ON THE STATE AND METHODS OF PREDICTIVE MAINTENANCE OF PIPELINES AT MINING ENTERPRISES. PROSPECTS FOR THE APPLICATION OF FUZZY MODELING

Authors:

K.M. Trofimov, R.K. Khalkechev
National University of Science and Technology MISIS (NUST MISIS), Moscow, 119049, Russian Federation, e-mail: syrus@list.ru
Authors Information
Trofimov K.M. – Postgraduate Student of the Department of Information and Communication Technologies at the University of Science and Technology of the National University of Science and Technology MISIS (NUST MISIS), Moscow, 119049, Russian Federation, e-mail: trofimovkonstantin2002@gmail.com
Khalkechev R.K. – Doctor of Engineering Science, Professor of the Department of Information and Communication Technologies at the University of Science and Technology of the National University of Science and Technology MISIS (NUST MISIS), Moscow, 119049, Russian Federation, e-mail: syrus@list.ru

UDC: 658.581:621.643 c K.M. Trofimov, R.K. Khalkechev, 2026
DOI: http://dx.doi.org/10.18796/0041-5790-2026-8-62-64

Abstract

The presented article analyzes the current state of research in the field of predictive maintenance of pipeline systems at mining enterprises. It is established that models developed within the framework of the mechanical approach demonstrate a higher degree of quantitative adequacy compared to those obtained using machine learning and artificial intelligence. However, the inherent uncertainty in the input parameters of such models (it is impossible to specify exact values along the entire length of the pipeline) reduces the value of the obtained results. To address this issue, an approach based on fuzzy modeling of degradation processes is proposed. It should be noted that, in this case, fuzzy set theory is used as a generalization of error theory rather than as a means of expressing expert judgments. The application of the proposed approach makes it possible to develop structurally robust models.

Keywords: Predictive maintenance, pipeline, forecasting, fuzzy modeling, longitudinal stresses, model, structural stability, machine learning.

References

Hussain M., Zhang T. Big Data Analytics in Energy Pipeline Integrity Management. Singapore: Springer Nature Singapore, 2025. 330 p.
Timashev S., Bushinskaya A. Diagnostics and Reliability of Pipeline Systems. Cham: Springer International Publishing, 2016. 407 p.
Tawk M., Mustapha S., Trad F., Saad G. Service life prediction in pipelines using machine learning techniques. International Journal of Computational Intelligence Systems. 2025;(18):319. DOI: 10.1007/s44196-025-01058-1.
Hussain M., Zhang T., Dwight R., Jamil I. Energy pipeline degradation condition assessment using predictive analytics – challenges, issues, and future directions. Journal of Pipeline Science and Engineering. 2024;(4):100178. DOI: 10.1016/j.jpse.2024.100178.
Zhang W., Fu X., Hu M., Xu K., Dai K., Shi J., Ji Y., Dong C. Effects of external corrosion defect growth on wall pipeline under internal pressure and various defect sizes with mechano-electrochemical interaction. Materials and Corrosion. 2024;(75):1348–1358. DOI: 10.1002/maco.202414391.
Prokopyev L.A., Golikov N.I., Saraev Yu.N. Crack Growth in the Field of Residual Stresses in Welded Joints of Pipelines Used in a Cold Climate. Diagnostics, Resource and Mechanics of materials and structures. 2024;(5): 159-169. DOI: 10.17804/2410-9908.2024.5.159-169.
Нечеткая модель определения формы устойчивого целика в углевмещающих породах / Р.К. Халкечев, Ю.М. Левкин, К.В. Халкечев и др. // Уголь. 2024;(1):61-63. DOI: 10.18796/0041-5790-2024-1-61-63. Khalkechev R.K., Levkin Yu.M., Khalkechev K.V., Kuzmenko S.Yu. Fuzzy model of the shape determining of a stable pillar in coalbearing rocks. Ugol’. 2024;(1):61-63. (In Russ.). DOI: 10.18796/0041-5790-2024-1-61-63.
Халкечев Р.К. Нечеткая математическая модель изменения концентрации трещин в минерале под действием внешней нагрузки // Горный информационно-аналитический бюллетень (научно-технический журнал). 2019. № 6. С. 97-105. DOI: 10.25018/0236-1493-2019-06-0-97-105. Khalkechev R.K. Fuzzy mathematical model of fracture concentration changes in a mineral under external load. Gornyj informatsionno-analiticheskij byulleten'. 2019;(6):97-105. (In Russ.). DOI: 10.25018/0236-1493-2019-06-0-97-105.
Халкечев Р.К. Применение теории мультифрактального моделирования процессов деформирования и разрушения породных массивов с целью краткосрочного прогнозирования внезапных выбросов угля и газа // Уголь. 2019;(7):48-50. DOI: 10.18796/0041-5790-2019-7-48-50 Khalkechev R.K. Multifractal modeling theory application of rock mass deformation and destruction processes with the aim of shortterm forecasting sudden coal and gas outbursts. Ugol’. 2019;(7):48-50. (In Russ.). DOI: 10.18796/0041-5790-2019-7-48-50
Халкечев К.В., Левкин Ю.М., Абрамкин Н.И. Разработка математической модели поля напряжений в окрестности магистральной трещины продольного сдвига в кровле горной выработки // Уголь. 2024;(7):52-54. DOI: 10.18796/0041-5790-2024-7-52-54. Khalkechev K.V., Levkin Yu.M., Abramkin N.I. Development of a mathematical odel of the stress field in the vicinity of a longitudinal shear main crack in the mine roof. Ugol’. 2024;(7):52-54. (In Russ.). DOI: 10.18796/0041-5790-2024-7-52-54.
Халкечев Р.К., Левкин Ю.М., Халкечев К.В. Разработка математической модели поля напряжений в целиках слоистой текстуры на угольных месторождениях // Уголь. 2023;(8):84-86. DOI: 10.18796/0041- 5790-2023-8-84-86. Khalkechev R.K., Levkin Yu.M., Khalkechev K.V. Mathematical model development of the stress field in the pillars stratified texture in coal deposits. Ugol’. 2023;(8):84-86. (In Russ.). DOI: 10.18796/0041-5790-2023-8-84-86.
Чуличков И.А. Математические методы нелинейной динамики. М.: ФИЗМАТЛИТ, 2000. 296 с.

For citation

Trofimov K.M., Khalkechev R.K. On the state and methods of predictive maintenance of pipelines at mining enterprises. Prospects for the application of fuzzy modeling. Ugol’. 2026;(8):62-64. (In Russ.). DOI: 10.18796/0041-5790-2026-8-62-64.

Paper Info
Received: May 27, 2026
Reviewed:
Accepted: June 30, 2026