The Automatic Analytics Framework for Multiple Oscillations in the Coupled Control Loops via a New Variant of Slow Feature Analysis

Abstract Oscillation is a frequent type of control performance degradation in the process. Multiple oscillations may propagate in the coupled control loops, bringing challenges to detection and localization of oscillations. In this paper, a time-frequency analysis framework including detection, extraction, and localization of oscillations is proposed. The method is based on a new variant of slow feature analysis (SFA), termed multi-lag derivatives dynamic slow feature analysis (MDSFA), and a new indicator, termed oscillation matched degree (OMD). To detect and reveal the possible oscillation sources, MDSFA is proposed to extract features with different rates from the observed data and probe into the time-delay effect and multi-lag autocorrelations specific to control loops. To pinpoint the root loops and travel paths of oscillations, the OMD indicator is designed via the spectral analysis, which can measure the oscillation frequencies and amplitudes. The proposed method is verified to be able to detect and locate oscillations automatically and efficiently via the real thermal power process.