TY - GEN

T1 - Maintenance Optimization Within the Lifecycle Management of the Gas Compressor's Electric Motors

AU - Mironenko, Yaroslav V.

AU - Khalyasmaa, Alexandra I.

N1 - The research was carried out within the state assignment with the financial support of the Ministry of Science and Higher Education of the Russian Federation (subject No. FEUZ-2022-0030 Development of an intelligent multi-agent system for modeling deeply integrated technologicalsystems in the power industry).

PY - 2023/6/29

Y1 - 2023/6/29

N2 - As a part of the paper, the issue of optimizing repairs and maintenance of electrically driven gas pumping units are considered. The existing approach to the operation and maintenance of electric gas pumping units, both in the Russian Federation and abroad was described. Also, the statistics of their failures, the possibility of using a life cycle management system to assess the current state of electrical facilities and manage production assets was analyzed. In order to optimize and improve the reliability of the results of assessing the current state of this equipment, the main existing classical methods are considered, as well as the possibilities of using artificial intelligence methods. In the course of the study, models were prepared to assess the current state of electrical facilities, based on monitoring the main diagnostic (temperature, vibration) and operational (load, pressure) parameters. These models use machine learning algorithms, common in technical diagnostics: bagging and gradient boosting. The achieved accuracy in assessing the current state of electrically driven gas pumping units allows using these models as the basis for a life cycle management system. The main reason is reducing the costs and increasing the service life of electrically driven gas pumping units.

AB - As a part of the paper, the issue of optimizing repairs and maintenance of electrically driven gas pumping units are considered. The existing approach to the operation and maintenance of electric gas pumping units, both in the Russian Federation and abroad was described. Also, the statistics of their failures, the possibility of using a life cycle management system to assess the current state of electrical facilities and manage production assets was analyzed. In order to optimize and improve the reliability of the results of assessing the current state of this equipment, the main existing classical methods are considered, as well as the possibilities of using artificial intelligence methods. In the course of the study, models were prepared to assess the current state of electrical facilities, based on monitoring the main diagnostic (temperature, vibration) and operational (load, pressure) parameters. These models use machine learning algorithms, common in technical diagnostics: bagging and gradient boosting. The achieved accuracy in assessing the current state of electrically driven gas pumping units allows using these models as the basis for a life cycle management system. The main reason is reducing the costs and increasing the service life of electrically driven gas pumping units.

UR - http://www.scopus.com/inward/record.url?partnerID=8YFLogxK&scp=85172025626

U2 - 10.1109/EDM58354.2023.10225198

DO - 10.1109/EDM58354.2023.10225198

M3 - Conference contribution

SN - 979-835033687-0

VL - 2023-June

T3 - International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices, EDM

SP - 1180

EP - 1185

BT - International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices, EDM

PB - IEEE Computer Society

T2 - 2023 IEEE 24th International Conference of Young Professionals in Electron Devices and Materials (EDM)

Y2 - 29 June 2023 through 3 July 2023

ER -