陕西煤炭2024,Vol.43Issue(3) :63-67.DOI:10.20120/j.cnki.issn.1671-749x.2024.0312

基于深度学习的煤矸石计量研究

Detection and measurement of coal gangue based on deep learning

秦雷 张富民 李亚威 田亮亮
陕西煤炭2024,Vol.43Issue(3) :63-67.DOI:10.20120/j.cnki.issn.1671-749x.2024.0312

基于深度学习的煤矸石计量研究

Detection and measurement of coal gangue based on deep learning

秦雷 1张富民 1李亚威 1田亮亮2
扫码查看

作者信息

  • 1. 济宁市金桥煤矿,山东济宁 272200
  • 2. 中信重工开诚智能装备有限公司,河北唐山 063020
  • 折叠

摘要

针对在煤矿皮带输送机上难以对煤矸石实时计量,结合图像处理技术和深度学习技术,提出基于Yolact算法的皮带矸石动态计量方法.首先对图像进行预处理,包括滤波、光照增强;然后采用轻量级的残差结构作为Yolact算法的特征提取主干,对皮带矸石进行实时的实例分割;最后二值化矸石分割结果,引入开源跨平台计算机视觉库OpenCV,利用像素阈值计算矸石的具体数量和面积,通过搭建矿用皮带矸石分拣装置,验证矸石计量算法的可行性.结果表明,皮带矸石动态计量方法能够有效学习矸石特征,网络计量皮带中矸石面积和位置信息的准确率为94.66%,网络的检测速度为30.72 FPS.该方法能对煤矿皮带中的矸石进行有效计量.

Abstract

In view of the difficulty for real-time measurement of coal gangue on the belt conveyor in coal mine,a dynamic measurement method of belt Gangue based on Yolact algorithm is proposed in combination with image processing technology and deep learning technology.Firstly,the image is preprocessed,including filtering and illumination enhancement.Then,the lightweight residual structure is used as the feature extraction backbone of Yolact algorithm to segment the belt gangue in re-al time.Finally,binarize the segmentation results of gangue,introduce the open source cross platform computer vision library Opencv,and calculate the specific quantity and area of gangue using pixel threshold.The feasibility of the gangue metering algorithm is verified by building a belt gangue sorting device.The experimental results show that the proposed method can effectively learn the characteristics of gangue.The accuracy of measuring the area and position of gangue on the belt by the network is 94.66%,and the detection speed of the network is 30.72 FPS.The proposed method can effectively measure the gangue on the coal mine belt.

关键词

煤矸石计量/实例分割/智能设备/卷积神经网络

Key words

coal gangue measurement/instance segmentation/intelligent equipment/convolutional neural network

引用本文复制引用

出版年

2024
陕西煤炭
陕西省煤炭工业协会 神华神东煤炭集团有限责任公司 陕西煤业化工集团有限责任公司

陕西煤炭

影响因子:0.204
ISSN:1671-749X
参考文献量18
段落导航相关论文