Please use this identifier to cite or link to this item:
Title: Data Mining Applied to Decision Support Systems for Power Transformers’ Health Diagnostics
Authors: Khalyasmaa, A. I.
Matrenin, P. V.
Eroshenko, S. A.
Manusov, V. Z.
Bramm, A. M.
Romanov, A. M.
Issue Date: 2022
Publisher: MDPI
Citation: Data Mining Applied to Decision Support Systems for Power Transformers’ Health Diagnostics / A. I. Khalyasmaa, P. V. Matrenin, S. A. Eroshenko et al. // Mathematics. — 2022. — Vol. 10. — Iss. 14. — 2486.
Abstract: This manuscript addresses the problem of technical state assessment of power transformers based on data preprocessing and machine learning. The initial dataset contains diagnostics results of the power transformers, which were collected from a variety of different data sources. It leads to dramatic degradation of the quality of the initial dataset, due to a substantial number of missing values. The problems of such real-life datasets are considered together with the performed efforts to find a balance between data quality and quantity. A data preprocessing method is proposed as a two-iteration data mining technology with simultaneous visualization of objects’ observability in a form of an image of the dataset represented by a data area diagram. The visualization improves the decision-making quality in the course of the data preprocessing procedure. On the dataset collected by the authors, the two-iteration data preprocessing technology increased the dataset filling degree from 75% to 94%, thus the number of gaps that had to be filled in with the synthetic values was reduced by 2.5 times. The processed dataset was used to build machine-learning models for power transformers’ technical state classification. A comparative analysis of different machine learning models was carried out. The outperforming efficiency of ensembles of decision trees was validated for the fleet of high-voltage power equipment taken under consideration. The resulting classification-quality metric, namely, F1-score, was estimated to be 83%. © 2022 by the authors.
Access: info:eu-repo/semantics/openAccess
SCOPUS ID: 85136936305
WOS ID: 000833110400001
PURE ID: 30720872
ISSN: 22277390
DOI: 10.3390/math10142486
metadata.dc.description.sponsorship: Ministry of Education and Science of the Russian Federation, Minobrnauka
The research funding from the Ministry of Science and Higher Education of the Russian Federation (Ural Federal University Program of Development within the Priority-2030 Program) is gratefully acknowledged.
Appears in Collections:Научные публикации, проиндексированные в SCOPUS и WoS CC

Files in This Item:
File Description SizeFormat 
2-s2.0-85136936305.pdf7,38 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.