Standard

Predicting District Heating Networks Fault Location with Graph Neural Networks. / Plokhikh, Ivan; Pushkarev, Dmitriy; Gobyzov, Oleg и др.

в: Energies, Том 19, № 12, 2920, 20.06.2026.

Результаты исследований: Научные публикации в периодических изданиях › статья › Рецензирование

Harvard

APA

Vancouver

Plokhikh I, Pushkarev D, Gobyzov O, Filimonov S, Dekterev A, Mullyadzhanov R и др. Predicting District Heating Networks Fault Location with Graph Neural Networks. Energies. 2026 июнь 20;19(12):2920. doi: 10.3390/en19122920

Author

Plokhikh, Ivan ; Pushkarev, Dmitriy ; Gobyzov, Oleg и др. / Predicting District Heating Networks Fault Location with Graph Neural Networks. в: Energies. 2026 ; Том 19, № 12.

BibTeX

@article{609a81b378024a5593ebd8d771655995,
title = "Predicting District Heating Networks Fault Location with Graph Neural Networks",
abstract = "District heating networks (DHNs) are critical infrastructure prone to physical failures such as leakage-related faults, which cause significant energy and financial losses. Traditional physics-based monitoring methods are computationally expensive and require the continual recalibration of complex mathematical models, while standard data-driven approaches often fail due to the scarcity of real-world sensor data. This study addresses these challenges by proposing a topology-aware graph neural network (GNN) architecture for fault localization. The methodology follows a two-stage process: first, a graph attention-based architecture is designed and optimized using a synthetic dataset to effectively capture multi-step neighborhood dependencies. Second, the model is adapted and evaluated on a physically simulated dataset of a real urban DHN, comprising 187 nodes and 42,570 operational states. The problem is formulated as a multi-class classification task across supply and return subnets. The results demonstrate high predictive performance, achieving an accuracy of 96% on the supply subnet and 91% on the return subnet. Analysis of prediction errors reveals a strong bias towards local topological mistakes, indicating the model{\textquoteright}s ability to capture the physical propagation of disturbances. These findings highlight the efficacy of GNNs in handling sparse data and exploiting network topology for robust DHN monitoring.",
keywords = "district heating, fault detection, fault localization, graph neural networks, network topology, thermohydraulic simulation",
author = "Ivan Plokhikh and Dmitriy Pushkarev and Oleg Gobyzov and Sergey Filimonov and Alexander Dekterev and Rustam Mullyadzhanov and Sergey Alekseenko",
note = "This work was supported by a grant for research centers, provided by the Ministry of Economic Development of the Russian Federation in accordance with the subsidy agreement with the Novosibirsk State University dated 17 April 2025 No. 139-15-2025-006: IGK 000000C313925P3S0002.",
year = "2026",
month = jun,
day = "20",
doi = "10.3390/en19122920",
language = "English",
volume = "19",
journal = "Energies",
issn = "1996-1073",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "12",

}

RIS

TY - JOUR

T1 - Predicting District Heating Networks Fault Location with Graph Neural Networks

AU - Plokhikh, Ivan

AU - Pushkarev, Dmitriy

AU - Gobyzov, Oleg

AU - Filimonov, Sergey

AU - Dekterev, Alexander

AU - Mullyadzhanov, Rustam

AU - Alekseenko, Sergey

N1 - This work was supported by a grant for research centers, provided by the Ministry of Economic Development of the Russian Federation in accordance with the subsidy agreement with the Novosibirsk State University dated 17 April 2025 No. 139-15-2025-006: IGK 000000C313925P3S0002.

PY - 2026/6/20

Y1 - 2026/6/20

N2 - District heating networks (DHNs) are critical infrastructure prone to physical failures such as leakage-related faults, which cause significant energy and financial losses. Traditional physics-based monitoring methods are computationally expensive and require the continual recalibration of complex mathematical models, while standard data-driven approaches often fail due to the scarcity of real-world sensor data. This study addresses these challenges by proposing a topology-aware graph neural network (GNN) architecture for fault localization. The methodology follows a two-stage process: first, a graph attention-based architecture is designed and optimized using a synthetic dataset to effectively capture multi-step neighborhood dependencies. Second, the model is adapted and evaluated on a physically simulated dataset of a real urban DHN, comprising 187 nodes and 42,570 operational states. The problem is formulated as a multi-class classification task across supply and return subnets. The results demonstrate high predictive performance, achieving an accuracy of 96% on the supply subnet and 91% on the return subnet. Analysis of prediction errors reveals a strong bias towards local topological mistakes, indicating the model’s ability to capture the physical propagation of disturbances. These findings highlight the efficacy of GNNs in handling sparse data and exploiting network topology for robust DHN monitoring.

AB - District heating networks (DHNs) are critical infrastructure prone to physical failures such as leakage-related faults, which cause significant energy and financial losses. Traditional physics-based monitoring methods are computationally expensive and require the continual recalibration of complex mathematical models, while standard data-driven approaches often fail due to the scarcity of real-world sensor data. This study addresses these challenges by proposing a topology-aware graph neural network (GNN) architecture for fault localization. The methodology follows a two-stage process: first, a graph attention-based architecture is designed and optimized using a synthetic dataset to effectively capture multi-step neighborhood dependencies. Second, the model is adapted and evaluated on a physically simulated dataset of a real urban DHN, comprising 187 nodes and 42,570 operational states. The problem is formulated as a multi-class classification task across supply and return subnets. The results demonstrate high predictive performance, achieving an accuracy of 96% on the supply subnet and 91% on the return subnet. Analysis of prediction errors reveals a strong bias towards local topological mistakes, indicating the model’s ability to capture the physical propagation of disturbances. These findings highlight the efficacy of GNNs in handling sparse data and exploiting network topology for robust DHN monitoring.

KW - district heating

KW - fault detection

KW - fault localization

KW - graph neural networks

KW - network topology

KW - thermohydraulic simulation

UR - https://www.scopus.com/pages/publications/105042950370

UR - https://www.mendeley.com/catalogue/a38fb8ee-b94e-3058-acb2-d70bd021918f/

U2 - 10.3390/en19122920

DO - 10.3390/en19122920

M3 - Article

VL - 19

JO - Energies

JF - Energies

SN - 1996-1073

IS - 12

M1 - 2920

ER -

ID: 85460745