基于MT-CNN的矿井带式输送机输煤量检测技术

Coal conveying quantity detection of mine belt conveyor based on MT-CNN

为实现矿井带式输送机输煤量检测的信息化、智能化,提出基于MT-CNN的矿井带式输送机输煤量检测技术。为了全面提升输煤量检测技术,从而提高矿井效益,选取了多任务卷积神经网络(MT-CNN)对检测目标进行多核心识别检测,优化了图像直线信息和边缘信息的提取效率,构建了良好的网络层次结构,优化了信息连接通道,从而全面提高图像识别分析和数据检测处理的效果。通过MT-CNN技术对输煤量的轮廓形态和荷载状态进行分析运算,经过图像样本数据训练获取矿井带式输送机输煤量的相关数据。研究结果表明,该技术能够有效提高输煤量图像识别的真实性,而检测时间缩短49%,计算结果准确率提高到98%,有效提高了输煤量检测的效率和准确度,具有较好的应用性能和良好的使用效果。加强矿井带式输送机的输煤量检测,可以为后续研究提供依据,很大程度上推动了相关技术发展,实现矿井信息化、智能化、现代化发展。

In order to realize the informatization and intelligence of coal conveying quantity detection of mine belt conveyor,the coal conveying quantity detection technology of mine belt conveyor based on MT-CNN is proposed.The multi-task convolutional neural network(MT-CNN)is selected to perform multi-core recognition and detection of the detection target,optimize the extraction efficiency of image straight line information and edge information,build a good network hierarchy,optimize the information connection channel,and improve the effect of image recognition analysis and data detection and processing.The contour morphology and load state of the coal conveying quantity are analyzed and calculated by MT-CNN technology,and the relevant data of the coal conveying quantity of the mine belt conveyor are obtained through image sample data training.The experimental results show that the research technology can effectively improve the authenticity of the image recognition of coal conveying quantity,shorten the detection time by 49%,and increase the accuracy of the calculation results to 98%,which proves that the research technology can effectively improve the efficiency and accuracy of the coal conveying quantity detection,and has good application performance and good use effect.Strengthening the coal conveying quantity detection of mine belt conveyor can provide a basis for follow-up research,promote the development of related technologies to a large extent,and realize the development of mine information,intelligence and modernization.