Latest revision as of 22:47, 28 January 2021

Abstract

Pressure drop prediction in pipes is an old petroleum engineering problem. There is a long history of attempts to develop empirical correlations to predict the pressure drop in pipes. Some of these attempts have produced correlations that provide good prediction in some cases. However, their general applicability is questionable. Correlations that address only a specific class of problems exist. These types of correlation usually perform better than those which attempt to meet the need of a variety of problems. Usually, the higher the number of variables in the model the lesser the reliability and general applicability of the correlations. This is the result of using methodologies such as conventional regression analysis. In such methodologies, the chances of correctly and completely capturing the relationship between variables decreases as the number of variables increases. Many parameters could be involved in these types of problems, such as gas-oil ratios in two phase systems, water flow in three phase systems, and inclination angles of the pipe, to name a few. In this paper, the authors introduce a new methodology for developing prediction models for pipes. This method which has been named Virtual Measurement in Pipes (VMP), incorporates artificial neural networks (ANN) to address the development of tools to predict pressure drops in pipes and optimum design of pipelines under a variety of circumstances. The fundamental problem with conventional approaches resides in the inherent sequential and pointwise (as opposed to parallel and distributed) information processing methods used in development of such correlations. Because of this shortcoming, conventional methodologies are unable to address, define, or unravel the highly complex relationships between many variables involved in th e process. In this paper, artificial neural networks are used to develop a Virtual Measurement Tool to survey flowing bottom hole pressure (BHP) in multi-phase systems using information such as oil, gas and water flow rates, temperature, oil and gas gravity, pipe length, surface pressure, and inclination angles of the pipe. The developed Virtual Measurement Tool has been applied to th e published field data for flowing BHP predictions. VMP's predictions are compared to existing methods and the enhancement is clearly demonstrated. The developed VMP is applied to wellbore hydraulic problems. It addresses three-phase (oil, water, and gas) flow in wellbores. This tool applies to a variety of wells, including vertical wells and those with various degrees of inclination.

Original document

The different versions of the original document can be found in:

• http://dx.doi.org/10.2523/30975-ms

• http://pdfs.semanticscholar.org/0368/e04718e1180684c6e578c2edc191c39d43dc.pdf

• http://shahab.pe.wvu.edu/Publications/Pdfs/30975.pdf,

https://www.onepetro.org/doi/10.2118/30975-MS,

http://www.osti.gov/scitech/biblio/182254-virtual-measurement-pipes-part-flowing-bottom-hole-pressure-under-multi-phase-flow-inclined-wellbore-conditions,

https://shahab.pe.wvu.edu/Publications/Pdfs/30975.pdf,

https://academic.microsoft.com/#/detail/1963616025

• http://www.onepetro.org/google/Papers/SPE/eLibrary_Papers/spe/1995/95ERM/00030975/00030975.pdf?id=00030975&soc=SPE,

http://dx.doi.org/10.2118/30975-ms

DOIS: 10.2118/30975-ms 10.2523/30975-ms