文献类型：期刊文献

中文题名：煤矿带式输送机分拣机器人异物识别与定位系统设计

英文题名：Design of foreign object recognition and positioning system for sorting robot of coal mine belt conveyor

作者：薛旭升[1,2];杨星云[1,2];齐广浩[3];马宏伟[1,2];毛清华[1,2];尚新芒[4]

第一作者：薛旭升

机构：[1]西安科技大学机械工程学院,陕西西安710054;[2]陕西省矿山机电装备智能检测与控制重点实验室,陕西西安710054;[3]北京联合大学北京市信息服务工程重点实验室,北京100101;[4]西安重装韩城煤矿机械有限公司,陕西韩城715400

第一机构：西安科技大学机械工程学院,陕西西安710054

年份：2022

卷号：48

期号：12

起止页码：33-41

中文期刊名：工矿自动化

外文期刊名：Journal Of Mine Automation

收录：CSTPCD;;北大核心:【北大核心2020】；

基金：国家重点研发计划青年科学家项目(2022YFF0605300);国家自然科学基金面上项目(51975468);陕西省自然科学基础研究计划项目(2019JQ-802);国家自然科学基金重点项目(51834006);西安市科技计划项目(22GXFW0067)。

语种：中文

中文关键词：煤矿带式输送机;分拣机器人;机器视觉;双目视觉;目标异物;异物识别与定位

外文关键词：coal mine belt conveyor;sorting robot;machine vision;binocular vision;target foreign object;foreign object recognition and positioning

摘要：机器视觉已在煤矿带式输送机分拣机器人目标检测与识别方面具有一定的理论基础,但目前煤矿带式输送机分拣机器人目标识别主要针对煤矸石识别,对造成输送带穿透、撕裂等的异物目标识别的研究较少,且在目标异物精确定位方面的研究也较少。针对上述问题,设计了一种基于机器视觉的煤矿带式输送机分拣机器人异物识别与定位系统,可对输送带上存在的不同类型和不同形状的异物进行识别与定位。采用双目视觉实时获取输送带上异物图像信息,并对图像进行预处理,基于Canny算子进行图像信息增强,通过灰度拉伸方法改进图像边缘信息,突出煤矿带式输送机上异物的边缘特征;利用形态学方法提取异物形状特征,建立异物图像特征样本库,通过图像特征匹配的方式解算出异物存在区域,实现异物类型的检测、分类与识别;在异物类型成功识别的基础上,以目标异物边缘特征值为基础,建立目标异物的感兴趣区域(ROI),构建相机、输送带与目标异物坐标转换关系,利用多目标质心快速计算方法求取目标异物质心坐标,实现对目标异物的定位。系统样机实验结果表明:煤矿带式输送机分拣机器人异物识别与定位系统异物识别率不受尺寸、材质和颜色等因素影响,能够实现输送带目标异物图像的采集、处理、特征提取、识别和位置定位,识别率为92.5%以上,目标异物位置定位平均误差为3%左右。
Machine vision has a certain theoretical basis in target detection and recognition for sorting robot of coal mine belt conveyor.But current target recognition of sorting robot of coal mine belt conveyor is mainly aimed at coal-gangue recognition.There are few kinds of research on the recognition of foreign object targets causing conveyor belt penetration and tearing,and also few kinds of research on the precise positioning of target foreign object.In order to solve the above problems,a foreign object recognition and positioning system based on machine vision for sorting robots of coal mine belt conveyor is designed.The system can recognize and position different types and shapes of foreign objects on the conveyor belt.The image information of the foreign objects on the conveyor belt in real-time is obtained by adopting binocular vision,and the image is preprocessed.Image information is enhanced based on the Canny operator.The gray stretching method is used to improve image edge information to highlight the edge features of foreign objects on coal mine belt conveyor.The morphological method is used to extract foreign object shape features,and establish foreign object image feature sample library.The image feature matching method is used to solve the existing area of foreign objects to realize the detection,classification and recognition of foreign objects.On the basis of the successful recognition of foreign object type,the region of interest(ROI)of the target foreign object is established based on the edge feature value of the target foreign object.The coordinate conversion relationship is built between the camera,conveyor belt and target foreign object.The fast multi-target centroid calculation method is used to obtain the centroid coordinate of the target foreign object,so as to realize the positioning of the target foreign object.The experimental result of the system prototype shows that the foreign object recognition rate of foreign object recognition and positioning system for sorting robot of coal mine belt conveyor is not affected by the size,material,color and other factors,the system can realize the image acquisition,process,feature extraction,recognition and positioning of the target foreign object of coal mine conveyor belt.The recognition rate is above 92.5%,and the average error of the target foreign object positioning is about 3%.