Distributed predictive control system for the condition of power grid equipment based on the operating time for a defect

Relevance. In the context of the digital transformation of the electric power industry, the urgency of developing distributed control systems for the condition of electrical network equipment based on forecasting the operating time for a defect with the determination of the adaptive frequency of preventive action is increasing.

The purpose. To justify the expediency of creating and applying a similar electrical installation repair management system based on thermal imaging control (TIC) statistics as an alternative to local on-line monitoring systems based on various temperature sensors. To develop a predictive mathematical model to determine the operating time for a developed defect in the equipment. To form a methodology for calculating the adaptive frequency of equipment withdrawal for repair according to technical condition.

Methods. The research uses methods of statistical data processing and statistical hypothesis testing, the formation of homogeneous Markov models with continuous time and numerical modeling in the MathCAD software environment.

Results. The article reveals the relevance of the topic, outlines the methodological aspects of a distributed predictive control system for repairs of electrical network equipment, shows its advantages over local control systems based on modern temperature sensors, suggests models for predicting operating time for a developed defect in equipment and the frequency of its preventive repairs according to the actual technical condition. The calculation of the frequency of preventive maintenance of CTS-6/0.4 kV transformers of one of the electric utilities is given based on the forecast of operating time for a developed defect, illustrating the possibilities of the claimed technique.

Conclusion. The proposed system of distributed predictive control of the technical condition of electrical network equipment based on operating time for a defect, unlike local temperature control systems based on modern sensors, has great functionality with significant cost savings. Its use is guaranteed to ensure the effectiveness of equipment prevention management due to the high reliability of the forecast of operating time for a defect and the determination of the adaptive frequency of preventive action.

1. Ermakova D. A., Fateev V. A. Information System for Predicting the Technical Condition of Electrical Equipment Devices, BIO Web of Conferences 63, 02007 (2023) ASE-2023. https://doi.org/10.1051/bioconf/20236302007. (In Russ).

2. Timothy L. J., Shantala A. R., Kevin E. W., Condition Prediction for Manufacturing Electrical Equipment, IFAC Proceedings Volumes, Vol. 37, Issue 4, 2004, pp. 373-382, https://doi.org/10.1016/S1474-6670(17)36145-1.

3. Shcherbatov I., Lisin E., Rogalev A., Tsurikov G., Dvoˇrák M. and Strielkowski W. Power Equipment Defects Prediction Based on the Joint Solution of Classification and Regression Problems Using Machine Learning Methods, Electronics 2021, 10, 3145. https://doi.org/10.3390/electronics10243145.

4. Levin V.M., Guzhov N.P., Boyarova D.A. Risk-based approach to choosing the production asset management strategy for energy company. // Power engineering: research, equipment, technology. 2023; 25 (6). S. 29-42. doi:10.30724/1998-9903-2023-25-6-29-42. (In Russ.).

5. Shpiganovich A.N., Shpiganovich A.A., Petrov A.R., Gracheva E.I. Thermal imaging control of electrical equipment of industrial enterprises // Power engineering: research, equipment, technology. 2024; 26(2). S. 68-77. https://doi.org/10.30724/1998-9903-2024-26-2-68-77. (In Russ.).

6. Laib dit Leksir Y., Mansour M., Moussaoui A. Localization of thermal anomalies in electrical equipment using Infrared Thermography and support vector machine // Infrared Physics & Technology, Vol. 89, 2018, pp. 120-128. https://doi.org/10.1016/j.infrared.2017.12.015.

7. Balakrishnan G.K., Yaw C.T., Koh S.P., Abedin T., Raj A.A., Tiong S.K., Chen C.P. A Review of Infrared Thermography for Condition-Based Monitoring in Electrical Energy: Applications and Recommendations // Energies 2022, 15, 6000. https://doi.org/10.3390/en15166000.

8. Levin V.M. Upravlenie nadezhnost'yu i tekhnicheskim sostoyaniem oborudovaniya v zadachah ekspluatacii elektricheskih setej: monografiya / V.M. Levin, D.V. Tanfil'eva. – Novosibirsk: Izd-vo NGTU, 2023. – 240 s. (In Russ).

9. Prokopov E.S., Vysogorec S.P., Lesiv A.V. Innovacionnaya tekhnologiya v oblasti obnaruzheniya defektov kontaktnyh soedinenij i kontaktov komplektnyh raspredelitel'nyh ustrojstv. – Energetika i neftegazohimicheskij kompleks Tatarstana v nachale XXI veka, 2020, № 16. Dostupno po: https://energoneftegazhim.ru/cat/89/1038/ (data obrashcheniya 05.09.2024). (In Russ).

10. Vysogorec S.P., Lesiv A.V. Monitoring sostoyaniya kontaktnoj sistemy elektrooborudovaniya v setyah 0,4-10 kV sistemoj «TermoSensor». – Informacionnyj spravochnik. Vyp. 2. Proektirovanie, montazh, naladka i ekspluataciya elektrooborudovaniya, 2018. S. 30–45. (In Russ).

11. Ohlopkov A.V., Sigitov O.YU., Bitnev V.D., Lapuhin S.N., Kunickij A.G. Tekhnicheskie resheniya po obnaruzheniyu peregreva elementov raspredelitel'nyh ustrojstv napryazheniem 0,4–10 kV // Elektrichestvo 2022, №3. https://doi.org/10.24160/0013-5380-2022-3-58-66. (In Russ).

12. Sitkin M.K., Stroganov K.A., Lyulin B.N., Popova. E.M., SHubarev V.A. Primenenie besprovodnyh sistem monitoringa temperatury PAV-Termo proizvodstva OAO «Avangard» v elektricheskih shkafah. Dostupno po: https://mwelectronics.etu.ru/assets/files/2023/novoe/574-578.pdf (data obrashcheniya 05.09.2024). (In Russ).

13. Gavrilov A.V. Kompleks monitoringa temperatury PARMA KMT // Elektroenergiya. PEREDACHA I RASPREDELENIE. 2023, №3(78). S. 126-127. (In Russ).

14. Topil'skij D.V. Sozdanie sistemy upravleniya remontami energeticheskogo oborudovaniya na osnove risk-orientirovannogo podhoda na baze informacionnoj sistemy «Upravlenie planovopredupreditel'nymi remontami energooborudovaniya (UPPRE)» // Izvestiya Sankt-Peterburgskogo gosudarstvennogo ekonomicheskogo universiteta. 2023, № 2(140). S. 94-102. (In Russ.).

15. Ephraim Y. and Merhav N. Hidden Markov processes in IEEE Transactions on Information Theory, Vol. 48, № 6, pp. 1518-1569, June 2002, doi: 10.1109/TIT.2002.1003838.

16. Bouguila N., Fan W., Amayri M. Hidden Markov Models and Applications // Springer 2022, ISBN 978-3-030-99141-8. https://doi.org/10.1007/978-3-030-99142-5.

17. Smirnov N.V., Belugin D. A. Teoriya veroyatnostej i matematicheskaya statistika v prilozhenii k geodezii. – M.: Nedra, 1969. – 379 s. (In Russ).

18. Levin V.M., Luk'yanova E.A., Sorokin I.V. Adaptaciya periodichnosti tekhnicheskogo obsluzhivaniya oborudovaniya elektricheskih setej po nablyudaemoj chastote neispravnostej. V kn. Avtomatizaciya i energosberezhenie mashinostroitel'nogo i metallurgicheskogo proizvodstv, tekhnologiya i nadezhnost' mashin, priborov i oborudovaniya: materialy X Mezhdunarodnoj nauchno-tekhnicheskoj konferencii. – Vologda: VoGU, 2015. S. 101-105. (In Russ)