基于多特征融合的浮选尾煤灰分检测  

Ash content detection of flotation tailings based on multi-feature fusion

作　　者：刘航涛 吕振福[1,2] 丁国峰 李作敏 张博冉[1,2] 周脉强 LIU Hangtao;LYU Zhenfu;DING Guofeng;LI Zuomin;ZHANG Boran;ZHOU Maiqiang(Zhengzhou Institute of Multipurpose Utilization of Mineral Resources,CAGS,Zhengzhou 450006,China;China National Engineering Research Center for Utilization of Industrial Minerals,Zhengzhou 450006,China;School of Chemical Engineering and Technology,China University of Mining and Technology,Xuzhou 221116,China)

机构地区：[1]中国地质科学院郑州矿产综合利用研究所,河南郑州450006 [2]国家非金属矿资源综合利用工程技术研究中心,河南郑州450006 [3]中国矿业大学化工学院,江苏徐州221116

出　　处：《煤炭工程》2025年第2期186-193,共8页Coal Engineering

基　　金：中国地质调查局基础地质调查项目(DD20221699)。

摘　　要：针对基于浮选尾煤图像的灰分检测特征提取种类单一、不全面等问题,提出了一种基于机器视觉多特征融合的尾煤灰分预测方法。在浮选现场获取工业尾煤图像数据集,采用RGB(红、绿、蓝)颜色、灰度、灰度共生矩阵等常规特征和颜色共生矩阵特征对尾煤图像进行描述;通过相关性矩阵研究图像特征与尾煤灰分之间的关系;采用主成分分析法(PCA)降低原始特征维数,以不同主成分个数作为输入,尾煤灰分作为输出,构建支持向量回归(SVR)模型进行尾煤灰分预测。试验结果表明:多特征融合显著提高了尾煤灰分预测模型精度,更加全面地描述了尾煤特征,并且模型性能优于以单一类型特征作为输入的模型,此方法可为浮选智能化建设提供理论依据。To solve the problem of single and incomplete feature extraction types in ash detection based on flotation tailings images,a method for predicting the ash content of tailings based on machine vision multi feature fusion was proposed.An industrial tailings image dataset was obtained on the flotation field.RGB(Red,Green,and Blue)color features,grayscale features,gray level co-occurrence matrix features and color co-occurrence matrix features were used to describe tailings images.The relationship between features and ash content of tailing was studied through correlation matrix.Principal component analysis(PCA)was used to reduce the dimensions of primary feature space,principal components with different numbers were used as inputs,tailings ash content was used as output,and a support vector regression(SVR)model was built to predict the tailings ash content.The experimental results show that the multi-feature fusion significantly improves the accuracy of the tailings ash content prediction model,provides a more comprehensive description of the tailings characteristics,and performs better than models that use a single type of feature as input.This method can provide a theoretical basis for the intelligent construction of flotation.

关 键 词：尾煤灰分 颜色共生矩阵 特征融合 主成分分析 支持向量回归 

分 类 号：TD94[矿业工程—选矿]