Two-dimensional multiphase batch process monitoring based on sparse canonical variate analysis

• Published in: Journal of process control Vol. 116; pp. 185 - 198
• Main Authors: Zhang, Shumei, Bao, Xiaoli
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.08.2022
• Subjects: Batch processes; Fault detection; Sparse canonical variate analysis; Two-dimensional dynamics; Variable selection; Sparse canonical variate analysis; Two-dimensional dynamics; Fault detection; Batch processes; Variable selection
• ISSN: 0959-1524; 1873-2771
• DOI: 10.1016/j.jprocont.2022.06.007

Most industrial batch processes involve inherent dynamic characteristics in both within-batch time direction and batch-wise direction. In order to ensure process safety and improve process performance, the two-dimensional dynamics should be analyzed during batch process monitoring. In this work, two-dimensional region of support (2D-ROS) is first constructed to select and preserve the relevant samples for the current measured sample by calculating autoregressive orders with Akaike information criterion (AIC) in time direction and measuring the similarity with the weighted Euclidean distance in batch-wise direction. Afterwards, sparse canonical variate analysis (SCVA) algorithm is performed to yield sparse canonical vectors, which is especially advantageous for eliminating the irrelevant variables and facilitating the interpretation of underlying relationships of process variables. Meanwhile, given most measurements are subject to the non-Gaussian distribution, the upper control limits (UCLs) in 2D-SCVA can be estimated using kernel density estimation (KDE). The achieved results obtained from a numerical dynamic example and the benchmark fed-batch penicillin fermentation process clearly verify that the proposed method performs well for detecting abnormal operation for the batch processes. •Two-dimensional sparse canonical variate analysis (2D-SCVA) method is proposed for dynamic industrial process monitoring.•The proposed method extracts the inherent dynamic correlations in within-batch time direction and batch-wise direction.•The irregular region of support is determined to select the most related variables and eliminate the unrelated variables.•SCVA algorithm is performed to facilitate the interpretation of underlying relationships of process variables.