液载是陆上和海上气井面临的长期挑战，尤其是在低气量时。经验相关性通常用于检测液载，但由于对液体行为和流动状态一致性的假设过于简单，这种方法在现场应用中往往缺乏准确性。在完整的论文中，作者介绍了一种数据驱动的液载检测和预测 (LLDP) 方法，该方法利用高频气量和油管头压力测量来确定液载的开始，并用它来校正通过经验方法计算出的临界速率。
所提出的 LLDP 方法利用常用的高频表面气速和油管头压力测量数据，计算出指示流动不稳定性的诊断统计代理特征。检测到气速后，使用反馈控制对气速进行后续调整，有助于通过不断校准经验相关性来确定修正的临界速率。
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.
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.
