Dual-Level Electric Submersible Pump (ESP) Failure Classification: A Novel Comprehensive Classification Bridging Failure Modes and Root Cause Analysis

Abstract

Electric submersible pumps (ESPs) are critical for artificial lift operations; however, they are prone to frequent failures, often resulting in high operational costs and production downtime. Traditional ESP failure classifications are limited by lack of standardization and the conflation of failure modes with root causes. To address these limitations, this study proposes a new two-step integrated failure modes and root cause (IFMRC) classification system. The new framework clearly distinguishes between failure modes and root causes, providing a systematic, structured approach that enhances fault diagnosis and failure analysis and can lead to better failure prevention strategies. This methodology was validated using a case study of over 4000 ESP installations. The data came from Egypt’s Western Desert, covering a decade of operational data. The sources included ESP databases, workover records, and detailed failure investigation (DIFA) reports. The failure modes were categorized into electrical, mechanical, hydraulic, chemical, and operational types, while root causes were linked to environmental, design, operational, and equipment factors. Statistical analysis, in this case study, revealed that motor short circuits, low flow conditions, and cable short circuits were the most frequent failure modes, with excessive heat, scale deposition, and electrical grounding faults being the dominant root causes. This study underscores the importance of accurate root cause failure classification, robust data acquisition, and expanded failure diagnostics to improve ESP reliability. The proposed IFMRC framework addresses limitations in conventional taxonomies and facilitates ongoing enhancement of ESP design, operation, and maintenance in complex field conditions.

1. Introduction

In the oil and gas industry, maintaining and enhancing oil production from wells is a persistent challenge. To address this challenge, artificial lift systems, such as electric submersible pumps (ESPs), are deployed. ESPs are used in both newly drilled wells and mature wells [1]. The latter have surpassed their peak production phase, in which natural reservoir pressure can no longer sustain optimal production. ESPs are deployed to increase production in these underperforming wells, allowing continued hydrocarbon recovery at enhanced rates despite the decline in reservoir energy [2]. Considered as one of the fastest-growing artificial lift methods, ESPs are deployed in both onshore and offshore wells, comprising over 33% of the world’s one million operational wells [3]. Moreover, ESPs are widely regarded as a reliable solution for offshore applications. They are deployed in over 90% of offshore wells to efficiently pump oil at high rates [4]. In 2022, ESPs accounted for over 40% of the global artificial lift market value and contributed approximately 60% of global oil production [5].

Known for their versatility, ESPs are capable of handling a broad range of oil production volumes, from as low as 150 BPD to as high as 150,000 BPD, making them adaptable to diverse application requirements [6]. Additionally, they operate with pump intake pressures of less than 100 psi, manage high water cuts, and function at significant depths under diverse oil reservoir harsh conditions [7]. ESPs are susceptible to unexpected failures, leading to a cessation of pump flow. These failures often arise from a combination of mechanical, electrical, and operational issues that can result in significant operational disruptions and substantial financial losses due to unplanned downtime and costly interventions [8]. Several attempts in the literature have tried to perform ESP failure analysis, detailing all failure types and associated components [9].

Variability in ESP failure rates across different oilfields has also been extensively documented, highlighting significant discrepancies in performance and reliability [10]. Nevertheless, more ambiguity is still in place due to the lack of clear distinction between failures. Accurate classification and analysis of ESP failures are critical for diagnosing root causes, optimizing maintenance strategies, and improving overall reliability [11]. Ultimately, a systematic failure analysis framework not only minimizes operational costs but also extends equipment lifespan and improves mean time between failures (MTBF), delivering measurable operational and financial advantages [12].

This study proposes the concept of categorizing failures into two-step classification—first into distinct modes, and second by addressing their root causes through a comprehensive, structured approach.

Overview of Previous Work on Electrical Submersible Pump (ESP) Failure Classifications:

The primary challenges in ESP systems revolve around premature failures and short run lives. ESPs have an average lifespan of 2 years. In some oilfields, the run life has been less than 330 days, as mentioned in multiple references [10,13,14]. These failures are often unpredictable, which complicates the timely replacement of the equipment. Consequently, failures are usually associated with the high costs of workovers and production losses, which are regarded as significant concerns [14]. In the realm of ESP technology advances, ongoing innovations are proving advantageous for oil companies by enhancing reliability, performance, and durability, especially in demanding and harsh operating conditions [15]. Understanding these failure modes aids in the implementation of preventive measures, including regular maintenance, monitoring, and the utilization of appropriate materials and designs to mitigate the impact of harsh operating conditions [16]. Root cause analysis plays a crucial role in the identification of the specific reasons behind failures and the implementation of effective solutions. Continuous monitoring and predictive maintenance practices are instrumental in significantly enhancing the reliability and lifespan of ESP systems [17].

Establishing clear, context-specific failure definitions is essential for professionals working with ESPs, as it improves communication, troubleshooting, and maintenance strategies while ensuring alignment with industry standards [9]. According to reference [18], failure is the inability of an item to perform its intended function. A failure mode describes how a failure occurs, while a failed item refers to any component or system assessed independently. A failure descriptor identifies the apparent cause, whereas the root cause traces the conditions or events leading to failure. ESP failure classifications provide structured frameworks to categorize failures based on characteristics, mechanisms, and operational impacts. Defining these failures within specific organizational contexts is crucial for effective management.

API RP 11S1 [19] serves as a foundational framework for documenting and classifying ESP failures, offering standardized practices, schematics, and failure codes such as LPRO (low production), POFF (production off), and DHSH (downhole short). Reference [20] complements this by providing visual guidance on ESP teardown procedures and highlighting recurrent component-level failure mechanisms. The data obtained from these teardown reports—coded systematically under API RP 11S1—can be integrated into failure databases, enabling more structured analysis for troubleshooting operational issues, comparing equipment performance, and ultimately enhancing ESP run life. While the IFMRC framework builds on this foundation, it extends the classification by incorporating multidomain diagnostic inputs, sensor-based anomalies, and contextual metadata, thereby enabling more granular and actionable insights. See

Table A3. Crosswalk between API RP 11S1 code and IFMRC framework.

API Code	API Description	Mapped IFMRC Category	Mapped IFMRC Description
LPRO	Low Production	Operational—Reservoir Impact	Reservoir depletion or low drawdown
POFF	Production Off	Electrical/Operational	Power failure, VSD/SWB trip, or shut-in condition
RSIH	Resize (Increase Production)	Not a failure—Operational Change	-
RSDH	Resize (Decrease Production)	Not a failure—Operational Change	-
DHSH	Downhole Short	Electrical—Downhole Short Circuit	Cable or motor insulation breakdown
LPUM	Locked Pump	Mechanical—Pump Stuck/Seized	Debris, gas lock, or mechanical jamming
LOAM	Drawing Low Amps	Electrical—Control System Failure	Faulty VSD setting or underload trip condition
HIAM	Drawing High Amps	Electrical—Motor Burnout	High load, phase imbalance, or motor overheating
HITB	Hole in Tubing	Root Cause—Wellbore Environment	Mechanical damage or corrosion leading to leakage
CSRP	Casing Repair Required	Root Cause—Wellbore Environment	Casing deformation, collapse, or corrosion
WKOV	Workover	Not a failure	-
STIM	Stimulation Required	Not a failure—Reservoir Enhancement	-
LOGG	Logging Well Required	Not a failure—Diagnostic Action	-
COVT	Converting Well	Not a failure—Strategic Reuse	-
TEST	Testing Well	Not a failure—Diagnostic Action	-
TSPN	Temporary Suspending Well	Not a failure—Operational Pause	-
ABAN	Abandoning Well	Not a failure—Lifecycle Conclusion	-
OTH1–5	Other (1–5)	Various	-
7000	Splice Failure	Electrical—Cable Fault	Splice or termination failure
7010	Cable Failure	Electrical—Cable Fault	Jacket abrasion, crush, or thermal degradation
7020	Motor Flat Failure	Electrical—Motor Burnout	Electrical insulation breakdown, winding failure
7030	Pigtail Failure	Electrical—Connector Fault	Improper torque, contact loss, or corrosion
7040	Tubing Failure	Root Cause—Wellbore Environment	Corrosion, scaling, or mechanical stress failure
7070	No Failure, Equip. Changed	Not a failure	-
7080	Unknown	Insufficient data for failure classification	-
7090	Other Failures	Insufficient data for failure classification

in Appendix C for a crosswalk between API RP 11S1 and IFMRC classification schemes.

Typical failure mode classifications, as discussed by several references [9,21,22], encompass various mechanical, material, electrical, and other issues. Mechanical failures include leaking, failed pressure tests, stuck or bent components, burst equipment, and broken or disconnected parts. Material-related failures involve burning, corrosion, wear, melting, or overheating. Electrical failures are characterized by short circuits, open circuits, or faulty power supplies. Other causes include plugging with solids or contamination of fluids. The predominant modes of ESP failures shifted from mechanical to electrical components, based on an analysis of approximately 170 ESP failures recorded between 2003 and 2010 from a vendor’s operations in the North Sea, as per reference [23]. Failure modes in ESP systems have been categorized in various ways [24], and four key modes have been identified: mechanical failures, electrical failures, control and system failures, and thermal failures, as supported by [25,26]. According to reference [27], ESP failure modes can be categorized into several key areas. Failures often arise from well conditions, such as corrosion affecting the motor and pump housings, scaling that insulates housing and clogs pump stages, and erosion caused by sand and abrasives. Design issues, including improper pump sizing, can accelerate wear and reduce system lifespan. Installation errors, such as inadequate pre-installation checks or poor assembly, introduce defects that compromise performance. Equipment defects further contribute to operational inefficiency, while electrical failures—stemming from unstable power supplies, voltage spikes, and phase imbalances—overstress motors and cables [12]. In their analysis of the Wafra field within the Kuwait–Saudi Arabia Divided Zone Group (DZG), the authors categorized ESP failures into four primary groups based on affected components rather than underlying failure modes. These classifications were as follows: motor failures (40%), pump failures (22%), cable failures (26%), and other miscellaneous failures (12%). Also, some literature focused on some factors that cause failures of specific components of ESP systems, as mentioned by [28,29]. Unbalanced voltage supply, broken rotor bars, rotor–stator eccentricity, and inter-turn winding faults are factors that can cause motor failure. Additionally, alternative classification approaches, such as the binary distinction between normal and faulty operations, have been proposed by others [30]. Reference [31] focused on binary classification for component-level failures, where the operational states of components were categorized as either normal or faulty. The rest of the literature refers to anomalies and pump stoppages as failures; however, these are often temporary interruptions due to operational limits and protection set points, not permanent failures. Anomalies that could lead to failure, as discussed by [32], include issues such as three-phase unbalance, string leakage, underload shutdown, and overload shutdown. In the Permian region’s horizontal wells, excessive heat (35%) and solid-related issues (29%), such as sand and abrasives, are the leading causes of ESP failures. Other factors, including oversized ESPs (16%), cable or pothead failures (15%), and miscellaneous causes (5%), contribute to a smaller portion of failures, with heat and solids accounting for over half of all ESP issues [33]. Both references [34,35] classified ESP failures into three main areas: electrical, mechanical, and operational issues. Electrical failures include cable failure, motor failure, overload (tripping), and connection severance. Mechanical failures are commonly caused by component breakage, corrosion (both sweet and sour types), dislocation, and leakage. Operational failures are often due to high temperatures, pressure surges (kicks), multiphase gas issues, scale or solid deposition, and challenges arising from deviated wells. These failure modes highlight the complexity of maintaining ESP systems and the need for effective monitoring and mitigation strategies.

The Egyptian Petroleum Corporation (EGPC) [36] classifies ESP failures into three main categories: electrical, mechanical, and non-ESP system-related, similar to reference [4]. Electrical failures include motor short circuits (S.C.), cable issues, and penetrator faults. Mechanical failures encompass motor and pump shaft bearing failures, seal damage, pump sticking, and wear. Non-ESP-related failures involve operational and environmental factors like high water cut, low flow, corrosion, or tubing holes. This classification enables targeted diagnostics and efficient maintenance strategies to address specific failure modes effectively. EGPC’s root cause classification tries to standardize failures into ESP-related and non-ESP-related categories. Non-ESP failures include sand or proppant production (S), plugging (P), tubing leaks (T), depleted formations (D), operational issues (O), and human errors (H). ESP-related failures cover cable issues (R, F), vendor-related problems (V), motor burnout (M), and undefined causes pending further analysis (N). This system streamlines diagnostics, enabling precise identification of failure origins and targeted corrective actions.

It is observed that earlier ESP failure classifications often suffer from a lack of standardization and clear differentiation between failure modes and root causes. For instance, motor failure is often mistakenly categorized as a root cause, despite being a consequence of underlying issues like excessive heat, water intrusion, or poor system design. This lack of precision creates ambiguity, hinders effective failure analysis, and reduces the utility of such classifications in real-world applications. Additionally, the absence of standardized frameworks leads to subjective bias, making it difficult to derive actionable insights. These limitations underscore the need for more comprehensive and data-driven classification systems to improve ESP reliability and operational efficiency.

To address this challenge, the integrated failure modes and root cause (IFMRC) two-step classification introduces a structured and systematic approach to categorize and analyze failures. This classification enhances the precision of root cause identification by integrating failure mode data with root cause insights, enabling the development of targeted solutions and predictive maintenance strategies. Such an approach is vital for improving the reliability and operational efficiency of ESP systems in increasingly demanding environments.

2. Methodology

This study employs a mixed-methods approach, combining quantitative analysis of actual field data with qualitative insights from a comprehensive literature review. The integration of these methods addresses the lack of consistency and standardization in existing electric submersible pump (ESP) failure classifications, providing a robust foundation for developing a new, systematic framework.

• Quantitative Data: Field data from over 4000 ESP installations in Egypt’s Western Desert, spanning 10 years of recorded parameters, were collected from an ESP team, engineering databases, workover records, and failure investigation reports (DIFA). These data provide a reliable and diverse foundation for identifying failure patterns and trends.
• Qualitative Data: A thorough literature review was conducted to identify gaps and inconsistencies in existing ESP failure classifications. The literature review highlighted the mix up between failure modes and root causes and led to the development of a structured framework that clearly distinguishes between failure modes and root causes.

Data Collection

The two types of data were collected to aid in developing the two-step integrated classification system. These data included the following:

• Field Data: Failure records from ESP installations, including failure modes, root causes, operational conditions, and troubleshooting logs were extracted from engineering databases and database systems.
• Literature Data: Existing classifications and failure descriptors from academic and industry sources were reviewed to identify gaps and inconsistencies.

Development of a Novel Integrated Failure Modes and Root Cause (IFMRC) Two-step Classification

Both the collected data and failure analysis classification from the literature were used to develop the new two-step failure classification system. The new classification system has two steps, which are explained below.

Step 1. Failure Mode Classification (Figure 1)

Benefits of using Failure Mode Classification: The proposed classification offers several key advantages. It ensures comprehensive coverage by addressing a broad spectrum of failure modes, including electrical, mechanical, hydraulic, chemical, and environmental and operational factors. Focusing on component-level failures enhances diagnostic precision and enables targeted interventions by linking specific component issues to broader failure modes. The system is highly applicable in maintenance and design, aiding in root cause analysis and identifying vulnerabilities in ESP components, ultimately improving reliability. With its applicability in both academic research and practical field operations, this classification system fosters a deeper understanding and more effective mitigation of ESP failures. A detailed description of the failure modes and their respective subcategories and components can be found in Appendix A.

Step 2. Root Cause Failure Classification (Figure 2)

Benefits of the Root Cause classification: The root cause classification is focused on failure mechanisms, recognizing that multiple factors can contribute to a single failure mode, thus enabling a thorough root cause analysis (RCA) and effective corrective action planning. It is practical for field applications, allowing the identification of primary failure factors, which supports targeted prevention strategies, enhances troubleshooting accuracy, and reduces downtime. This approach also supports continuous improvement by fostering a deep understanding of failure mechanisms, leading to advancements in ESP design, manufacturing, operations, and maintenance, ultimately enhancing system reliability and performance. A detailed description of the root causes and their respective subcategories can be found in Appendix B.

Justification for the proposed two-step classification:

The two-step classification offers a comprehensive analysis of failure mechanisms, considering the interconnectedness of ESP subsystems. By categorizing failures into electrical, mechanical, hydraulic, chemical, and operational types, it provides a holistic view that aids engineers in design, operation, and maintenance. It enhances predictive maintenance by identifying failure interactions, leading to more precise strategies. The system improves diagnostics by focusing troubleshooting efforts on the relevant components, such as motors or cables for electrical failures. By identifying root causes, it enables effective remediation and drives systematic investigation. It supports design optimization by highlighting failure interaction points and improving operational parameters to prevent issues like gas lock. Targeted safety measures are implemented for each failure type, and cost efficiency is achieved by addressing the most common failures with targeted solutions. The system standardizes knowledge transfer and training, providing a common language for engineers, while facilitating benchmarking and performance evaluation to drive continuous improvement. These classifications go beyond theoretical concepts as they offer practical frameworks that enhance the reliability, efficiency, and safety of ESP systems.

Development of the Classification Framework

The framework was developed in two steps, supported by a fishbone chart and flowchart for clarity of failure identification and classification, as shown in Figure 3 and Figure 4, respectively.

The fishbone chart shown in Figure 3 provides a visual representation of different failure types categorized based on their underlying root causes. It follows a structured skeleton, starting with failure modes at the top, branching into specific failure categories, and leading toward failure classification on the right. The structured hierarchy helps in identifying how failures originate.

• Root Causes (leftmost box) serve as the fundamental sources of failures; these causes may be directly causing the failure, or multiple interrelated factors may be contributing to a failure.
• Failure Categories include the following:
• Chemical Failures (e.g., corrosion, chemical attacks).
• Mechanical Failures (e.g., stuck pump, broken shaft).
• Electrical Failures (e.g., power surges, cable short circuits).
• Hydraulic Failures (e.g., fluid pressure issues, seal degradation).
• Environmental Failures (e.g., extreme temperatures, high sand and abrasive content).
• Operational Failures (e.g., human errors, repeated startup/shutdown).

This diagram can be used in risk assessment, root cause analysis (RCA), and failure mode and effects analysis to systematically identify, classify, and prevent failures in the oilfield.

The flowchart in Figure 4 guides the process of diagnosing and analyzing pump failure events through structured steps:

• Pump Down Notification—Identify an issue requiring investigation.
• Data Collection—Gather relevant operational data and obtain a failure potential from history.
• Failure Event Decision:

• Pump Up? → System resumes normal operation.
• Pump Down? → Failure event occurred.

4

Failure Analysis:

• Step 1: Identify the failure mode.
• Step 2: Determine the root cause.

5

Documentation and Action—Findings are recorded in a report and used as input for modeling to improve system reliability.

This structured approach ensures a systematic diagnosis of pump failures, helping with troubleshooting, documentation, and predictive maintenance.

The classification was applied to a case study of over 4000 ESP installations in Egypt’s Western Desert, where failure modes and root causes were systematically analyzed. The dataset reflects a wide range of operating conditions, including varying well depths, pump settings from shallow to deep, and diverse corrosive environments, including high-H₂S wells. Statistical methods were used to assess the consistency and reliability of the classification. While the framework aligned well with real-world data, limitations such as incomplete root cause analysis records and subjective failure descriptions were encountered. These challenges emphasize the need for improved data quality and the need for a classification that distinguishes between failure modes and root causes.

The proposed classification improves upon existing frameworks by offering broader applicability and finer granularity. Unlike traditional classifications that often conflate failure modes and root causes, this framework clearly distinguishes between the two, enabling more precise diagnostics. Additionally, it incorporates modern operational challenges, such as high sand production and gas lock, which are not adequately addressed in older systems. The integration of both qualitative and quantitative data also sets this framework apart, making it more adaptable to diverse operational environments.

Western Desert Case Study: Applying the Proposed Two-Step Classification

In this case study, we examine more than 4000+ installations across the Western Desert, distributed over the full extension of the Western Desert in Egypt (see map in Figure 5). Reported workovers: in the examined dataset, there were more than four thousand workovers. Data were collected from multiple sources, including the ESP database, drilling and workover well records, and insights from the engineering team’s field database. Additionally, this was supplemented with office-generated annual failure reports and (DIFA) reports, ensuring a comprehensive and well-rounded dataset for analysis. Notice that out of 4000 ESP installations, a total of 3190 records show ESPs that stopped operating due to failure and were subsequently pulled. The remaining 800 cases were either manually stopped (not classified as failures) or pulled for reasons unrelated to ESP failure. These non-failure reasons include economic decisions, optional fracturing, pump type changes (e.g., switching to SRP or PCP), ESP upgrades or downgrades, well recompletions, or conversion to injection or water source wells. Additionally, 990 cases were not investigated due to missing or incomplete root cause analysis. To assess the robustness of our conclusions in light of this missing data, we conducted a sensitivity analysis by reassigning the unknown cases to (i) the most frequent root cause and (ii) the least frequent root cause and found no material change in the overall rankings. Furthermore, we evaluated the association between failure modes and root causes using a chi-square test of independence, which yielded a statistic of 342 with 324 degrees of freedom and a p-value of 0.2356—indicating no statistically significant relationship at the 5% level, though the high degrees of freedom warrant cautious interpretation. We also calculated Cramér’s V to assess association strength. The initial result was inflated due to sparsity in the contingency table. After grouping infrequent failure modes into a single “Other” category, the recalculated Cramér’s V was 0.16, indicating a weak association. Therefore, the conclusions of this case study are based on the 2200 cases with complete (DIFA) records and have been tested for sensitivity to data limitations.

Failure Modes

Figure 6 shows the failure modes distribution of ESPs in the WD area, with the frequency of each failure type depicted by the number of occurrences. The most common failure mode is motor short circuit (Motor S.C.), which accounts for over 1000 failures. Low flow follows closely behind, with just under 1000 failure incidents. Round cable short circuit (R-Cable S.C.) also appears frequently but with fewer failures than motor and low flow issues. Pump shaft bearing (Pump Sh. B) failures are moderate in comparison, while tubing hole failures occur less often. The stuck pump is another less frequent failure mode. Penetrator short circuit (Pent. S.C.) and flat cable short circuit (F-Cable S.C.) are among the least common failure types, with very few reported incidents. The others category includes all other failure types such as human errors, but these contribute to a smaller proportion of total failures. Overall, the data emphasize that motor-related and flow-related failures are the primary causes of ESP failures, with cable and pump issues being less prevalent.

Figure 7 highlights the most frequent root causes. The prominence of scale deposition (plugging) and tubing leaks suggests persistent issues related to the wellbore environment and operational mismanagement. Extreme temperature fluctuations and defective manufacturing processes appear to be critical contributors, indicating the need for tighter material selection and operational control. A noticeable cluster of electrical issues (grounding faults, power instability) further emphasize the role of a consistent power supply. This root cause classification refines the failure mode data by excluding non-failure events and correlating observed failure modes with detailed root causes and (DIFA) reports.

Key Observations of the Western Desert Case Study:

This practical case study from oilfields in Egypt clearly highlights the critical challenge of misclassifying non-failure operational modes as failure modes, underscoring the need for precise differentiation in diagnostic and predictive maintenance frameworks, as well as mixing failure observations with root causes, creating confusion and ambiguity that hinders any further analysis of the data. This case study serves as a foundation for conducting a more accurate and in-depth analysis using a two-step classification approach, refined and enriched by integrating data from multiple sources. These challenges emphasize the need for structured classification systems and adaptable approaches to effectively address ESP failures. The case study shows the importance of enhancing (DIFA) coverage. Despite the diverse range of failure modes recorded in ESP systems, only a subset undergoes dismantle, inspection, and failure analysis (DIFA), with root cause analysis (RCA) performed for just 2200 cases due to operational and logistical challenges. Expanding (DIFA) beyond warranty-triggered inspections is crucial for building a comprehensive failure database and improving predictive maintenance. However, operational challenges, such as delayed retrieval of pump strings, decontamination of NORM-exposed systems, and reliance on visible issues like scale deposits, often hinder RCA and (DIFA). Failure modes and root cause analysis highlight critical trends and areas for improvement. Scale deposition (plugging) is the most frequent cause, significantly impairing pump efficiency and triggering secondary failures, such as motor overload and impeller plugging, necessitating prioritized preventive strategies. Tubing or casing leaks, often resulting from corrosion, wear, or sealing issues, underscore the importance of robust materials and inspection protocols. Extreme heat and temperature fluctuations, the third leading cause, highlight the thermal sensitivity of ESP components, particularly motors, emphasizing the need for proper sealing, lubrication, and pump selection based on thermal conditions. Cable failures, including grounding issues and defective materials, point to vulnerabilities in manufacturing and installation, suggesting the need for stricter quality assurance and better training for personnel. Human errors and fluid contamination, such as water ingress, further contribute to failures, which are linked to inadequate training, poor procedures, or ineffective wellbore isolation. Addressing these interconnected issues through tailored operational practices and enhanced preventive measures is critical to mitigating cascading failures.

Figure 8 presents the distribution of Motor S.C. (short circuit) failure cases across various root causes identified in Appendix A. The most dominant contributors include excessive heat or extreme temperature fluctuations, cable splice/grounding issues, and scale deposition. Mechanistically, prolonged exposure to elevated temperatures degrades motor insulation materials, leading to electrical breakdown and eventual short circuits. Similarly, poor cable splicing and grounding defects create direct electrical paths to the ground, resulting in Motor S.C. events. Additionally, internal motor contamination from scale deposition and fluid ingress introduces conductive pathways that further promote short circuiting. This clear association between specific operational and environmental conditions and Motor S.C. failures reinforces the need for improved temperature management, cable handling practices, and fluid control to enhance ESP reliability.

Case Study: Cobra-08—ESP Reliability and Diagnostic Precision with IFMRC

Field Overview:

Cobra-08 is a high-profile vertical well in the Western Desert, targeting the Lower Baharya formation. It initially delivered over 3000 BOPD of naturally flowing crude. After an artificial lift was installed, the well remained productive but began exhibiting performance anomalies and recurrent failures.

Chronology of Events and Failures (Pre-IFMRC):

March–December 2020:

Low flow symptoms emerged twice (Mar–Dec 2020 and Feb–Jun 2021), and each was tied to a suspected tubing or casing leak.

December 2020:

A sudden R-cable short circuit (S.C.) triggered a shutdown.

Production and Electrical Trends:

Over the same timeframe, the ESP data showed rising DHP (downhole pressure) (from ~1000 to 1500 psi), stable WHFP (~80 psi), and gradually dropping current draw, indicating motor loading stress.

Deferred oil production spiked to 65 STB/D, especially during generator-related shutdowns.

IFMRC Diagnostic—What Could Have Changed

If the IFMRC framework had been operational during this period, the following improvements would have likely emerged:

Multifactor Isolation: the recurrence of “Low Flow” issues might not have defaulted to tubing leaks alone.

Domain Mapping via Hierarchical Pathways, using the two-step IFMRC tree:

Failure Mode: Flow instability

Root Causes Considered: Wellbore environment, tubing or casing leak

Expert consensus (with data context) would favor a composite diagnosis over repeated tubing replacement—saving at least one full workover cycle (~30+ days).

Operational Cost Avoidance:

A conservative estimate suggests over 8000 STB of deferred oil could have been avoided.

Reducing unnecessary workovers (estimated USD 150 K each) would have provided tangible cost savings.

3. Discussion

The paper highlights the critical challenge of misclassifying normal operational modes as failures, emphasizing the need for precise differentiation in diagnostic and predictive maintenance systems. It also addresses the issue of conflating failure events with their root causes, leading to confusion and ambiguity that obstructs effective data analysis. The use of two-step classification of ESP failures reveals several interconnected challenges that, when addressed through targeted strategies, can significantly enhance system reliability and performance. Aging, vibration failures, gas decompression, and reservoir depletion highlight the critical need for predictive maintenance tools and advanced diagnostic systems. These tools can preemptively identify and mitigate common failure modes, reducing downtime and operational costs. Among these issues, scale-related failures are particularly prevalent, underscoring the importance of proactive scale management. Real-time downhole monitoring and tailored chemical inhibitors can effectively mitigate scale accumulation. However, the current reliance on manual monitoring processes—such as monthly fluid sampling and delayed laboratory analysis—often results in outdated data and suboptimal chemical treatment. Implementing SCADA systems and downhole capillary injection systems would enable real-time adjustments, reducing over- or undertreatment by over 40% and minimizing unplanned workover costs.

Motor short circuit (Motor S.C.) is the most frequent failure mode in the dataset, indicating potential issues with motor design, overheating, or electrical instability. Root causes could include poor insulation, excessive heat, or voltage fluctuations. They may also be linked to fluid contamination, scale deposition, or operational mismanagement, which can exacerbate motor stress and lead to short circuits. The high frequency of stuck pump failures suggests issues such as scale deposition, sand production, or mechanical wear. These failures are often caused by improper fluid handling or inadequate maintenance. Chemical injection practices or reservoir depletion could also contribute to this failure mode by altering fluid properties or increasing debris in the wellbore.

Chemical incompatibility further complicates these challenges, accounting for 20% of failures due to unanticipated reactions like scaling or emulsion formation scale deposition, which is a significant challenge in ESP systems, leading to various failure modes, such as tubing and pump plugging, reduced pump efficiency, motor overheating, increased wear and tear, stuck equipment, corrosion under deposit, electrical failures, excessive vibration, reduced productivity, and sensor malfunctions. To mitigate these issues, operators can employ a combination of chemical inhibition, mechanical removal, acidizing, water chemistry management, and real-time monitoring. Additionally, optimizing flow velocities, using scale-resistant materials, and conducting periodic cleaning and maintenance are crucial. By proactively addressing scale deposition through these strategies, operators can minimize downtime, enhance system reliability, and maintain efficient production rates, ultimately extending the lifespan of ESP systems and reducing operational costs.

Manufacturing defects and inadequate quality control (QC) further exacerbate the problem, leading to early equipment failures. Strengthening material inspections, reliability testing, and standardized quality assessments at the manufacturing stage can improve operational longevity. Additionally, high-frequency causes such as tubing or casing leaks, excessive heat, and cable issues rank prominently after scale deposition. Addressing these challenges requires robust design, better material selection, and enhanced installation protocols. Ensuring a reliable power supply, regular maintenance of gensets, and daily well surveys to adjust parameters can reduce frequent start–stop cycles and electrical issues.

By addressing interconnected challenges through targeted preventive measures, advanced monitoring systems, and improved operational practices, operators can significantly enhance ESP reliability, reduce costs, and achieve sustainable production targets. This comprehensive approach not only mitigates immediate failure risks but also fosters long-term operational efficiency and safety. The integration of AI and machine learning into the IFMRC framework can further enhance its predictive and diagnostic capabilities by leveraging historical failure data to anticipate and prevent ESP failures. AI models can automate root cause analysis, detect real-time anomalies, and recommend prescriptive maintenance actions, reducing downtime and operational costs. Predictive maintenance systems and digital twins can optimize performance by simulating operational scenarios and enabling early issue detection. Despite challenges like data quality and implementation costs, AI integration can probably transform the IFMRC framework into a proactive tool, improving ESP reliability, efficiency, and sustainability in oil production.

4. Conclusions

This paper presents a new two-step failure classification method for ESP wells. The classification was applied on a dataset that included more than 4000 ESP installations. Based on the work conducted in this paper, the following conclusions can be drawn:

• The proposed two-step classification system provides a holistic view of ESP failures by integrating interconnected subsystems. It encompasses previous literature classifications, enhances diagnostic accuracy, eliminates confusion, and supports efficient troubleshooting and root cause identification. The framework also standardizes knowledge transfer, enabling personnel to better anticipate, detect, and manage failures.
• The two-step classification system includes five failure modes and five main root cause categories, with some root causes contributing to different types of failures. This makes the framework general and applicable to various environments beyond the Western Desert case history. It can be extended to offshore operations and unconventional reservoirs with appropriate contextual validation.
• The two-step classification was applied to a large dataset from the Western Desert, comprising over 4000 failure events from more than 350 wells over a 10-year monitoring period. Several benefits were observed, including improved failure analysis and more targeted remediation strategies.
• The case history reveals that failure modes are rarely caused by a single root cause but are often the result of multiple contributing factors. A detailed root cause analysis, combined with proactive maintenance and operational improvements, is crucial to addressing these failures effectively.
• Applying the two-step classification revealed that issues with chemical injection practices in the case history led to a significant number of failures. This was identified as a prominent root cause, and remedial actions are currently underway to address the problem based on the case study.
• Based on the findings of the case study, the motor short circuit was identified as a major failure mode, primarily driven by excessive heat and temperature fluctuations. These thermal stresses emerged as the dominant contributing root cause, leading to motor insulation degradation and eventual burnout.
• Some failure modes are complicated and require deep analysis. For example, motor short circuits should be accompanied by (DIFA) to better understand the root causes and enable effective remedial actions.