The method of fully mechanized top-coal caving mining has become the main method of mining thick-seam coal. The process parameters of fully mechanized caving will affect the recovery rate and gangue content of top coal. Through numerical simulation software, the top-coal recovery rate and gangue content, under different fully mechanized caving process parameters, were simulated, and the influence law of different fully mechanized caving process parameters on top-coal recovery rate and gangue content was obtained. A decision model for top-coal caving process parameters was established with a BP neural network, and the optimal top-coal caving parameters were obtained for the actual situation of a working face. On this basis, a in-lab similarity simulation test of the particle material was carried out. The results show that the top-coal recovery rate and gangue content were 86.56% and 3.45%, respectively, and the coal caving effect was good. A BP neural network was used to study the decisions optimizing fully mechanized caving process parameters, which effectively improved the decision-making efficiency thereabout and provided a basis for realizing intelligent, fully mechanized caving mining.

In view of the insufficient characteristics and depth acquisition difficulties encountered in the process of uniocular vision measurement, the posture measurement scheme of tunneling equipment based on uniocular vision was proposed in this study. The positioning process of coal mine tunneling equipment based on monocular vision was proposed to extract the environmental features and match the features, and the RANSAC algorithm was used to eliminate the pair of mismatching points. This was done to solve the optimized matching pair and realize the pose estimation of the camera. The pose solution model based on the triangulation depth calculation method was proposed, and the PNP solution method was adopted based on the three-dimensional spatial point coordinates so as to improve the visual measurement accuracy and stability and lay the foundation for the 3D reconstruction of the roadway. This was done to simulate the downhole environment to build an experimental verification platform for monocular visual positioning. The experimental results showed that the position measurement accuracy of the uniocular visual roadheader positioning method within 60 mm and 1.3° could realize the accurate registration of the point cloud in the global coordinate system. The time required for the whole monocular visual positioning was only 179 ms, so it had good real-time performance.

For deep-buried thick top-coal roadways under high stress, there exists great difficulty in controlling the stability of the surrounding rock as well as in the necessity for low driving speeds. Taking the return air roadway 20201 (RAR 20201) of the Dahaize Coal Mine as the background, this paper presents a typical engineering case of a deep-buried thick top-coal roadway in a western mine. Through methods such as in situ investigation, theoretical analysis, numerical simulation and engineering practice, we studied the deformation and failure mechanisms of the surrounding rock in a deep-buried high-stress thick top-coal roadway, and revealed the driving speed effect. Results show that compared with shallow buried roadways, the deep-buried thick-roof coal roadway suffers a greater range of damage and failure. The roof damage is so deep that it exceeds the action range of bolts, resulting in the stress transferring to both sides, which affects the stability of the roadway surroundings. The curve of unloading disturbance stress produced by roadway head-on driving is in accordance with the “power exponential” composite function; that is, the faster the driving speed, the less unloading disturbance intensity that is exerted on the roof strata. This paper puts forward targeted cooperative control countermeasures of efficient driving and support in a deep-buried thick top-coal roadway. On one hand, the support efficiency of a single bolt is improved so as to reduce the overall support density; on the other hand, under low support density, the driving-supporting circulation efficiency is also accelerated so as to weaken the unloading disturbance and improve roadway formation speed. Engineering practice shows great control effect of the roadway surrounding rock, and the roadway formation speed is also greatly improved. This research can provide reference for efficient driving and support design in similar deep-buried thick top-coal roadways.

Coal is an important resource for China and even for the whole world. With the improvement of mechanization, automation and intelligence of coal mining equipment in China, there has been an imbalance between the speed of mining and of excavating. Adopting efficient cutting paths is beneficial to improving roadway excavation efficiency and alleviating the imbalance between mining and excavation. In this paper, taking the 12307 belt roadway of Wangjialing Coal Mine as the research background, the geomechanical parameters and distribution characteristics of the surrounding rock were observed and studied, and the test results of in-situ stress, surrounding rock structure and surrounding rock strength were obtained. Based on the test results, a numerical model was established, and the stress and displacement distribution law of the surrounding rock of the roadway under different cutting paths were analyzed, and two optimal cutting paths were proposed based on the actual situation, and industrial tests were carried out. The test results show that using the “snake” cutting path from bottom to top, the roadway section forming effect is good, and a single cycle excavation takes 34 min, which verified the effectiveness of the cutting path design. On the basis of specific engineering geological conditions, excavation equipment and technology, combined with experimental testing, numerical simulation and other methods, the roadway excavation cutting path can be optimized, and the research results can provide a reference for the design of cutting paths for coal mine excavation roadways with the same geological conditions.

Monitoring the deformation of rock surrounding deep coal mine roadways is critical for operational safety, yet conventional methods are often inefficient and lack the precision to capture complex geomechanical behavior. To address this challenge, we developed and validated a high-precision analysis workflow utilizing 3D laser scanning. This methodology integrates a multi-stage point cloud filtering process with a hybrid Principal Component Analysis and Iterative Closest Point (PCA-ICP) algorithm for high-fidelity registration of multi-temporal datasets, enabling deformation analysis via cloud-to-cloud (C2C) distance calculations. Applied to the No. 20105 belt conveyor roadway in the Dahaize coal mine, our method achieved a registration root mean square error (RMSE) of only 0.0136 m. The analysis revealed a distinct pattern of asymmetric deformation; while the roof and floor remained stable, the right wall exhibited significant convergence, with displacement in the lower section being substantially greater than in the upper section. This study establishes a robust methodology capable of rapidly generating comprehensive, centimeter-scale 3D deformation maps for entire roadway sections, providing a timely and quantitative basis for evaluating support performance, forecasting geohazard risks, and optimizing stability control in deep mining operations.