2024, Vol. 11, No. 3. - go to content...

Permanent address of this page - https://resources.today/en/01inor324.html

Метаданные этой статьи так же доступны на русском языке

DOI: 10.15862/01INOR324 (https://doi.org/10.15862/01INOR324)

Full article in PDF format (file size: 678.6 KB)

For citation:

Abdullin T.R., Isavnin A.G. Methodology for planning repair work at heating network facilities based on regression models. Russian journal of resources, conservation and recycling. 2024; 11(3). Available at: https://resources.today/PDF/01INOR324.pdf (in Russian). DOI: 10.15862/01INOR324

Methodology for planning repair work at heating network facilities based on regression models

Abdullin Timur Ramilevich
The Kazan State Power Engineering University, Kazan, Russia
E-mail: tiabdullin96@gmail.com
ORCID: https://orcid.org/0009-0006-3617-9948
RSCI: https://elibrary.ru/author_profile.asp?id=1197477

Isavnin Alexey Gennad’evich
Kazan Federal University, Naberezhnye Chelny, Russia
E-mail: isavnin@mail.ru
ORCID: https://orcid.org/0000-0001-6413-3329
RSCI: https://elibrary.ru/author_profile.asp?id=33832
WoS: https://www.webofscience.com/wos/author/rid/M-7336-2015
SCOPUS: https://www.scopus.com/authid/detail.url?authorId=6603223931

Abstract. The article considers the problem of planning repair work at heating network facilities, which is a key aspect for ensuring the reliability and uninterrupted functioning of this infrastructure. Effective planning of repair activities allows not only to prevent emergencies, but also to significantly reduce operating costs. This paper proposes a solution for optimizing repair planning based on the use of regression models. An experiment was conducted using a real data set, within which single-factor and multifactor regression were applied. The main objective of the experiment was to assess the accuracy and applicability of these models for predicting the required volume of repair work. Analysis of the results showed that linear regression models demonstrate low efficiency in solving problems of this class. This indicates that more complex models or methods must be used to improve the accuracy and reliability of planning repair work in heating networks. The work emphasizes the limitations of linear regression models and opens up prospects for further research in the field of machine learning. The study focuses on the importance of further development and implementation of modern machine learning technologies for solving planning problems in heating networks. The proposed approaches can significantly improve the decision-making process, which will contribute not only to increasing the reliability of heating networks, but also to the overall economic efficiency of their operation. As a result, the article opens up new opportunities for further research in the field of applying machine learning to manage repair work in heating networks.

Keywords: heating networks; linear regression; data set; forecasting; visualization; machine learning; model

Download article in PDF format