To achieve the precise regulation of air flow in mine ventilation systems and the abnormal identification of air window opening, as well as to improve the intelligent level of mines, it is necessary to conduct real-time and accurate detection of underground air window opening. Aiming at the problems of reduced object detection accuracy caused by low illumination and shadow interference in underground mines, as well as the difficulty in deployment and real-time operation of existing detection models due to large parameters and computational complexity, this paper proposes a real-time and accurate detection model CFW-YOLO (C2f_Faster and WIoUv3 Enhanced YOLO) for underground air window opening based on the improved YOLOv8n. With high precision and lightweight as objectives, the CFW-YOLO model replaces the original C2f structure in the backbone network with the C2f_Faster module, which ensures that the network can effectively extract features from input images during high-speed operation, improves detection accuracy while reducing the number of parameters and computational complexity. In the training phase, the WIoUv3 (Wise Intersection over Union version 3) loss function is adopted to replace the CIoU (Complete Intersection over Union) loss function. The learning weights of samples with different quality are balanced through a dynamic non-monotonic mechanism and gradient gain allocation strategy, reducing the influence of harmful gradients and improving the detection accuracy. Images of air windows with different openings were collected and labeled on the experimental platform, and the dataset covers 41 types of air window openings ranging from 0 to 40 cm. Data augmentation was realized by adjusting illumination and adding random shadows, which enhances the generalization ability of the model under complex lighting conditions. The air window opening detection model was trained, and the independent contributions of the two improvements were verified through ablation experiments and comparative tests. A hardware and software system architecture for adjusting air doors integrated with CFW-YOLO model was designed, and the system composition and workflow were analyzed from four aspects: perception, early warning, control, and human-computer interaction. The results show that compared with the original YOLOv8n model, the precision and mean average precision of CFW-YOLO are increased by 3.4% and 0.7%, respectively, and the number of parameters, floating-point operations, and model size are reduced by 0.47 M, 1.2 G, and 0.9 MB, respectively, verifying the accuracy and real-time performance of the improved model.
Aiming at the problem that coal mine dual-wavelength photoelectric smoke sensors suffer zero drift caused by dust accumulation during long-term operation in underground high-dust environments, which seriously degrades the accuracy of fire smoke detection, this paper analyzes the mechanism of zero drift induced by dust accumulation based on light scattering theory with reference to actual underground coal mine working conditions. It is clarified that the damage to the optical characteristics of the reflective bottom surface by dust particles accumulated at the bottom of the optical maze serves as the primary cause of sensor zero drift. Based on the Lorenz-Mie theory, the distribution of dust particles is normalized and simplified, and a unified mathematical model of scattered light intensity affected by deposited dust particles is established. By analyzing the influence of gradual dust accumulation and its distribution variation on independent scattering and secondary scattering, the varying characteristics of scattered light intensity with dust accumulation parameters at different dust deposition stages are summarized. Combined with actual underground coal mine production conditions, the macroscopic variation law of zero drift is induced: the dust deposition process can be divided into three stages, namely the sparse dust accumulation stage, the adjustment stage, and the dense dust accumulation stage. The sensor zero point presents a stepwise linear rise in the sparse dust accumulation stage; in the adjustment stage, the rising rate of the zero point gradually slows down; in the dense stage, the zero point tends to stabilize with slight fluctuating growth, and its specific rising rate is correlated with the height of the dust layer and the distance from the top surface of the dust layer to the photoelectric receiving unit, both of which are affected by the internal dust accumulation rate of the sensor. Industrial tests were carried out with four prototypes arranged at two high-dust measuring points in an underground coal mine. The test results show that the dust accumulation evolution conforms to the variation characteristics of the sparse stage, adjustment stage and dense stage. Based on the above conclusions, ideas for applying the proposed law to zero drift correction and design suggestions for the optical maze of smoke sensors are put forward.
Slope stability of open-pit mines in cold regions is affected by adverse climate, engineering disturbance and other factors, which can easily induce geological disasters such as frost heave cracking, thaw subsidence and sliding collapse of rock masses. To explore the variation law of microscopic pore structure inside slope rock mass of open-pit mine under freeze-thaw action and reveal its freeze-thaw damage and deterioration mechanism, taking the mudstone from the slope of north Huolinhe Open-pit Mine in Inner Mongolia as the research object, freeze-thaw cycle tests of mudstone under different temperature gradients and different freeze-thaw cycle times were systematically carried out. Scanning Electron Microscope (SEM) was adopted to perform high-resolution scanning on internal fractures of mudstone to observe the morphological changes of microscopic pores inside mudstone. On this basis, advanced image processing technology was used to accurately extract and quantitatively count pore information from SEM images denoised by an optimization algorithm, and the pixel coverage method was applied to calculate the fractal dimension for characterizing the complexity of pore structure. The results show that: with the increase of freeze-thaw cycles and the decrease of freeze-thaw temperature, the smooth lamellar structures inside mudstone gradually decrease, while flaky and honeycomb deterioration structures increase significantly, presenting obvious freeze-thaw damage characteristics; the pore size distribution exhibits a trend of decreased average proportion of small pores and increased average proportion of medium and large pores, the average proportion of small pores in specimens decreases from 81.60% to 77.53%, the average proportion of medium pores rises from 17.84% to 21.90%, and the average proportion of large pores increases from 0.52% to 0.59%, which reflects the evolutionary process that small pores develop, penetrate under frost heave force and transit to larger pore sizes; the fractal dimension of pores obtained from SEM images of specimens shows a declining trend under multiple observation perspectives, indicating that freeze-thaw damage continues to intensify with the change of test conditions, and the overall pore structure evolves from complex to simple.
To respond to the development initiative of green mines, improve the permeability and fluidity of inorganic grouting materials under complex working conditions, and promote their development, an inorganic micro-nano grouting material for mining was developed using ultra-fine cement, slag, steel slag and fly ash as main raw materials, with composite activators adopted to adjust the setting time. Taking the grouting modification project of ZF303 isolated coal face in Xiagou Coal Mine as the engineering background, performance tests of mine-used inorganic micro-nano grouting materials under different water-cement ratios were carried out. Firstly, the performance tests on fluidity, viscosity, setting time, bleeding rate and compressive strength of grouting materials were carried out. Secondly, the stability characteristics of the hardened grout concretion were examined via immersion durability tests. Finally, based on the test results, multi-dimensional quantitative characterization and comprehensive evaluation were conducted on the workability, mechanical properties and durability indexes of the grouting material. The performance test results show that: in fluidity and setting time tests, when the water-cement ratio of the grouting material ranges from 0.2 to 0.4, no obvious fluidity loss occurs within 2 hours, and final setting is achieved after 6 hours; in viscosity and strength tests, the slurry of the grouting material features high viscosity and stability in the short term, and the maximum compressive strength of its grout concretion reaches 100.3 MPa at 28 days. Immersion durability test results indicate that during 0-60 days of immersion, the cementitious substances do not fully fill the grout concretion, leading to a gradual increase in specimen strength; during 90-120 days of immersion, the concretion is gradually compacted by cementitious materials, generating internal expansion stress and thus reducing the strength of the grout concretion. Field application results show that the mining inorganic micro-nano grouting material can effectively fill micro-cracks in surrounding rock, enhance the bonding strength, improve the integrity of surrounding rock, control roadway deformation and reduce roadway maintenance frequency.
Following coal mine accidents, large-scale rescue equipment is often unable to operate underground due to narrow mine spaces and complex environments. With its distinctive locomotion mechanism, a bionic snake-like robot can adapt to various terrain conditions and flexibly navigate confined spaces, and reach areas inaccessible to rescue workers. It can also be equipped with cameras, gas sensors, life detectors and other devices to monitor the accident site and collect data in real time, providing support for rescue decision-making. This paper reviews the research progress of bionic snake-like robots worldwide in recent years and their typical applications in coal mine rescue, and finds that certain achievements have been made in the collaborative rescue, wireless control and accident early warning of snake-like robots for coal mine disasters. However, given the complicated and volatile harsh environments caused by coal mine accidents, critical technical challenges remain in further improving rescue efficiency and the robot’s environmental adaptability. Accordingly, this study further analyzes these key technologies and their development status: perception and navigation technologies in complex environments, including image enhancement, stereo vision and multi-sensor information fusion, have effectively enhanced the environmental perception ability of bionic snake-like robots. Nevertheless, the robot’s special structure and locomotion characteristics still impose limitations on the accuracy of environmental sensing and mapping. In unstable underground accident environments, the explosion-proof performance of snake-like robots can be significantly improved through material optimization, positive-pressure explosion-proof design and power supply protection, but these measures may also degrade their locomotion performance. Extensive studies on obstacle avoidance, obstacle-assisted locomotion and obstacle surmounting targeting complex terrain features have effectively enhanced the robot’s adaptability to complicated terrains. However, the constructed accident scenes are mostly manually set with obstacles of simple shapes, with few tests carried out in real rescue scenarios; thus, further verification is required. Extensive and in-depth research on existing key technical bottlenecks is of great significance for improving rescue efficiency, ensuring personnel safety and reducing disaster losses, and will also become an important research direction in the development of emergency rescue technologies, and the application of bionic snake-like robots in coal mine rescue will continue to expand.
