Two-phase flow regime identification in a horizontal pipe was realized based on the liquid phase velocity information and the machine learning method. Ultrasound Doppler velocimetry was employed to measure the liquid velocity. Statistical features extracted from the velocity time series data, such as mean, root mean square, and power spectral density, were used to realize real-time flow regime identification. In addition, two novel parameters—maximum velocity ratio and maximum velocity difference ratio—were proposed to identify plug and decaying slug flow. Different classification algorithms were employed to achieve a high identification accuracy. Moreover, transient flow regime identification with a fast response was realized based on two classification algorithms—long–short term memory and convolutional neural network. The results show that the accuracy of real-time flow regime identification based on a flow regime map can reach up to 93.1% using support vector machine, the maximum velocity ratio and maximum velocity difference ratio are effective in identifying plug and decaying slug flow, and transient flow regime identification under slug flow condition can be realized with an accuracy of 94% based on a convolutional neural network (CNN). Decaying slugs with long lengths confuse the CNN and are responsible for the error in identification. The results presented herein are expected to expand the available knowledge on two-phase flow regime identification.

Two-phase flow regime identification based on the liquid-phase velocity information and machine learning

Numerical simulation of the plug and the slug flow regimes have been performed using the Multi-Fluid VoF and Shear Stress Transport (SST) k–ω models in a horizontal pipe with 44 mm diameter. The superficial velocities during the current study were set at 0.16, 1.64 & 3 m/s for the gas phase and 1 m/s for the liquid one. The pressure and the velocity equations were solved together, utilizing the PIMPLE algorithm in all cases of the present study. The VoF model, as well as the experimental outcomes, were applied to assess the results of Multi-Fluid VoF model. The qualitative comparison of numerical results with the experimental visualization revealed that the Multi-Fluid VoF model simulates precisely the interfacial structure of slug and plug flows, as well as the chronological formation of the slug. The length ratio of the gas slug to the liquid slug goes up with the gas superficial velocity increment; this issue increases the probability at low liquid hold-ups and decreases the higher ones. The Multi-Fluid VoF provided much more matching with the mentioned probability changes in comparison to the VoF model. The pressure drop calculated using Multi-Fluid VoF in the Lockhart–Martinelli framework illustrated a 21.8% improvement averagely in comparison to the VoF model. The obtained transitional slug velocities showed that the Multi-Fluid VoF model presented a maximum error of 8.17% versus the experimental values, while the mentioned error for the VoF model was estimated at 22.01%. Notwithstanding the mentioned advantages, the Multi-Fluid VoF model significantly increased, both the execution time of simulation as well as the associated costs.

Yusnanda Agus Nusirwan

Papers

Experimental investigation on the initiation and flow development of gas-liquid slug two-phase flow in a horizontal pipe