Process Monitoring under Closed-loop Control with Performance-relevant Full Decomposition of Slow Feature Analysis

Close-loop control is widely used in modern industrial process which brings obvious process dynamics. Disturbances on process may be compensated by the control actions, and thus it may have little influence on the process performance like product quality and waste discharge. Therefore, process monitoring without considering the influences of process variations on performance and process dynamics may cause nuisance alarms. To achieve comprehensive process monitoring, performance-relevant full decomposition of slow feature analysis, termed PFDSFA here, is proposed for processes under closed-loop control by simultaneously considering the influences of process variations and control actions on performance and process dynamics. First, the proposed algorithm extracts variations directly relevant to performance variables using canonical correlation analysis. In this way, process variable space can be decomposed into performance-relevant subspace and process-relevant subspace. Next, static and dynamic variations of each subspace are extracted to distinguish operating condition deviations from real faults. The proposed monitoring structure offers a fine-scale decomposition of process variations, and also achieves comprehensive process monitoring of process static and dynamic characteristics. Besides, it can effectively indicate whether a disturbance influences the performance and process dynamics. Finally, the proposed method is applied to the Tennessee Eastman process to terrify the efficacy.