Design of a coal drawing volume monitoring system for fully mechanized top-coal caving faces based on the binocular camera

WU Jie; ZHANG Ningbo; YIN Peidong; SONG Xubin

doi:10.11799/ce202506001

Abstract：In order to solve the problem that the existing coal gangue identification method based on natural rays can not directly calculate the gangue mixing rate at the coal drawing opening,a monitoring system of coal drawing based on binocular camera was designed.The system monitors the discharge amount from the coal drawing opening,calculates the mixing rate of coal gangue combining with the natural ray coal gangue identification data,and helps to determine the reasonable closing time of the drawing opening.The grid line projection method is adopted in the system to project the grid image to the coal flow surface of the scraper conveyor near the coal drawing opening,and the high-precision point cloud data of the coal flow contour is obtained by scanning with a binocular camera;The three-dimensional point cloud model is constructed by projection and micro grid division,and the finite element volume calculation method is introduced to slice processing.Combining with the trapezoid method,the slice volume is calculated and summed to obtain the total volume of coal flow.At the same time,the telescopic support structure is designed to realize the flexibly adjust and protect the detector.Laboratory tests show that the measurement error of the system is less than 5%under different coal flow accumulation conditions.The tile state error is about 5%,the stack state error is 4.6%～4.9%,and the root mean square error is 0.2952,showing high accuracy and stability.The system provides reliable real-time monitoring data for intelligent coal caving,supports accurate calculation of gangue mixing rate,which is significant for improving the practicability of coal gangue automatic identification technology,and provides a new technical means for intelligent construction of coal mine.