中厚板轧制过程智能化温度预报模型  

Intelligent Temperature Prediction Model for Plate Rolling

作　　者：谭文[1] 刘振宇[1] 支颖[1] 吴迪[1] 郑芳[2] 王巍[2] 

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110004 [2]宝山钢铁股份有限责任公司研究院,上海201900

出　　处：《钢铁研究学报》2006年第12期23-26,共4页Journal of Iron and Steel Research

基　　金：国家自然科学基金资助项目(50474086;50334010)

摘　　要：采用有限元(FEM)程序模拟计算了中厚板轧制过程中的温度变化,得到与实测温度符合甚好的模拟结果。以模拟计算结果为基础,建立了BP神经网络和回归温度预报模型。采用两种模型对中厚板热轧过程中轧件表面温度变化情况进行了预报。结果表明,神经元网络模型的预报值较回归模型更接近FEM模拟计算值和实测值,可将神经元网络模型应用于中厚板轧制过程中轧件表面温度变化的在线预报。The temperature variation during plate rolling was simulated by using FEM. The simulation results were in good agreement with the measured values. BP neural network and Regression models were built based on the simulation results, and predictions about temperature variation were carried out by using the two models. The results showed that the neural network model was more accurate than the regression model, indicating that the neural network model can be applied to on-llne temperature prediction during plate rolling.

关 键 词：BP神经网络模型 回归模型 在线温度预报 中厚板轧制 

分 类 号：TG335.5[金属学及工艺—金属压力加工]