Aiming at the characteristics of low sensitivity and narrow frequency range of existing microseismic monitoring sensors for mine water hazard prevention and control, a piezoelectric acceleration sensor for microseismic monitoring based on a kind of triangular shear structure is proposed. Firstly, the structure of the triangular shear piezoelectric acceleration sensor is designed, and its dynamic model is built. The structural and material parameters related to natural frequency and sensitivity are analyzed. Then, the selection of piezoelectric ceramic materials is discussed. The parametric design of the designed sensor is carried out, and its finite element structural model is built by ANSYS. The modal analysis, resonance response analysis, and piezoelectric analysis of the designed sensor are carried out. The simulation results indicate that the working frequency and sensitivity of the designed sensor meet the requirements of microseismic monitoring. Response surface optimization is adopted to analyze the influence of sensor element design variables on the sensitivity and resonant frequency of the designed sensor. The reoptimized design of the reference sensor improves the resonant frequency of the designed sensor by 9.46% and the charge sensitivity by 18.96%. Finally, the designed sensor is calibrated, and the microseismic signal detection experiment is carried out. The results indicate that the resonant frequency of the designed sensor is 6150 Hz, the working frequency is 0.1-2050 Hz, and the charge sensitivity is 1600 pC/g. The sensor can detect microseismic signals with a wide frequency range and high sensitivity.
The waste mine water is produced in the process of coal mining, which is the main cause of mine flood and environmental pollution. Therefore, economic treatment and efficient reuse of mine water is one of the main research directions in the mining area at present. It is an urgent problem to use an intelligent algorithm to realize optimal allocation and economic reuse of mine water. In order to solve this problem, this paper first designs a reuse mathematical model according to the mine water treatment system, which includes the mine water reuse rate, the reuse cost at different stages and the operational efficiency of the whole mine water treatment system. Then, a hybrid optimization algorithm, GAPSO, was proposed by combining genetic algorithm (GA) and particle swarm optimization (PSO), and adaptive improvement (TSA-GAPSO) was carried out for the two optimization stages. Finally, simulation analysis and actual data detection of the mine water reuse model are carried out by using four algorithms, respectively. The results show that the hybrid improved algorithm has better convergence speed and precision in solving the mine water scheduling problem. TSA-GAPSO algorithm has the best effect and is superior to the other three algorithms. The cost of mine water reuse is reduced by 9.09%, and the treatment efficiency of the whole system is improved by 5.81%, which proves the practicability and superiority of the algorithm.
Coal mining not only produces a large amount of mine water but also may cause water pollution. Therefore, economic treatment and efficient reuse of mine water are the main research directions of the mine area at present, and the realization of optimal dispatching and efficient reuse of mine water is an urgent problem to be solved. Based on the Na Lin mining area as an example, based on maximizing the reuse rate of mine water, summarizes the mine water level fractionation utilization pathway and classification of mine water dispatching mode, build the Na Lin mining area water supply dispatching model, analyzed the Na Lin River No. 2 mining area water supply dispatching model and the space-time change of water dispatching, through comparing with traditional dispatching model, the results showed that: The constructed water dispatching model can significantly improve the mine water recycling rate in Na Lin river mine area, which provides a certain theoretical basis for the study of efficient utilization of mine water.
This study proposes a novel model, CUs-YOLO, to address the challenges of detecting coal and gangue under complex conditions, including light spots from illumination, image blurring due to noise, and colour distortion. It also tackles limitations in local feature extraction and the tendency of existing models to lose target information. In the backbone network, the convolutional layers in CSPNet are enhanced using CondConv, which employs weighted convolutional kernels to increase model capacity while reducing computational cost. To mitigate information loss during upsampling in the pyramid structure of the original model’s neck, this study improves the Content-Aware ReAssembly of Features operator by adding convolutional layers and replacing the original upsampling structure, thereby enhancing detail retention and reconstruction quality. Additionally, a dedicated coal and gangue data acquisition and detection device was developed, and a dataset was constructed to support experimentation. Experimental results demonstrate that the CUs-YOLO model achieved an average detection accuracy of 98%, a giga floating point operations of only 2570 599, and a real-time recognition speed of 60.2 frames per second, confirming the effectiveness of the proposed enhancements. Comparative experiments further validate the superior performance of CUs-YOLO, which combines lightweight design with high recognition accuracy. This offers a promising solution for the intelligent identification of coal and gangue in complex environments, with significant practical application value.
7 February 2023 in Journal of Electrical Engineering & Technology