Variants of slow feature analysis framework for automatic detection and isolation of multiple oscillations in coupled control loops

Abstract

Oscillation is a frequent type of control performance degradation. Usually, multiple oscillations simultaneously propagate through coupled control loops, bringing challenges to detection and isolation. An automatic oscillation analytics scheme is proposed that extracts oscillations before oscillation detection and isolation. Two variants of slow feature analysis (SFA), termed multi-lag SFA and multi-lag dynamic SFA, are proposed and compared to explore the time-lag effect and multi-lag autocorrelations. A novel isolation index is proposed to reveal the attenuation trend of oscillations from the energy viewpoint. One of the main advantages is that the proposed framework incorporates an oscillation extraction by using multi-lag dynamic SFA, greatly improving the performance for oscillation detection and isolation. The proposed method is also applicable to ascertain roots and travel paths in the presence of multiple oscillations, requiring little human supervision. Moreover, the framework is easy to implement, which shows its abilities, both in simulations and real industrial data.