It is well-known that large amounts of data are collected and processed during the operation of electric submersible pumps. To optimize the work of mining control center operators, it is recommended to use an automated emergency prevention system. In this way, operators will be able to receive timely information about possible equipment failures, which in its turn will increase the service life of the equipment and reduce operating costs for repairs. The purpose of the present research is to develop a model predicting submersible pumping equipment failures using the method of artificial intelligence. To identify the most accurate model, the paper compares the following forecasting methods: the nearest neighbour method and the linear classifier building method. The presented correlation was created on the basis of 30 parameters obtained from 272 wells of the Eastern Siberia field. Being used, it enabled error-free prediction of failures and complications in pumping equipment operation depending on the gas factor and frequency. Thus, the developed model can be used by oil and gas enterprises to predict failures and accidents in the operation of submersible pumping equipment. The conducted study shows that the prediction accuracy of the required parameter in the developed artificial intelligence model exceeds the results of conventional statistical methods. The model also can be useful for future optimization of processes when field planning and developing. Artificial intelligence is the best prediction method of submersible pumping equipment failures, due to its high speed and accuracy, cognitive technologies are widely used in big data processing.
It is known that oil in reservoir conditions is characterized by the content of a certain amount of dissolved gas. As reservoir pressure decreases this gas is released from oil significantly changing its physical properties, primarily its density and viscosity. In addition, the oil volume also reduces, sometimes by 50–60 %. In this regard, when calculating reserves, it is necessary to justify the reduction amount of the reservoir oil volume when oil is extracted to the surface. For this purpose, the concept of formation volume factor of reservoir oil has been introduced. The formation volume factor of oil is considered one of the main characterizing parameters of crude oil. It is also required for modeling and predicting the characteristics of an oil reservoir. The purpose of the present work is to develop a new empirical correlation for predicting the formation volume factor of reservoir oil using artificial intelligence methods based on MATLAB software, such as: an artificial neural network, an adaptive neuro-fuzzy inference system, and a support vector machine. The article presents a new empirical correlation extracted from the artificial neural network based on 503 experimental data points for oils from the Eastern Siberia field, which was able to predict the formation volume factor of oil with the correlation coefficient of 0.969 and average absolute error of less than 1 %. The conducted study shows that the prediction accuracy of the desired parameter in the developed artificial intelligence model exceeds the accuracy of study results obtained by conventional statistical methods. Moreover, the model can be useful in the prospect of process optimization in field planning and development.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.