摘要
在水泥熟料生产过程中,针对衡量产品质量的生料分解率不能在线检测的难题,将递归限定记忆主元分析和最小二乘支持向量机结合,提出了基于限定记忆主元分析的最小二乘支持向量机方法。限定记忆主元分析不但解决了传统主元分析的缺点和数据饱和现象,而且简化了最小二乘支持向量机的结构。该方法已经成功应用于酒钢宏达水泥厂水泥熟料生产生料分解过程,取得了显著的应用效果。
In the cement clinker production process,raw meal decomposition rate is directly related to the quality of final products.It is difficult to be measured online by sensors.A soft measurement model is proposed by combining the recursive fixed-memory principal component analysis(RFMPCA) with least squares support vector machines(LS-SVM).The RFMPCA is applied to the model,which not only solved drawbacks of conventional PCA and data saturation,but also simplified the LS-SVM structure.The proposed model is successfully applied to the raw meal decomposition process of Jiuganghongda Cement Plant in China,and the application results show its effectiveness.
出处
《控制工程》
CSCD
北大核心
2011年第4期495-499,共5页
Control Engineering of China
基金
国家高技术研究发展计划项目(2007AA041404)
国家重点基础研究发展计划项目(2009CB320604)
高等学校学科创新引智计划项目(B08015)
教育部科学技术研究重大项目(308007)
关键词
生料分解率
限定记忆主元分析
最小二乘支持向量机
raw meal decomposition rate
recursive fixed-memory principal component analysis
least squares support vector machines