基于图像识别技术的刮板链故障检测方法研究  

Research on Method for Fault Detection of Scraper Chain Based on Image Recognition Technology

作　　者：焦瑞 刘宇轩 苏醒 闫小鹏 李旺 沈丰 杨皓 Jiao Rui;Liu Yuxuan;Su Xing;Yan Xiaopeng;Li Wang;Shen Feng;Yang Hao(Ninxia Tiandi Benniu Industrial Group Co.,Ltd.,Yinchuan 750000,China;National and Local Joint Engineering Laboratory of Intelligent Manufacturing Technology for Coal Mine Comprehensive Mining and Transportation Equipment,Shizuishan 753001,China)

机构地区：[1]宁夏天地奔牛实业集团有限公司,银川750000 [2]煤矿综采输送设备智能制造技术国家地方联合工程实验室,宁夏石嘴山753001

出　　处：《煤矿机械》2024年第12期163-167,共5页Coal Mine Machinery

基　　金：宁夏回族自治区重点研发计划项目(2024BEE04007);中国煤炭科工集团第四批项目收益分红激励项目(2024CGZH01);天地科技股份有限公司科技创新创业资金专项项目(2024-TD-MS011)。

摘　　要：煤矿井下刮板输送机链条断裂多发于使用初期磨合和后期疲劳阶段,主要由设备刮卡、链条磨损及变形引起。现有基于霍尔传感器和电感类接近开关的监测手段在复杂矿井环境下效果有限,尤其是在预测链条临近断裂状态方面。因此提出了采用图像识别技术的刮板链故障检测方法,详细介绍了该技术的基本原理与实际应用,旨在提高刮板链组件故障的识别精度和预警能力。For scraper conveyor chains in underground coal mine,chain breakages predominantly occur during the initial running-in phase and later stages of fatigue,primarily due to equipment abrasion,chain wear and deformation.Current monitoring techniques using Hall sensors and inductive proximity switches have limited effect in complex mine environments,especially in predicting the pre-fracture state of chains.Therefore,proposed scraper chain fault detection method using the image recognition technology.Introduced the fundamental principles and practical applications of this technology in detail,so as to enhance the accuracy of fault identification and early warning capabilities for scraper chain component.

关 键 词：图像识别 图像处理 特征提取 系统选型 参数设定 

分 类 号：TD528.3[矿业工程—矿山机电]