and Technology Beijing, Beijing 100083, China

School of Resources and Safety Engineering, University of Science and Technology Beijing, Beijing 100083, China

Nanchang Branch, Beijing Sloco Resource Technology Co., Ltd., Nanchang 330006, China

Funding

Blastability and Blasting Damage Mechanism of Freeze-Thaw Rock Mass in Open-Pit Mines in Cold Regions

References (40)

Show source-provided references
1. Cao, S., Yilmaz, E., and Song, W. (2018). Evaluation of Viscosity, Strength and Microstructural Properties of Cemented Tailings Backfill. Minerals, 8.10.3390/min8080352 ↗
2. Cemented paste backfill for mineral tailings management: Review and future perspectives10.1016/j.mineng.2019.106025 ↗
3. Yan, Z. (2025). Mechanical Behavior and Roof-Contact Control Mechanism of Prestressed Filling in the Deep Mine, University of Science and Technology Beijing.
4. Research progress on mining with backfill technology of underground metalliferous mine
5. Research on roof-contact backfilling technology in underground mines
6. Analysis of deformation characteristics of immediate roof based on filling rate and time effect10.1007/s12517-022-09465-w ↗
7. Research on the Rate of Roof-contacted Filling and the Load-bearing Properties of Filling Body
8. Chen, F., Liu, J., Zhang, X., Wang, J., Jiao, H., and Yu, J. (2022). Review on the Art of Roof Contacting in Cemented Waste Backfill Technology in a Metal Mine. Minerals, 12.10.3390/min12060721 ↗
9. Experimental Study on Backfilling Mine Goafs with Chemical Waste Phosphogypsum10.1155/2019/9218916 ↗
10. Effect of Roof-Contact Rate on Stability of Backfill
11. Influence of new hydrophobic agent on the mechanical properties of modified cemented paste backfill10.1016/j.jmrt.2019.09.039 ↗
12. Optimization Proportioning Test on Mixed Aggregate of Waste Rock and Copper Slag Tailings
13. Fang, Z. (2020). Investigation on the Flow and Settlement Law of Ice-Containing Cemented Paste Backfill Slurry in High Temperature and Deep Well, Xi’an University of Science and Technology.
14. Effect of Naphthalene-based Superplasticizer on the Performances of Different Types of Tailings Backfill Materials
15. Bleeding Characteristics of Coarse Aggregate Filling Slurry and Its Influence on the Performance of Backfill
16. Investigation of the Sedimentation Property of Backfill Material on the Basis of Rheological Test: A Case Study of Iron Tailings10.1155/2018/9530767 ↗
17. Analysis on Bleeding and Setting Performance of Filling Slurry
18. Experimental study on the shrinkage performance of backfill slurry
19. Analysis of Shrinkage and Bleeding Characteristics of Backfill Slurry
20. Research on the shrinkage of tailings and its influence factors
21. Flow settlement law of gangue paste-like filling slurry in roomand-pillar goaf
22. Study on settling performance of total tailings slurry mixed with cement in Xishimen iron mine
23. Flow Settlement Law and Construction Parameter Optimization of Filling Slurry in High Stage Stope of Zhongguan Iron Mine
24. Research on flow sedimentation law of filling slurry and mechanical characteristics of backfill body
25. Monitoring of in-situ properties for cemented tailings backfill that under drainage condition10.1016/j.conbuildmat.2022.129254 ↗
26. Effect of curing humidity on the deformation and mechanical properties of cemented paste backfill10.1080/17480930.2023.2252272 ↗
27. Flocculation, dewatering and sedimentation behaviour of mine backfill slurry in deep cone thickener (DCT)
28. Learning representations by back-propagating errors10.1038/323533a0 ↗
29. Comparative evaluation of genetic algorithm and backpropagation for training neural networks10.1016/S0020-0255(00)00068-2 ↗
30. Crested Porcupine Optimizer: A new nature-inspired metaheuristic10.1016/j.knosys.2023.111257 ↗
31. Zhang, S., Yang, C., and Zhao, D. (2026). Study on Compressive Strength Prediction of Steel Fiber Recycled Aggregate Concrete Based on GA–PSO–BP Neural Network. Buildings, 16.10.3390/buildings16122316 ↗
32. Xu, Y., Mao, J., Zhuge, W., Yu, X., and Wu, P. (2026). Prediction and Evaluation of Hardened Concrete Strength: Based on Machine Learning and Mixture Composition, Springer.10.1007/978-981-96-8237-9 ↗
33. Application of a GA-BP Neural Network in Accurately Characterizing the Diffusion Range of Groundwater Pollutants
34. Experimental investigation and GA-BP prediction of vertical tensile performance of laminated rubber bearings under shear deformation
35. The Denoising Methodology for In-Situ Infrared Spectroscopy Based on CPO-VMD
36. Random Forests10.1023/A:1010933404324 ↗
37. A tutorial on support vector regression10.1023/B:STCO.0000035301.49549.88 ↗
38. Chen, T., and Guestrin, C. (2016, January 13–17). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
39. Gravity Transport Parameter Analysis and Pipe Network Wear Law of Filling Pipeline in Daye Iron Mine
40. Analysis of Gravity Flow Pipeline Transportation and Pipeline Wear for an Iron Mine