Rockbursts are common geological disasters in underground engineering, and rockburst proneness evaluation is an important research subject. In this study, a multidimensional cloud model was used to evaluate the rockburst proneness level, and the control variable method was used to establish 15 multidimensional cloud (MC) models. The key factors affecting the accuracy of multidimensional cloud model evaluation are numerical characteristics, weight, and normalization methods. The optimal numerical characteristics calculation method of a multidimensional cloud model was determined, and an improved CRITIC (IC) weight method was optimised by introducing the relative standard deviation and an improved quantisation coefficient. Six rockburst indexes were used as input for the multidimensional cloud model, including the elastic deformation energy index $Wet$⁠, maximum tangential stress $σθMPa$ of a cavern, uniaxial compressive strength $σcMPa$⁠, uniaxial tensile strength $στMPa$⁠, strength brittleness coefficient $B1=σc/στ$⁠, and stress coefficient $σθ/σc$⁠. The model was used to learn 271 groups of complete rockburst cases, and the MC-IC rockburst proneness evaluation method was established. The performance of the proposed MC-IC rockburst proneness method was verified by an 8-fold cross-validation and confusion matrix (precision, recall, F₁). The method was tested to evaluate 20 groups of rockburst cases from the Jiangbian Hydropower Station, and the accuracy reaches 95%. The evaluation results were compared with three empirical criteria: four cloud-based methods, three unsupervised learning methods, and four supervised learning methods; the accuracy of the method established in this paper is 93.33%. The results showed that the MC-IC method had an excellent performance in evaluating rockburst proneness and can provide a practical basis for identifying rockburst hazard areas in deep engineering.

Deep soft rock roadways at about 1 km depth experience significant deformation due to concentrated stress ahead of the working face and dynamic loads from the hard roof layer. We propose an integrated control method that couples directional roof cutting, which interrupts stress transfer with constant resistance, and large deformation cable reinforcement to accommodate residual movement. The calibrated FLAC3D model indicates a lower front of face stress and a diminished cyclic build up of elastic strain energy in the roof, which reduces roadway convergence. Field data from Face 13403 corroborate the method’s effectiveness: the average hydraulic support load on the roof cutting side was 20.3 MPa, which is 30.1% lower than on the non-cutting side; deformation stabilized about 320 m behind the face; the final roof to floor and rib to rib closures were 1.10 m and 1.47 m; and the entry remained fit for the next panel. These results indicate that coupling roof cutting with constant resistance cable reinforcement reduces mining-induced loads while increasing deformation tolerance, providing a practical solution for stabilizing kilometer-deep soft rock roadways.