改进黑猩猩算法动态优化冷轧FGC厚差控制研究
Research on dynamic optimization of cold rolling FGC thickness deviation control by improved chimp algorithm
-
摘要: 为提高冷轧轧制力模型的计算精度,减小带钢头部厚度超差长度,提高带钢成材率,本文对基本黑猩猩优化算法进行了改进,用其对影响轧制力计算的变形抗力和摩擦因素进行动态调整,获得最佳的轧制力计算模型。仿真实验结果表明:采用优化后模型,各机架设定轧制力与实际值偏差不超过2.12%,其标准差由优化前的10.4%降至1.2%。生产实践证明:轧制力模型优化后带钢头部厚度超差长度小于20 m的比例,从优化前的35.84%增加到至60.2%,证明该方法能显著提高轧制力模型预报精度,从而提高带钢成材率。Abstract: In order to improve the setting calculation accuracy of the cold rolling force model, reduce the length of the thickness deviation at the head of the strip, and improve the yield of the strip, basic chimp optimization algorithm is improved. And then, it is used to dynamically adjust for the deformation resistance and friction factor that affect calculation of rolling force, so as to find the best rolling force calculation model. The simulation experiment results show that by the optimized model, the deviation between the set rolling force of each stand and actual value is not more than 2.12%, and its standard deviation is reduced from 10.4% before optimization to 1.2%. Practice production proved that the proportion of the thickness deviation length of the strip head less than 20 m after rolling force optimization has increased from 35.84% before optimization to 60.2%. It is proved that the method can significantly improve the prediction accuracy of the rolling force model and improve the yield of the strip.
下载: