Failure prediction of reservoir pressure maintenance system at the Prirazlomnoye Arctic Offshore field

• Published in: IOP Conference Series: Materials Science and Engineering
• Main Author: Kurchatov, I M
• Format: Article in Journal/Newspaper
• Language: unknown
• Published: IOP Publishing 2021
• Subjects: Arctic; Prirazlomnoye
• Online Access: http://dx.doi.org/10.1088/1757-899x/1201/1/012084; https://iopscience.iop.org/article/10.1088/1757-899X/1201/1/012084; https://iopscience.iop.org/article/10.1088/1757-899X/1201/1/012084/pdf

Abstract Failures of reservoir pressure maintenance system at offshore facilities cause production losses and a significant increase in OPEX. Predicting failures of a water injection pump or its parts can highly improve the overall performance by promptly adjusting operating parameters to prevent failure occurrence or by scheduling maintenance to reduce unplanned repairs and to minimize downtime. This is particularly relevant for Arctic offshore projects, characterized by considerable logistical challenges and substantial environmental safety risks. The paper presents a data-analytic approach for failure prediction for the water injection pump operated at the ice-resistant GBS Prirazlomnaya. The study used pump failure history and field sensor data to predict the technical condition and identify a failed component in advance. An ARIMA model implemented in the R software environment was developed for the analysis. The results demonstrate that the approach works appropriately based on the generalized risk assessment and feedback from subject matter experts.