递推PLS方法及其在过程监控中的应用  

Recursive PLS method and its application in process monitoring

作　　者：苏金明[1] 李春富[1] 孙如田[2] 侯平智[1] 王建中[1] 

机构地区：[1]杭州电子科技大学自动化学院,浙江杭州310018 [2]克拉玛依职业技术学院,新疆克拉玛依833600

出　　处：《机电工程》2010年第3期93-95,99,共4页Journal of Mechanical & Electrical Engineering

基　　金：浙江省科技计划面上资助项目(2009C31161)

摘　　要：针对处理批量数据时传统的偏最小二乘(PLS)模型无法在线更新的问题,提出了结合遗忘因子法的递推PLS算法,进而更新Qa控制限,有效地克服了传统PLS中Qa无法反映系统时变性的缺点。并对异丁烯酸甲酯(MMA)聚合反应过程中的数据进行了仿真分析。研究结果表明,递推PLS方法大大降低了监控过程中的误报率和漏报率,提高了监控系统的性能。Aiming at the problem that recursive partial least square（PLS） model is not updated with process changes, which may lead to increased false alarm rate. Recursive PLS with forgetting factor method was proposed. When new data was available, the PLS model and the corresponding Qa, control limit were updated to accommodate the process change. A MMA polymerization batch process was studied. The simulation result demonstrates that recursive PLS method can greatly reduce the false alarm rate and omission rate in the monitoring process, and improve its performance.

关 键 词：递推偏最小二乘 过程监控 间歇过程 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]