0
Research Papers: Petroleum Engineering

Application of Artificial Neural Network–Particle Swarm Optimization Algorithm for Prediction of Gas Condensate Dew Point Pressure and Comparison With Gaussian Processes Regression–Particle Swarm Optimization Algorithm

[+] Author and Article Information
Abbas Khaksar Manshad

Department of Petroleum Engineering,
Abadan Faculty of Petroleum Engineering,
Petroleum University of Technology,
Abadan, Iran

Habib Rostami

Department of Computer Engineering,
School of Engineering,
Persian Gulf University,
Bushehr 75168, Iran

Seyed Moein Hosseini, Hojjat Rezaei

Department of Petroleum Engineering,
Ahwaz Faculty of Petroleum Engineering,
Petroleum University of Technology (PUT),
Ahwaz, Iran

1Corresponding author.

Contributed by the Petroleum Division of ASME for publication in the JOURNAL OF ENERGY RESOURCES TECHNOLOGY. Manuscript received July 22, 2014; final manuscript received November 4, 2015; published online January 11, 2016. Editor: Hameed Metghalchi.

J. Energy Resour. Technol 138(3), 032903 (Jan 11, 2016) (6 pages) Paper No: JERT-14-1223; doi: 10.1115/1.4032226 History: Received July 22, 2014; Revised November 04, 2015

For gas condensate reservoirs, as the reservoir pressure drops below the dew point pressure (DPP), a large amount of valuable condensate drops out and remains in the reservoir. Thus, prediction of accurate values for DPP is important and leads to successful development of gas condensate reservoirs. There are some experimental methods such as constant composition expansion (CCE) and constant volume depletion (CVD) for DPP measurement but difficulties in experimental measurement especially for lean retrograde gas condensate causes to develop of different empirical correlations and equations of state for DPP calculation. Equations of state and empirical correlations are developed for special and limited data sets and for unseen data sets they are not generalizable. To mitigate this problem, in this paper we developed new artificial neural network optimized by particle swarm optimization (ANN-PSO) for DPP prediction. Reservoir fluid composition, temperature and characteristics of the C7+ considered as input parameters to neural network and DPP as target parameter. Comparing results of the developed model in this research with Gaussian processes regression by particle swarm optimization (GPR-PSO), previous models and correlations shows that the predictive model is accurate and is generalizable to new unseen data sets.

FIGURES IN THIS ARTICLE
<>
Copyright © 2016 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Fig. 3

Flow chart for ANN-PSO

Grahic Jump Location
Fig. 4

Scatter plot of model prediction DPP values versus measured values (training step)

Grahic Jump Location
Fig. 5

Scatter plot of model prediction DPP values versus measured values (validation step)

Grahic Jump Location
Fig. 6

Scatter plot of model prediction DPP values versus measured values (testing step)

Grahic Jump Location
Fig. 7

Scatter plot of model prediction DPP values versus measured value (general model)

Grahic Jump Location
Fig. 8

Impact of input variables on gas condensate DPP

Grahic Jump Location
Fig. 9

Impact of temperature on gas condensate DPP

Grahic Jump Location
Fig. 10

Comparison between ANN-PSO and GPR-PSO predictions

Grahic Jump Location
Fig. 2

ANN inputs for prediction of DPP

Grahic Jump Location
Fig. 1

Structural design of three layer feed-forward ANNs

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In