Conference Paper

Use of Artificial Intelligence to Measure Gas Flow Rate, Bongkot Asset

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Greater Bongkot North is a gas field located in Gulf of Thailand and on production since 1993. Most of the old wellhead platforms (30%) lack remote well test facilities which requires personnel visits for any well test measurement. Often, well testing in these platforms get lower priority compared to other operations in a matured field. This project implemented artificial intelligent (AI) technique to estimate gas rate from other available engineering and geological parameters. A new approach using machine learning was applied to estimate gas production rate where actual measurements are not available. Actual production well test data was used to train the model. Input parameters used were: Surface facility information Fluid properties Production condition Geological setup A blind test on the subset of historical data showed a level of confidence (R2) value of 0.93. This provided confidence to proceed with a full field pilot. A pilot was conducted during January to May 2018. The area of pilot was spread across various geological, operating and surface condition setups to reduce sampling bias. The pilot demonstrated the following use cases: Improved prediction accuracy in wells with no recent test, achieving primary object of model. Detection of well behavior changes: The model could detect changes in well behavior without human intervention much before the trends become obvious for engineers to detect. Improved potential estimation in wells with leaks in wellhead chokes where conventional analysis followed in Bongkot is not possible due to improper wellhead shut-in pressure measurement. Improved efficiency with production allocation: The conventional method requires significant time (40-80 person hours per month) to make the data available for production allocation. This can be shortened significantly by use of this method In essence, this project demonstrated the potential use of artificial intelligent to improve efficiency in a matured gas field operating under marginal conditions.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

Conference Paper
Objective/Scope Accurate well production rate measurement is critical for reservoir management. The production rate measurement is carried out using surface devices, such as orifice flow meter and venturi flow meter. For large offshore fields development with a high number of wells, the installation and maintenance costs of these flowmeters can be significant. Therefore, an alternative solution needs to be developed. This paper described the successful implementation of Artificial Intelligence in predicting the production rate of big-bore gas wells in an offshore field. Methods, Procedures, Process Successful application of AI depends on capitalizing on a large set of data. Therefore, flowing parameters data were collected for more than 30 gas wells and totaling over 100,000 data points. These wells are producing gas with slight solid production from a high-pressure high-temperature field. In addition, these wells are equipped with a multistage choke that reduces the noise and vibration levels. An Artificial Neural Network is trained on the data using Gradient Descent method as the optimization algorithm. The network takes as an input the upstream and downstream pressure and temperature, and the choke size. The output is the gas rate measured in MMscf/day. Results, Observations, Conclusions The data set was divided into 70% for training the neural network and 30% for validation. Artificial Neural Network (ANN) was used and the developed model compared exceptionally well with the gas rates measured from the calibrated venturi meters. The gas rate estimation was within a 5% error. The model was developed for two types of completions: 7" and 9-5/8" production tubing. One of the challenges was how to estimate the choke wear which plays a major role in the quality of the choke size data. A linear choke wear deterioration is applied in this case, while work in progress is taking place for acquiring acoustic data that can significantly improve the choke wear modeling. Novel/Additive Information The novel approach presented in this paper capitalizes on Al analytics for estimating accurate gas flow rate values. This approach has improved the reservoir data management by providing accurate production rate values which has drastically improved the reservoir simulation. Moreover, the robustness of the AI model has forced us to rethink the conventional design of installing a flow meter for every well. As shown in this paper, the AI model served as an alternative to conventional venturi meters. We believe that the application of AI models to other aspects of production surveillance will lead to a shift into how operators design production facilities.
Conference Paper
Full-text available
In this work we describe a machine learning pipeline for facies classification based on wireline logging measurements. The al- gorithm has been designed to work even with a relatively small training set and amount of features. The method is based on a gradient boosting classifier which demonstrated to be effec- tive in such a circumstance. A key aspect of the algorithm is feature augmentation, which resulted in a significant boost in accuracy. The algorithm has been tested also through participation to the SEG machine learning contest.
Article
Full-text available
A multivariate analysis is presented for the study of the vector boson fusion (VBF) Higgs boson decaying to a pair of tau leptons. While the VBF production mechanism of the Higgs is roughly an order of magnitude lower in cross section than the dominant gluon-gluon fusion mechanism, it is shown that VBF produces a distinctive signature that is well suited for detection by multivariate analyses. A number of discriminant variables are explored in addition to a direct comparison of different machine learning toolkits. Ultimately, a statistical significance of 7.9 is achieved for detection of the VBF Higgs boson in this truth level study.
Conference Paper
Directional drilling is a complex process involving the remote control of tool alignment and force application to a very long drill string subject to variable external forces. Controlling bit tool face orientation while ensuring adequate rate of penetration (ROP) is quite challenging, with aspects that have been described as more art than science. Improving this control helps preserve proper well trajectory and eliminate deviations that require corrective measures and add to well costs. An artificial intelligence system was developed to learn from the actions of expert directional drillers and the mechanics of drilling simulations. Machine learning algorithms were employed to improve the efficiency of directional drilling: optimized ROP, less tortuous borehole, less personnel on board (POB), and consistency across operations. The system ingests historical and simulation data corresponding to the information used and actions taken by expert directional drillers and uses that data to generate decisions that result in efficient slide drilling. To create a system for controlling tool face angle and guiding drill bit sliding during directional drilling, relevant historical data from directional drilling operations was gathered. Much of this data was recorded in the drilling logs, which the drilling operator traditionally uses to control drilling parameters. The collected data was then filtered and used to structure and train artificial neural networks and select appropriate hyperparameters. Reinforcement learning methods were used to refine the neural networks trained on historical data. A computational model for drill string physics was used to simulate the mechanics of directional drilling. A successfully trained network was considered one that minimized deviation from planned wellbore trajectory, minimized tortuosity, and maximized ROP. The neural network developed could replicate the decisions of expert directional drillers within a small error (<3%). Reinforcement learning was then successfully used to improve network performance, particularly for conditions not previously considered. Since the algorithm has demonstrated competence in the historical and simulated realms, it will be further tested as a real-time advisory system for control of directional drilling operations. The system will be tested in simulation with an expert directional driller before use in a field drilling operation. Ultimately, the algorithm can be directly integrated into drilling operations, enabling fully automated directional drilling.
Conference Paper
Sand management is one of the key component of Bongkot production processes. Current sand production prediction is based on a model which requires sonic and density logs for all the wells. However, a combination of complex well architecture and focus on reducing well cost resulted in many wells not having acquired these important logs. This project has implemented new technique of "Artificial Neural Network" to solve this problem. Using this method, synthetic logs are generated to obtain the values of missing sonic and density data. These data are then used in the existing sand models to predict sand production potential. This project was evaluated with three field cases. The sand failure predictions based on synthetic rock properties matched with actual sand production. Therefore, the sand prediction workflow has been updated to include log synthetic if acroustic or density log are missing.
Conference Paper
When many daily measurements of a thermal EOR field are taken throughout production, it is not cost effective to manually interpret trends to update reservoir models, so we developed an automated data-driven approach for production prediction using machine learning techniques. This is a two-step scheme that first predicts auxilary field measurements from directly-controlled field settings, then uses these predicted field measurements to predict production. The full two-step prediction process needs further refinement, but the second step alone shows promise for aiding in automated interpretation of data. Time shifts from daily seismic surveys improved production predictions.
Article
Boosting is a general method for improving the accuracy of any given learning algorithm. This short overview paper introduces the boosting algorithm AdaBoost, and explains the un-derlying theory of boosting, including an explanation of why boosting often does not suffer from overfitting as well as boosting's relationship to support-vector machines. Some examples of recent applications of boosting are also described.
Production Monitoring Using Artificial Intelligence, APLT Asset. Presented at the SPE Intelligent Energy International
  • G Olivares
Olivares, G. et al. 2012. Production Monitoring Using Artificial Intelligence, APLT Asset. Presented at the SPE Intelligent Energy International, Utrecht, Netherland, 27 -29 March 2012. SPE 149594.