Improving electric submersible pumps efficiency and mean time between failure using permanent magnet motor

Gas lift has been the primary artificial lift method for wells in an offshore brownfield in Malaysia for the past 30 years. However with depleting and unstable gas lift supply coupled with the increase in water production, an alternative artificial lift strategy needed to be developed. A revisit to the Field Development Plan (FDP) in 2003 has found that Electric Submersible Pump (ESP) could be the solution to overcoming the field's overwhelming dependency on gas lift. During a workover campaign in 2008, 3 ESPs were installed – marking the first production ESP in Malaysia. The ESPs have increased the well production from the gas lift baseline production and on top of that, there is a 66% additional incremental production from the re-allocation of approximately 1 MMSCFD of lift gas from the ESP wells. The success of the three ESPs has developed interest from the field operator to have more units installed. By end of 2011, a total of 5 ESPs has been installed in the field. They consisted of conventional ESPs, followed by an ESP in a pod with a Distributed Temperature Sensor (DTS) cable and a dual ESP with bypass tubing. Another 3 installations have been planned in the near future. The operator is also looking at the potential and feasibility of a rigless deployment for the ESP - either by using coiled tubing or a standard slickline service. In an offshore environment where rig cost and rig availability is of concern to well uptime and project economics, alternative ESP deployment has been seen as the next frontier of ESP technology to increase revenue. The transformation of artificial lift strategy in the field – from gas lift to ESPs - has been very progressive and profoundly significant to the operator's continual technological advancement in the industry. Introduction Bokor field is located 45 km offshore Sarawak, East Malaysia. It was discovered in 1974 and started production in 1984. The field reaches its peak production of 30000 barrel of oil production in 1990. Bokor field comprises of 3 production platform which are BODP-A, BODP-B and BODP-C, one processing platform (BOP-A) and one compressor platform (BOK-A). BODP-A, BODP-B and BOK-A are interconnected by bridge link while the BODP-B and C are only accessible via boat. Power generation is located in BOK-A and limited to BODP-A and BOP-A. The rest of the production platforms have solar power system limited to the platform's Supervisory Control And Data Acquisition (SCADA) system and basic utility. Due to the field unconsolidated formation sand, all of the wells in the early years were completed with cased hole gravel pack. Strong water aquifer in Bokor provides good and continuous pressure support, however increasing water cut becomes a severe problems to the surface facilities and increased demand to the lift gas. As an initiative to boost productions in the field, the operator ties a new relationship with Schlumberger to be its technical partner in 2002. The main objective of the partnership is to produce the incremental oil from the field. Bokor field comprises of more than 100 strings of oil wells with half of them is idle and the rest are producing on gas lift with several string on natural flow.

It is estimated that 95% of oil wells globally use Artificial Lift and 2014 statistics show that Electrical Submersible Pumps (ESPs) represents 43% of the global annual artificial lift spend[0]. Occidental Petroleum is a large user of ESPs, with over 2,200 in West Texas alone, and while ESPs can produce at high rate, they are also high cost. In today's low oil price environment, it is imperative that ESPs are operated efficiently to produce at the lowest cost per barrel. When applying ESPs to unconventional wells, efficient production is even more important with the added operational complications of producing frac sand, high gas/oil ratio (GOR) reservoirs, and rapidly changing flow rates. These three factors can dramatically shorten ESP run lives if not properly managed. Providing surveillance, monitoring, and optimization to Occidental's more than 400 unconventional wells required improved field data delivery systems, surveillance practices, and optimization techniques to meet this challenge. To achieve this, Occidental internally-developed a system for real-time ESP decision making that combines real-time data transmission, a data analytics tool, and an ESP analysis engine, all supported by trained staff and engineering workflows. By pulling all of these components together in one platform called "OxyLIFT," production engineers have a tool to enable rapid problem detection and diagnosis. The OxyLIFT system represents a major step forward in real-time decision making. By performing an automated analysis process on thousands of ESPs, Occidental can take proactive action on production losses at any point in the ESP's operational phase, as well as enabling semi-predictive failure analysis. Most importantly, the system highlights proactive ESP replacement opportunities which minimizes both production downtime and equipment losses. This system can be applied to any type of ESP well however the challenges associated with an unconventional well will be specifically investigated and explained with multiple case studies.

Where the pressure in oil or gas reservoir is not sufficient, in order to increase the production rate, an artificial lift method is required. There are several methods for obtaining artificial lift, including gas injection and electrical submersible pumps. Electrical submersible pumps are more controllable, offer faster installation, and are more economic than other methods, especially for vertical and deviated wells. Electrical submersible pumps systems consist of several parts, including the pump, an electric motor, cables, and a control board. The electric motor plays an important role in an electrical submersible pumps system, and it must produce high torque under high temperature and high-pressure conditions. For small diameter wells, there is also a constraint on the motor diameter. These harsh conditions and constraints require special motors. In this article, the desired criteria for such a motor for this application are represented; then, a comparison is made among several types of motors, including induction motors and various permanent magnet motors, and the resulting best choices are proposed.

Electrical submersible pumps (ESPs) are widely used as an artificial lift technique utilized for oil production worldwide. Run and pull reports and production tests were analyzed. The paper also recommends mitigation strategies for determined failures to prolong an ESP run life. Electrical failures are the most common ESP failures mainly due interruptions and discontinuations in electricity supply. Technical and operational failures because of improper ESP pump selection and planning. Employing ESP system design that takes into consideration reservoir potential and reservoir fluid and rock properties, while also accounting for the economic factor, can prevent these failures. Mechanical failures are mostly material dependent. It is therefore important to properly select material that is compatible and corrosion resistant to prevent grounded cable and motor and hole in production tubing. Suitable material implementation prolongs run life of an ESP assembly. Employing the proper material prevents component failures. Implementing suitable scale inhibitor to deal with scale depositions as well as utilizing gravel pack for sand screening assists in reducing ESP failures. Regular well cleaning may also reduce pump flow passages being stuck. Some ESP assembly failures are related and can cause other failures. Thus, early prevention of such failures results in failures discontinuation.

Marathon Oil operates several brownfields in the Rockies, most of which are approaching a producing life of 100 years. Most of the fields are on waterflood, with 86% of the oil production coming from the artificial lift method of electrical submersible pumps (ESPs). This ESP lift method has helped maximize the production of recoverable oil in these fields, achieving higher drawdowns and larger fluid volume handling. Prior to 2010, Marathon's 770 ESPs were operated with out downhole gauges or sensors and no ESP real time systems were in use. This made it difficult to properly monitor the well and the equipment, leading to improperly sized ESPs, limited artificial lift optimization and lost oil production. In 2010 Marathon began installing downhole sensors in all ESP wells that were pulled for either a failure or a workover and download the data into an ESP real-time monitoring, diagnosis and analysis software system. At the time of this paper, Marathon has installed downhole sensors in 430 of the 770 ESP wells. All ESP wells are presently being monitored via the ESP real-time monitoring and analysis software. During this short period of real-time monitoring, Marathon has realized production gains of more than 700 barrels of oil per day (BOPD) in one of the fields. This paper compares previous operations to the results and data from the installation and connection of downhole sensors to the real-time ESP monitoring program. Monitoring methodologies, analysis and proper ESP optimization are detailed in several case studies.

In the Gulf of Mexico, the rapid pressure depletion and reservoir depth of the Lower Tertiary intervals lead to low oil recovery. A high-reliability, through-tubing subsea electrical submersible pump (ESP) system that takes an integrated approach to production optimization will enable producers to cost-effectively extract more hydrocarbons from the increasingly challenging reservoirs in today's subsea assets. The potential increase in production depends on the maximum drawdown pressure limitations of both well casing design and rock strength. ESPs in deepwater fields are also considered to be an enhancer rather than an enabler by extending the production plateau 5 to 8 years after initial well/field startup with natural flow and seabed boosting. Hence, a robust ESP system that can be installed and operated a few years after field startup without a workover for replacing the upper completions. A robust, reliable ESP would unlock additional value to deepwater operators by delaying CAPEX and eliminating ESP failures, such as degradation of components due to high-pressure/high-temperature (HP/HT) cycling, during the first few years of nonoperation. Designing ESPs for deepwater application is a multidisciplinary challenge and needs to be approached from a full system-reliability standpoint rather than improvements to the ESP hardware alone. Implementation of ESPs in deep water requires both upfront planning at a full-system level and high degree of flexibility for installation, deployment, and retrieval. Finally, because the impact of an unplanned ESP failure is significantly detrimental to project economics, efforts to improve robustness of the ESP hardware must be complemented with automation of ESP operation to reduce or eliminate operator-induced failures. Recent industry improvements in machine learning and predictive analytics need to be leveraged to implement condition-based monitoring of ESPs to better anticipate failures and plan for replacements and/or adjustments to extend the life of degraded units. A collaborative project was undertaken to develop the concept of an alternatively deployed through-tubing ESP (TTESP) system targeted for deepwater subsea operations. The goal was to reduce intervention costs, which, together with ESP run life, are the primary factors influencing the economics of subsea ESPs, including conventionally deployed through-tubing ESPs. The project scope encompassed the downhole hardware, from immediately below the subsea tree through the upper completion, as well as deployment and retrieval equipment and methodology. Economic analyses of subsea fields were conducted to identify the factors contributing to intervention costs so that alternatives could be developed. Multiple concepts were evaluated, and the proof-of-concept system was selected based on superior economic return compared with the baseline. During this proof-of-concept phase, significant testing of key technologies was conducted. The studies showed that conventional intervention vessels and methods will not reduce the intervention costs associated with TTESPs. Lighter vessels together with technologies and methods that minimize intervention time and frequency—and, consequently, reservoir damage and deferred production—are the answer. Eliminating the wait for an available offshore rig is also a key factor in improving overall production economics. The proposed alternatively deployed TTESP system and its associated deployment methodology could reduce the intervention time by half and eliminate reservoir damage. This unconventional deployment could be conducted with lighter service vessels, further reducing intervention costs.

An artificial lift is a technique for pumping fluids in the petroleum industry today. Most artificial lift that is used nowadays is an electrical submersible pump (ESP). ESP is very convenient and reliable for lifting production. It applies under offshore and onshore industries, where it has high displacement capacity and flexibility to handle various sizes and flow rates under different well conditions. Due to severe operating conditions, ESP may experience fatigue failure, an undesirable malfunction resulting in a shortened service life. Early failure detection on ESP is imperative to prevent a major failure in the pump and reduce the cost of the damage. This study provides an in-depth examination of condition monitoring and early failure detection, with a focus on mechanical and electrical failures. This paper begins with a description of the ESP working principle followed by an analysis of ESP fault and numerous ESP performance monitoring techniques, including the application of early detection. Finally, the authors summarize ESP’s failures, including detection methods for each failure. Besides, recommendations for future research to increase ESP’s lifetime are also discussed. This review revealed that the lifetime of existing ESP can be extended if extensive monitoring of ESP conditions and advanced fault detection methods are applied.

Summary Managing large-scale electrical submersible pump (ESP) operations and assessing their performance can be a challenging task. Diverse operational environments, widely spread geographical areas, large ESP populations, and different service providers are some of the complications facing operators. Nonetheless, it is vital to the success of any artificial lift project to establish a performance evaluation structure that can effectively capture deficiencies and highlight improvements. While many operators focus on run life statistics as the central key performance indicator (KPI) for ESPs, these types of statistics may not be sufficient in providing meaningful information to decision makers. Other important ESP performance parameters include ESP shutdowns (both planned and unplanned), restart time of tripped ESPs, commissioning time, failure rate, and the number of premature ESP failures. Thus, a comprehensive study was jointly initiated between an oil operator and ESP vendors to establish KPIs that drive improvements in all aspects. The selected KPIs were developed in a structure that ultimately focuses on maximizing production availability and revenue generation. By constructing the ESP KPI framework, subpar performance areas were clearly visible by both the operator and the service provider. Decision makers were able to identify and act on fields that lag in performance while exerting efforts to improve underperforming service providers. Furthermore, regular meetings were conducted to review the established KPIs and recommend some action items, which might focus on either technical or operational solutions. Finally, KPI targets were set on the basis of the review of historical trends and were assigned to be challenging yet relevant and attainable. The followed practice can prove to be successful in forming a common ground where service providers can quantify losses by the operator as a result of ESP performance deficiencies. Comprehensive data collection and keeping of ESP trips, failures, and replacements are critical to the success of this work. Regular review of field reports and well performance are imperative to accurately compute the various KPI formulas. In fact, many of the KPI calculations can be automated to capitalize on the available communication networks installed in the field to improve ESP monitoring and accurately assess their performance.

All of Total E&P Congo’s production comes from offshore wells and the majority of these producers use secondary lift, mainly gas-lift and ESP (Electrical Submersible Pump). The efficiency of ESP and high delta pressure operation means that all new field developments use them along with a number of gas-lift conversions. One disadvantage of using ESP is the need for frequent intervention which, when coupled with a high work over cost and subsequent deferred production, both due to dependence on available work-over vessels in the region, can lead to exceedingly high operating costs. Moving away from this rig dependency towards a lighter operation would mitigate these drawbacks and greatly reduce the operation cost of the ESP systems deployment. Those changes are possible with the Wire Line Retrievable ESP (WR-ESP) technology. An initial work over is to set permanent completion elements. When the WR-ESP is retrieved, the tubing and the ESP power cable stay in place (permanent completion). The WR-ESP technology provides full bore access below ESP, short and light BHA, and uses permanent magnet motor (PMM) to increase the efficiency. Well screening for the pilot installation were done for Total E&P Congo wells. The selected candidate (Field A well) allows a simple and robust completion with little operation complexity. High safety standards are guaranteed during production and also during future well intervention. The use of slick line unit for ESP change-out is the key of this technology due to its flexibility, rapid mob-demobilization, and small operational cost compared to offshore pulling unit or rig. This bold way of deploying ESP is possible due to two main technical innovations:

Electric Submersible Pumps (ESPs) and Gas lift (GL) are well-known artificial lift techniques that can achieve a significant increase in production when properly designed and optimized. The discussion of whether choosing GL or ESP has generated numerous conflicting studies. The conversion of gas lifted wells to ESP or vice versa have been driven by the need for improved efficiency and increased production rate in mature fields. This work focuses on the successful application of ESPs to replace GL in numerous Permian Basin wells. The approach involved selecting an oilfield asset initially gas lifted and later was converted to ESP in the Permian Basin. The performance of wells under both artificial lift systems was carefully monitored, documented, and compared. Well models were built and matched followed by sensitivity analysis to determine GL and ESP lifting limits. A comparative assessment of CAPEX, OPEX, operational constraints, and oil recovery was performed to evaluate the economic and technical viability of each technique. Field data demonstrated the significant production gains achieved after the conversion from GL to ESPs. Pump stages were able to lower the Bottom Hole Pressure (BHP) by up to a 1000 psi in comparison to GL, which in return, allowed the operating companies to maximize production. The average oil rate increased by up to 70% in some wells. Based on the simulation results, gas lift capability in achieving high drawdown is limited making it ineffective in low reservoir pressure. In addition, the limited gas injection rate and gas injection pressure in the field prevented operating companies from optimizing the GL system. ESP achieved a net revenue incremental increase of approximately 20% and 250% rate of return of the initial capital investment (CAPEX) in two selected wells. To maximize production from mature assets, high drawdown is needed. With the advancement in gas handling and separation, ESPs have become more efficient and reliable. And despite the higher initial costs, ESPs can deliver improved operational performance and economic returns in the Permian Basin, making them a viable alternative to traditional gas lift methods.

Intelligent artificial lift technology is increasingly being used in Belayim Marine Field to enhance the value of maturing assets and new development wells. Wells equipped with electric submersible pumps (ESPs) are particularly suited to this blend of old and new. For years, the performance of ESPs has been monitored and controlled from the surface to prevent early pump failure by adjusting the frequency of the signal sent to the pump's variable speed drive (VSD) motor controller. This adjustment has also been used to avoid under-loading an ESP and increase production volume. To find this optimal operating range, real-time data and modeling are used to design the pump to fit the specific requirement of each well. Most recently, Belayim Petroleum has taken the concept a step further by deploying intelligent artificial lift in combination with stimulation technology aimed at reservoir management to help restore production from the 113-M-97-H well in Belayim Marine field, which is located in the central part of the Gulf of Suez, along the coast of the Sinai Peninsula. This new development well was drilled horizontally with maximum angle of 88°, and a 211 m. horizontal open-hole section was completed with 3.5-in. excluder screens. The well once achieved 22-hour good recovery at 550 BOPD. Then the production declined and the well was shut in due to low amperage, followed by no recovery caused by severe loss of circulation, which created a filter cake plugging the near wellbore pores. Complex stimulation treatment and flow, and well geometry and completion, as well as the offshore environment have complicated workover operations on this depleted reservoir and unproductive well issues. With intelligent ESP, a cost-effective stimulation was successfully deployed and enabled to evaluate production streaming data, such as pump intake pressure and temperature during the treatment across the horizontal section. Already equipped with in-well electric power cables, protectors, and multi-sensors, as well as a power controller VSD at the surface, this intelligent ESP system also enabled clean-out process at different production rates. Once clean reservoir fluids were observed during the flowing period, the ESP was stopped for a pressure build-up. A post-stimulation well test was performed to evaluate the treatment's effectiveness before running the new completion, hence minimizing intervention time to restore production promptly, reducing rig time, and achieving optimum completion design for long-term productivity of the well.

Accurate performance prediction of Electric Submersible Pumps (ESPs) operating under viscous fluid conditions remains a significant challenge in artificial lift operations. This study evaluates ESP performance across a broad range of oil viscosities (1–600 cP) and varying water cuts, aiming to develop and validate improved predictive models that address limitations of existing empirical correction methods. Two ESPs were experimentally tested at multiple rotational speeds, following a rigorous procedure involving oil property characterization, systematic loop testing, and repeated validation trials. Key parameters, including pump flow rate, developed head, and brake horsepower (BHP), were systematically recorded and analyzed. Results indicate substantial shortcomings in conventional empirical correction methods and dimensionless analyses, particularly at low flow conditions. Both tested ESPs exhibited clear performance degradation with increased oil viscosity, notably highlighting limitations in pumps with fewer stages. This study also introduces a new high-viscosity ESP performance calibration model based on Turzo (2000) model structure. The novel model developed in this study, validated using experimental data of nine ESPs from Tulsa University Artificial Lift Projects (TUALP) and literature sources, showed significantly improved accuracy in predicting ESP behavior for viscosities up to 650 cP. The model provides critical insights for improved ESP design, operational decision-making, and predictive performance modeling under challenging, high-viscosity conditions. The investigation further identified important variability in head and BHP factors with flow rate and viscosity. The findings underscore the need for additional testing with higher-viscosity fluids and diverse ESP designs to further enhance model robustness.

This article, written by Assistant Technology Editor Karen Bybee, contains highlights of paper OTC 19083, "The New Deepwater Oil and Gas Province in Brazil: Flow Assurance and Artificial Lift: Innovations for Jubarte Heavy Oil," by Giovani Colodette, Carlos A.G. Pereira, Cezar A.M. Siqueira, Geraldo A.S.M. Ribeiro, Roberto Rodrigues, Joao S. de Matos, and Marcos P. Ribeiro, Petrobras, originally prepared for the 2007 Offshore Technology Conference, Houston, 30 April-3 May. The paper has not been peer reviewed. The full-length paper presents a review of the artificial-lift (AL) and flow-assurance challenges faced in the exploitation of Jubarte heavy oil, starting from the features of the Pilot Phase. The challenges posed and innovations proposed and implemented for Phase 1 field development, as well as expectations for the subsequent Phase 2, are detailed. Introduction The Jubarte field is in the north part of the Campos basin, approximately 80 km offshore from the state of Espírito Santo, at a water depth between 3,280 and 4,922 ft. The field discovery occurred in January 2001, when an interval containing 17°API oil was identified in sandstones of Maastrichtian age. During the evaluation phase, a study based on the concept of value information supported the decision to drill a horizontal appraisal well. In February 2002, the well was drilled, with a 3,510-ft horizontal length, and was completed with an openhole gravel pack. The result was a well productivity index (PI) 13 times greater than the PI obtained with the vertical well. An extended well test (EWT) was proposed and approved. In the EWT, which started in October 2002, Petrobras made use of the floating production, storage, and offloading (FPSO) vessel Seillean, a dynamically positioned vessel with a rig capable of performing light workover operations. The well was connected to the FPSO through a 5 5/8-in.-inside-diameter drillpipe riser. Using an innovative solution, a 900-hp, 25,000-B/D-capacity electrical submersible pump (ESP) was installed above the wet tree. In case of ESP failure, the drillpipe riser could be recovered by the FPSO for pump retrieval and replacement. The good results obtained in the EWT led to its continuation in a Pilot Phase, which lasted until January 2006. After the Pilot Phase, the Jubarte Phase 1 production was started with the FPSO P-34. This new development phase comprises four production wells, and a 60,000-B/D oil-production rate is expected. One of the wells represents an innovative installation of the ESP on the seabed, another well has a downhole ESP installed, and the remaining two wells produce with gas lift (GL). GL backup can be used in the ESP wells while awaiting repair in case of pump failure. The ultimate Jubarte production system (Phase 2), to be implemented in 2011, will comprise 11 new wells plus the four wells from Phase1, and seven water-injection wells, connected to the FPSO P-57. During this production phase, all production wells will run ESPs installed on the seabed as the main AL method, with GL as backup.

_ For decades, artificial lift optimization has relied heavily on manual intervention, periodic well tests, and the judgment of experienced engineers. Electric submersible pumps (ESPs), gas lift, and beam pumps (the three most widely used lift systems) each have presented their own optimization challenges, such as balancing set points, managing compressor constraints, and interpreting dynamometer cards. These processes, while effective, have historically been time-intensive, reactive, and difficult to scale across large well inventories. The accelerating deployment of machine learning (ML) and automation is changing this landscape. By embedding intelligence into the control loop, operators now can move from reactive decision-making to proactive, continuous optimization. What was once a manual task handled by individual engineers is increasingly performed by autonomous systems that learn from data, adjust in real time, and scale effortlessly across hundreds or thousands of wells. Recent case studies illustrate how this transformation is unfolding across different lift types, each demonstrating that the age of autonomy in artificial lift is no longer aspirational but is now an operational reality. Neural-network models trained on ESP data sets in the Permian Basin now recommend and directly write optimal pump set points, as shown in paper SPE 219528. The deployment delivered a 2–4% oil uplift and longer run life, while demonstrating full self-pumping capability, where pumps operate with minimal human oversight. In gas lift, ExxonMobil’s large-scale rollout of a closed-loop optimization workflow has been equally impactful. As detailed in paper SPE 219553, more than 1,300 wells are now managed by an automated system that runs multirate tests, updates downhole pressure models, and applies ML for wells without gauges. The outcome: a consistent approximately 2% production uplift, achieved with little incremental operational or capital expenditure. On the beam-pump side, manual interpretation of dynamometer cards is being replaced by real-time ML classification. In paper SPE 224979, more than 700,000 dynacards were analyzed with models such as XGBoost and convolutional neural networks, achieving approximately 95% classification accuracy. By integrating with OSIsoft AF and exception-based surveillance, the solution provides predictive analytics and proactive alerts, reducing downtime and extending equipment life. When comparing the three approaches, some clear distinctions emerge. In ESP optimization (SPE 219528), operators relied on neural networks to recommend and autonomously adjust set points, achieving production uplift across more than 200 wells. Gas lift optimization (SPE 219553) took a broader fieldwide approach, scaling a closed-loop workflow to more than 1,300 wells, where multirate testing and ML models continuously updated injection rates, delivering uplift at minimal incremental cost. Meanwhile, beam-pump optimization (SPE 224979) focused less on direct production uplift and more on reliability and predictive surveillance, where ML models enabled proactive maintenance and reduced downtime. Despite their differences, the three initiatives share commonalities: Each system moved from manual, engineer-driven adjustments to automated and autonomous optimization; each leveraged ML in combination with existing field infrastructure; and each demonstrated that even modest per-well improvements, when scaled across hundreds or thousands of wells, translate into substantial fieldwide gains. Across ESPs, gas lift, and beam pumps, these case studies demonstrate a unifying shift: ML is redefining artificial lift as a self-optimizing, continuously learning system. Production uplifts of 2–4%, when multiplied across fields, translate into substantial incremental barrels. Equipment longevity improves as systems learn to operate within optimal ranges, while engineers are freed from repetitive monitoring to focus on higher-value analysis. The advances described here are more than isolated technical improvements; they are signposts of a broader digital transformation across upstream operations. Artificial lift, long the domain of manual adjustments and engineer intuition, is now becoming a proving ground for autonomy. By embedding AI into the very core of production systems, operators are not just optimizing individual wells; they are building the foundation of the digital oilfield of the future, where decisions are data-driven, workflows are autonomous, and engineers focus their expertise on complex challenges rather than routine tuning. Summarized Papers in This October 2025 Issue SPE 219528 - Machine Learning Optimizes Autonomous ESP Use in the Permian by Ryan D. Erickson, Vital Energy, et al. SPE 219553 - Gas Lift Optimization in the Permian Uses Machine Learning, Artificial Intelligence by Pooya Movahed, ExxonMobil, et al. SPE 224979 - Real-Time Machine Learning Enhances Dynacard Surveillance, Predictive Analytics by Shifa Khaliah Al Kiyumi, Daleel Petroleum, et al.

Summary In this paper we provide an overview comparing induction motors (IMs) and permanent-magnet motors (PMMs) for electrical-submersible-pump (ESP) applications. The design and performance differences of the two types of motors are compared and discussed. The PMM advantage and unique applications are highlighted. The requirement of a different control strategy to operate a PMM is described. Some key safety aspects that field engineers need to be aware of with PMMs are also addressed in this paper. The information we present includes a literature review and the latest research and development results. We cover the operating principles of the IM and the PMM, selection of permanent-magnet materials, operating frequency, stator windings, and magnetic poles. PMMs offer better efficiency, higher power-factor performance, and compactness. Ideal applications include slim-well applications, through-tubing rigless deployment, Y-tool completion, and electric-submersible-progressive cavity pumps (ESPCPs). We will also shed some light on why conventional IMs cannot be used to drive ESPCPs directly without speed-reduction gearboxes. It is very likely that the use of PMMs will increase for ESP applications in the near future, and this will require engineers to acquire a basic understanding of this technology. This paper intends to provide a high-level comparison between IMs and PMMs in the ESP industry.