“Three straight and two flat” is the inevitable demand when realizing the intelligent mining of a fully mechanized mining face. To address the crucial technical issue of lacking accurate perception of the shape of the scraper conveyor during intelligent coal mining, a three-dimensional curvature sensor involving fiber Bragg grating (FBG) is used as a perceptive tool to conduct curve reconstruction research based on different local motion frames and to reconstruct the shape of the scraper conveyor. Firstly, the formation process of the ‘S’-shaped bending section of the scraper conveyor during the pushing process is determined. Based on the FBG sensing principle, a mathematical model between the variation in the central wavelength and the strain and curvature is established, and the cubic B-spline interpolation method is employed to continuously process the obtained discrete curvature. Secondly, based on differential geometry, a spatial curve reconstruction algorithm based on the Frenet moving frame is derived, and the shape curve prediction interpolation model is built based on a gated recurrent unit (GRU) model, which reduces the impact of the decrease in curve reconstruction accuracy caused by damage to some grating measuring points. Finally, an experimental platform was designed and built, and sensors with curvature radii of 6 m, 7 m, and 8 m were tested. The experimental results showed that the reconstructed curve was essentially consistent with the actual shape, and the absolute error at the end was about 2 mm. The feasibility of this reconstruction algorithm in engineering has been proven, and this is of great significance in achieving shape curve perception and straightness control for scraper conveyors.

The foundation of intelligent collaborative control of a shearer, scraper conveyor, and hydraulic support (three-machines) is to achieve the precise perception of the status of the three-machines and the full integration of information between the equipment. In order to solve the problems of information isolation and non-flow, independence between equipment, and weak cooperation of three-machines due to an insufficient fusion of perception data, a fusion method of the equipment’s state perception system on the intelligent working surface was proposed. Firstly, an intelligent perception system for the state of the three-machines in the working face was established based on fiber optic sensing technology and inertial navigation technology. Then, the datum coordinate system is created on the working surface to uniformly describe the status of the three-machines and the spatial position relationship between the three-machines is established using a scraper conveyor as a bridge so that the three-machines become a mutually restricted and collaborative equipment system. Finally, an indoor test was carried out to verify the relational model of the spatial position of the three-machines. The results indicate that the intelligent working face three-machines perception system based on fiber optic sensing technology and inertial navigation technology can achieve the fusion of monitoring data and unified expression of equipment status. The research results provide an important reference for building an intelligent perception, intelligent decision-making, and automatic execution system for coal mines.

Roof water inrush accidents in coal mine driving roadways occur frequently in China, accounting for a high proportion of major coal mine water hazard accidents and causing serious losses. Aiming at the lack of research on the mechanism of roof water inrush in driving roadways and the difficulty of predicting water inrush accidents, this paper constructs a local damage criterion for coal–rock mass and a seepage–fracture coupling model based on peridynamics (PD) bond theory. It identifies three zones of water-conducting channels in roadway surrounding rock, the water fracture zone, the driving fracture zone, and the water-resisting zone, revealing that the damage degree of the water-resisting zone dominates the transformation mechanism between delayed and instantaneous water inrush. A discriminant function for the effectiveness of water-conducting channels is established, and a single-index prediction and evaluation system based on damage critical values is proposed. A “geometry damage” dual-control water inrush prediction model within the PD framework is constructed, along with a non-local action mechanism model and quantitative prediction method for water inrush. Case studies verify the threshold for delayed water inrush and criteria for instantaneous water inrush. The research results provide theoretical tools for roadway water exploration design and water hazard prevention and control.

Roadways serving island longwall panels are highly susceptible to severe asymmetric deformation under extreme eccentric loading from multiple adjacent goafs. To address the difficulties in characterizing the surrounding rock load imbalance and the high false-negative rates of conventional algorithms under extremely imbalanced monitoring data, an intelligent assessment method integrating spatially asymmetric physical features with cost-sensitive learning was developed. Implicit equation analysis and numerical simulation clarified the mechanical mechanism by which principal stress axis deflection induces butterfly-shaped asymmetric rotational failure, enabling the construction of dimensionless integrated asymmetry and structural transfer asymmetry coefficients. Reconstruction of the cost-sensitive objective function increased the recall rate for hazardous samples from 37.5% (baseline model) to 92.2%, while maintaining a precision of 96.7%. Following the field implementation of a three-tier differentiated roadway control scheme, the integrated asymmetry coefficients at critically eccentrically loaded stations (i.e., Station 12 and Station 07) remained below 0.2 during the monitoring period, enabling real-time intelligent perception and proactive stability control of roadways subjected to complex eccentric loading. Ultimately, this study confirms the viability of integrating physics-informed features with machine learning, demonstrating significant potential for advancing the transition toward intelligent and proactive safety management in complex underground construction.