| Summary: | Crude oil properties data were gathered from publications for modeling correlations and artificial neural networks (ANN), which could be used to predict bubble point pressure and bubble point oil formation volume factor. The data sets were screened for redundant data. Each data set was selected randomly and divided into developing, and test data sets. Nonlinear regression was the technique used to develop each correlation. For ANN development, the developing data sets were randomly divided into training, validation, and testing sets. Different network architectures and transfer functions were used for developing the best ANN models. To ensure their accuracy and applicability, the developed models were tested and compared with other published correlations using the testing data sets, which had not been used for developing correlations and ANNs. The results showed that the developed models gave better performance compared to other existing correlations.
|
|---|
