Study on Measure Approach of Void Fraction in Narrow Channel Based on Fully Convolutional Neural Network

Void fraction is one of the key parameters for gas-liquid study and detection nuclear power system state. Based on fully convolutional neural network (FCN) high-speed photography, an indirect void measure approach flow boiling condition in narrow channels developed this paper. Deep learning technique applied to extract image features can better realize identification gas liquid phase complicated pattern high fraction, obtain instantaneous value analyzing monitoring. This paper verified FCN method with visual experiment data. Compared time-averaged experimental results calculated by energy conservation empirical formula, relative deviations are within 11%, which verifies reliability method. Moreover, recognition show that has promising improvement scope application compared traditional morphological method, meanwhile saves design cost. In future, it be measurement state monitoring under complex working conditions.