Aiming at the problems of misdetection, omission and low recognition accuracy of coal gangue recognition due to the harsh environmental factors such as low illumination, motion blur and large quantities of coal gangue mixing in coal mines, a coal gangue recognition method based on XBS-YOLOv5s is proposed. Simulate the actual underground production environment to build a machine vision platform, construct a coal gangue image data set, and provide a test environment for various target detection algorithms. In this paper, we construct a real-time detection model of coal gangue in the complex environment of coal mine by fusing SimAM parameter-free attention mechanism, BiFPN feature fusion network and XIoU loss function in YOLOv5s, so as to improve the model’s ability of extracting, fusing and localizing key features of the target. The experimental results show that the recognition accuracy of XBS-YOLOv5s algorithm for coal gangue in the complex environment of low illumination, motion blur and large quantities of coal gangue mixed are effectively improved. Its mean average precision reaches 96%, which is 4.3% higher than the original YOLOv5s algorithm, meanwhile, compared with other YOLO series algorithms, it has the best comprehensive detection performance, which can provide technical support for intelligent and efficient sorting of coal gangue.

Specific to a problem of large vibro-impact aris ing from the cutting unit of the hard rock tunnel boring machine (TBM), a hybrid magnetic coupler based on soft start was proposed in this paper. The mathematical model for total eddy current losses of such a coupler was established by field-circuit method. Then, magnetic-thermal coupling simulation was performed by virtue of three-dimensional finite element software. In addition, an experimental prototype was independently designed; by comparing the model with experimental data, validity of the above mathematical model was verified. The relevant research results indicated that calculated values were consistent with experimental values, and the magneto thermal coupling method could be applied to accurately analyze temperature distribution of the hybrid magnetic coupler. By contrast to the existing magnetic coupling of the same dimension, output efficiency of the hybrid magnetic coupler was improved by 1.2%. Therefore, this research technique can provide references for designing the cutting unit of hard rock TBM with a high start impact.

In order to improve the detection accuracy of an algorithm in the complex environment of a coal mine, including low-illumination, motion-blur, occlusions, small-targets, and background-interference conditions; reduce the number of model parameters; improve the detection speed of the algorithm; and make it meet the real-time detection requirements of edge equipment, a real-time obstacle detection method in the driving of driverless rail locomotives based on DeblurGANv2 and improved YOLOv4 is proposed in this study. A blurred image was deblurred using DeblurGANv2. The improved design was based on YOLOv4, and the lightweight feature extraction network MobileNetv2 was used to replace the original CSPDarknet53 network to improve the detection speed of the algorithm. There was a high amount of background interference in the target detection of the coal mine scene. In order to strengthen the attention paid to the target, the SANet attention module was embedded in the Neck network to improve the detection accuracy of the algorithm under low-illumination, target-occlusion, small-target, and other conditions. To further improve the detection accuracy of the algorithm, the K-means++ algorithm was adopted to cluster prior frames, and the focal loss function was introduced to increase the weight loss of small-target samples. The experimental results show that the deblurring of the motion-blurred image can effectively improve the detection accuracy of obstacles and reduce missed detections. Compared with the original YOLOv4 algorithm, the improved YOLOv4 algorithm increases the detection speed by 65.85% to 68 FPS and the detection accuracy by 0.68% to 98.02%.

Aiming at the problem in measuring the nonuniformly distributed pressure generated by the pipe belt conveyor when conveying raw coals, a hexagonal adjustable pressure measuring device for the idler group is proposed. The dynamic model of the pipe belt conveyor clamping‐type roller group is established. In order to simplify the calculation process of mechanical analysis, the modal analysis is carried out to determine the factors which will influence the pressure. The pipe diameter and filling rate are selected as the key control factors by the sensitive analysis of pressure of the pipe belt conveyor clamping type roller group. An adjustable diameter‐type supporting roller group experiment device is self‐designed, and the dynamic pressure change of the roller group and each roller pressure are tested. The results show that the average error between the simulated and tested values of the pressure of the idler group at different filling rates is 7.3%; the theoretical and simulated values of the pressure of the idler group are in good agreement with the experimental values. The study provides a theoretical basis and experimental reference for the design and application of pipe belt conveyors.

In order to effectively solve the current problems of magnetic couplers such as large area and complex internal coil, the Halbach array magnetic coupler was proposed. According to the specific characteristics of the hybrid magnetic coupler structure, the mathematical model of air gap magnetic flux density is established by using the combination of electric circuit and electromagnetic field solution. Based on the current superposition, the current is converted to the surface of the copper conductor, and the electromagnetic torque model of the space magnetic field is established by integrating the induced electromotive force along the circumferential direction. In order to verify the correctness of theoretical analysis, the 1:4 prototype was designed and manufactured. Then simulation verification and experiment measurement on its mechanical behaviour are performed. The results show that the maximum error of theoretical value, simulation value and test value is 9.3%. Under the same volume size, the output torque of Halbach array magnetic coupler is increased by 16.1% compared with the ordinary disk magnetic coupler. The research could provide the reference for the design and experimental research of magnetic coupler.