A Bayesian Network Approach to Earth Fault Localization in Medium Voltage Electricity Grids

Anders L Madsen, Somesh Bhattacharya, Hans-Peter Schwefel, Rasmus L Olsen
Proceedings of the 13th International Conference on Probabilistic Graphical Models, PMLR 343:545-558, 2026.

Abstract

Earth faults are the most commonly occurring fault type in Medium Voltage electricity distribution grids. Electricity distribution grids in Central Europe are compensated, meaning the network continues to operate after an earth fault. However, during the time-consuming search process via grid switching, secondary faults can occur, leading to outages. Digital twins, through their automated physics-informed topology and measurement-integration capabilities, can leverage generated training data and available measurements to pinpoint earth-fault locations without additional hardware to be deployed in the grid. This paper demonstrates how Bayesian networks can aid earth fault localization within a digital twin framework in electricity distribution grids. The proposed method uses stored voltage signatures from the digital twin to train a Bayesian network model. The results of an experimental analysis prove the efficacy of Bayesian networks when applied to observations of EMT voltages of the faulty phase. Ongoing work focuses on integrating this approach into a digital twin framework to actively support distribution system operators in locating earth faults.

Cite this Paper

BibTeX
@InProceedings{pmlr-v343-madsen26a, title = {A {Bayesian} Network Approach to Earth Fault Localization in Medium Voltage Electricity Grids}, author = {Madsen, Anders L and Bhattacharya, Somesh and Schwefel, Hans-Peter and Olsen, Rasmus L}, booktitle = {Proceedings of the 13th International Conference on Probabilistic Graphical Models}, pages = {545--558}, year = {2026}, editor = {Camps-Valls, Gustau and Leonelli, Manuele and Varando, Gherardo}, volume = {343}, series = {Proceedings of Machine Learning Research}, month = {09--11 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v343/main/assets/madsen26a/madsen26a.pdf}, url = {https://proceedings.mlr.press/v343/madsen26a.html}, abstract = {Earth faults are the most commonly occurring fault type in Medium Voltage electricity distribution grids. Electricity distribution grids in Central Europe are compensated, meaning the network continues to operate after an earth fault. However, during the time-consuming search process via grid switching, secondary faults can occur, leading to outages. Digital twins, through their automated physics-informed topology and measurement-integration capabilities, can leverage generated training data and available measurements to pinpoint earth-fault locations without additional hardware to be deployed in the grid. This paper demonstrates how Bayesian networks can aid earth fault localization within a digital twin framework in electricity distribution grids. The proposed method uses stored voltage signatures from the digital twin to train a Bayesian network model. The results of an experimental analysis prove the efficacy of Bayesian networks when applied to observations of EMT voltages of the faulty phase. Ongoing work focuses on integrating this approach into a digital twin framework to actively support distribution system operators in locating earth faults.} }
Endnote
%0 Conference Paper %T A Bayesian Network Approach to Earth Fault Localization in Medium Voltage Electricity Grids %A Anders L Madsen %A Somesh Bhattacharya %A Hans-Peter Schwefel %A Rasmus L Olsen %B Proceedings of the 13th International Conference on Probabilistic Graphical Models %C Proceedings of Machine Learning Research %D 2026 %E Gustau Camps-Valls %E Manuele Leonelli %E Gherardo Varando %F pmlr-v343-madsen26a %I PMLR %P 545--558 %U https://proceedings.mlr.press/v343/madsen26a.html %V 343 %X Earth faults are the most commonly occurring fault type in Medium Voltage electricity distribution grids. Electricity distribution grids in Central Europe are compensated, meaning the network continues to operate after an earth fault. However, during the time-consuming search process via grid switching, secondary faults can occur, leading to outages. Digital twins, through their automated physics-informed topology and measurement-integration capabilities, can leverage generated training data and available measurements to pinpoint earth-fault locations without additional hardware to be deployed in the grid. This paper demonstrates how Bayesian networks can aid earth fault localization within a digital twin framework in electricity distribution grids. The proposed method uses stored voltage signatures from the digital twin to train a Bayesian network model. The results of an experimental analysis prove the efficacy of Bayesian networks when applied to observations of EMT voltages of the faulty phase. Ongoing work focuses on integrating this approach into a digital twin framework to actively support distribution system operators in locating earth faults.
APA
Madsen, A.L., Bhattacharya, S., Schwefel, H. & Olsen, R.L.. (2026). A Bayesian Network Approach to Earth Fault Localization in Medium Voltage Electricity Grids. Proceedings of the 13th International Conference on Probabilistic Graphical Models, in Proceedings of Machine Learning Research 343:545-558 Available from https://proceedings.mlr.press/v343/madsen26a.html.

Related Material