A Framework for Flow Pattern Analysis and Identification Based on Dual-Domain Feature Extraction and Deep Learning
- 4 March 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (8) , 13480-13489
Abstract
A flow pattern analysis framework based on the combination of dual-domain feature extraction and deep learning is proposed. Measurement data of flow patterns are collected using a resistance sensor array. For flow pattern analysis, A novel approach combining Choi-Williams distribution (CWD) and limited penetrable visibility graph (LPVG) is proposed to construct complex networks. The average degree index and global efficiency index are calculated, and the topological structure of the complex network is analyzed to reveal the nonlinear dynamic behavior of flow patterns. Regarding flow pattern identification, a pseudo-image encoding (PIE) method is employed to encode the energy time series from time-frequency analysis and the degree sequence from complex networks into two types of two-dimensional grayscale images to complete the feature extraction in the energy domain and the network domain. A novel deep learning classification model, the dual-input feature fusion network (DIFFN), is proposed to use two types of grayscale images as network inputs to complete flow pattern identification. The results indicate that our framework allows effectively characterizing the nonlinear dynamic behaviors during the evolution of different gas-liquid flow patterns. Meanwhile, the identification accuracy of the three flow patterns can reach 95%.Keywords
Funding Information
- National Natural Science Foundation of China (61973115)
This publication has 30 references indexed in Scilit:
- Study on the characteristics of gas-liquid two-phase flow with forward-rotation in reactor coolant pump under LOCAAnnals of Nuclear Energy, 2024
- Experimental study of hydrodynamic characteristics in three-phase coarse particle fluidized flotation columnChemical Engineering Journal, 2024
- FPRnet: A lightweight multi-domain multi-stream network for complex horizontal oil-water two-phase flow pattern recognitionFlow Measurement and Instrumentation, 2023
- Analysis and identification of gas-liquid two-phase flow pattern based on multi-scale power spectral entropy and pseudo-image encodingEnergy, 2023
- Convolutional neural network trained with synthetic pseudo-images for detecting an acoustic sourceApplied Acoustics, 2021
- Spatiotemporal statistical characteristics of multiphase flow behaviors in fuel reactor for separated-gasification chemical looping combustion of solid fuelChemical Engineering Journal, 2021
- Choi–Williams distribution in linear canonical domains and its application in noisy LFM signals detectionCommunications in Nonlinear Science and Numerical Simulation, 2020
- Investigating the hydrodynamics of airlift pumps by wavelet packet transform and the recurrence plotExperimental Thermal and Fluid Science, 2018
- Analysis of total energy and time-frequency entropy of gas–liquid two-phase flow patternChemical Engineering Science, 2012
- Modelling flow pattern transitions for steady upward gas‐liquid flow in vertical tubesAIChE Journal, 1980