In-Situ Fault Detection of Submerged Pump Impellers Using Encapsulated Accelerometers and Machine Learning

Abstract

Vertical turbine pumps in oil and gas operations rely on motor-mounted accelerometers for condition monitoring. However, these sensors cannot detect faults at submerged impellers exposed to harsh downhole environments. We present the first study deploying encapsulated accelerometers mounted directly on submerged impeller bowls, enabling in-situ vibration monitoring. Using a lab-scale pump setup with 1-meter oil submergence, we collected vibration data under normal and simulated fault conditions. The data were analyzed using a suite of machine learning models -- spanning traditional and deep learning methods -- to evaluate sensor effectiveness. Impeller-mounted sensors achieved 91.3% average accuracy and 0.973 AUC-ROC, outperforming the best non-submerged sensor. Crucially, encapsulation caused no statistically significant performance loss in sensor performance, confirming its viability for oil-submerged environments. While the lab setup used shallow submergence, real-world pump impellers operate up to hundreds of meters underground -- well beyond the range of surface-mounted sensors. This first-of-its-kind in-situ monitoring system demonstrates that impeller-mounted sensors -- encapsulated for protection while preserving diagnostic fidelity -- can reliably detect faults in critical submerged pump components. By capturing localized vibration signatures that are undetectable from surface-mounted sensors, this approach enables earlier fault detection, reduces unplanned downtime, and optimizes maintenance for downhole systems in oil and gas operations.