DIGITAL TWIN OF GAS RECIPROCATING COMPRESSOR UNIT: CONCEPT, ARCHITECTURE & PILOT IMPLEMENTATION

Abstract

Combination of information and operational technologies has led to a new way of production, to a new technological revolution, known as Industry 4.0. The Digital Twin plays a central role in this technology. The Digital Twin is a predictive maintenance tool, and allows you to simulate various options for device failures taking into account their operation modes, environmental influences and various degrees of wear. The concept of creating a digital twin of a real physical object of research is proposed - an AJAX DPS-180 internal combustion engine with a gas piston compressor, which is designed to pump gas from gas wells. A feature of its work is autonomous long-term operation in the field with the remoteness of the service personnel, direct environmental impact and ensuring the reliability and stability of work. Therefore, monitoring the parameters of the engine with the subsequent prediction of its failures is especially important. The work on creating a digital twin for AJAX DPS-180 is being carried out in cooperation and with the support of Armco-Engineering, the operator of this equipment. Six stages of the process of creating a digital twin of a given object are shown: collection and preliminary processing of data on the technical state of a real object; early detection of malfunctions, predicting the time of failure; service planning; optimization of financial and time resources for service. Equipping a real object with various sensors made it possible to continuously collect data on its technical condition, and technologies of the industrial Internet of things, such as Big Data and the predictive statistical model, predict failure times with high accuracy. The developed and implemented schemes for equipping an object with data collection equipment and a diagram of the flow of this data in the Internet of Things are presented. The basis of the data collection system is a microcontroller, a set of a crankshaft speed sensor and thermocouples, a multiplexer and 16-bit analog-to-digital converters that convert thermo-EMF of thermocouples. At the moment, channels for measuring the speed, coolant and exhaust gas temperatures have been implemented. It is proposed to use the ThingSpeak server as a remote resource as a cloud aggregator and carrier of this data. The MATLAB mathematical package integrated into the resource is used as a data analyzer.