Discrimination Between Reservoir Models in Well-Test Analysis

1995 ◽  
Vol 10 (02) ◽  
pp. 114-121 ◽  
Author(s):  
Anraku Toshiyuki ◽  
R.N. Horne
Keyword(s):  
Well Test ◽  
Well Test Analysis ◽  
Test Analysis ◽  
Reservoir Models

Automatic reservoir model identification method based on convolutional neural network

2021 ◽  
pp. 1-11
Author(s):  
Xuliang Liu ◽  
Wenshu Zha ◽  
Zhankui Qi ◽  
Daolun Li ◽  
Yan Xing ◽  
...  
Keyword(s):  
Classification Accuracy ◽  
Field Data ◽  
Model Identification ◽  
Well Test ◽  
Reservoir Model ◽  
Well Test Analysis ◽  
Test Analysis ◽  
Reservoir Models ◽  
Actual Field ◽  
Model Recognition

Abstract Well test analysis is a crucial technique to monitor reservoir performance, which is based on the theory of seepage mechanics, through the study of well test data, to identify reservoir models and estimate reservoir parameters. Reservoir model recognition is the first and essential step of well test analysis. It is usually judged by professionals' experience, which results in low efficiency and accuracy. This paper is devoted to applying convolutional neural network (CNN) to well test analysis and proposes a new intelligent reservoir model identification method. Eight reservoir models studied in this paper include homogenous reservoirs with different outer boundaries such as infinite acting boundary, circular, single, angular, channel, U-shaped and rectangular sealing fault boundaries and a radial composite reservoir with infinite acting boundary. Well testing data used in this paper, including actual field data and theoretical data generated by analytical solutions. To improve the classification accuracy of actual field data, noise processing was carried out on the data before training. The CNN that is most suitable for model recognition has been obtained through trial-and-error procedures. The availability of proposed CNN is proved with actual field cases of Daqing oil field, China. The method realizes the automatic identification of reservoir model with the total classification accuracy (TCA) of test data set of 98.68% and 95.18% for original data and noisy data respectively.

Connecting Data, Model and Process to Streamline and Enhance Single-Point Production Well Test Validation

2021 ◽  
Author(s):  
Mohamad Mustaqim Mokhlis ◽  
Nurdini Alya Hazali ◽  
Muhammad Firdaus Hassan ◽  
Mohd Hafiz Hashim ◽  
Afzan Nizam Jamaludin ◽  
...  
Keyword(s):  
Test Data ◽  
Single Point ◽  
Database Systems ◽  
Test Validation ◽  
Well Test ◽  
Production Well ◽  
Well Test Analysis ◽  
Test Analysis ◽  
Digital Ecosystem ◽  
Well Model

Abstract In this paper we will present a process streamlined for well-test validation that involves data integration between different database systems, incorporated with well models, and how the process can leverage real-time data to present a full scope of well-test analysis to enhance the capability for assessing well-test performance. The workflow process demonstrates an intuitive and effective way for analyzing and validating a production well test via an interactive digital visualization. This approach has elevated the quality and integrity of the well-test data, as well as improved the process cycle efficiency that complements the field surveillance engineers to keep track of well-test compliance guidelines through efficient well-test tracking in the digital interface. The workflow process involves five primary steps, which all are conducted via a digital platform: Well Test Compliance: Planning and executing the well test Data management and integration Well Test Analysis and Validation: Verification of the well test through historical trending, stability period checks, and well model analysis Model validation: Correcting the well test and calibrating the well model before finalizing the validity of the well test Well Test Re-testing: Submitting the rejected well test for retesting and final step Integrating with corporate database system for production allocation This business process brings improvement to the quality of the well test, which subsequently lifts the petroleum engineers’ confidence level to analyze well performance and deliver accurate well-production forecasting. A well-test validation workflow in a digital ecosystem helps to streamline the flow of data and system integration, as well as the way engineers assess and validate well-test data, which results in minimizing errors and increases overall work efficiency.

scholarly journals WELL TEST ANALYSIS AND INTERPRETATION: THE USE OF ARTIFICIAL NEURAL NETWORK

2020 ◽  
Vol 04 (11) ◽  
pp. 438-446
Author(s):  
Samuel Lucky Arubi ◽  
Bibobra Ikporo ◽  
Sunday Igbani ◽  
Ann Obuebute ◽  
Sylvester Okotie
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Well Test ◽  
Well Test Analysis ◽  
Test Analysis ◽  
Artificial Neural
Sign in / Sign up

Export Citation Format

Share Document