已证实专家系统是选矿控制的极好工具。以矿石类型在线分类为基础的专家系统已设计完成,并在本文中进行了阐述。近年来,神经网络计算法已崭露头角,可用于计算那些大多数传统方法已证明无法解决的问题。研究中,对在线聚类法与矿石分类的克赫诺特征图进行了比较。研究所用测试数据取自奥托昆普黑特诺(Hi-tura)矿。 Expert system has proven to be an excellent tool for beneficiation control. An expert system based on online classification of ore types has been designed and described in this paper. In recent years, neural network computing has come to the forefront and can be used to calculate the problems that most of the traditional methods have proved impossible to solve. In the study, the König feature maps of on-line clustering and ore classification were compared. The test data used for the study was taken from the Hi-tura mine.