Improved Data Mining for Production Diagnosis of Gas Wells with Plunger Lift through Dynamic Simulations

Abstract

Plunger lift has been widely used in unconventional gas wells to remove liquid accumulation from the well.. Production surveillance provides large amount of data of production process and normal and abnormal operations, which can be used in machine learning (ML) and Artificial Intelligence (AI) to develop algorithms for anomaly diagnosis and operation optimization. However, in the surveillance data the majority is related to daily operation and the data of failure cases are rare. Also the failure cases may not be repeatable and many failure case signatures are not available until they happen. Large data size of anomaly cases are needed to improve the ML model accuracy. Dynamic simulation of the plunger lift process offers an alternative way to generate synthetic data on the specified anomalies to be used to train the ML model. It also helps better understand the trends reflected in the surveillance data and their root causes. From the available surveillance data of gas wells equipped with plunger lift, the simultaneous measurements of different parameters at different points in a production system with normal and abnormal occurrences can be analyzed and the correspondent trends/signatures can be identified. The typical signatures that conform to pre-determined anomalous patterns can be obtained. Using a commercial transient multiphase flow simulator, the actual field data of tubing/casing pressures can be matched through a tuning process. Trial-and-error is needed to improve the dynamic plunger lift model so that a good agreement with the production data can be achieved by adjusting the reservoir performance, plunger parameters or surface pipeline boundary conditions. Following the validation under different flow conditions, synthetic datasets for various operational and flow conditions can be generated by performing parametric studies. Unlike the field data, the synthetic data from the dynamic simulations mainly comprise anomaly signatures (e.g. tubing rupture, missed arrival of plunger, etc.), which can be added to the ML data pool to reduce the data covariance and increase independency.

The DigitalTwin from an Artificial Intelligence Perspective

“…[27], aiming to do an automated process planning for CPS and [25] doing non-convex hull based anomaly detection in cyberphysical prodution systems could use the AITWin. Other examples are [1] who gives a detailed review of ML for diagnoses in production or [36] who analysis gas wells. In every work the causality API of the AITwin can be used.…”

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

“…Using exponential equations to describe gas inflow and linear equations to describe water inflow, Gasbarri and Wiggins (2001) [19] designed a plunger motion model combined with surface pipelines. In addition, previous studies predicted plunger's movement by analyzing wellbore acoustic signals, casing pressure changes [20], plunger movement in the wellbore based on smart plunger wellbore parameter testing [21], and by dynamically simulating plunger movement using data mining [22]. Regardless of the method or model applied, gas well productivity equations based on a steady flow describe the formation inflow characteristics [23][24][25].…”

Study on the effect of cetyltrimethylammonium bromide on gas-liquid flow characteristics at low gas flow rates and gas pressure

“…This problem is one of the most essential in the Cenomanian gas production and world gas production. For its solution, special studies are carried out [4,5,6,7] and various technologies are used, such as compression, velocity tubing, plunger lift, gas lift, rod pump, electric centrifugal pump, etc. [8,9,10,11,12].…”