Data-Driven-Based Forecasting of Two-Phase Flow Parameters in Rectangular Channel

Qingyu Huang,Yang Yu,Yafeng Wang,Zhixin Pang,Bo Pang,Yaoyi Zhang,Di Chen

doi:10.3389/fenrg.2021.641661

Abstract

In the current nuclear reactor system analysis codes, the interfacial area concentration and void fraction are mainly obtained through empirical relations based on different flow regime maps. In the present research, the data-driven method has been proposed, using four machine learning algorithms (lasso regression, support vector regression, random forest regression and back propagation neural network) in the field of artificial intelligence to predict some important two-phase flow parameters in rectangular channels, and evaluate the performance of different models through multiple metrics. The random forest regression algorithm was found to have the strongest ability to learn from the experimental data in this study. Test results show that the prediction errors of the random forest regression model for interfacial area concentrations and void fractions are all less than 20%, which means the target parameters have been forecasted with good accuracy.

Highlights

In various industrial equipment of nuclear power systems, gas-liquid two-phase flow phenomenon is widespreaded
The route that four two-phase flow parameters obtained from rectangular channel experiments are modeled and predicted by LR, random forest regression (RFR), support vector regression (SVR), and back propagation neural network (BPNN) is introduced in detail
The goal of this research is to explore the calculation of two-phase flow parameters based on data-driven methods in rectangular channels

Summary

Introduction

In various industrial equipment of nuclear power systems, gas-liquid two-phase flow phenomenon is widespreaded. Research on the two-phase flow plays an important role in improving the safety and operational reliability of evaluation system equipment. For two-phase flow system, the interfacial area concentration and void fraction are two of the most important parameters. This experimental platform is shown, which can carry out the research of the vertical air-water two-phase flow in the channels with various cross-sectional area under normal temperature and pressure conditions. The experiment uses three sets of electrodes as the void meters, and the measurement data can be used for flow pattern identification and calibration. Conductivity probes are arranged at the position of the void meters to obtain local physical parameters such as the interfacial area concentration, void fraction, and bubble velocity. The probe measuring setpoints are arranged in the radial position with 30 ∼ 31 measuring setpoints, and the measuring setpoint arrangement positions are shown in Figure 3, where X represents the radial distance of the probes

Objectives

Methods

Findings

Discussion

Conclusion