The high-frequency air-coupled ground penetrating radar (GPR) can realize real-time dynamic detection of coal–rock strata in mines. However, the inaccurate strata positioning and low accuracy for coal and rock thickness detection, due to the thin layer effect theory and interference sources from the coal mining face, is one of the important problems restricting intelligent coal mining. This letter proposes a scheme of coal–rock strata location algorithm according to analyze the accuracy and error of coal–rock strata detection based on air-coupled radar. The relationships between the sampling sequence numbers of the interfaces are obtained, according to the 2-D maps of the relative errors of the layer thickness within the range of the main lobe extremum points and the lines fitted by least square algorithm. Compared with conventional layer recognition methods, the novel algorithm can improve the accuracy of interface identification and the stability of the system. The verification experiment results show that the recognition error of air–coal interface and coal–rock interface is between 2.0% and 7.1% and 2.4% and 7.6%, respectively.

Detailed detection of geological hazard sources is an important and yet challenging problem that remains unsolved. In this letter, we propose a whole closed space intrinsically safe Ground Penetrating Radar (GPR) system for geological hazard detection in coal mine roadway. Compared with many existing GPRs for half-space, this GPR system is characterized by achieving a stable radiation pattern and improved gain throughout the bandwidth. The improved performance for the system is achieved by the newly microwave front end design, adding round corners on the antenna radiation surface to improve radiation efficiency, designing resistive loading for better impedance matching, and optimizing shielding cavity dimensions to eliminate environmental interference. For design validation, a field experiment in mine roadway conditions is conducted, and the results show that the developed system has a good performance in mining roadway with depth detection accuracy at 0.5 m and direction detection accuracy at 1.5 m.

Accurately obtaining the geological characteristic digital model of a coal seam and surrounding rock in front of a fully mechanized mining face is one of the key technologies for automatic and continuous coal mining operation to realize an intelligent unmanned working face. The research on how to establish accurate and reliable coal seam digital models is a hot topic and technical bottleneck in the field of intelligent coal mining. This paper puts forward a construction method and dynamic update mechanism for a digital model of coal seam autonomous cutting by a coal mining machine, and verifies its effectiveness in experiments. Based on the interpolation model of drilling data, a fine coal seam digital model was established according to the results of geological statistical inversion, which overcomes the shortcomings of an insufficient lateral resolution of lithology and physical properties in a traditional geological model and can accurately depict the distribution trend of coal seams. By utilizing the numerical derivation of surrounding rock mining and geological SLAM advanced exploration, the coal seam digital model was modified to achieve a dynamic updating and optimization of the model, providing an accurate geological information guarantee for intelligent unmanned coal mining. Based on the model, it is possible to obtain the boundary and inclination information of the coal seam profile, and provide strategies for adjusting the height of the coal mining machine drum at the current position, achieving precise control of the automatic height adjustment of the coal mining machine.