铜冶炼节能参数优化学习模型研究  

The module of energy saving parameter optimization of copper smelting

作　　者：张晓龙[1] 尧世文[2] 胡建杭[1] 董人菘[1] 王华[1] 

机构地区：[1]昆明理工大学冶金节能减排教育部工程研究中心,云南昆明650093 [2]云南铜业股份有限公司冶炼加工总厂,云南昆明650093

出　　处：《计算机与应用化学》2012年第7期822-824,共3页Computers and Applied Chemistry

基　　金：国家自然科学基金资助项目(50906035)

摘　　要：针对铜冶炼过程中的能耗难以预测的问题,提出基于支持向量回归的铜冶炼节能过程参数优化学习方法:,首先分析影响铜能耗的各种参数,然后利支持向量回归算法对输入参数和输出能耗之间的关系进行训练,从而筛选出最优参数,为生产能耗控制模型提供了基础。实验结果:表明,提出方法:较传统的BP神经网络算法相比具有学习速度快,收敛性好,泛化能力强等特点,且能耗预测的平均相对误差小于7%。For the energy consumption problem in the copper smelting process, this paper proposes an energy saving parameter optimization approach based on support vector regression. First analysis of various parameters affecting the copper energy consumption, then the relationship between input parameters and output energy training support vector regression algorithm, which filter out the optimal parameters to provide a basis for the production of energy control model. The experimental results show that the proposed method compared to more traditional BP neural network with fast learning speed, convergence and generalization ability, and energy consumption forecast average relative error of less than 7%.

关 键 词：铜冶炼 艾萨炉 能耗 支持向量回归 

分 类 号：TQ015.9[化学工程] TP391.9[自动化与计算机技术—计算机应用技术]