摘要
运用多元统计投影原理,结合改进PCR方法,建立了钢坯出口温度变量和过程变量之间的主元回归预测模型,最后基于某钢厂实际生产数据对模型的参数进行了求取.校验和误差分析表明,该模型能提前5～25分钟预测出钢坯的出口温度,且预测误差满足工业应用的精度要求.
This paper establishes a pivot element predictive r egression model between billet temperature variable and process variables with m ulti-statistic projection principle and PCR method, and parameters of the model are reckoned based on the actual data from a steel works. Check and error analy sis indicate that this model can predict billet exit temperature 10~25 minutes i n advance, and the predicting error can satisfy the demands of industrial applic ation accuracy.
出处
《信息与控制》
CSCD
北大核心
2005年第3期340-343,共4页
Information and Control
关键词
加热炉
主元回归(PCR)
钢温预报
heating-furnace
principal component regression (PCR)
prediction of billet temperature
