A model was developed to predict the bubble point pressure of saturated reservoirs. The model was based on artificial neural networks and was developed using 700 generic data sets which are representative of the Niger Delta region of Nigeria. The data set was first cleaned to remove erroneous and repeated data points. After cleaning, 618 data points were remaining. Of the 618 data points, 463 were used to train the ANN model, 93 were used to cross-validate the relationships established during the training process and the remaining 62 were used to test the model to evaluate its accuracy. A backward propagation network utilizing the LM algorithm was used in developing the model. The first layer consisted of four neurons representing the input values of reservoir temperature, API oil gravity, gas specific gravity, and solution GOR. The second (hidden) layer consisted of 26 neurons, and the third layer contained one neuron representing the output value of the bubble point pressure. The results showed that the developed model provides better predictions and higher accuracy than the existing empirical correlations considered when exposed to an additional 13 data points which were unseen by the model during its development. The model provided predictions of the bubble point pressure with an absolute average percent error of 3.98%, RMSE of 177.6479 and correlation coefficient of 0.9851. Trend analysis was performed to check the behavior of the predicted values of P_b for any change in reservoir temperature, oil API gravity, gas gravity and solution GOR. The model was found to be physically correct. Its stability indicated that it did not overfit the data, implying that it was successfully trained.
Transparent open-box learning network and artificial neural network predictions of bubble-point pressure compared
