量子鱼群算法优化RBF网络的浮选预测模型

传统的浮选过程分析主要依靠人工化验,其采样化验周期较长,难以满足控制要求,使得浮选精矿品位偏低,因此建立浮选精矿品位预测模型是必要的。利用神经网络在非线性复杂系统研究中的优势,在分析浮选过程工艺指标相关影响因素的基础上建立了一种基于量子鱼群算法优化的RBF神经网络预测模型。仿真结果表明,提出的模型能准确地对浮选过程的经济指标进行全局预测,满足优化浮选药剂添加的计算要求。

Application of RBF-net in flotation prediction model based on quantum artificial fish school algorithm

The traditional analysis procedure in flotation mainly rely on manual test which has a longer sam-pling test cycle and is difficult to satisfy the control requirement,it is leading to low flotation ore grade,there-fore,it is necessary to design a prediction model of flotation ore grade. Using the advantage of nonlinear com-plex system of neural network,a RBF network prediction model based on quantum fish school algorithm is de-signed through analyzing the related factors. The simulation results show that the model can predict globally the economic indexes of flotation process,and satisfy the computational requirements of optimizing adding flotation medicament.