基于人工神经网络模型的含锑硫化矿氧化浸出行为预测

来源期刊:中国有色金属学报2018年第10期

论文作者:田庆华 洪建邦 辛云涛 郭学益

文章页码:2103 - 2112

关键词:人工神经网络;浸锑过程;预测;相关系数;相对重要性

Key words:BP neural network model; leaching process of antimony; prediction; correlation coefficient; relative importance

摘    要:锑的浸出率是氧化处理含锑硫化矿时的重要结论指标,在氧化浸出过程中通过条件控制来得到更好的浸出率具有十分重要的意义,为了模拟和预测含锑硫化矿的氧化浸出过程,用人工神经网络模型对浸锑过程进行模拟,建立起单隐层8节点的“5-8-1型”误差逆向传播神经网络模型,所建人工神经网络模型可以对反应过程做出有效的模拟和预测,实验值与预测值的相关系数可达99%以上。并根据所建神经网络模型中不同输入量在网络中节点权重的不同,得出相关条件因素对锑浸出率的相对重要性从高到低依次为:盐酸浓度,反应温度,搅拌速度,液固比,反应时间。

Abstract: The leaching rate of antimony is an important index for the treatment of antimony sulfide ore. It is very important to obtain better leaching rate through conditional control in the process of oxidation leaching. In order to simulate and predict the oxidation leaching process of antimony containing sulfide ore, BP Neural network model was used to simulate the leaching process of antimony, and a 5-8-1 type model was established. The neural network model could predict the leaching efficiency of antimony in the process exactly, the correlation coefficient between experimental data and predicted data could reach 99%. According to the weights of inputs in the neural network model, the importances of different impacts are in the descending order: HCl concentration, temperature, stirring speed, liquid to solid ratio, time.

相关论文

  • 暂无!

相关知识点

  • 暂无!

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号