Adaptive partitioning PCA model for improving fault detection and isolation

In chemical process, a large number of measured and manipulated variables are highly correlated. Principal component analysis (PCA) is widely applied as a dimension reduction technique for capturing strong correlation underlying in the process measurements. However, it is difficult for PCA based fault detection results to be interpreted physically and to provide support for isolation. Some approaches incorporating process knowledge are developed, but the information is always shortage and deficient in practice. Therefore, this work proposes an adaptive partitioning PCA algorithm entirely based on operation data. The process feature space is partitioned into several sub-feature spaces. Constructed sub-block models can not only reflect the local behavior of process change, namely to grasp the intrinsic local information underlying the process changes, but also improve the fault detection and isolation through the combination of local fault detection results and reduction of smearing effect. The method is demonstrated in TE process, and the results show that the new method is much better in fault detection and isolation compared to conventional PCA method.

Fault detection results for fault 5 by global PCA (a) and APPCA sub-block 5 (b) (black solid line: monitor statistics; red dashed line: 99% control limit). The global PCA can only detect the fault at the beginning, in the range between sample 160 and sample 340. The fault is barely detected by monitor statistics after sample 340, because the control loops can compensate for fault 5 and bring process variables back to their desired values. According to the fault detection results with the global PCA, the process probably mistakenly corrects the fault after sample 340 through the control operations. However, sub-block 5 in the proposed APPCA method can detect the fault during the whole fault operation.Figure optionsDownload as PowerPoint slide