SPE Reservoir Evaluation & Engineering
Volume 12, Number 1, February 2009, pp. 8-13

SPE-123423-PA

Application of Artificial Neural Networks to Downhole Fluid Analysis

View full textPDF ( 476 KB )

DOI  More information 10.2118/123423-PA http://dx.doi.org/10.2118/123423-PA

Citation

  • Hegeman, P., Dong, C., Varotsis, N., and Gaganis, V. 2009. Application of Artificial Neural Networks to Downhole Fluid Analysis. SPE Res Eval & Eng12 (1): 8-13. SPE-123423-PA. doi: 10.2118/123423-PA.

Discipline Categories

  • 6 Reservoir Description and Dynamics
  • 6.6 Reservoir Monitoring/Formation Evaluation
  • 6.2 Fluids Characterization

Summary

Reservoir characterization and asset management require comprehensive information about formation fluids. Obtaining this information at all stages of the exploration and development cycle is essential for field planning and operation. Traditionally, fluid information has been obtained by capturing samples and then measuring the pressure/volume/temperature (PVT) properties in a laboratory. More recently, downhole fluid analysis (DFA) during formation testing has provided real-time fluid information. However, the extreme conditions of the downhole environment limit the DFA-tool measurements to only a small subset of the fluid properties provided by a laboratory. Nevertheless, these tools are valuable in predicting other PVT properties from the measured data. These predictions can be used in real time to optimize the sampling program, to help evaluate completion decisions, and to understand flow-assurance issues.

The petroleum industry has devoted much effort to developing computational methods to model phase behavior. Two approaches are prevalent—simple correlations and equation-of-state (EOS) models. However, in recent years, artificial-neural-network (ANN) technology has been applied successfully to many petroleum-engineering problems, including the prediction of PVT behavior. ANN technology can recognize patterns in data, adjust dynamically to changes, infer general rules from specific cases, and accept a large number of input variables. An ANN architecture can allow for continuous improvement by expanding the training database with new data.

In this paper, we present the application of ANN technology to DFA. We demonstrate this with an ANN model that uses the DFA-tool measurements of fluid composition as input and produces predictions of gas/oil ratio (GOR), a key PVT property used in real time to monitor a formation-tester sampling job. The ANN also provides an uncertainty estimation of its outputs as a quality-assurance indicator. We compare ANN results with those from the algorithms used by DFA tools.

© 2009. Society of Petroleum Engineers

View full textPDF ( 476 KB )

History

  • Original manuscript received: 27 July 2007
  • Meeting paper published: 4 December 2007
  • Revised manuscript received: 31 July 2008
  • Manuscript approved: 1 August 2008
  • Published online: 2 March 2009
  • Version of record: 26 February 2009