基于多变量图像分析的铜矿泡沫浮选分类与识别  

Classification and Recognition for Copper Froth Flotation Process Based on Multivariate Image Analysis

作　　者：徐德刚[1] 赵盼磊 陈晓[1] 谢永芳[1] 阳春华[1] 

机构地区：[1]中南大学信息科学与工程学院,长沙410083

出　　处：《北京工业大学学报》2014年第7期967-973,共7页Journal of Beijing University of Technology

基　　金：国家自然科学基金资助项目(61104135);中国博士点基金资助项目(20110162130011);中国博士后基金特别资助项目(2012T50705)

摘　　要：针对矿物浮选过程中以人工观测为主的浮选状态监测易受人主观因素影响,长流程的浮选现场难以实时获得生产状态信息,引起在线监测信息的不准确性及滞后,严重影响浮选生产工况及时调整,造成生产过程资源和能源浪费的问题,基于多变量图像分析方法研究矿物加工领域的泡沫浮选过程泡沫图像的分析与特征表征,并融合多变量图像分析、多分辨率分析、多分辨率-多变量图像分析、改进分水岭的图像分割算法和基于模板匹配的宏块跟踪方法,提取铜矿泡沫图像的颜色、纹理、尺寸、速度和稳定度特征.在此基础上,对铜矿泡沫浮选生产状态进行了分类与识别,并建立泡沫图像变量特征与工艺指标之间的关系模型,可用来预测铜矿泡沫品位.应用结果表明:该方法可实现铜矿浮选过程的实时监控及生产状态的识别.Monitoring the flotation based on artificial observation in the mineral flotation process is vulnerable to subjective factors. It is very difficult to derive the status information because of the long process of flotation production. This will lead to information inaccuracy and serious lag for the online monitoring process, which affects the adjustment of flotation conditions and brings about a huge waste of resources and energy. Based on multivariate image analysis methods, this paper studied the process of froth flotation in the field of mineral processing in term of image analysis and characterization methods. This method integrates multivariate image analysis, multi-resolution analysis, multi-resolution-multivariate image analysis, improved watershed segmentation image algorithms and template matching method, which can be used to extract the color, texture, size, speed, and stability characteristics of copper froth images. Furthermore, the copper production status of froth flotation can be classified and identified, and the relationship model between the characteristics of forth image variables and process indicators is established. The method can be used to predict the froth grade of copper pulp and monitor the indicators of copper production process with identifying different flotation status.

关 键 词：多变量图像 泡沫浮选 泡沫图像 品位 

分 类 号：TP27[自动化与计算机技术—检测技术与自动化装置]