融合CBAM的Mask R-CNN模型在球团识别与粒径测量中的应用  

Application of Mask R-CNN model combined with CBAM in pellets identification and particle size measurement

作　　者：王猛 刘卫星 李喆 李浩 齐西伟 杨爱民 WANG Meng;LIU Weixing;LI Zhe;LI Hao;QI Xiwei;YANG Aimin(North China University of Science and Technology Institute of Metallurgy and Energy,Tangshan 063210,Hebei,China;North China University of Science and Technology Comprehensive Test and Analysis Center,Tangshan 063210,Hebei,China;North China University of Science and Technology College of Science,Tangshan 063210,Hebei,China;North China University of Science and Technology Hebei Engineering Research Center for Iron Ore Optimization and Pre-Iron Process Intelligence,Tangshan 063210,Hebei,China)

机构地区：[1]华北理工大学冶金与能源学院,河北唐山063210 [2]华北理工大学综合测试分析中心,河北唐山063210 [3]华北理工大学理学院,河北唐山063210 [4]华北理工大学铁矿石优选与铁前工艺智能化河北省工程研究中心,河北唐山063210

出　　处：《烧结球团》2025年第1期85-94,125,共11页Sintering and Pelletizing

基　　金：河北省教育厅青年科学基金资助项目(QN2024226)。

摘　　要：球团粒径的大小是影响高炉透气性、高炉冶炼效率与能源消耗的主要因素之一。本文针对工业条件下球团粒径难以精准测量的问题,采用融合注意力机制Mask R-CNN模型对球团进行分割与粒径测量。在对球团图像进行预处理后,构建了球团数据集,对比了多种主干网络的训练表现,并与多个分割模型进行了精度对比。此外,利用像素点统计分割掩膜面积实现了球团粒径的测量。结果表明,ResNet50作为主干网络在球团的特征提取中更具优越性。引入Convolutional Block Attention Module(CBAM)的Mask R-CNN模型对比初始模型A mean提高了2.18%。对比BlendMask、SOLOv2、YOLACT以及CondInst等分割模型,改进后的模型在分割精度上也有优势,并能更好地处理分割细节。此外,与Image J测量的球团粒径相比,本文所提出的球团粒径测量方法的最大误差保持在±1.8 mm之内,A_(IoU=0.5)可达到0.9483。The pellet size is one of the main factors affecting blast furnace air permeability,blast furnace smelting efficiency and energy consumption.In order to solve the problem that the pellet size is difficult to measure accurately under industrial conditions,the Mask R-CNN model combined with attention mechanism is used to segment and measure the pellet size.After preprocessing the pellets image,the pellet dataset is constructed,the training performance of a variety of backbone networks is compared,and the accuracy is compared with multiple segmentation models.In addition,the pellet size is measured by using the pixel statistically segment mask area.The results show that ResNet50 is superior as the backbone network in feature extraction of pellets.The Mask R-CNN model of Convolutional Block Attention Module(CBAM)is introduced,which improve by 2.18%compared to the initial model A mean.Compared with BlendMask,SOLOv2,YOLAT and CondInst,the improved model also has advantages in segmentation accuracy and can better handle segmentation details.In addition,compared with the pellet size measured by Image J,the maximum error of the pellet size measurement method proposed in this paper is kept within±1.8 mm,and A_(IoU=0.5)can reach 0.9483.

关 键 词：球团粒径 Mask R-CNN 迁移学习 ResNet CBAM 

分 类 号：TF046.6[冶金工程—冶金物理化学] TP18[自动化与计算机技术—控制理论与控制工程]