Predicting dynamic formation pressure using artificial intelligence methods

نویسندگان

چکیده

Determining formation pressure in the well extraction zones is a key task monitoring development of hydrocarbon fields. Direct measurements require prolonged shutdowns, resulting underproduction and possibility technical problems with subsequent start-up wells. The impossibility simultaneous shutdown all wells pool makes it difficult to assess real energy state deposit. This article presents research aimed at developing an indirect method for determining without shutting down investigation, which enables determine its value any time. As mathematical basis, two artificial intelligence methods are used – multidimensional regression analysis neural network. technique based on construction multiple equations shows sufficient performance, but high sensitivity input data. study process establishment during different periods deposit development. Its application expedient case regular actual determinations indicators as network reliably even minimal set data implemented specially designed software product. relevant continuing evaluate promising prognostic features assessing deposits zones.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Predicting seminal quality with artificial intelligence methods

0957-4174/$ see front matter 2012 Elsevier Ltd. A http://dx.doi.org/10.1016/j.eswa.2012.05.028 ⇑ Corresponding author. E-mail address: [email protected] (D. Gil). 1 These authors equally contributed to this work. Fertility rates have dramatically decreased in the last two decades, especially in men. It has been described that environmental factors, as well as life habits, may affect semen quality...

متن کامل

Performance Comparison of Artificial Intelligence Methods for Predicting Cash Flow

Cash flow forecasting is indispensable for managers, investors and banks. However, which method is more robust has been argued under the condition of small size samples. With sliding window technique we create the Response Surface, Back Propagation Neural Network, Radial Basis Functions Neural Network and Support Vector Machine models respectively, which are examined by comparing performances o...

متن کامل

Artificial Intelligence Methods for Ambient Intelligence

Ambient Intelligence (ISTAG (2001) Scenarios for Ambient Intelligence in 2010) is a vision that enables intelligent environments with pervasive technology. In this vision human users are at the cent re, but machine and human are seen as equal, collaborating, to improve both human being and machine performance. Ambient Intelligence offers many benefits. For example, by inst rumenting public and ...

متن کامل

Bayesian Methods in Artificial Intelligence

In many problems in the area of artificial intelligence, it is necessary to deal with uncertainty. Using probabilistic models can also improve efficiency of standard AI-based techniques. Commonly used methods for dealing with uncertainty include Bayesian models, which can be used to describe and work with probabilistic systems effectively. This article reviews several models based on the Bayesi...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Zapiski Gornogo instituta

سال: 2022

ISSN: ['2411-3336', '2541-9404']

DOI: https://doi.org/10.31897/pmi.2022.11