Data-Driven Approach Enhances Liquid-Loading Detection and Prediction

_ This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 218841, “A Data-Driven Journey Into Liquid-Loading Detection and Prediction, ” by Utkarsh Sinha, Prithvi Singh Chauhan, and Hardikkumar Zalavadia, SPE, Xecta Digital Labs, et al. The paper has not been peer reviewed. _ Liquid loading is a persistent challenge in onshore and offshore gas wells, particularly at low gas rates. Empirical correlations are used commonly to detect liquid loading, but this method often lacks precision in field applications because of oversimplified assumptions regarding liquid behavior and flow‑regime consistency. In the complete paper, the authors introduce a data‑driven approach for liquid‑loading detection and prediction (LLDP) that harnesses high‑ frequency gas‑rate and tubinghead‑pressure measurements to identify the onset of liquid loading and use it to correct critical rates computed by empirical methods. Introduction Leveraging commonly available surface gas‑rate and tubinghead‑pressure measurements collected at high frequency, the proposed LLDP method computes diagnostic statistical proxy features indicative of flow instability. Upon detection, subsequent adjustment to gas rates using feedback control facilitates the determination of corrected critical rate by calibration of empirical correlations continuously. This also allows prediction of when reservoir energy will no longer be sufficient to lift the liquids combined with the corrected critical gas curve and estimate time to liquid loading. Application of the LLDP method across multiple gas fields demonstrates its efficacy in detecting liquid‑loading events accurately without bias or interpretation. Several case studies are presented in the complete paper to illustrate the field applicability of the proposed method. In one of the applications, adjusted critical rates are used to optimize gas lift operations, resulting in substantial cost savings by minimizing the need for lift gas‑injection demand. Methodology Critical Gas Rate. Proper understanding of critical gas rate guides effective well management and production life‑cycle optimization. In the complete paper, three correlations from the literature are used to calculate gas critical velocity. The authors discuss characteristics of, and differences between, the three correlations. The equation used to accomplish this signifies the minimum velocity needed at a given pressure for efficient fluid transportation without liquid fallback. The onset of liquid loading corresponds to when the liquid velocity falls to zero at the desired location in the wellbore. Gas rates surpassing critical values throughout the wellbore trajectory ensure liquid droplet conveyance to the surface. Liquid-Loading Detection. The LLDP method uses high‑frequency measurements, namely wellhead pressure, metered gas rate, and water rate. Metered rates are optional and used wherever available. The measurements are taken over a moving window horizon (for example, 24–72 hours, adjustable based on available production history) and the window slides over a fixed step size (for example, 4–24 hours). The window size could be adjusted to accommodate lower measurement resolution. Two methods of liquid‑loading detection—variance analysis and frequency analysis—are detailed in the complete paper.