基于变量展开和时变协方差的连续更新的MPCA及其在批过程故障监测中的应用(英文)

Consecutively updated MPCA with variable-wise unfolding and time-var- ying covariances with application to fault monitoring of batch process

针对传统的多向主元分析(MPCA)模型批过程监测的缺陷,提出了一种基于变量展开和协方差随时间变化的连续更新的MPCA批过程故障监测方法。该方法将基于批次展开能够去除采样数据的主要非线性动态性的优点与基于变量展开不需要对被监测的新批次的未反应完的数据进行预估的优点结合起来,用于批过程的故障监测,一旦因此判断出某一新批次过程正常,则模型参考数据库就随之更新。在实时监测新的批过程时,只需利用已收集到的数据信息,并且在线连续地更新模型参考数据库,提高了批过程性能监测的准确性,克服了MPCA不能处理非线性过程和实时性问题。通过采用该方法与传统的MPCA方法对青霉素补料分批发酵过程的实时监测,结果表明该方法比传统的MPCA更适合于对缓慢变化的批过程进行监测,具有更可靠的监测性能。

When muhiway principal component analysis（MPCA） is used for on-line batch monitoring, the future behavior of each new batch must be inferred up to the end of the batch operation at each time. On the other hand, because MPCA is a fixed-model monitoring technique, it gives false alarms when it is used to monitor real processes whose normal operation involves slow changes. In this paper, a new statistical batch monitoring approach is proposed. The proposed method does not require prediction of the future values while the dynamic relations of data are preserved by using time-varying score covariance structures. It also enhances the reliability of the monitoring system by consecutively updating the database of normal batches. The proposed method was applied to monitoring fed-batch penicillin production, and the simulation results clearly show that the ability of the proposed method to adapt to new normal operating conditions eliminates the many false alarms and the advantages of the proposed method in comparison to conventional MPCA.