A Hybrid Physical and Machine Learning Model to Diagnose Failures in Electrical Submersible Pumps

Abstract

Abstract Electrical submersible pumps (ESPs) are among the most common artificial lift techniques in highly productive oil wells. The ESP failures are extremely costly to the producers and must be minimized. This study proposes a hybrid approach utilizing multi-class classification machine learning (ML) models to identify various specific failure modes (SFMs) of an ESP. A comprehensive dataset and various ML algorithms are utilized, considering the physics of fluid flow through the ESP. The ML models are based on field data gathered from the surface and downhole ESP monitoring equipment over five years of production of 10 wells. The dataset includes the failure cause, duration of downtime, the corresponding high-frequency (per minute) pump data, and well-production data. The prediction periods of 3 hours to 7 days before the failure are evaluated to minimize false alarms and predict the true events. Four modeling designs are used to handle the data and predict ESP failure. These designs differ in the input parameters used for the model and signify the effect of including the physical parameters in failure prediction. Several ML models are tested and evaluated using precision, recall, and F1-score performance measures. The K-Nearest Neighbor (KNN) model outperforms the other algorithms in forecasting ESP failures. Some other tested models are Random Forest (RF), Decision Tree (DT), Multilayer Perceptron (MLP) Neural Network, etc. According to the data, most ESP operational failures are characterized as electrical failures. The ML models show similarly good performances with high true prediction rates in predicting ESP failures for all the tested designs. The design that integrates the effects of gas presence and pump efficiency while minimizing the number of input variables is suggested for general use. Increasing the prediction period up to 3 days results in a negligible drop in the model’s performance, showing that the model can predict ESP failures accurately three days before their occurrences. However, the forecasts show increases in missed failures and false alarms for prediction periods of more than three days, making three days the selected prediction period. These ML models will aid operators in avoiding undesirable events, reducing downtime, and extending the lifespan of ESPs. ESP failures are unanticipated but common occurrences in oil and gas wells. It is necessary to detect the onset of failures early and prevent excessive downtime. This study’s model allows engineers to detect failures early, diagnose potential causes, and propose preventive actions. It is crucial in transitioning from a reactive event-based to proactive and predictive maintenance of artificial lift operations.