Effective Electrical Submersible Pump Management Using Machine Learning

Artificial lift plays an important role in petroleum industry to sustain production flowrate and to extend the lifespan of oil wells. One of the most popular artificial lift methods is Electric Submersible Pumps (ESP) because it can produce high flowrate even for wells with great depth. Although ESPs are designed to work under extreme conditions such as corrosion, high temperatures and high pressure, their lifespan is much shorter than expected. ESP failures lead to production loss and increase the cost of replacement, because the cost of intervention work for ESP is much higher than for other artificial lift methods, especially for offshore wells. Therefore, the prediction of ESP failures is highly valuable in oil production and contributes a lot to the design, construction and operation of oil wells. The contribution of this study is to use 3 machine learning algorithms, which are Decision Tree, Random Forest and Gradient Boosting Machine, to build predictive models for ESP lifespan while using both dynamic and static ESP parameters. The results of these models were compared to find out the most suitable model for the prediction of ESP life cycle. In addition, this study also evaluated the influence factor of various operating parameters to forecast the most impact parameters on the duration of ESP. The results of this study can provide a better understanding of ESP behavior so that early actions can be realized to prevent potential ESP failures.

Inter-stage performance and energy characteristics analysis of electric submersible pump based on entropy production theory

The electric submersible pump(ESP) is a crucial apparatus utilized for lifting in the oil extraction process.Its lifting capacity is enhanced by the multi-stage tandem structure, but variations in energy characteristics and internal flow across stages are also introduced. In this study, the inter-stage variability of energy characteristics in ESP hydraulic systems is investigated through entropy production(EP) analysis,which incorporates numerical simulations and experimental validation. The EP theory facilitates the quantification of energy loss in each computational subdomain at all ESP stages, establishing a correlation between microscopic flow structure and energy dissipation within the system. Furthermore, the underlying causes of inter-stage variability in ESP hydraulic systems are examined, and the advantages and disadvantages of applying the EP theory in this context are evaluated. Consistent energy characteristics within the ESP, aligned with the distribution of internal flow structure, are provided by the EP theory, as demonstrated by our results. The EP theory also enables the quantitative analysis of internal flow losses and complements existing performance analysis methods to map the internal flow structure to hydraulic losses. Nonetheless, an inconsistency between the energy characterization based on EP theory and the traditional efficiency index when reflecting inter-stage differences is identified. This inconsistency arises from the exclusive focus of the EP theory on flow losses within the flow field, disregarding the quantification of external energy input to the flow field. This study provides a reference for the optimization of EP theory in rotating machinery while deeply investigating the energy dissipation characteristics of multistage hydraulic system, which has certain theoretical and practical significance.

Energy Consumption Analysis and Optimization of Electric Submersible Pump System

Electric submersible pumps account for a considerable proportion in the development of the Bohai Oilfield. Improving the system efficiency of the electric submersible pump wells, ensuring that the units operate in the high-efficiency zone, is essential. Analysis shows that the efficiency of the electric submersible pump system depends on the wear and tear of each component of the submersible pump equipment, the setting of operational parameters, and more importantly, the production status and daily management level of the oil well. Therefore, improving the structural performance of the submersible pump product, optimizing the parameters setting of the oil well, strengthening daily management, establishing a scientific management system, and improving the production management process and system can effectively improve the production efficiency and economic benefits of the oil well, and further achieve the goal of energy saving and emission reduction. In addition, it is necessary to actively promote the concept and technology of energy saving and emission reduction, encourage oilfield enterprises to explore effective measures to reduce the energy consumption of the electric submersible pump system by strengthening the scientific management system, and achieve a green, low-carbon, and high-quality development of oilfield production to achieve the unity of economic benefits, social benefits, and environmental benefits. This article applies the above measures in the P oilfield to achieve energy optimization of submersible electric pump systems, reducing the daily power consumption of single well submersible electric pump systems by 371 kWh per day, increasing the submersible electric pump's lifespan by 200 days, generating considerable project benefits.

Pressure pulsation in stages of electric submersible pump at shut-off under various speeds

Electric submersible pumps were widely used in agricultural fields,petroleum and various other industries. The pressure pulsation caused fatigue failure due to vibration in electric submersible pump and affects the life and performance of its system. The objective of this study was to experimentally investigate the characteristics of pressure pulsation which were generated at various stages of a multistage electric submersible pump during closed valve operation at different speeds. An electric submersible pump with five stages was selected for conducting experiments. A variable frequency drive( VFD)was used to operate the electric submersible pump at five different speed settings from 40 to 60 Hz. Piezoresistive pressure transducers were mounted at each stage of the electric submersible pump to capture the unsteady pressure signals. At each speed setting,the electric submersible pump was operated at the shut-off condition and the signals of unsteady pressure from all the five stages were captured. A fast fourier transformation( FFT) was carried out on the pressure signals to convert into frequency domain.From the spectra of pressure pulsation signals,the characteristics of pressure pulsation are obtained for each stage and for various speed settings which were then used to understand its variation with speed and stages.

Development and Application of a Surface High-pressure Injection Device Using a Submersible Electric Pump

Injection recovery is an important measure for increasing the oil recovery rate of an oil field. One way is that centrifugal pumps or plunger pumps are used in an injection station to responsible for injection over a large area under the same pressure. This method is ineffective for low-permeability layers. For the oilfields in dispersed distribution in the marginal areas of Daqing, the low water-absorbing section needs an injection with a high delivery pressure and a low discharge capacity; another way is to install the submersible electric pump upside down, but because the submersible electric pump and the motor are underground, it is difficult for installation and maintenance. Introduced in this paper is the development and application of a surface high-pressure injection device with a submersible electric pump. Bysuccessful resolving some problems, such as the axial force of the submersible electric pump, sealing, level regulation of the pump, coaxiality and vibration, the device has the good points of running smoothly, moving easily, installation and maintains quickly and long period of running. This device can effectively solve the injection of the low water-absorbing section and of oilfields in dispersed locations. The recovery rate of oilfields is also enhanced.

Research on Pick-up Feature of ESP Recording Charts Based on Bitmap Images

During the oil production, in order to monitor the working conditions of an electrical submersible pump （ESP）,an electrical current recorder is used to monitor the electric motor current of an ESP. The recorder charts indicate various working conditions of the ESP. Subtle malfunctions or abnormal problems of the ESP can be detected and further analyzed from various features of these current curves on the recording charts. Presently, these current charts are manually read and analyzed in oil fields. In this paper, a diagnosis expert system is presented for automatically analyzing these current recording charts and identifying the working condition of the ESP. This expert system includes an open knowledge base, which can be updated or enriched according to the identified features of the current curves on the recording charts, and a condition monitoring and failure pattern recognition method, which is called ＂pick-up method of feature of the recording chart＂, and can be correctly applied in most cases. It has been shown that this expert system can effectively improve the accuracy and efficiency of failure diagnosis and working condition monitoring of ESPs.