A novel multiphase flow water cut modeling framework based on multi-level multi-scale convolutional neural network

Water cut measurement is crucial in oil-watermultiphase flows, particularly in late-stage oilfield extraction, where high water production presents significant operational challenges. This paper proposes a novel Multi-Level Multi-Scale Convolutional Neural Network (MLMS-CNN) to achieve water cut estimation. The model is designed to extract and analyze complex flow characteristics through three key modules. The multi-level feature learning module fuses spatial and amplitude-phase features from sensor data, while the multi-scale feature fusion module captures flow structures across multiple scales. Additionally, the fully convolutional measurement module ensures precise water cut prediction. Experimental results demonstrate that the model achieves a mean square error of 0.013%, highlighting its potential for enhancing real-time industrial multiphase flow monitoring and optimization.