| Issue |
E3S Web Conf.
Volume 152, 2020
2019 International Conference on Power, Energy and Electrical Engineering (PEEE 2019)
|
|
|---|---|---|
| Article Number | 02002 | |
| Number of page(s) | 4 | |
| Section | Renewable Energy and Energy Engineering | |
| DOI | https://doi.org/10.1051/e3sconf/202015202002 | |
| Published online | 14 February 2020 | |
Optimization of the features extraction method in cyber physical systems of monitoring energy infrastructure facilities
Moscow State University of Civil Engineering, Yaroslavskoe shosse, 26, 129337, Russia
* Corresponding author: vladk_94@mail.ru
The study presents an optimization method of sliding windows parameters selection in the features extraction procedure in cyber physical systems during data processing of the technical condition of energy and electric infrastructure facilities. The method is based on utilizing genetic algorithm and objective functions related to the quality of the classification of the defects by hazard degree. Proposed method was verified on the experimental data acquired from the technical condition monitoring of the vertical oil tanks. The results obtained from the experiment confirm the proposal that this method can be applied for effectively solving problems related to features extraction in monitoring, risk management and classification of maintenance defects in the power and electrical engineering facilities.
© The Authors, published by EDP Sciences, 2020
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.