基于sub-MPLS的多阶段间歇过程质量预测与控制

针对大部分多阶段间歇过程,质量多数难以在线测量与控制问题,提出一种新颖的在线质量预测方法,基于子时段的MPLS质量预测方法.首先,采用聚类分析方法对间歇过程时间片矩阵PCA负载矩阵进行分类,依据过程变量相关性的变化,过程被分成几个操作阶段,然后,定出与质量变量最相关的阶段,在该阶段建立sub-MPLS在线质量预测模型,另外,还提出一种闭环质量控制方案.在一个典型的多阶段间歇过程-注塑过程的应用结果表明了所提出方法的有效性.

Quality prediction and control of multi-stage batch processes based on sub-MPLS

For most multistage batch processes,the final product quality are usually available at the end of the batch,which makes it difficult to realize on-line quality control.A novel method is thus developed to improve process analysis and on-line quality predictions for multistage batch processes,based on the stage-based subMPLS(multiway partial least square)quality prediction methods.Firstly,using clustering methods based on the stage-based sub-PCA(principal component analysis),the process is divided into several operation stages according to the change of process correlation,the most relevant stage to the quality variable is defined,and then sub-MPLS models are developed for that stage for on-line quality prediction. In addition,a closed-loop quality control system is proposed.The proposed method is finally applied to the injection molding process,a typical multistage batch process,and the results prove the effectiveness of the proposed quality prediction method and quality control scheme.