Gas-liquid two-phase flow state identification method and system based on multi-sensor information fusion

Abstract

The invention provides a gas-liquid two-phase flow state identification method and system based on multi-sensor information fusion, and belongs to the technical field of pipe flow state identification, and the method comprises the steps: obtaining real-time monitoring data of a measurement pipeline, the real-time monitoring data being signals collected by a plurality of sensors in real time; performing feature extraction on the real-time monitoring data based on a local geometric feature sub-network and a global single-point feature sub-network in the trained multi-feature fusion convolutional neural network; fusing the extracted features by adopting an attention feature fusion strategy based on an attention fusion layer in the trained multi-feature fusion convolutional neural network; and based on the fused features, identifying the flow state of the gas-liquid two-phase flow in the measurement pipeline. According to the scheme, the universality and recognition efficiency of gas-liquid two-phase flow state recognition can be improved.

Images