For rational disposal of solid wastes, low-cost cemented paste backfills (CPB) were prepared with iron tailings, ground granulated blast-furnace slag (GGBS), and calcium carbide slag (CS). To ensure that CPB can be effectively utilized in mine backfill projects, the effects of solid contents, GGBS content, CS/GGBS ratio, and mixing water on the workability and mechanical properties of CPB were investigated. The results indicated that when the solid content was 70%, the GGBS content was 14%, the CS/GGBS ratio was 0.4, the mixing water was tap water, the fluidity of fresh CPB slurry was 167 mm, and 28d unconfined compressive strength (UCS) of CPB reached 2.89 MPa, at which time the effect of the activation of the GGBS with CS was optimal. The analysis of X-ray diffraction (XRD), scanning electron microscopic imaging (SEM), thermogravimetric analysis (TG-DTG), and Fourier transform infrared spectroscopy (FTIR) demonstrated that the hydration products are mainly C-S-H gels, C-A-S-H, hemicarbonate, and hydrotalcite in CS-GGBS cementitious material. The C-S-H gel content gradually increased with increasing curing time and CS content (15%–35%). When the CS content was increased to 25%, the C-S-H gel content significantly increased, which improved the overall structural compactness and increased the UCS of CPB.

To investigate the issues related to significant environmental damage and poor resource utilization of soda residue (SR), the composition and microstructure of hydration products of the GGBS (ground granulated blast-furnace slag) synergistically activated by NaOH-SR are characterized by an X-ray diffraction (XRD), Fourier-transform infrared spectrometry (FTIR), thermogravimetric–differential thermogravimetric (TG-DTG) analysis, and scanning electron microscope X-ray energy dispersive spectrometry (SEM-EDS). The effect of SR proportion, activator dosage, and water-to-binder ratio on the hydration process is studied. Results indicate that the hydration products mainly include hydrated calcium chloroaluminate (3CaO·Al₂O₃·CaCl₂·10H₂O, FS), hydrated calcium aluminosilicate (Ca₂Al₃(SiO₄)₃OH, C-A-S-H), halite (NaCl), calcite (CaCO₃), and C-S-H gel. With the increase in SR proportion (especially from 80% to 90%), the C-S-H gel yield decreases significantly, while the FS yield rapidly increases, and the T-O-Si (T = Al or Si) peak shifts to a higher wavenumber range (955 cm⁻¹ to 975 cm⁻¹). With the decrease in activator dosage (40% to 15%), the hydration reaction gradually weakens, and the FTIR band of the T-O-Si (T = Al or Si) shifts to the lower wavenumber range (968 cm⁻¹ to 955 cm⁻¹). Then, cemented paste backfills (CPBs) are prepared with iron tailings as the aggregate. At mass content of 75%, SR proportion of 80%, and activator dosage of 30%, the fluidity of the CPB reaches 267.5 mm with a 28-day unconfined compressive strength (UCS) of 2.4 MPa, confirming that SR- and NaOH-synergistically-activated GGBS has great application prospects in backfill mining.

This study utilizes machine learning (ML) techniques to predict the performance of slag-based cemented tailings backfill (CTB) activated by soda residue (SR) and calcium carbide slag (CS). An experimental database consisting of 240 test results is utilized to thoroughly evaluate the accuracy of seven ML techniques in predicting the properties of filling materials. These techniques include support vector machine (SVM), random forest (RF), backpropagation (BP), genetic algorithm optimization of BP (GABP), radial basis function (RBF) neural network, convolutional neural network (CNN), and long short-term memory (LSTM) network. The findings reveal that the RBF and SVM models demonstrate significant advantages, achieving a coefficient of determination (R²) of approximately 0.99, while the R² for other models ranges from 0.86 to 0.98. Additionally, a dynamic growth model to predict strength is developed using ML techniques. The RBF model accurately predicts the time required for filling materials to reach a specified strength. In contrast, the BP, SVM, and CNN models show delays in predicting this curing age, and the RF, GABP, and LSTM models tend to overestimate the strength of the filling material when it approaches or fails to reach 2 MPa. Finally, the RBF model is employed to perform coupling analysis on filling materials with various mix ratios and curing ages. This analysis effectively predicts the changes in filling strength over different curing ages and raw material contents, offering valuable scientific support for the design of filling materials.