Plunger lifted, and free-flowing gas wells experience a wide range of issues and operational inefficiencies such as liquid-loading, downhole and surface restrictions, stuck or leaking motor control valves, and metering issues. These issues can lead to extended downtime, equipment failures, and other production inefficiencies. Using data science and machine-learning algorithms, a self-adjusting anomaly detection model considers all sensor data, including the associated statistical behavior and correlations, to parse any underlying issues and anomalies and classifies the potential cause(s). This paper presents the result of a Proof of Concept (PoC) study conducted for a South Texas operator encompassing 50 wells over a three-month period. The results indicate an improvement compared to the operators’ visual inspection and surveillance anomaly detection system. The model allows operators to focus their time on solving problems instead of discovering them. This novel approach to anomaly detection improves workflow efficiencies, decreases lease operating expenses (LOE), and increases production by reducing downtime.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.