矿用带式输送机胶带表面缺陷检测系统研究  

Defect detection system for mining conveyor belt surface based on reliable region fusion

作　　者：雷高阳 李俊杰 王凯旋 李根生 李海超 LEI Gaoyang;LI Junjie;WANG Kaixuan;LI Gensheng;LI Haichao(School of Information and Control Engineering,China University of Mining and Technology,Xuzhou 221000,China;Xin’an Coal Mine of Henan Dayou Energy Co.,Ltd.,Luoyang 471842,China;School of Information Engineering,Xuzhou College of Industrial Technology,Xuzhou 221140,China;School of Vehicle and Transportation Engineering,Henan University of Science and Technology,Luoyang 471000,China;Hangzhou Olida Elevator Co.,Ltd.,Hangzhou 311600,China)

机构地区：[1]中国矿业大学信息与控制工程学院,江苏徐州221000 [2]河南大有能源股份有限公司新安煤矿,河南洛阳471842 [3]徐州工业职业技术学院信息工程学院,江苏徐州221140 [4]河南科技大学车辆与交通工程学院,河南洛阳471000 [5]杭州奥立达电梯有限公司,浙江杭州311600

出　　处：《煤炭工程》2024年第8期158-164,共7页Coal Engineering

摘　　要：针对矿用带式输送机胶带表面缺陷识别困难、定位不准确的问题,提出了基于可靠区域融合的矿用带式输送机胶带表面缺陷检测系统。首先,利用迁移学习方法和公开数据集训练了YOLOv4及SSD模型,并根据预测分数和重叠情况提出了缺陷检测结果决策级融合方法,决策级融合YOLOv4和SSD两个模型的最大化可靠区域,以此实现带式输送机胶带缺陷识别和定位。结合公开数据集和胶带表面缺陷数据集对所提方法的有效性和可靠性进行了测试和分析,结果表明所提方法能够充分利用YOLOv4和SSD模型的检测结果,取得较高的准确率、召回率和重叠率,且在胶带表面缺陷数据集中达到超过85%的准确率和0.6以上的重叠率,这有利于胶带的缺陷检测和维修保养,从而保证矿用带式输送机的安全可靠运行。Aiming at the difficulties in identifying and locating surface defects on mining conveyor belt,a mining conveyor belt surface defect detection system was designed based on reliable region fusion.Firstly,the YOLOv4 and SSD models were trained using public datasets with the transfer learning,and the decision-level fusion method was proposed for defect detection results based on its predicted score and overlapping situation.At the decision level,the two models of YOLOv4 and SSD are fused to maximize reliable regions,which can achieve defect identification and localization of conveyor belt.The effectiveness and reliability of the proposed method were validated and analyzed through public datasets and mining conveyor belt defect datasets.The results illustrated that the proposed method can fully utilize the detection results of YOLOv4 and SSD models to achieve high accuracy,recall,and overlap rates.It can achieve the accuracy rate and overlap rate of over 85%and 0.6,respectively.The defect detection system is beneficial for defect detection and maintenance of mining conveyor belt,and it is significant for safe and reliable operation of the mining belt conveyor.

关 键 词：矿用带式输送机 缺陷检测 决策级融合 区域融合 图像检测 

分 类 号：TD528[矿业工程—矿山机电]