基于泡沫纹理信度分配SVM的矿物浮选工况识别  

Performance recognition using texture credit distributed SVM for froth flotation process

作　　者：阳春华[1] 任会峰[1] 桂卫华[1] 鄢锋[1] 唐朝晖[1] 

机构地区：[1]中南大学信息科学与工程学院,长沙410083

出　　处：《仪器仪表学报》2011年第10期2205-2209,共5页Chinese Journal of Scientific Instrument

基　　金：国家杰出青年科学基金(61025015);国家自然科学基金(61071176);国家863计划(2009AA04Z124)资助项目

摘　　要：针对矿物浮选过程中泡沫纹理各向异性、纹理特征信度差异以及类间样本数分布不均等问题,提出一种浮选工况的自动识别方法。首先基于多角度融合的空间灰度共生矩阵计算角二阶矩、熵、惯性矩、逆差矩和相关性等二阶统计量描述泡沫纹理特征,然后引入信息熵的概念,以二阶统计量的信息增益分配各种纹理特征对分类器的信度,再通过类间样本数加权策略消除样本分布的不平衡性,最后实现了一对一加权支持向量机的浮选工况识别。工业现场泡沫图像测试结果表明,该方法能够有效降低小样本的错分率,提高整体识别率。A performance recognition method for mineral froth flotation process is presented,where multiple imbalance exists in texture directions,feature credit and sample distribution.Firstly,second order statistics such as angular second moment,entropy,moment of inertia,moment of deficit and relevance are extracted based on four-direction fused spatial gray co-occurrence matrix to avoid the adverse effects of directions.Then information entropy is introduced to evaluate the feature credit of the texture features via the information gains.Furthermore,the imbalance of sample distribution is eliminated with between-class weighted strategy,and a performance recognition model is established using one-versus-one weighted support vector machine（OVO-WSVM）.Industrial on-site experiment verifies that the proposed method can decrease the misclassification rate of small samples and increase overall recognition rate.

关 键 词：泡沫浮选 工况识别 纹理特征 信度分配 支持向量机 

分 类 号：TP274.3[自动化与计算机技术—检测技术与自动化装置]