DOI: 10.18503/1995-2732-2023-21-3-155-169
Abstract
Problem Statement (Relevance). The introduction of new LED-based technologies in lighting networks leads to new problems in ensuring and controlling the quality of electrical energy and assessing reliability of lighting networks. The non-linear nature of these lighting devices and complexity of maintenance create significant obstacles to obtaining real benefits of electricity savings and make it difficult to calculate the real cost savings. To address the problems described, there is a need to improve the quality control process and develop predictive maintenance strategies as a way to improve efficiency of lighting network quality management. Objectives. The research is aimed at studying and analyzing the possibility and feasibility of using predictive maintenance strategies in LED lighting networks. Methods Applied. The authors use a comprehensive research approach that includes an analysis of relevant literature and specific practices for using the predictive approach in electric grids, methods of predictive modeling, analytics, and a structural analysis. Originality. The paper proposes a strategy for using predictive maintenance methods, showing the example of a predictive mathematical model with elements of machine learning, factoring into the control context of the main parameters of lighting networks. Result. The paper presents the predictive maintenance strategy, using the example of a predictive mathematical model, recommendations developed for a practical application of the proposed predictive maintenance strategy in lighting networks for fault prediction, optimization of maintenance schedules and integration of a quality management process into an operation procedure. The results show the possibility and feasibility of implementing a predictive maintenance strategy to improve efficiency of quality control processes, reliability and cost savings in LED lighting networks. Practical Relevance. The results of the study have important practical relevance for lighting industry professionals in the field of lighting network quality management. By applying the developed models and strategy, organizations can optimize maintenance resources, reduce downtime periods and ensure the improved quality of LED lighting systems.
Keywords
predictive maintenance, lighting networks, LED lighting fixtures, quality management, quality of electricity in lighting networks, energy efficiency of lighting networks
For citation
Kuzmenko V.P., Solenyi S.V. A Predictive Maintenance Model for Quality Management of LED Lighting Networks. Vestnik Magnitogorskogo Gosudarstvennogo Tekhnicheskogo Universiteta im. G.I. Nosova [Vestnik of Nosov Magnitogorsk State Technical University]. 2023, vol. 21, no. 3, pp. 155-169. https://doi.org/10.18503/1995-2732-2023-21-3-155-169
1. Segovia-Muñoz D., Xavier Serrano Guerrero, Antonio Barragán-Escandón. Predictive maintenance in LED street lighting controlled with telemanagement system to improve current fault detection procedures using software tools. Renewable Energy and Power Quality Journal. 2022;20:379-386. DOI: 10.24084/repqj20.318
2. Mahdi Karami, Reinhard Madlener. Smart predictive maintenance strategy based on cyber-physical systems for centrifugal pumps: A bearing vibration analysis. FCN Working Paper No. 14/2019. DOI: 10.2139/ssrn. 3544199
3. Prytkova E.A., Davydov V.M. Analysis of the use of hierarchical neural network methods in quality control. Vestnik Magnitogorskogo gosudarstvennogo tekhnicheskogo universiteta im. G.I. Nosova [Vestnik of Nosov Magnitogorsk State Technical University]. 2023;21(1):74-81. (In Russ.) doi.org/10.18503/1995-2732-2023-21-1-74-81
4. Egorov D.E., Dovgun V.P., Boyarskaya N.P., Yan A.V., Slyusarev A.S. Power factor correction in power delivery systems with multiphase nonlinear loads. Izvestiya vysshikh uchebnykh zavedeniy. Problemy energetiki [Power Engineering: Research, Equipment, Technology]. 2020;22(6):3-15. (In Russ.) DOI: 10.30724/1998-9903-2020-22-6-3-15
5. De Luca R., Ferraro A., Galli A., Gallo M., Moscato V., Sperlì G. A deep attention-based approach for predictive maintenance applications in IoT scenarios. Journal of Manufacturing Technology Management. 2023;34(4):535-556. doi.org/10.1108/JMTM-02-2022-0093
6. Boyarskaya N.P., Dovgun V.P., Egorov D.E., Novikov V.V., Shandrygin D.A. Minimization of power losses in passive power filters. Izvestiya vysshikh uchebnykh zavedeniy. Problemy energetiki [Power Engineering: Research, Equipment, Technology]. 2021;23(6):42-52. (In Russ.) DOI: 10.30724/1998-9903-2021-23-6-42-52
7. Mirza Rayana Sanzana, Tomas Maul et al. Application of deep learning in facility management and maintenance for heating, ventilation, and air conditioning. Automation in Construction. 2022;141:104445. ISSN 0926-5805. doi.org/10.1016/j.autcon.2022.104445
8. Chen Gong, Haiping Xu, Zengquan Yuan, Jinhua Liang. The accelerated life test investigation and lifetime prediction method for LED driver. 2022;355-359. DOI: 10.1109/ICPEA56363.2022.10052233
9. Kuzmenko V. et al. Definition and approximation of the light flux degradation of a LED lamp. IOP Conference Series: Materials Science and Engineering. 2020;734:012197. DOI: 10.1088/1757-899X/734/1/ 012197
10. Kalechits V.N. Features of modeling the operating modes of outdoor lighting lines. Energetika. Izvestiya vysshikh uchebnykh zavedeniy i energeticheskikh obedineniy SNG [Proceedings of the CIS Higher Education Institutions and Power Engineering Associations]. 2022;65(6):499-510. (In Russ.) DOI: 10.21122/ 1029-7448-2022-65-6-499-510
11. Kuzmenko V.P., Solenyi S.V. Study on the influence of LED spotlights on the processes of managing the quality of electrical energy and energy efficiency. Omskii nauchnyi vestnik [Omsk Scientific Bulletin]. 2021;2(176):15-19. (In Russ.)