Hybrid functional networks for PVT characterisation

Munirudeen Oloso, Mohamed Bader-El-Den, James Buick, Mohamed Hassan Sayed

Research output: Chapter in Book/Report/Conference proceedingConference contribution

90 Downloads (Pure)

Abstract

Predicting pressure volume temperature properties of black oil is one of the key processes required in a successful oil exploration. As crude oils from different regions have different properties, some researchers have used API gravity, which is used to classify crude oils, to develop different empirical correlations for different classes of black oils. However, this manual grouping may not necessarily result in correlations that appropriately capture the uncertainties in the black oils. This paper proposes intelligent clustering to group black oils before passing the clusters as inputs to the functional networks for prediction. This hybrid process gives better performance than the empirical correlations, standalone functional networks and neural network predictions.
Original languageEnglish
Title of host publicationSAI Intelligent Systems Conference 2017
Subtitle of host publicationIntelliSys 2017
PublisherIEEE
Pages936-941
Number of pages6
ISBN (Electronic)978-1-5090-6435-9
ISBN (Print)978-1-5090-6436-6
DOIs
Publication statusPublished - 26 Mar 2018
Event2017 Intelligent Systems Conference - America Square Conference Center, London, United Kingdom
Duration: 7 Sep 20178 Sep 2017
http://www.saiconference.com/IntelliSys

Conference

Conference2017 Intelligent Systems Conference
Abbreviated titleIntelliSys 2017
Country/TerritoryUnited Kingdom
CityLondon
Period7/09/178/09/17
Internet address

Keywords

  • pressure volume temperature (PVT)
  • API gravity
  • clustering
  • functional networks
  • neural network

Fingerprint

Dive into the research topics of 'Hybrid functional networks for PVT characterisation'. Together they form a unique fingerprint.

Cite this