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.

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.

In the context of intelligent coal mining faces, the strapdown inertial navigation system (SINS) serves as a pivotal technology for realizing the autonomous positioning of shearers. However, due to the complex underground environment, the positioning precision and stability of SINS have yet to meet the requirements for the normalized operation of intelligent mining faces. This limitation severely impedes the widespread application of SINS in coal mines. To address these challenges and enhance the performance of shearer SINS, this paper proposes a positioning accuracy improvement method based on the SINS and optical fiber sensing system (OFSS). By leveraging the spatial consistency between the shearer trajectory and the shape curve of the scraper conveyor, a SINS/OFSS integrated positioning model tailored to the shearer’s motion characteristics is established. Furthermore, a position mapping mechanism is introduced to achieve spatiotemporal consistency between the real-time position of the shearer and the discrete points on the scraper conveyor’s shape curve. Subsequently, a shearer trajectory time-series prediction model is constructed using historical states to predict future trajectories. This model serves to evaluate and perform a secondary correction on the positioning results, thereby further strengthening the error correction capability. Finally, simulation experiments and platform tests are conducted to validate the effectiveness of the proposed method. The results indicate that under both normal cutting and oblique cutting conditions, the positioning precision and stability of the proposed method significantly outperform comparative methods. The combination of the SINS/OFSS integrated positioning model and the TCN-BiLSTM-Attention (TBA) prediction model effectively mitigates SINS positioning errors, realizing a substantial improvement in shearer positioning accuracy.