基于改进PSO-KMeans煤炭异物筛选算法研究  

Research on Foreign Matter Screening Algorithm in Coal Based on Improved PSO-KMeans

作　　者：朱名乾 刘宾[1] ZHU Mingqian;LIU Bin(School of Information and Communication Engineering,North University of China,Taiyuan 030051)

机构地区：[1]中北大学信息与通信工程学院,太原030051

出　　处：《舰船电子工程》2024年第2期35-39,共5页Ship Electronic Engineering

基　　金：国家自然基金青年基金项目(编号:62201520)资助。

摘　　要：采煤过程中异物自动识别和分拣是实现矿业信息化的关键技术之一。传统双能X射线系统根据R值算法可有效识别出煤炭中混杂的钢筋与胶皮,却难以识别与煤炭组成成分相似的木质杂质。针对这一问题,提出基于L_(0)范数最小化与改进PSO-KMeans的木质杂质筛选算法,借助L_(0)范数最小化算法平滑图像,去除煤灰干扰,利用改进PSO-KMeans聚类算法与基于距离变换的分水岭算法实现图像分割,根据离心率与矩形度进行木质杂质识别,并通过仿真实验验证方法的可行性。经验证此方法能有效筛选出煤炭中混杂的木质杂质。Automatic identification and sorting of foreign matters are key technologies to realize mining informatization.The traditional dual energy X-ray system can effectively identify the mixed iron and rubber by R-value algorithm.But it is difficult to identify the wooden impurities similar to coal.To solve the problem,a wooden impurities screening algorithm based on L_(0) norm mini⁃mization and improved PSO-KMeans is proposed.The image is smoothed by L_(0) norm minimization to remove coal ash.And it can be segmented by improved PSO-KMeans algorithm and watershed algorithm based on distance transformation.Later,wooden impuri⁃ties can be identified according to eccentricity and squareness.With simulation experiment,it is verified that this method can effec⁃tively screen out the mixed wooden impurities in coal.

关 键 词：L_0范数最小化算法 粒子群优化算法 K均值聚类算法 分水岭算法 

分 类 号：TN911.73[电子电信—通信与信息系统]