An Artificial Intelligence Approach to Well Test Interpretation
Abstract/Contents
- Abstract
- The improvements in well test analysis from the former "straight line approach" to its current state are strongly related to the use of computers in this field. Automation of the interpretation procedure has been achieved by automating the type-curve matching. This automation not only speeds up the analysis but also increases its reliability by providing a match free of any subjective consideration of goodness. Subjectivity is however still present in the choice of the interpretation model used to match the data. The objective of this study is to automate this choice.A log-log plot of the pressure derivative constitutes an appropriate diagnostic tool to choose an analytical model for given data. It yields distinct features for different flow regimes, which an expert can recognize and relate to specific models. The complete interpretation model is then obtained by combining these various components. Using the log-log plot enables the expert to visually replace the original data by a symbolic representation, describing the response like a succession of shapes. If the data are smoothed, we can easily reproduce this substitution. We will assume that such a smoothing can be performed and therefore concentrate on choosing an interpretation model for smoothed data only.Artificial intelligence language and techniques are used to achieve an adequate representation of the response as well as to simulate the reasoning processes involved in the identification of a model. The knowledge of the producible theoretical responses is included using tree structures, and can therefore be easily augmented with new models.Some correlations are also presented which relate the size of the shapes produced by particular models to the value of the parameters associated with them. These relations are used to give a first match from which an automated type-curve matching can start.
Description
Type of resource | text |
---|---|
Date created | June 1987 |
Creators/Contributors
Author | Allain, Olivier |
---|---|
Primary advisor | Horne, Roland N. |
Degree granting institution | Stanford University, Department of Petroleum Engineering |
Subjects
Subject | School of Earth Energy & Environmental Sciences |
---|---|
Genre | Thesis |
Bibliographic information
Access conditions
- Use and reproduction
- User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
Preferred citation
- Preferred Citation
- Allain, Olivier.. (1987). An Artificial Intelligence Approach to Well Test Interpretation. Stanford Digital Repository. Available at: https://purl.stanford.edu/mb654bp1848
Collection
Master's Theses, Doerr School of Sustainability
View other items in this collection in SearchWorksContact information
- Contact
- brannerlibrary@stanford.edu
Also listed in
Loading usage metrics...