基于视觉监控的煤矿传送带防冻液自动喷洒系统
Automatic antifreeze spraying system for coal mine conveyor belt based on visual monitoring
张凯 1郝康将 2刘卓昆 3彭甫镕 2李国栋4
作者信息
- 1. 晋能控股装备制造集团 信息中心,山西 晋城 048000
- 2. 山西大学 大数据科学与产业研究院,山西 太原 030006
- 3. 泰国易三仓大学 马丁德图尔管理与经济学院,泰国 北榄府 10270
- 4. 太原科技大学 材料科学与工程学院,山西 太原 030024
- 折叠
摘要
为解决煤矿煤炭传送过程中,操作人员因失误、疲劳导致防冻液喷洒不足或过量,致使煤炭与传送带粘连或打滑,进而造成生产事故的问题,研发了一种基于视觉监控的煤矿传送带防冻液自动喷洒系统.通过边缘算法对现场传送带图像的检测识别与分类,系统对防冻液阀门下达远程控制指令,完成防冻液的自动喷洒.引入一种基于u-net的图像数据增强方法(U-NHME)对原数据集样本进行增强,然后采用YOLO-V7 作为网络进行目标定位与识别,实现了全天候室外图像的准确识别.采用Map等评价指标对不同煤量的图像进行增强、训练与识别.实验结果表明,相比YOLO-V7 原始网络,本研究算法的识别精度提高了2 百分点,提高了传送带煤量识别精度.
Abstract
Aiming at the insufficient or excessive antifreeze spraying due to manual operation during coal transmission in coal mines,resulting in the adhesion or slippage of coal on conveyor belts,and then causing production accidents,an automatic antifreeze spraying system for coal mine conveyor belts based on visual monitoring is developed.Through the detection,recognition and classification of on-site conveyor belt images by edge algorithms,the system issues remote control instructions to the antifreeze valve to complete the automatic spraying of antifreeze.A u-net-based image data augmentation method(U-NHME)is introduced to augment the original dataset samples,and then YOLO-V7 is used as the network for target localization and recognition,so as to achieve accurate recognition of all-weather outdoor images.Map and other evaluation indexes are used to enhance,train and recognize images with different coal quantities.Experimental results show that,compared with the original YOLO-V7 network,the recognition accuracy of the proposed algorithm is 2 percentage points higher,and the recognition accuracy of conveyor belt coal quantity is improved.The system is highly reliable and scalable,bringing a more efficient,safe and environmentally friendly production method to the coal industry.
关键词
计算机视觉/图像增强/煤量识别/自动控制/防冻液喷洒Key words
computer vision/image enhancement/coal quantity identification/automatic control/antifreeze spraying引用本文复制引用
出版年
2024
NETL
NSTL
万方数据