建立宽厚板轧制负荷分配模型的一种新方法

A New Method for Building Load-distributing Model in Plate Rolling Process

本文针对宽厚板轧制过程计算机控制系统的重要模型之一——轧制负荷分配模型 ,提出了一种建立该模型的新方法。这种方法不同于目前常用的单纯建立负荷分配的统计或优化数学模型的建模方法 ,而是采用知识发现和数据挖掘 (KDD)的方法对轧制运行数据库进行挖掘 ,从中提取代表熟练操作工人丰富的操作和负荷分配经验的关联规则 ,进而建立知识模型和数学模型相结合的负荷分配模型。轧制实验证明 ,采用新方法建立的模型优于传统的基于统计或优化的负荷分配数学模型。

Schedule generation model is regarded as one of the most important models for plate rolling process control computer systems.In this paper a novel method for generating rolling schedule is presented,which is fundamentally different from the existing methods.The new method uses the KDD (Knowledge Discovery in Database) techniques to discover association rules between rolling parameters in a large database of rolling operation,and based on these rules,a schedule model which combines knowledge model and mathematical model is built up.Rolling practice shows that the schedule generated by the new method is superior to the schedule by existing methods.