Predicting Oil Flow Rate due to Multiphase Flow Meter by Using an Artificial Neural Network

Abstract

Multiphase flow meters are being utilized to provide quick and accurate well test data in many oil production applications. These include applications in remote or unmanned locations, topside applications that minimize platform space, and subsea applications. Flow rates of phases (oil, gas, and water) are the most important parameters that are detected by multiphase flow meters. Conventional multiphase flow meter data collecting is done in long periods, because of radioactive sources usage as detector and unmanned location due far distance of wells. In this article, a new method for oil rate prediction of wells based on artificial neural networks due to a real case of multiphase flow meters is presented. Temperatures and pressures of lines have been set as input variable of network and oil flow rate as output. In this case a 600 data set of 31 wells in one of the northern Persian Gulf oil fields of Iran was used, which was collected in three-month periods for each well from December 2002 to November 2010. Alternatively, artificial neural networks can be used confidently without personnel and environmental problems.