Determination of Reservoir Model from Well

Determination of Reservoir Model from Well - Scientia...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Scientia Iranica, Vol. 15, No. 4, pp 487{493 c Sharif University of Technology, August 2008 Research Note Determination of Reservoir Model from Well Test Data, Using an Arti cial Neural Network R. Kharrat 1 ; and S.M. Razavi 1 Nowadays, neural networks have a wide range of usage in di erent elds of engineering. In the present work, this method is used to determine a reservoir model. Model identi cation, followed by parameter estimation, is a kind of visual process. Pressure derivative curves showing more features are usually used to determine the reservoir model based on the shape of the curve and no calculation is included. So, it is di cult to convert this kind of visual process to an applicable algorithm for computers. In fact, the model identi cation is a pattern recognition which is best done by an Arti cial Neural Network (ANN). If neural networks were learned successfully, they would be able to categorize di erent shapes into di erent groups, due to their visual characterization. So, their use in such a job would seem to be useful. In this work, it is shown how to train, examine and use neural networks to determine a reservoir model. The input of an ANN is fty points of the normalized pressure derivative type curve. Each ANN is trained, based on a speci c model, and the output of the ANN is the probability of occurrence of a fed curve to the related model. INTRODUCTION It may seem di cult to relate between well testing and ANN. But it is proven today that none of the science branches are independent, especially in engineering elds, which are all based on mathematics and physics. In this work, for instance, ANNs, which are quite applicable to computer and electronic sciences, are used in the eld of well testing in petroleum engineering. First, characteristic plots and their derivatives, as well as semi-derivative log curves, will be introduced, which are the main tools of well test interpretation, in order to determine the reservoir model. Then, a brief review on ANN will be presented and nally a method, using these two tools to determine the reservoir model, will be discussed. AN INTRODUCTION TO WELL TESTING Well testing is done to determine parameters, such as permeability, skin and wellbore storage. In conven- tional methods, the duration of data related to the well, reservoir and boundaries must be speci ed rst. 1. Research Center, Petroleum University of Technology, Tehran, Iran. *. To whom correspondence should be addressed. E-mail: kharrat@put.ac.ir Then, for each portion, the related equation is applied to determine the parameters related to that part, either by plotting or matching. Usually, partitioning the data is done by means of a Generalized Plot (GP) or Pressure Type Curves (PTC), which are the logarithmic plot of P vs. t . New methods are all based on the determination of
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 04/05/2011 for the course PETE 689 taught by Professor Staff during the Spring '08 term at Texas A&M.

Page1 / 7

Determination of Reservoir Model from Well - Scientia...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online