Volume fraction determination of the annular three-phase flow of gas-oil-water using adaptive neuro-fuzzy inference syst
- PDF / 2,393,068 Bytes
- 21 Pages / 439.37 x 666.142 pts Page_size
- 104 Downloads / 147 Views
Volume fraction determination of the annular three-phase flow of gas-oil-water using adaptive neuro-fuzzy inference system Gholam Hossein Roshani1 · Alimohammad Karami2 · Ehsan Nazemi3 · Farzin Shama4
Received: 18 August 2017 / Revised: 5 January 2018 / Accepted: 11 January 2018 © SBMAC - Sociedade Brasileira de Matemática Aplicada e Computacional 2018
Abstract The use of adaptive neuro-fuzzy inference system (ANFIS) has been reported for predicting the volume fractions in a gas–oil–water multiphase system. In fact, the volume fractions in the annular three-phase flow are measured based on a dual energy metering system consisting of 152 Eu and 137 Cs and one NaI detector using ANFIS. Since the summation of volume fractions is constant, therefore ANFIS must predict only two volume fractions. In this study, three ANFIS networks are applied. The first is utilized to predict the gas and water volume fractions. The next one is applied to predict the gas and oil, and the last one is used to predict the water and oil volume fractions. In the next step, ANFIS networks must be trained based on numerically obtained data from MCNP-X code. Then, the average testing errors of these three networks are computed and compared. The network with the least error has been selected as the best predictor model. Keywords Annular · Adaptive neuro-fuzzy inference system · Three-phase Mathematics Subject Classification 76M40 · 92B20 · 03E72 · 28E10 · 28A75
1 Introduction The oil and gas production industry has a need for accurate measurements of the oil and gas fractions in pipelines. Improved production techniques have made it economically feasible
Communicated by Marcos Eduardo Valle.
B
Farzin Shama [email protected]
1
Electrical Engineering Department, Kermanshah University of Technology, Kermanshah, Iran
2
Young Researchers and Elite Club, Kermanshah Branch, Islamic Azad University, Kermanshah, Iran
3
Nuclear Science and Technology Research Institute, Tehran, Iran
4
Department of Electrical Engineering, Kermanshah Branch, Islamic Azad University, Kermanshah, Iran
123
G. H. Roshani et al.
to produce from smaller reservoirs by using subsea and even down whole production units (Åbro and Johansen 1999). In the presented flow meter in (Miller et al. 1999), all gamma lines and X-ray lines of sufficient intensity from an 241 Am source (14, 18, 21, 26 and 60 keV) were measured. Only two energies were necessary to find the volume fractions of three phases, the additional energies are used to improve the accuracy and measure the salinity (Miller et al. 1999). Roshani et al. (2013) showed the ability of ANFIS to predict the fluid density in a constructed gamma ray densitometer for pipes of various diameters and different fluids densities. It was found that, flow regime information can be used to improve measurement accuracy on gas volume fractions and as complementary information for other types of flow instrumentation to enhance the corresponding accuracy. A method based on dual modality densitometry using MLP was presented by Ro
Data Loading...
