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

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.