Predictive modeling with applications in decision support systems for oil and gas production
MetadataShow full item record
In the past decade, artifical neural networks (ANN) has given us self-driving cars, practical speech recognition and more effective web search. It is in interest of petroleumindustry to research the applicability of ANNs in decision support systems for the operation of oil and gas production systems. This interest coincides with increased availability of computational power and sensor data in the petroleum industry. This thesisinvestigates on using different feed forward ANN architectures and their applicability tovirtual flow metering and steady-state production optimization applications. The predictive capability of the proposed models are assessed on steady-state production dataacquired from an offshore production system located on the Norwegian continentalshelf.The results presented in this thesis shows that feed forward ANNs can be used as virtual flow meters with accuracy comparable to modern virtual flow meters with averageerrors below 10%. Compared to physics based virtual flow meter models, feed forwardANNs are fast to build and maintain, and requires lower level of engineering skill, making it a cheaper alternative to physics based virtual flow models. The results shows thatthe proposed neural network model for production optimization do not have accuracygood enough to be used for production optimization. Production optimization involvesexploring and evaluating many possible operating points and requires therefore better predictive capabilities than virtual flow models which the model could not provide.However, there is room for improvements and the results are therefore promising.