Converting ESP Real-Time Data to Flow Rate and Reservoir Information for a Remote Oil Well

Camilleri, Lawrence; Gindy, M. El; Rusakov, A.; Adoghe, S.

doi:10.2118/176780-ms

Cited by 10 publications

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Real-Time Liquid Rate and Water Cut Prediction From the Electrical Submersible Pump Sensors Data Using Machine-Learning Algorithms

et al. 2023

View full text Add to dashboard Cite

This study presents a novel data-driven approach for calculating multiphase flow rates in electrical submersible pumped wells. Traditional methods for estimating flow rates at test separators fail to identify production trends and require additional costs for maintenance. In response, virtual flow metering (VFM) has emerged as an attractive research area in the oil and gas industry. This study introduces a robust workflow utilizing symbolic regression, extreme gradient boosted trees, and a deep learning model that includes a pipeline of convolutional neural network (CNN) layers and long short-term memory algorithm (LSTM) layers to predict liquid rate and water cut in real time based on pump sensors' data. The novelty of this approach lies in offering a cost-effective and accurate alternative to the usage of multiphase physical flow meters and production testing. Additionally, the study provides insights into the potential of data-driven methods for VFM in electrical submersible pumped wells, highlighting the effectiveness of the proposed approach. Overall, this study contributes to the field by introducing a new, data-driven method for accurately predicting multiphase flow rates in real time, thereby providing a valuable tool for monitoring and optimizing production processes in the oil and gas industry.

show abstract

Real-Time Liquid Rate and Water Cut Prediction From the Electrical Submersible Pump Sensors Data Using Machine-Learning Algorithms

et al. 2023

View full text Add to dashboard Cite

show abstract

Providing Accurate ESP Flow Rate Measurement in the Absence of a Test Separator

Camilleri

Gindy

Rusakov

2016

SPE Annual Technical Conference and Exhibition

View full text Add to dashboard Cite

Where well rates are outside the range of the test separator, operators usually have no choice but to estimate well production using back allocation techniques, which rarely capture the variance in flow rate over time. This was the case of a well in the Thistle field in the UK sector of the North Sea, where high-frequency flow rate was accurately calculated using ESP real-time data, which was instrumental in measuring inflow properties. The liquid flow-rate calculation was based on the principle that the power absorbed by the pump is equal to that generated by the motor, which provides a linear equation that can be resolved for rate. Water cut (WC) was calculated by measuring the production tubing differential pressure (DP), which provides the average fluid density, which is subsequently converted to a WC. Analytical equations are used throughout the process, ensuring that the physics are respected at all times. This yields greater repeatability and confidence than analogous methods, which are based on correlations and artificial intelligence. The calculations provided continuous liquid flow-rate and WC trends over the 6-month life of the ESP with a frequency of one calculation per minute with excellent repeatability and resolution. This enabled us to calculate inflow properties such as productivity index (PI) and skin, as well as history matching a reservoir simulation of the drainage area. This was essential to explaining why production dropped from 1500 to 500 B/D over a period of 8 months, which was found to be a lack of pressure support. The fall in production also caused production instability because of severe slugging, which could be remediated by concurrently increasing the tubing head pressure and ESP frequency without changing the drawdown. In addition to demonstrating the superiority of an analytical virtual flowmeter over correlations or artificial intelligence, the method also shows how the model can be calibrated accurately using an alternative pump reference curve, which is independent of flow rate, as opposed to traditional centrifugal pump curves. Flow-rate independence was indispensable because of the inability to physically measure rates with the existing test separator and was key to delivering accurate results.

show abstract

Testing the Untestable… Delivering Flowrate Measurements with High Accuracy on a Remote ESP Well

Camilleri

El-Gindy

Rusakov

et al. 2016

Day 2 Tue, November 08, 2016

View full text Add to dashboard Cite

Flow-rate testing is the most fundamental form of reservoir surveillance and is typically performed on a monthly basis using a test separator. Unfortunately, in some remote locations, the logistical challenges are so onerous that testing cannot be conducted with sufficient frequency and, in some cases, testing is only performed once per year. This case study demonstrates the novel use of ESP gauge data for obtaining accurate liquid rate and water cut trends in an unmanned desert location without the need for mobilizing surface well testing hardware. The liquid flow rate calculation was based on the principle that the power absorbed by the pump is equal to that generated by the motor, which provides a linear equation which can be resolved for rate. Water cut was calculated by measuring the production tubing differential pressure, which provides the average fluid density, which is subsequently converted to a water cut. Analytical equations are used throughout the process ensuring that the physics are respected at all times, which yields greater repeatability and confidence than analogous methods, which are based on correlations and artificial intelligence. The algorithms used real-time data from existing permanent downhole gauges and ESP surface controllers, which provided the necessary measurement metrology to capture well performance transients and provide a full production history. This method also has the advantage that there is no need to mobilise testing equipment to the well site thereby minimizing cost as well as eliminating flaring and HSE risks associated with remote location operations. This case study demonstrated a new technique for providing continuous calibration of the flowrate models without any physical measurement of flowrate or fluid specific gravity, while taking into consideration changing well and ESP performance over time. This novel calibration method is also based on analytical equations and derived from first principles. After one year of production, a test separator was specially mobilized to the well-site to validate the liquid rate and water cut calculations and associated calibration technique to consider the method for field wide application. This case study demonstrates that the proposed real-time algorithm provides the necessary metrology and data frequency to determine the production index as well as a trend of drainage area reservoir pressure over time. It enables a reduction in physical testing frequency while providing liquid rate and water cut with high frequency, repeatability and resolution thereby delivering both cost savings and improvements in information quality.

show abstract

Converting ESP Real-Time Data to Flow Rate and Reservoir Information for a Remote Oil Well

Cited by 10 publications

References 2 publications

Real-Time Liquid Rate and Water Cut Prediction From the Electrical Submersible Pump Sensors Data Using Machine-Learning Algorithms

Real-Time Liquid Rate and Water Cut Prediction From the Electrical Submersible Pump Sensors Data Using Machine-Learning Algorithms

Providing Accurate ESP Flow Rate Measurement in the Absence of a Test Separator

Testing the Untestable… Delivering Flowrate Measurements with High Accuracy on a Remote ESP Well

Contact Info

Product

Resources

About