Combined artificial intelligence modeling for production forecast in a petroleum production field

  • Marco Antonio Ruiz- Serna Universidad Nacional de Colombia – Sede Medellín
  • Guillermo Arturo Alzate- Espinosa Universidad Nacional de Colombia – Sede Medellín
  • Andrés Felipe Obando- Montoya Universidad Nacional de Colombia – Sede Medellín
  • Hernán Dario Álvarez- Zapata Universidad Nacional de Colombia – Sede Medellín
Keywords: Artificial Intelligence, Forecasting, Oil production, Modeling, Data mining

Abstract

This paper presents the results about using a methodology that combines two artificial intelligence (AI) models to predict the oil, water and gas production in a Colombian petroleum field. By combining fuzzy logic (FL) and artificial neural networks (ANN) a novelty data mining procedure is implemented, including a data imputation strategy. The FL tool determines the most useful variables or parameters to include into each well production model. ANN and FIS (fuzzy inference systems) predictive models identification is developed after the data mining process. The FIS models are capable to predict specific behaviors, while ANN models are able to forecast an average behavior. The combined use of both tools under few iterative steps, allows to improve forecasting of well behavior until reach a specified accuracy level. The proposed data imputation procedure is the key element to correct false or to complete void positions into operation data used to identify models for a typical oil production field. At the end, two models are obtained for each well product, conforming an interesting tool given the best accurate prediction of fluid phase production.

How to Cite
Ruiz- Serna, M. A., Alzate- Espinosa, G. A., Obando- Montoya, A. F., & Álvarez- Zapata, H. D. (2019). Combined artificial intelligence modeling for production forecast in a petroleum production field. CT&F - Ciencia, Tecnología Y Futuro, 9(1), 27-35. https://doi.org/10.29047/01225383.149

Downloads

Download data is not yet available.
Published
2019-05-10
Section
Scientific and Technological Research Articles