A reasonable arrangement of filling pipelines can solve the problems of low line magnification, a high flow rate, large pipe pressure, etc., in deep well filling slurry transportation. The transportation pressure loss value of filling slurry is the main parameter for the layout design of filling pipelines. At present, pressure loss data are mainly obtained through the loop pipe experiment, which has problems such as a large amount of labor, high cost, low efficiency, and a limited amount of experimental data. In this paper, combined with a new generation of artificial intelligence technology, the random forest machine learning algorithm is used to analyze and model the experimental data of a loop pipe to predict the pressure loss of slurry transportation. The degree of precision reaches 0.9747, which meets the design accuracy requirements, and it can replace the loop pipe experiment to assist with the filling design.

This study systematically investigates the mechanical behavior and failure mechanisms of cemented tailings backfill (CTB) prepared from classified and unclassified tailings across cement-to-tailings (C/T) ratios of 1:8, 1:6, and 1:4 and slurry concentrations of 60%, 65%, and 70%. Specimens were evaluated by uniaxial compression (UCS) tests, failure mode observation, and SEM. The results show that increasing C/T and concentration markedly enhances compressive strength: the maximum 28-day UCS reached 5.38 MPa under unclassified tailings, C/T = 1:4, 70%. Moreover, unclassified tailings exhibited a later-age strength gain of 244.9%, far exceeding the 58.5% observed for classified tailings. Failure modes evolve from brittle splitting to shear-dominated behavior as mixes densify, reflecting a transition from near-symmetric early-age stress/microstructural fields to asymmetric localized failure (symmetry breaking). SEM reveals that higher binder ratios and concentrations promote C-(A)-S-H-dominated gel formation, improved ITZ continuity, and reduced apparent porosity, thereby restraining microcrack initiation and coalescence. These findings elucidate the micro-to-macro mechanisms governing CTB strength and failure and provide field-relevant guidance for mix optimization and safe, efficient underground backfilling.