烧结机尾断面图像在线处理与分析方法研究  

Study on Method for On-line Processing and Analyzing Sectional Image of Sintering Machine Discharge End

作　　者：宋宝宇[1] 杨春雨[1] 杨东晓[1] 费静[1] 王奎越[1] 

机构地区：[1]鞍钢股份有限公司技术中心,辽宁鞍山114009

出　　处：《鞍钢技术》2011年第3期13-17,共5页Angang Technology

摘　　要：针对烧结机尾断面图像的特点,提出一种在二维直方图上基于优化模糊C-均值聚类与分层划分的图像分割方法,结合轮廓增强等预处理手段,可以快速、高效的对烧结机尾断面图像进行在线处理。在提取图像中有效特征的基础上,采用BP神经网络建立数据分析框架,并结合现场看火经验,对其进行训练。试验结果表明,该方法稳定可靠,图像分割迅速,分析结果准确。According to the characteristic of cross section image of the sintering machine tail,this paper gives an image segmentation method based on optimization FCM and layered dividing on Two-dimensional Histogram.Combined with the preprocessing technique of the edge enhancement,the cross section image of sintering machine tail can be on-line processed rapidly and effectively.Based on extracting the valid image characteristic and using BP neural network,the data analysis frame is established and trained associated with the experience of the plant operator.The experiment results show that this method is stable and reliable,which divides the image rapidly and analyzes the results exactly.

关 键 词：烧结机 图像处理 模糊C-均值聚类 BP神经网络 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]