Abstract A flow pattern identification method of gas-liquid two-phase flow in vertical pipeline based on multiple empirical mode decomposition (MEMD) and convolution neural network (CNN) is proposed.Based on the measurement data collected by the digital electrical resistance tomography (ERT) system,MEMD analysis is carried out after preprocessing.By calculating the Pearson correlation coefficient between each component and the original signal,the eigenmode function (IMFs) is selected and the Hilbert marginal spectrum is solved.The standard deviation and mean value of Hilbert marginal spectrum are extracted as convolution neural network (CNN)input to identify the flow pattern.The results show that the method can effectively identify bubbly flow,slug flow and slug flow,and the average recognition accuracy can reach 96.43%.
Gu C, Qiao X Y, Li H Y, et al. Misfire fault diagnosis method for diesel engine based on MEMD and dispersion entropy ［J］. Shock and Vibration, 2021, 2021:9213697.
Zhang L F, Zhu Y F. Two phase flow pattern identification based on mo-plp-elm and electrical capacitance tomography［J］. Acta Metrologica Sinica, 2021, 42 (3):334-338.
［2］
Zhang Y, Azman A N, Xu K W, et al. Two-phase flow regime identification based on the liquid-phase velocity information and machine learning ［J］. Experiments in Fluids, 2020, 61(10):212.
Zhang L F, Zhu Y F. Two phase flow pattern and parameter prediction based on Particle Swarm Optimization Extreme Learning Machine and electrical capacitance tomography［J］. Acta Metrologica Sinica, 2020, 41 (12):1488-1493.
Guo W, Liu C P, Wang L. Temperature fluctuation on pipe wall induced by gas-liquid flow and its application in flow pattern identification［J］. Chemical Engineering Science, 2021, 237:116568.
［8］
Liu W L, Tan C, Dong F. Doppler spectrum analysis and flow pattern identification of oil-water two-phase flow using dual-modality sensor［J］. Flow Measurement and Instrumentation, 2021, 77: 101861.
Li L P, Dang R R, Fan Y Y. Improved EEMD algorithm and its application in multiphase flow detection［J］. Journal of Instrumentation, 2014, 35 (10):2365-2371.
Weng R Y, Sun B, Zhao Y X, et al. Identification method of gas-liquid two-phase flow pattern based on adaptive optimal kernel and convolution neural network［J］. CIESC Journal, 2018, 69(12):5065-5072.
［14］
Liu S, Sun Y, Zhang L Y. Fault diagnosis approach of rolling bearing based on NA-MEMD and FRCMAC［J］. The Journal of Engineering, 2018, 2019(13):107-113.
Liang X Y, Lin X K, Quan J C, et al. Research progress of image instance segmentation based on deep learning［J］. Acta Electronica Sinica, 2020, 48 (12):2476-2486.
Chen L Y, Yin J W, Sun Z Q, et al. Identification of blunt body flow pattern of gas-liquid two-phase flow based on EEMD Hilbert spectrum［J］. Journal of Instruments and Instruments, 2017, 38 (10):2536-2546.
［4］
Chen Y T, Li K, Han Y. Electrical resistance tomography with conditional generative adversarial networks ［J］. Measurement Science and Technology, 2020, 31(5): 055401.
［5］
Tan C, Wang N N, Dong F. Oil-water two-phase flow pattern analysis with ERT based measurement and multivariate maximum Lyapunov exponent［J］. Journal of Central South University, 2016, 23(1): 240-248.
［7］
Xu Q, Wang X Y, Liang L, et al. Identification of flow regimes using platform signals in a long pipeline with an S-shaped riser ［J］. Chemical Engineering Science, 2021, 244:116819.
Sun B, Bai H Z, Huang Y M. Application of AR model based on EMD and ICA in two-phase flow pattern identification［J］. CIESC Journal, 2010, 61 (11): 2789-2795.
［13］
She Q S, Ma Y L, Meng M, et al. Noise-assisted MEMD based relevant IMFss identification and EEG classification ［J］. Journal of Central South University, 2017, 24(3):599-608.
［17］
Taitel Y, Bornea D, Dukler A E. Modelling flow pattern transitions for steady upward gas-liquid flow in vertical tubes［J］. AIChE Journal, 1980, 26 (3):345-354.
2023, Vol. 44 
