泡沫图像处理技术在矿物浮选作业中的应用

The Bubble Image Processing Technology in the Application of Mineral Flotation Operation

结合云南省院省校合作项目浮选泡沫层测控系统开发及产业化研发过程,介绍一种基于数字图像处理及识别技术的浮选过程控制新思路。在浮选生产中,浮选泡沫表面纹理与浮选工况密切相关,直接反映泡沫层的矿化程度(品位高低)。通过对云南某铅锌矿选厂浮选泡沫图像的分析处理,提取出能够表示泡沫层特征的参数,达到间接测量气泡的大小、纹理、稳定性、流动性等泡沫层特征状况。采用邻域灰度相关矩阵法提取特征参数,然后用神经网络进行分类,给出浮选效果的分类判断。

Combined with the college-province-university cooperation project of Yunnan province of flotation foam layer control system development and industrialization process, a new thinking of process control of flotation based on digital image processing and recognition technology was introduced in this paper. In the production of flotation, the flotation foam surface texture and flotation conditions are closely related. The flotation foam surface texture can reflect the degree of mineralization of the foam layer （the grade of mineralization） directly. Through the analysis processing of flotation foam image in a lead--zinc mineral produce factory of Yunnan province, the characteristic parameters of foam layer were obtained. The size, the texture, the stability and the fluidity of the foam layer status can be measured indirectly based on these parameters. The correlation matrix of neighborhood was used to extract the characteristic parameters. And then the neural network was used to classify and to make a classification judge to the flotation effect.