基于深度学习技术的爆堆块度识别方法研究  

Research on Fragment Size Identification Method of Blasting Pile based on Deep Learning Technology

作　　者：陈立军 蔡国强 张文斌 CHEN Li-jun;CAI Guo-qiang;ZHANG Wen-bin(China Railway 19 Bureau Group Mining Investment Co.,LTD.,Manzhouli 021400,China)

机构地区：[1]中铁十九局集团矿业投资有限公司新巴尔虎右旗分公司,满洲里021400

出　　处：《爆破》2024年第1期196-201,220,共7页Blasting

摘　　要：在露天矿爆破开采过程中,大块率是评价爆破质量的一个重要指标。较高的大块率不仅会大大降低采装效率,同时也增加二次破岩的费用,因此大块率统计是露天矿开采中一项重要工作。针对目前矿山存在的矿岩大块率统计复杂且准确性不高的问题,以乌努格吐山铜钼矿为研究对象,收集了矿区内台阶爆破爆堆图像数据,构建了基于深度学习的爆堆大块率统计模型。首先基于U-net矿岩图像分割模型,初步分割标注处理的数据集,建立了矿岩轮廓初次分割效果图。在残差学习模块基础上,改进Resu-net模型,优化训练标注数据,获得了最终矿岩轮廓分割效果图。最后,采用OpenCV图像处理技术,通过最小外接矩形法确定了爆堆块度尺度信息。结果表明,本研究提出的U-net+Resu-net爆堆块度优化分割模型准确率达到97.84%,爆堆矿岩图像分割数据较准确。通过OpenCV技术与相机单目成像原理相结合的方法,实现了倾斜爆堆矿岩图像的爆堆块度统计。此外,所开发的交互式界面操作简单,可快速统计大块尺寸。满洲里乌努格吐山铜钼矿的应用表明,该方法可高效、准确统计爆堆块度,具有一定的推广价值。Boulder yield is an important index to evaluate the blasting quality in the blasting process of an open pit mine.Since a high boulder yield will not only greatly reduce the mining efficiency,but also increase the cost of secondary rock breaking,so fragments size statistics is an important work in open pit mining.Aiming at the problem that the statistics of fragment size is complex and not accurate enough,a statistical model of boulder yield was built by deep learning based on the takes the image data of blasting piles collected in the Unugetushan copper and molyb-denum mine.Firstly,the annotated data set was initially segmented into an initial effect diagram of the mine rock con-tour based on the U-net image segmentation model.And then,the annotated data for training was optimized and the Resu-net model was improved on the basis of the residual learning module,which resulted in the final segmentation effect map of mine rock contour.Finally,the fragment size information of the blasting pile was obtained through the minimum external rectangle method combined with OpenCV image processing technology.The results show that the segmentation accuracy of U-net+Resu-net fragment size optimization model proposed in this study is 97.84%with an accurate image data segmentation.The statistics of fragment size in an inclined blasting pile is realized by OpenCV technology combined with the camera monocular imaging principle.In addition,the developed interactive in-terface is simple to operate and can quickly calculate the boulder yield.

关 键 词：爆堆块度 深度学习 单目成像 矿石分割 

分 类 号：TU45[建筑科学—岩土工程]