Root-Cause Identification and Production Diagnostic for Gas Wells with Plunger Lift

Abstract

The paper presents an application of the regression tree technique as a root-cause identification and production diagnostic tool, and presents case studies for gas wells using the plunger-lift system. The regression tree model is data-driven and easy to construct, and does not require all of the parameters that a first principle-based model often requires. Thus, these models are quite useful in cases where real-time data or the required data for a detailed analysis are unavailable. To improve prediction capability, a cross-validation technique was used to optimize tree size. A total of 8–10 variables that could potentially impact the gas production rate were considered, with case studies conducted on actual field data. Questions, such as which group of wells are performing well or poorly, are quickly answered. Regression tree analysis, when applied at the field level, can identify a group of wells that underperform compared to other wells. As a result, an asset team can prioritize wells identified as poor performers. Further, a statistical analysis helps to gain insight into understanding the causal relationship between the gas production rate and various operational variables. Based on this analysis, recommendations are also provided to improve the gas production rate of poorly performing wells. Individual well models were also constructed to identify the root causes for high or low gas production based on operational changes made over a certain period of time. Only a few of the variables were found to have a significant impact on gas production. The interpretation of the decision tree indicated that additional operational variables, such as production time and pressure build-up time, should be included in the regression tree analysis to improve the diagnostic process. This paper summarizes these conclusions and recommends future work to improve the prediction capability of the regression tree analysis.

A Comparison of Machine Learning Approaches for Prediction of Permeability using Well Log Data in the Hydrocarbon Reservoirs

“…Finding the splitting criteria, which depends on inputs, a DT begins, and then the value of square error between observed and calculated outputs is minimized. Thus it will have one root node and two child nodes [48]. For further splitting, the same pattern will be repeated on all child nodes.…”

Experimental Study on the Coefficient of Internal Frictional Resistance in the Annular Gap during the Plunger Gas Lift Process

“…Although the plunger is placed in an annular gap with the tubing as it travels upstream and creates a turbulent seal [9,10] that prevents some of the fluid from falling back down to the bottom of the well, there is still friction generated by the annular gap between the plunger and tubing in the process; since the velocity of the plunger movement in a vertical wellbore can change from moment to moment, it causes the annular gap frictional resistance to change throughout the plunger's upward travel. However, previous studies usually ignored the friction between the plunger and liquid, treating the plunger and liquid column as a single unit and considering only the friction of the liquid column.…”

Research on the Inflow Performance of the Plunger Lift in the Shale Gas Horizontal Well

“…Presently, the drainage gas production technology of shale gas wells mainly includes plunger lift, foam drainage, and gas injection lift. Among these, the plunger lift is widely used in the field because of its simple operating process, as well as low maintenance and operational costs [12][13][14].…”