«Automation and Informatization of the fuel and energy complex»

Neural network approach to the problem of predicting multiphase flow components based on Venturi flow meter data

UDC: 004.85
DOI: 10.33285/2782-604X-2022-8(589)-43-49

Authors:

¹ ITMO University, Saint Petersburg, Russia
² Novosibisrk State University, Novosibirsk, Russia

Keywords: multiphase flow, flow prediction, the Venturi flow meter, neural networks, RNN, gas volume fracture (GVF), oil flow, gas flow, recurrent neural networks, RMLP

Annotation:

The article presents the result of the developed architecture experimental verification of a recurrent neural network for predicting oil and gas consumption by the parameters of the Venturi flow meter. The prediction quality, measured using the determination coefficient, is at the level of 0,90 for oil flow and 0,92 for gas flow. In addition to the consumption, the multiphase flow components, the proposed neural network architecture allows predicting a gas volume fracture (GVF). The carried out experiments showed the superiority of the data obtained by the Venturi flow meter as compared to the density meter data. The neural network does a good job of predicting increasing or decreasing dependence, but errors occur at the points of the trend change.

Bibliography:

1. Applications of Artificial Intelligence to Predict Oil Rate for High Gas-Oil Ratio and Water-Cut Wells / A.F. Ibrahim, R. Al-Dhaif, S. Elkatatny, D. Al Shehri // ACS Omega. – 2021. – Vol. 6, Issue 30. – P. 19484–19493. – DOI: 10.1021/acsomega.1c01676
2. Prediction performance advantages of deep machine learning algorithms for two-phase flow rates through wellhead chokes / H.S. Barjouei, H. Ghorbani, N. Mohamadian [et al.] // J. of Petroleum Exploration and Production. – 2021. – Vol. 11, Issue 3. – P. 1233–1261. – DOI: 10.1007/s13202-021-01087-4
3. Improved predictions of wellhead choke liquid critical-flow rates: Modelling based on hybrid neural network training learning based optimization / A. Choubineh, H. Ghorbani, D.A. Wood [et al.] // Fuel. – 2017. – Vol. 207. – P. 547–560. – DOI: 10.1016/j.fuel.2017.06.131
4. Khamis M., Elhaj M., Abdulraheem A. Optimization of choke size for two-phase flow using artificial intelligence // J. of Petroleum Exploration and Production Technology. – 2020. – Vol. 10, Issue 2. – P. 487–500. – DOI: 10.1007/s13202-019-0734-6
5. CNN-Based Volume Flow Rate Prediction of Oil–Gas–Water Three-Phase Intermittent Flow from Multiple Sensors / Jinku Li, Delin Hu, Wei Chen [et al.] // Sensors. – 2021. – Vol. 21, Issue 4. – DOI: 10.3390/s21041245
6. Measurement of the flow rate of oil and water using microwave and Venturi sensors with end-to-end dual convolutional neural network / Xiao Lin, Hongyu Wang, Zhe Chen [et al.] // Measurement: Sensors. – 2020. – Vol. 10-12. – DOI: 10.1016/j.measen.2020.100018