用非线性建模选取选矿工艺参数值

Selection of Parameter Values of Mineral Processing Technology Using Nonlinear Modelling

神经网络在用于选矿厂建模过程中 ,一般只用于预测选矿效果 ,很少用于指导选矿现场。本研究利用神经网络 ,从选矿生产历史数据本身出发 ,找到精矿品位和回收率与药剂用量的非线性关系 ,利用此关系确定药剂的用量 。

When used in the modelling of concentrator, neural network is generally used to predict the beneficiation results and seldom used for giving on site guidance. In this study, neural network is used to find the linear relationship between the concentrate grade, the recovery and the reagent dosage from the historical data of mineral processing, which is then used to determine the reagent dosage, so as to give on site guidance in concentrator production.