Neural network model of pumping units in oil preparation and pumping complex

Methods of improving the efficacy of oil extraction are highly sought after. One way to achieve such an improvement is to reduce the downtime of equipment and to implement measures to increase oil recovery for the entire life cycle of the well based on analysis of operational data. The work we present in this paper is aimed at improving a model of pumping units of the oil preparation and pumping complex. For this purpose, we employ an approach based on computational intelligence techniques and in particular an approach that is based on recurrent neural networks in combination with convolutional neural networks to address the problem of operative analysis of telemetric data from pumping units and to forecast the state of technological equipment. Our proposed approach provides an attractive model of optimizing the parameters of pumping equipment and thus a useful avenue of improving the efficacy of oil extraction.