Two-Step Dynamic Slow Feature Analysis for Dynamic Process Monitoring

Many successful classical multivariate statistical process monitoring (MSPM) approaches have been applied in industrial processes. However, most of these methods and their extended dynamic versions fail to distinguish real faults incurring dynamic anomalies from normal changes in operating conditions in process dynamics. One popular solution is based on slow feature analysis (SFA) and dynamic SFA (DSFA). Notice that SFA and DSFA use a pair of statistics for monitoring dynamic processes without considering dynamic structure. In this study, a two-step DSFA (TS-DSFA) is proposed for monitoring dynamic processes. TS-DSFA firstly separates dynamic components from dynamic processes, and then constructs a evaluation model of dynamic processes. TS-DSFA assists in distinguishing real faults from normal changes in operating conditions, and it shows good performance in monitoring dynamic processes with uncertain noises. Finally, a numerical case is presented to verify the effectiveness of the TS-DSFA.