Multistep Dynamic Slow Feature Analysis for Industrial Process Monitoring

Multivariate statistical process monitoring has been widely used in industry. However, traditional algorithms often ignore the dynamic characteristics of actual industry process. This study proposes a novel algorithm called multistep dynamic slow feature analysis (MS-DSFA), which has completed the full-condition monitoring of a dynamic system and divided dynamic structures more precisely. This algorithm achieves an optimal detection rate according to multiple control limits. To enrich the experiments, we select a numerical example, Tennessee Eastman process, and XJTU-SY bearing data sets to verify the universality of the algorithm. According to the overall score for optimal detection rates and false alarm rates, MS-DSFA stands out in the comparison of existing algorithms.