局部颜色特征与工艺参数融合的铜浮选入矿类型识别  

Identification of type of copper flotation feeding ore using fusion information of local color features and process parameters

作　　者：卢明[1] 谢永芳[1] 彭涛[1] 桂卫华[1] 

机构地区：[1]中南大学信息科学与工程学院,湖南长沙410083

出　　处：《控制理论与应用》2014年第10期1360-1367,共8页Control Theory & Applications

基　　金：国家创新研究群体科学基金资助项目(61321003);国家自然科学基金重点项目资助项目(61134006);国家自然科学基金资助项目(61273169;61473318);中央科研基本业务费中南大学国家杰青培育专项基金资助项目(2011JQ009);高等学校博士学科点专项科研基金优先发展领域资助课题(20110162130011)

摘　　要：针对铜浮选过程中矿源变化频繁而造成的浮选工况难以识别、生产过程不稳定等问题,在分析铜浮选流程特点的基础上,提出了一种局部颜色特征与关键工艺参数融合的铜浮选入矿类型识别方法.首先采用多元图像处理方法提取泡沫图像局部颜色特征,然后采用混合滤波、时间配准算法将其与关键工艺参数进行数据融合,最后用融合后的混合特征进行模糊聚类,得到隶属度矩阵和聚类中心.工业数据仿真结果验证了本文所提方法的有效性.The diversification of ore sources in a copper flotation process often causes difficulty in indentifying theflotation conditions as well as the instability of the production process. Considering the characteristics of copper flotationprocess, we put forward a feeding ore type recognition method using the fusion information of local color features and keyparameters of the process. Firstly, the local color feature of copper flotation froth image is extracted based on multivariateimage analysis method; then, it is fused with key process parameters based on the hybrid filter and time alignment algorithm,Finally, the mixed feature matrix after fusion is used in fuzzy clustering to obtain the membership matrix and the clustercenters. The proposed method is validated by simulation results of industry data.

关 键 词：铜浮选过程 局部颜色特征 工艺参数 数据融合 入矿类型 模糊聚类 

分 类 号：TD923[矿业工程—选矿] TD952