Pseudo-image-feature-based identification benchmark for multi-phase flow regimes

Abstract

Multiphase flow is a prevalent topic in many disciplines, and flow regime identification is an essential foundation in multiphase flow research. Computer vision and deep learning have achieved numerous excellent models, but many have not demonstrated satisfactory performance in fundamental research, including flow regime identification. This research proposes an advanced pseudo-image feature (PIF) as the flow regime descriptor and a benchmark of multiple deep learning classifiers. The PIF simulates the image format and compactly encodes the flow regime to a pseudo-image, which explicitly displays the implicit flow regime signals. This research further evaluates three proposed and five existing popular deep learning classifiers. The proposed benchmark provides a baseline for applying deep learning in flow regime identification. The proposed fully convolutional network (FCN) classifier achieved state-of-the-art performance, and the testing and verification accuracy respectively reached 99.95% and 99.54%. This research suggests that PIF has an excellent capability for flow regime representation, and the proposed deep learning classifiers achieve superior performance in flow regime identification compared to the existing classifiers. Industries can utilize the proposed multiphase flow identification technology to obtain greater production efficiency, productivity, and financial gain.