基于正交信号校正的连续退火机组带钢质量预测方法  

Steel Quality Prediction for CAPL Based on Orthogonal Signal Correction

作　　者：王超[1] 邵嘉麟[2] 

机构地区：[1]宝山钢铁股份有限公司冷轧厂,上海201900 [2]上海科学院,上海201203

出　　处：《仪表技术》2012年第12期1-4,43,共5页Instrumentation Technology

摘　　要：连续退火是改善带钢的力学性能的关键过程。但在实际生产过程中,连续退火过程机理复杂,并且对带钢质量的检测有很大的时间滞后,这给提高带钢质量带来了很大的障碍。文章利用正交信号校正提取与带钢质量密切相关的过程信息,选用偏最小二乘方法构建更为精准的带钢质量预测模型,具有良好的预测性能,可以及时准确地在线估计带钢质量。通过对现场实际数据的仿真分析证明了所提出方法的可行性和有效性。Continuous annealing line is a key process in improving steel＇s mechanical properties.But in the real production process,the mechanism of continuous annealing is complicated and the detection of steel quality has a long time lag,which brings great obstacle to improve steel quality.Here,orthogonal signal correction is used to extract process characteristics which are close to quality.Better prediction model refltecing the relationship between process variables and quality variables is built using PLS.It can guarantee the safety of production process by realizing quality prediction timely.A large number of simulations in real process show the feasibility and effectiveness of the proposed method.

关 键 词：连续退火机组 质量预测 正交信号校正 偏最小二乘 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]