Predict Subsea ESP Failures with Advanced Detection

Reduce downtime and costs with early failure prediction in harsh environments.

Discover how IET’s physics-based anomaly detection identified critical failure markers in subsea Electric Submersible Pumps (ESPs). 

By analyzing slow-sampled historian data, IET enabled operators to predict failures, minimize downtime, and avoid costly repairs. 

Predict Subsea ESP Failures with Advanced Detection

Reduce downtime and costs with early failure prediction in harsh environments.

Discover how IET’s physics-based anomaly detection identified critical failure markers in subsea Electric Submersible Pumps (ESPs). 

By analyzing slow-sampled historian data, IET enabled operators to predict failures, minimize downtime, and avoid costly repairs. 

The Challenge

A unique type of Electric Submersible Pump (ESP) was deployed by IET’s client to address reservoir-specific challenges. These ESPs were mounted in caissons on the sea floor, thousands of feet below sea level, operating in an extreme 24/7 service environment.

This harsh setting resulted in a shorter mean time between failures (MTBF), making failure prediction critical to minimize unplanned downtime and costly repairs. Unlike surface-mounted ESPs, the subsea location of these pumps introduced significant challenges:

  • Accessibility Issues: Located 8,000 feet below sea level, repairs and replacements were logistically complex and expensive.
  • Data Limitations: High-speed, large-scale data collection wasn’t feasible. The only available data came from a general historian with a slow sampling rate (1–10 seconds), far below the speeds typically required for effective equipment monitoring.
Electric Submersible Pump

The Investigation

The client had previously attempted to identify pump failures using statistical methods, but these efforts proved unsuccessful. They turned to IET, providing historical data to uncover potential failure markers.

IET’s team quickly developed new analytical approaches and test frameworks, focusing on the limited historian data. By applying advanced signal processing and statistical techniques, IET identified promising patterns and insights.

Key breakthroughs included:

  • Backspin Detection: IET developed a system to detect and alert operators to both major and minor backspin events in near real-time.
  • Failure Correlation: Historical data analysis revealed a strong correlation between backspin events and damage to the pumps’ thrust bearings, a key failure mode.
Electric Submersible Pump

The Solution

During the evaluation period, it was determined that applying IET’s monitoring, signal processing, and statistical techniques revealed markers in the historical data that pointed to an issue which progressively developed prior to the ultimate failure of the unit. These markers coincided with time frames in which it was determined that the pump inadvertently spun backwards due to a malfunctioning downstream check valve that allowed flow to reverse through the pump when it was shut down. This backspin has been known to cause damage to the unidirectional thrust bearings in the pump, eventually leading to failure.

The Results

ET’s innovative techniques demonstrated that even with low sample rates and compressed data, early indicators of ESP failure could be detected. The results-built confidence in the client’s ability to predict and prevent future failures.

Results Snapshot:

  • Early Failure Detection: Identified precursors to ESP failure using historian data alone.
  • Real-Time Alerts: Developed alerts for major and minor backspin events.
  • Damage Correlation: Linked backspin frequency and duration to thrust bearing damage.
  • Actionable Insights: Empowered operators to make informed decisions despite data limitations.

Executive Summary

This case study demonstrates how IET applied physics-based anomaly detection to identify early indicators of failure in subsea Electric Submersible Pumps (ESPs). Using historical operational data and engineering-based analysis, the project uncovered critical failure markers, enabling earlier intervention, reduced downtime, and improved equipment reliability despite limited sensor data.

Ready to Predict Failures Before They Happen?

Discover how IET’s physics-based anomaly detection can protect your assets and reduce downtime.

Other Case Studies

Explore our other projects:

Case Study 1

Electric Submersible Pump

Case Study 2

Valve Diagnostics​

Case Study 3

Acoustic Leak Detection​