摘要
间歇和半间歇过程在化学工业中占有重要地位,如何对其进行监控一直是过程控制领域研究的热点之一.现实过程中,数据大都存在离群点,易使多向部分最小二乘(MPLS)模型造成误差.针对MPLS统计监控受离群点影响的问题,提出一种基于鲁棒MPLS的统计监控分析和相应鲁棒监控统计量的计算方法.相对于普通MPLS,鲁棒MPLS在建模数据中存在离群点时仍能给出正确的统计监控模型,降低了建模过程对数据的要求.
Batch and semi-batch processes play an important role in chemical industry. In order to reduce the variations of the product quality, multivariate statistical process control methods based on multi-way partial least squares (MPLS) are proposed for on-line batch process monitoring. However outliers always exist in the data, traditional MPLS methods are strongly affected by outlying observations. A batch process monitoring method based on robust MPLS is proposed. The robust normal operating condition model and robust control limits are discussed in detail. The results show that the robust MPLS is resistant to possible outliers.
出处
《控制与决策》
EI
CSCD
北大核心
2005年第7期823-826,共4页
Control and Decision
基金
国家863计划项目(2001AA413110).
关键词
间歇过程监控
部分最小二乘
多向部分最小二乘
鲁棒部分最小二乘
Chemical industry
Condition monitoring
Least squares approximations
Quality control
Robustness (control systems)