Part of #Applying a Cutting Edge Solution to Predict Breakthrough Time of Water Coning in Naturally Fractured Reservoirs# :
Publishing year : 2012
Conference : Fourteenth National Congress of Chemical Engineering of Iran
Number of pages : 10
Abstract: Water coning causes water flow into the wellbore from below perforations and causes several problems in wellbore and surface facilities. To solve these problems, we must know the breakthrough time of water in the wellbore. In this paper, the potential application of feed-forward Artificial Neural Network (ANN) is proposed to predict the breakthrough time of water coning. The BP is implemented here to decide on the initial weights of the parameters used in the neural network. The developed BP-ANN model is examined using new experimental data. Results obtained from the developed BP-ANN model were compared with experimental data of water coning. The average relative absolute deviation between the model predictions and the experimental data was found to be less than 9%. Results from this study indicate that application of BP-ANN in breakthrough time prediction, which can lead to design of more efficient production scenarios.