铜闪速熔炼过程操作模式分级匹配技术与演化策略  

Operational pattern hierarchical matching and evolution strategy for copper flash smelting process

作　　者：桂卫华[1] 刘建华[1] 谢永芳[1] 

机构地区：[1]中南大学信息科学与工程学院,长沙410083

出　　处：《系统工程理论与实践》2013年第10期2714-2720,共7页Systems Engineering-Theory & Practice

基　　金：国家863计划项目(2009AA04Z137);国家杰出青年科学基金(61025015);国家自然科学基金(61074117);中央高校基本科研业务费专项(2011JQ009);国家创新群体科学基金(61321003)

摘　　要：针对铜闪速熔炼过程关键工艺参数无法在线检测、过程建模及优化控制困难的问题,阐述了基于数据的铜闪速熔炼过程操作模式优化方法.基于综合工况评判指标及操作模式智能分类方法构建优良操作模式库,在此基础上,提出操作模式分级匹配技术;借助投影寻踪回归思想,建立操作模式与综合工况评判指标之间的非线性关系模型,采用基于实数编码的加速遗传算法进行最优操作模式的获取,实现熔炼过程的优化控制.某冶炼厂生产数据验证了所提方法的可行性.Considering the difficulties of modeling, online-measurement of key process indexes, and optimal control in copper ash smelting process, a data-driven operational pattern optimization control strategy is discussed. Based on the formed superior operational pattern base, the method of hierarchical operational pattern matching and the strategy of operational pattern evolution are presented. The superior operational pattern base is constructed based on comprehensive status evaluation model and pattern classification methods. The projection pursuit regression model is established with the retrieved similar operational pattern set obtained by hierarchical matching. Then the optimal operational parameters are optimized by using the real coding based acceleration genetic algorithm. The simulation results of actual running data are given to verify the feasibility of the strategy proposed.

关 键 词：数据驱动 操作模式 优化控制 投影寻踪回归 铜闪速熔炼 

分 类 号：TP29[自动化与计算机技术—检测技术与自动化装置] TF811[自动化与计算机技术—控制科学与工程]