Application of Artificial Intelligence in Well Screening and Production Optimisation in Oredo Oilfields, Niger Delta, Nigeria
- Authors
- Lateef T. Akanji (University of Aberdeen, UK) | Joshua Dala (University of Aberdeen, UK) | Kelani Bello (University of Benin, Benin City, Nigeria) | Olafuyi Olalekan (University of Benin, Benin City, Nigeria) | Prashant Jadhawar (University of Aberdeen, UK)
- DOI
- https://doi.org/10.2118/198877-MS
- Document ID
- SPE-198877-MS
- Publisher
- Society of Petroleum Engineers
- Source
- SPE Nigeria Annual International Conference and Exhibition, 5-7 August, Lagos, Nigeria
- Publication Date
- 2019
- Document Type
- Conference Paper
- Language
- English
- ISBN
- 978-1-61399-691-1
- Copyright
- 2019. Society of Petroleum Engineers
- Disciplines
- Keywords
- Downloads
- 4 in the last 30 days
- 82 since 2007
- Show more detail
- View rights & permissions
SPE Member Price: | USD 9.50 |
SPE Non-Member Price: | USD 28.00 |
An enhanced neuro-fuzzy technique is deployed in production optimisation and fluid flow analysis for wells drilled and completed in Oredo oilfields Niger delta Nigeria. The impact of historical production data, reservoir rock and fluid properties, well geometry, architecture, completion profile and surface data on overall well deliverability is incorporated in the model. The artificial intelligence training process is complete at the point a minimum quantifiable error is obtained or when a value less than the set tolerance limit is reached. Production data obtained from the short and long-strings for wells completed in Oredo field was processed, analysed and input into the enhanced neuro-fuzzy algorithm. The adopted enhanced neuro-fuzzy system is capable of modelling the direct approach of Mamdani and that of Sugeno in a five-layer feed-forward neural network and fuzzy logic process designed and implemented in a C/C++ numerical computation objected oriented platform. This study highlights the significance of data analytics and artificial intelligence in well performance prediction and cost reduction and optimisation in oil producing wells.
File Size | 1 MB | Number of Pages | 10 |