An industrial process monitoring scheme with moving window slow feature analysis

Abstract With the development of the modern industries, the requirement for comprehensive and effective monitoring scheme of the industrial production process is growing significantly. Conventional monitoring methods treat the deviations as the abnormities and thus result in the invalid monitoring results, because the dynamic information cannot be extracted accurately, which may be caused by the transient process or new operation conditions, and real faults cannot be separated from the normal process changes. To cope with this limitation, a moving window slow feature analysis is proposed in this paper. First, the temporal dynamic features of the industrial production process are extracted to separate the temporal dynamics from the steady state. Second, an adaptive monitoring strategy is presented to accurately acquire the normal changes of the production process, including the normal shift of operation conditions and the slow time-varying behaviors, through updating model parameters and monitoring statistics when a query sample comes. In this way, the real dynamic anomalies can be distinguished from the normal dynamic behaviors and reduce the false alarms effectively. Finally, the effectiveness and practicality are demonstrated through an evaporation process.