摘要
针对高炉炉温与铁水硅含量呈正相关而非严格的线性关系和机制建模的主观性以及其难以建立各变量之间隐含的数学关系等的不足,在数据挖掘理论的基础上,对海量的样本数据进行预处理和特征提取,然后以高炉铁水温度为研究对象,建立了基于T-S模糊神经网络的高炉铁水温度预测模型。最后,应用某高炉数据进行模型验证,并将该模型与T-S模糊多元回归模型以及BP神经网络模型进行比较研究,仿真结果表明T-S模糊神经网络模型的有效性和优越性。
According to the shortage of the positively relation of blast furnace temperature and hot metal silicon rath- er than strict linear relationship, the subjectivity of the modelling by mechanism,and mechanism model dificuhly to estabish the connotative mathematic relation between every varables, the mass of the sample data was processed through preprocessing and feature extraction based on the theory of data mining, and then blast furnace hot metal temperature was deemed as the research object, blast furnace hot metal temperature prediction model was established based on T-S fuzzy neural network. And the model and T-S fuzzy regression model and BP neural network model were compared; Through using some blast furnace data for model test, simulation results show that T-S fuzzy neural network model performance is superior to other models.
出处
《钢铁》
CAS
CSCD
北大核心
2013年第11期11-15,共5页
Iron and Steel
基金
国家自然科学基金资助项目(61164018)
关键词
高炉铁水温度
T-S模糊回归
T-S模糊神经网络
blast furnace hot metal temperature
T-S fuzzy regression model
T-S fuzzy neural network model
