SVR-based prediction of point gas hold-up for bubble column reactor through recurrence quantification analysis of LDA time-series

Recurrence quantification analysis (RQA) has emerged as a useful tool for detecting singularities in non-stationary time-series data. In this paper, we use RQA to analyze the velocity–time data acquired using laser doppler anemometry (LDA) signals in a bubble column reactor for Single point and Multipoint point spargers. The recurring dynamical states within the velocity–time-series occurring due to the bubble and the liquid passage at the point of measurement, are quantified by RQA features (namely % Recurrence, % Determinism, % Laminarity and Entropy), which in turn are regressed using support vector regression (SVR) to predict the point gas hold-up values. It has been shown that SVR-based model for the bubble column reactor can be potentially useful for online prediction and monitoring of the point gas hold-up for different sparging conditions.