Single well virtual metering research and application based on hybrid modeling of machine learning and mechanism model

Mu, Juncheng; McArdle, Shane; Ouyang, Jinjie; Wu, Haifeng

doi:10.1016/j.jpse.2023.100111

Cited by 3 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To avoid direct measurement of gas-liquid velocity, many indirect flow measurement methods have been developed [11][12][13], among which the research on virtual flow meters on oil and gas pipelines has introduced a new idea for flow measurement. These measurement methods usually collect existing status detection sensor data on the pipeline, such as pressure, temperature, and flow rate data, and train artificial neural networks to achieve flow measurement.…”

Section: Introductionmentioning

confidence: 99%

Measurement of air-water counter-current flow rates in vertical annulus using multiple differential pressure signals and machine learning

Cao,

Dang,

Dang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Gas-liquid counter-current flow in vertical annulus is involved in multiple industrial fields such as petroleum engineering. For instance, in coalbed methane wells where liquid pumping is utilized, obtaining real-time gas-liquid flow in the annulus is crucial for the development and management of coalbed methane wells. However, due to complex flow conditions, this requirement is difficult to achieve through traditional flow measurement means. Therefore, this paper proposes a flow prediction method based on multiple sets of differential pressure signals and machine learning techniques. Experiments on air-water two-phase flow were conducted on a vertical annulus pipe with an inner/outer diameter of 75mm/125mm and adjustable eccentricity. The probability density function and power spectral density function of three sets of differential pressure signals collected at different heights in the annulus pipe were used as model inputs, and gas-liquid flow rate as output. A gas-liquid two-phase flow prediction model was constructed based on the artificial neural network model, and the hyper-parameters of the model were optimized using Bayesian optimization. The results show that on a test dataset of 440 combinations of conditions with air superficial velocity of 0.06~5.04m/s, water superficial velocity of 0.03~0.25m/s, and pipe eccentricity of 0, 0.25, 0.5, 0.75, 1, the model can achieve average prediction errors of 9.12% and 29.34% for gas and water flow, respectively. This indicates that the method can be applied to non-throttling, non-intrusive measurement of phase flow under annulus gas-liquid counter-current flow conditions.

show abstract

Section: Introductionmentioning

confidence: 99%

Measurement of air-water counter-current flow rates in vertical annulus using multiple differential pressure signals and machine learning

Cao,

Dang,

Dang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

Dynamic production optimization for offshore Electric Submersible Pump oilfields based on oil-water two phase virtual flow metering

Bai,

Kang,

et al. 2024

Petroleum Science and Technology

View full text Add to dashboard Cite

Correlating Flow Station Parameters with Oil Wells Performance

AlAklubi

2024

Day 2 Thu, March 14, 2024

View full text Add to dashboard Cite

Offshore production system assessment is very important to maintain and optimize wells performance including ESP, gas lift, natural flow wells, flow line network and de-bottlenecking. The oil production gain from optimization will add great value in maintaining production targets and increase the Maximum Sustained Capacity (MSC) which is the maximum production rate can be produced for stable period within a notice of not more than two months. Offshore optimization includes new facilities such as flow stations, gas lift capacity, introducing new ESP wells, laying down new flow lines and additional transmission lines. Production optimization changes warrant an update and reassessment of the production model used for optimization and de-bottleneck studies including the review and evaluation of the existing well & network models to develop a clear strategy and to update the production model with optimization. The optimal lifting rate according to the well level can be determined by varying the gas lifting rate and comparing its rate of change with the minimum economic rate of change which can be obtained during the ability tests for each well considering changing the gas lift injection rate to sense the impact on the production rate with the best increment to get within the given gas injection rate. In order to assist oil and gas field workers in daily activities and to optimize the time they spent checking and opening closed wells which is a tedious job especially during rough sea conditions and when there is no available means of transportation, a new way of tracking wells production throughout the flow lines pressure feeding the flow station are presented and examined in order to focus on some areas to regain the production loss due to wells shut in suffering from the back pressure exerted by other wells on the stream. Gathering data from several flow lines to build a database which will be much appreciated especially for offshore fields where there is no Supervisory Control and Data Acquisition "SCADA" Units during rough sea conditions and in emergency cases to overcome production loss.

show abstract

Single well virtual metering research and application based on hybrid modeling of machine learning and mechanism model

Cited by 3 publications

References 4 publications

Measurement of air-water counter-current flow rates in vertical annulus using multiple differential pressure signals and machine learning

Measurement of air-water counter-current flow rates in vertical annulus using multiple differential pressure signals and machine learning

Dynamic production optimization for offshore Electric Submersible Pump oilfields based on oil-water two phase virtual flow metering

Correlating Flow Station Parameters with Oil Wells Performance

Contact Info

Product

Resources

About