基于遗传规划的复杂过程优化控制策略
来源期刊:中南大学学报(自然科学版)2003年第4期
论文作者:桂卫华 陈晓方 岑丽辉
文章页码:331 - 334
关键词:遗传规划;多步综合评判;适应度函数;过程优化
Key words:genetic programming; multi-step comprehensive evaluation; fitness function; process optimization
摘 要:根据工业过程优化控制的多目标特性和连续生产平稳性的要求,提出了一种基于遗传规划的优化控制策略.该策略将复杂过程的优化控制看作一个多步的状态转移过程,在生产过程单目标参数辨识模型基础上,通过多步综合评判算法实现了过程多目标的综合评判,在最终的评价函数中引入了对过程状态波动性的惩罚项.遗传规划个体采用由若干时序关系运算符连接形成的链式结构,简化了进化求解过程,有利于指令在控制器上实现.进化得到的最优解是一个多步的过程控制方案,一方面通过调节控制参数使过程状态趋于最优;另一方面又保证参数变化不会过于剧烈,保证连续生产过程平稳.运用该优化控制策略在密闭鼓风炉熔炼过程进行模拟优化和实际应用,结果表明该方法能够实现熔炼过程工况的优化,有利于保持连续生产过程的稳定性.
Abstract: Considering the multi-objective feature and production stability in optimal control of complex process,this paper proposed an optimal control strategy based on genetic programming (GP). The strategy takes processoptimal control as a multi-step state transferring procedure. The fitness function is computed by multi-step comprehensive evaluation algorithm, which provides a synthetic evaluation of multi-objective in process state based on single objective model. The punishment to process state variance is also introduced for considering both optimal performance and stability of production. The individuals in GP are constructed with a chain linked by a few relation operators of time sequence. The optimal solution gained by evolution is a multi-step command schedule of process control, which ensures the optimization tendency and avoids violent process variation by adjusting control parameters. The strategy was applied in imperial smelting process, and the results showed its effectiveness for production objects optimization.