基于图像处理的生球粒度检测研究

Research on Particle Size Detection of Green Balls Based on Image Processing

球团矿是高炉炼铁的主要原材料之一,生球的粒度分布是影响球团矿质量的关键指标之一,因此准确测量球团粒度分布至关重要。针对传统方法中存在的不完全分割、过度分割等问题,提出了利用U-Net++网络来检测旋转圆盘造球机静止层的生球粒度分布。实验结果表明,该方法可以实现生球粒度的精准分割与粒度检测,并且得到的粒度检测结果与人工筛分结果相似。

Pellet ore is one of the main raw materials for blast furnace iron making.The particle size distribution of green ball is one of the key indexes affecting the pellet quality,so it is very important to accurately measure the particle size distribution of pellet.Aiming at the problems of incomplete segmentation and over-segmentation in traditional methods,a U-Net++network is proposed to detect the particle size distribution of green pellets in the stationary layer of a spinning disk pelletizer.The experimental results show that the method can realize the precise segmentation and particle size detection of green pellets,and the obtained particle size detection results are similar to those obtained by manual sieving.