摘要
在铝热连轧轧制过程的二级设定中,轧制力的准确性直接影响辊缝的设定和辊缝自适应时间,最终将影响成品的厚度精度。该文采用支持向量回归机(SVR)和传统数学模型相结合的方式预测轧制力,在模型预测中采用改进的人工蜂群(ABC)算法对SVR中的参数进行寻优,保证预测轧制力的准确性。将模型应用于某"1+4"铝热连轧现场的二级设定中,轧制效果良好,准确度远高于传统数学模型。
In the secondary setting of aluminum hot rolling process, whether the rolling force is accurate or not is directly related to the roll gap settings and self-adaptive time of roll gap, and it directly affects the accuracy of the thickness of the finished prod- uct. In this paper, the combination of supporting vector regression (SVR) and traditional mathematical model is used to predict the rolling force. In the model, the improved artificial bee colony (ABC) algorithm is used to optimize the parameters in the SVR to ensure a more accurate prediction of rolling force. This model is applied to the secondary settings of the "1+4" aluminum hot rnlling, the rollinu effect is excellent, and the accuracy is much higher than the traditional mathematical model.
出处
《塑性工程学报》
CAS
CSCD
北大核心
2014年第1期85-89,共5页
Journal of Plasticity Engineering
基金
河北省科学技术研究与发展计划基金资助项目(10212157)
国家冷轧板带及装备工程研究中心开放课题资助项目(2012005)
河北省工业计算机控制工程重点实验室开放课题资助项目
关键词
铝热连轧
支持向量回归机
人工蜂群算法
轧制力预报
aluminum hot strip mill
supporting vector regression
artifical bee colony algorithm
rolling force prediction