Review of Stuck Pipe Prediction Methods and Future Directions

Summary Stuck pipe events continue to be a major cause of nonproductive time (NPT) in well construction operations. Considerable efforts have been made in the past to construct prediction models and early warning systems to prevent stuck pipe incidents. This trend has intensified in recent years with the increased accessibility of artificial intelligence (AI) tools. This paper presents a comprehensive review of existing models and early-warning systems and proposes guidelines for future improvements. In this paper, we review existing prediction approaches on their merits and shortcomings, investigating five key aspects of the approaches: (1) the time-frequency and spatial bias of the data with which the models are constructed, (2) the variable space, (3) the modeling approach, (4) the assessment of the model’s performance, and (5) the model’s facility to provide intuitive and interpretable outputs. The analysis of these aspects is combined with advancements in anomaly detection across other relevant domains to construct guidelines for the improvement of real-time stuck pipe prediction. Existing solutions for stuck pipe prediction face numerous challenges, allowing this problem to remain unsolved in the broad scope of progressing drilling automation. In our analysis, we looked at notable approaches, including decentralized sticking prediction, sophisticated data-driven models coupled with explanation tools, and data-driven models coupled with physics-based simulations (hybrid sticking predictors). However, even these sophisticated approaches face challenges associated with general, nonspecific applicability, robustness, and interpretability. While the best approaches tackle some of these challenges, they often fail to address all of them simultaneously. Furthermore, we found that there is no standardized method for assessing model performance or for conducting comparative studies. This lack of standardization leads to an unclear ranking of (the merits and shortcomings of) existing prediction models. Finally, we encountered cases where unavailable information (i.e., information that would not be available when the model is deployed in the field for actual stuck pipe prediction) was used in the models’ construction phase (referred to here as “data leakage”). These findings, along with good practices in anomaly detection, are compiled in the form of guidelines for the construction of improved stuck pipe prediction models. This paper is the first to comprehensively analyze existing methods for stuck pipe prediction and provide guidelines for future improvements to arrive at more universally applicable, real-time, robust, and interpretable stuck pipe prediction. The application of these guidelines is not limited to stuck pipe prediction and can be used for predictive modeling of other types of drilling abnormalities, such as lost circulation, drilling dysfunctions, and so on. Additionally, these guidelines can be leveraged in any drilling and well construction application, whether it is for oil and gas recovery, geothermal energy, or carbon storage.