选矿摇床智能巡检机器人开发与应用

摇床受处理量、给矿浓细度等条件变化影响,床面各条矿带的颜色、位置、宽度时常改变,需要人工及时调整接矿板的位置以达到合格的精矿品位,工人劳动强度大。为了实现摇床作业的自动巡检和操作,通过计算机视觉技术采集摇床矿带照片,研究了矿带图像识别算法,并在此基础上开发了摇床智能巡检机器人。工业试验表明,摇床智能巡检机器人实现了对一组多张摇床矿带的自动采图,图像识别算法实现了对矿带宽度、边界和颜色特征的数字化识别解析,实现了自动调节接矿板至目标位置,达到了替代人工、提升选矿指标的目的。

Development and Application of Intelligent Inspection Robot for Table Concentrator

The colour, position and width of mineral belts on the table concentrator usually change due to the variations of feed capacity, ore size and pulp density, then operators need to adjust the partition plate position in time to reach the qualified concentrate grade, workers have to work in labor-intensive. The table concentrator mineral belt images were sampled by machine vision to develop the mineral belt images recognition algorithm. On this basis, an automatic inspection robot was developed.Results from industrial experiments are reported the automatic inspection robot of table concentrator can realize continuous sampling mineral belt images of a group of table concentrators. The image recognition algorithm can exactly obtain the width, boundary and colour features of the mineral belts and the robot can automatically adjust the plate to the position of the qualified concentrate grade, thus achieving the goal of replacing manual labor and improving the mineral recovery.