سال انتشار: ۱۳۹۱

محل انتشار: اولین کنفرانس بین المللی نفت، گاز، پتروشیمی و نیروگاهی

تعداد صفحات: ۷

نویسنده(ها):

arash yazdanpanah – petroleum university of technology
abdonabi hashemi –

چکیده:

Water coning caused water flow into the wellbore from below the perforations and causes several problems in wellbore and surface facilities. For solve these problems, we must know breakthrough time of water in wellbore. In this paper, potential application of feed-forward Artificial Neural network (ANN) optimized by Particle Swarm Optimization (PSO) is proposed to predict breakthrough time of water coning. The PSO is implemented here to decide on initial weights of the parameters used in neural network. Results obtained from the developed PSO-ANN model were compared with the experimental water coning data. The average relative absolute deviation between the model predictions and the experimental data was found to be less than 6.5%. Results from this study indicate that application of PSO-ANN in breakthrough time prediction which can lead to design of more efficient production scenarios.