基于随机森林的热轧带钢卷取温度预测  

Coiling temperature prediction of hot rolling strip based on random forest

作　　者：郝秋宇 龚殿尧[1] 田宝钱 丁鹿西 徐建忠[1] HAO Qiuyu;GONG Dianyao;TIAN Baoqian;DING Luxi;XU Jianzhong(State Key Laboratory of Rolling and Automation,Northeastern University,Shengyang 110819,China)

机构地区：[1]东北大学轧制技术及连轧自动化国家重点实验室,辽宁沈阳110819

出　　处：《冶金自动化》2023年第6期93-102,共10页Metallurgical Industry Automation

摘　　要：在带钢热连轧过程中,卷取温度是重要的工艺参数和主要的控制目标,其一定程度上可决定带钢的微观组织,从而影响产品的力学性能和使用性能。为进一步提高热轧带钢卷取温度控制精度,以某热连轧产线的实际生产数据为基础,采用随机森林(random forest,RF)算法建立了一种基于数据驱动的热轧带钢卷取温度预测模型,并采用贝叶斯优化算法确定RF模型的最优超参数,采用类似于网格搜索的方式确定贝叶斯优化算法自身超参数。同时,采用贝叶斯优化的决策树模型(decision tree,DT)、支持向量回归模型(support vector regression,SVR)和现场基于经典传热学建立的机理模型进行对比验证。模型测试结果表明,RF模型的预测结果有97%以上样本点预测误差在-10~10℃以内,相较于现场模型能更好地实现对卷取温度的预测,进一步提高卷取温度的控制精度。In the hot rolling strip process,the coiling temperature is an important process parameter and the main control objective,which can to some extent determine the strip steel microstructure,and affect the mechanical properties and usability of the product.To improve the accuracy of hot strip coi-ling temperature,based on the actual production data of a hot strip rolling line,a data driven coiling temperature prediction model for hot strip rolling was established using random forest(RF)algo-rithm.The Bayesian optimization algorithm is used to determine the optimal hyper-parameter of the RF model,and the grid search is used to determine the Bayesian algorithm hyper-parameters.At the same time,an decision tree model(DT)optimized by Bayesian optimization algorithm,support vector regres-sion model(SVR)and mechanism model based on classical heat transfer theory are used for compari-son and verification.The model testing results show that over 97%of the prediction results of the RF model have a prediction error within-10-10℃ for sample points.Compared to on-site models,it can predict the coiling temperature and further improve the control accuracy of coiling temperature.

关 键 词：热轧带钢 轧后冷却 随机森林算法 贝叶斯优化 卷取温度预测 

分 类 号：TG335.11[金属学及工艺—金属压力加工]