摘要
为了实现煤矿输送带纵向撕裂快速准确检测,设计了一种基于机器视觉的矿用输送带纵向撕裂识别仪。相比于传统的漏料检测法、压力检测法及非接触式的X射线检测法、音频检测法等方法,基于机器视觉的输送带纵向撕裂检测精度更高,应用范围更广,并可实时在线显示输送带特征图像。首先介绍了该仪器的总体架构和原理,其次详细介绍了AI计算模块等各种电路,然后介绍了输送带纵向撕裂识别的软件设计,最后在带式输送机上进行了试验验证。测试结果表明,该仪器检测精度及准确率高、实时性好,并可直观展示,满足煤矿智能化建设对输送带纵向撕裂检测的需求。
In order to achieve rapid and accurate detection of longitudinal tearing of coal mine conveyor belt,a longitudinal tearing recognition instrument for mining conveyor belt based on machine vision was designed.Compared to traditional methods such as leak detection,pressure detection,non-contact X-ray detection and audio detection,etc.,the conveyor belt longitudinal tearing detection based on machine vision has higher accuracy and wider application range,and can display conveyor belt characteristic imagesin real-time online.Firstly,the overall architecture and principle of this device were introduced.Secondly,various circuits such as the AI calculation module were detailed.Then,the software design of conveyor belt longitudinal tearing recognition was introduced.Finally,experimental verification was carried out on the belt conveyor.The test results show that this device has high detection accuracy and real-time performance,and can be visually displayed,which meets the needs of coal mine intelligent construction for conveyor belt longitudinal tearing detection.
作者
向兆军
Xiang Zhaojun(Chongqing Research Institute,China Coal Technology and Engineering Group,Chongqing 400039,China)
出处
《煤矿机械》
2025年第6期208-211,共4页
Coal Mine Machinery
基金
中煤科工集团重庆研究院有限公司重点研发项目(2022ZDXM02)。
关键词
输送带
纵向撕裂
机器视觉
线激光
神经网络
conveyor belt
longitudinal tearing
machine vision
line laser
neural network
