The article is devoted to the analysis of actual problems of automation of control of the installations of electric centrifugal pumps (ESPs) of oil producing wells and modern approaches to their solution. The solution of the problem requires the creation of complex multi-level systems for the adoption and implementation of control decisions. The top (planning) level of control requires the development of decision support systems that perform real-time collection and analysis of large amounts of information about the various work processes with ESPs. Actual tasks of this level are the development of models for identification and forecasting of oil production processes, as well as algorithms for finding control solutions aimed at optimizing these processes. Lower (operational) levels of management require the development of emergency and regulatory control systems that implement decisions taken at the upper levels. The actual tasks of this level of management are the development of dynamic models of the ESP process that provide the synthesis of optimal algorithms for implementing top-level management solutions, such as stabilization, I/O, emergency control. The main goals, tasks of these systems and approaches to the solution are considered. The analysis of ESP as a complex multiply connected control object is given. Controllable parameters, parameters of controlling and disturbing influences are distinguished. The generalized multilevel structure of the ESP control system and approaches to the construction of subsystems solving management tasks at various levels are considered. The approach to the construction of the system of the upper — planning level of the ESP control, the principles of its interaction with higher and subordinate systems is considered. The approach to the construction of the subsystem of the lower — operational level of the ESP control is considered. The tasks of this level of control are considered, including such as emergency control, regulation of the mode parameters, output to the operating mode. The classification of groups of emergency control tasks on protection from the most significant types of negative factors and approaches to their solution is given. The approach to the solution of the problem of ensuring the maximum oil production, as a problem of stabilizing the critical pressure at the pump inlet, is considered. Continuous and positional variants of algorithms for solving this problem are presented.
The paper proposes an algorithm for determining the flow rate of an oil producing well based on dynamometer data. The dynamogram is presented as a two-dimensional image processed using a convolutional neural network that solves the problem of nonlinear regression between the dynamogram image and the flow rate value. The structure of the dynamometer data collection and processing system is presented, the main steps of the data analysis algorithm are described. The resulting model makes it possible to estimate the production rate with an error in the range of 15-20%.
The purpose of developing data warehouse architecture is improving the storage subsystem as part of an intelligent oil well control system. To achieve this goal, it is necessary to develop the structure and information model of the storage subsystem. It is proposed to expand the exploration and exploitation data model of the Epicentre oil fields by adding new entities and a hierarchy of links. Highly effective architectural templates, taking into account the specifics of the research object and the accumulated experience of industry experts, are used. This will reduce the costs for development of the data warehouse architecture and will provide an opportunity for integration with existing information systems of a higher level of control and management-MES, ERP-and with other software and hardware complexes of the current level.
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.