Flow status identification based on multiple slow feature analysis of gas–liquid two-phase flow in horizontal pipes

Abstract

Abstract A gas–liquid two-phase flow is a highly complex and random process with complicated and variable flow statuses. The status identification of two-phase flows focuses on the situation of flow processes over specific time periods, as reflected by flow regimes, phase holdup, flow velocity, and other parameters. Aiming to discover how to obtain flow status information and identify the flow statuses of gas–liquid two-phase flows in horizontal pipes, a meticulous identification method based on multiple slow feature analysis combined with Bayesian inference is proposed, with concurrent monitoring of steady states and process dynamics. In this method, representational models for different typical flow regimes are established to describe both the steady states and temporal distributions. On this basis, by monitoring statistics and developing a Bayesian inference-based index, the current flow status can be identified online. Besides status identification, process dynamics are monitored to detect the dynamic characteristics of the current process with meaningful physical interpretation and deep process understanding. The application of this method to typical flow regimes and the status of transitions from bubble flow to slug flow demonstrates the feasibility and efficacy of the proposed method.