Performance-Indicator-Oriented Concurrent Subspace Process Monitoring Method

Process monitoring is an effective means to ensure process safety and improve product quality. On the one hand, it is possible that the fault will not affect process safety or product quality. On the other hand, not every fault affects both process safety and product quality simultaneously. To make process monitoring more purposeful and more accurate, a novel performance-indicator-oriented concurrent subspace (PIOCS) process monitoring method containing three subspaces with different degrees of importance is proposed in this paper. The first one is safety-related subspace, the second one is safety-unrelated quality-related subspace, and the third one is safety quality unrelated subspace. Through subspace division and construction, the fault can be categorized as safety-related fault, safety-unrelated quality-related fault, and safety quality unrelated fault. For mining safety and quality related information, both mechanism analysis and data analysis are used. In order to show the effectiveness and superiority, the proposed PIOCS method is tested under a number example and an industrial case study. Compared with traditional process monitoring methods, the proposed PIOCS method can obtain richer information, which is easy to show process operation condition clearly.