For multimode and multiphasebatch process monitoring,the analysis of between-mode differences,i.e.,discriminative information,can greatly enhance process understanding and improve monitoring ***,the related work has ...
详细信息
For multimode and multiphasebatch process monitoring,the analysis of between-mode differences,i.e.,discriminative information,can greatly enhance process understanding and improve monitoring ***,the related work has not been explicitly addressed *** solve the problem,this work demonstrates a process understanding and monitoring method based on between-mode similarity evaluation and discriminative information *** proposed method quantitatively evaluates the differences of each mode and accurately describes the causes of between-mode differences from data-driven ***,a Mahalanobis distance based index is defined to evaluate the between-mode similarity by analyzing the phase-wise differences of each mode and similar modes are ***,a multimode Fisher discriminant analysis algorithm is proposed to identify influential variables in sparse manner,which contribute most to mode *** the above analysis,between-mode discriminative information is explained and multiple monitoring models are developed for online process monitoring based on influential variables and the other uninfluential variables,*** proposed method provides a detailed insight into the inherent nature of multimodeprocesses and captures more process information to enhance one's understanding of the multimode *** feasibility and performance of the proposed algorithm are illustrated by a typical multimode and multiphasebatch process,i.e.,injection molding.
暂无评论