RESEARCH PAPER
Physics-Informed Spatiotemporal Deep Learning for Cable Fault Detection and Localization in Smart Power Grids
1
College of Electrical Engineering and Automation, Shandong University of Science and Technology, China
A – Conceptualization; B – Methodology; C – Software; D – Validation; E – Formal analysis; F – Investigation; G – Resources; H – Data curation; I – Writing – original draft; J – Writing – review & editing; K – Visualization; L – Supervision; M – Project administration; N – Funding acquisition
Submission date: 2025-12-27
Final revision date: 2026-03-10
Acceptance date: 2026-06-30
Online publication date: 2026-08-24
Corresponding author
Xingfan Su
College of Electrical Engineering and Automation, Shandong University of Science and Technology, 266590, Qingdao, China
College of Electrical Engineering and Automation, Shandong University of Science and Technology, 266590, Qingdao, China
KEYWORDS
Deep LearningDistributed Generation (DG)Fault DetectionGraph Neural Network (GCN)Power Grid CablePhysics-Informed Neural Networks (PINNs)
TOPICS
ABSTRACT
Reliable detection and localization of cable faults are essential for the secure operation of modern distribution networks, particularly with increasing distributed generation integration. This study proposes a physics-informed spatiotemporal deep learning framework for fault detection and localization in medium-voltage cable systems. The approach embeds telegrapher-equation residual constraints and distributed-generation boundary consistency within a physics-informed neural network to incorporate physical knowledge into the learning process. Long short-term memory networks capture transient temporal features of fault signals, while a topology-aware graph convolutional network identifies the faulted cable section within the network. A physics-regularized regression stage then estimates the precise fault distance inside the identified section. The framework is validated using electromagnetic transient simulations of a 10 kV underground cable network developed in PSCAD/EMTDC under various fault locations, grounding conditions, and distributed generation penetration levels.
REFERENCES (35)
1.
Chang C-K, Chang H-H, Boyanapalli BK. Application of pulse sequence partial discharge based convolutional neural network in pattern recognition for underground cable joints. IEEE Transactions on Dielectrics and Electrical Insulation 2022; 29(3): 1070-8. https://doi.org/10.1109/TDEI.2....
2.
Tang Z, Zhou K, Meng P, Li Y. A frequency-domain location method for defects in cables based on power spectral density. IEEE Transactions on Instrumentation and Measurement 2022; 71: 1-10. https://doi.org/10.1109/TIM.20....
3.
Yuan J, Zhang Y, Gang W, Tian J, Su L, Tu Z. Flexibility quantification and regulation of regional distributed energy system under multi-source uncertainties. Journal of cleaner production 2025; 501: 145323. https://doi.org/10.1016/j.jcle....
4.
Khaleghi A, Mahmood OS, Ghazizadeh-Ahsaee M, Rabori AM. Transient fault area location and fault classification for distribution systems based on wavelet transform and adaptive neuro-fuzzy inference system (ANFIS). Advances in Electrical and Electronic Engineering 2018; 16(2): 155. https://doi.org/10.15598/aeee.....
5.
Song E, Shin Y-J, Stone PE, Wang J, Choe T-S, Yook J-G, Park JB. Detection and location of multiple wiring faults via time–frequency-domain reflectometry. IEEE Transactions on Electromagnetic Compatibility 2009; 51(1): 131-8. https://doi.org/10.1109/TEMC.2....
6.
Chang SJ, Lee CK, Lee C-K, Han YJ, Jung MK, Park JB, Shin Y-J. Condition monitoring of instrumentation cable splices using Kalman filtering. IEEE Transactions on Instrumentation and Measurement 2015; 64(12): 3490-9. https://doi.org/10.1109/TIM.20....
7.
Saleh MU, Deline C, Benoit E, Kingston S, Edun AS, Jayakumar NKT, Harley JB, Furse C, Scarpulla M. An overview of spread spectrum time domain reflectometry responses to photovoltaic faults. IEEE Journal of Photovoltaics 2020; 10(3): 844-51. https://doi.org/10.1109/JPHOTO....
8.
Norouzi Y, Braun S, Frohne C, Seifi S, Werle P, editors. Effect of cable joints on frequency domain analysis. 2018 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP); 2018: IEEE. https://doi.org/10.1109/CEIDP..... https://doi.org/10.1109/CEIDP.....
9.
Shan B, Li S, Yu L, Wang W, Li C, Meng X. Effect of segmented thermal aging on defect location accuracy in XLPE distribution cables. IEEE access 2021; 9: 134753-61. https://doi.org/10.1109/ACCESS....
10.
Zhang H, Mu H, Lu X, Tian J, Zou X, Zhang G. A method for locating and diagnosing cable abrasion based on broadband impedance spectroscopy. Energy Reports 2022; 8: 1492-9. https://doi.org/10.1016/j.egyr....
11.
Ghosh S, Yang G, Moser AG, Anaraki SA. Testing and validation of travelling wave based fault detection and location method for offshore wind farm applications. Energy Reports 2023; 9: 431-40. https://doi.org/10.1016/j.egyr....
12.
Haohao C, Jing L, Ping C. Design of fault location algorithm based on online distributed travelling wave for HV power cable. PloS one 2024; 19(1): e0296513. https://doi.org/10.1371/journa....
13.
Pan X, Zhao D, Chen H, Shen A, Wu K. Incipient fault identification method for 10 kV power cables based on sheath current and DVAE-SAO-CatBoost. Electric Power Systems Research 2025; 245: 111583. https://doi.org/10.1016/j.epsr....
14.
Baayeh AG, Cappelle J, Kleemann M. Fault Location Method for Medium Voltage Cables Using Sheath Currents in Inverter-Based Resource Networks. IEEE access 2025. https://doi.org/10.1109/ACCESS....
15.
Ma X, Zhen W, Ren H, Zhang G, Zhang K, Dong H. A method for fault localization in distribution networks with high proportions of distributed generation based on graph convolutional networks. Energies 2024; 17(22): 5758. https://doi.org/10.3390/en1722....
16.
Uzel H, Özüpak Y, Alpsalaz F, Aslan E. Optimized ANN–RF hybrid model with optuna for fault detection and classification in power transmission systems. Scientific Reports 2025.
17.
Gashteroodkhani O, Majidi M, Etezadi-Amoli M, Nematollahi A, Vahidi B. A hybrid SVM-TT transform-based method for fault location in hybrid transmission lines with underground cables. Electric Power Systems Research 2019; 170: 205-14. https://doi.org/10.1016/j.epsr....
18.
De Xu N. Semi-Supervised Hybrid Ensemble Learning for Fault Detection in 20kV XLPE Cables. Informatica 2025; 49(20).
19.
Veerasamy V, Abdul Wahab NI, Ramachandran R, Thirumeni M, Subramanian C, Othman ML, Hizam H. High-impedance fault detection in medium-voltage distribution network using computational intelligence-based classifiers. Neural Computing and Applications 2019; 31(12): 9127-43.
20.
Peddakapu K, Srinivasarao P, Mohamed M, Liu X, Krishna Kishore D. Faults identification in high voltage direct current transmission lines using adaptive neuro-fuzzy inference system. International Journal of Modelling and Simulation 2023; 43(6): 813-31. https://doi.org/10.1080/022862....
21.
Fu H, Qiu L, Ai Y, Tu J, Yan Y. Deep learning-based fault detection and location in underground power cables using resonance frequency analysis. Electrical Engineering 2025; 107(4): 4051-62.
22.
Li Y, Gong C, Deng T, Jia Z, Wang F, Zhao Q, Zhang J. Partial Discharge Pattern Recognition Based on Swin Transformer for Power Cable Fault Diagnosis in Modern Distribution Systems. Processes 2025; 13(3): 852. https://doi.org/10.3390/pr1303....
23.
Tsotsopoulou E, Karagiannis X, Papadopoulos T, Chrysochos A, Dyśko A, Hong Q, Tzelepis D. Advanced fault location scheme for superconducting cables based on deep learning algorithms. International Journal of Electrical Power & Energy Systems 2023; 147: 108860.
24.
Chang SJ, Kwon G-Y. Anomaly detection for shielded cable including cable joint using a deep learning approach. IEEE Transactions on Instrumentation and Measurement 2023; 72: 1-10.
25.
Wan Q, Li Y, Yuan R, Meng Q, Li X. Fault identification and localization of a time− frequency domain joint impedance spectrum of cables based on deep belief networks. Sensors 2023; 23(2): 684. https://doi.org/10.3390/s23020....
26.
Said A, Hashima S, Fouda MM, Saad MH. Deep learning-based fault classification and location for underground power cable of nuclear facilities. IEEE access 2022; 10: 70126-42. https://doi.org/10.1109/ACCESS....
27.
Swaminathan R, Mishra S, Routray A, Swain SC. A CNN-LSTM-based fault classifier and locator for underground cables. Neural Computing and Applications 2021; 33(22): 15293-304. https://doi.org/10.1007/s00521....
28.
Samet H, Khaleghian S, Tajdinian M, Ghanbari T, Terzija V. A similarity-based framework for incipient fault detection in underground power cables. International Journal of Electrical Power & Energy Systems 2021; 133: 107309.
29.
Wang Y, Lu H, Xiao X, Yang X, Zhang W. Cable incipient fault identification using restricted Boltzmann machine and stacked autoencoder. IET Generation, Transmission & Distribution 2020; 14(7): 1242-50. https://doi.org/10.1049/iet-gt....
30.
Wang M-H, Lu S-D, Liao R-M. Fault diagnosis for power cables based on convolutional neural network with chaotic system and discrete wavelet transform. IEEE Transactions on Power Delivery 2021; 37(1): 582-90. https://doi.org/10.1109/TPWRD.....
31.
Fritsch M, Wolter M. Transmission model of partial discharges on medium voltage cables. IEEE Transactions on Power Delivery 2021; 37(1): 395-404. https://doi.org/10.1109/TPWRD.....
32.
Afandi O, Najafi A. Distribution Transformer Winding Fault Detection Based on Hybrid Wavelet‐CNN. International Transactions on Electrical Energy Systems 2025; 2025(1): 9936120. https://doi.org/10.1155/etep/9....
33.
Moloi K, Ndlela NW, Davidson IE. Fault classification and localization scheme for power distribution network. Applied Sciences 2022; 12(23): 11903.
34.
Siddique MNI, Shafiullah M, Mekhilef S, Pota H, Abido M. Fault classification and location of a PMU-equipped active distribution network using deep convolution neural network (CNN). Electric Power Systems Research 2024; 229: 110178.
35.
Nguyen BL, Vu TV, Nguyen T-T, Panwar M, Hovsapian R. Spatial-temporal recurrent graph neural networks for fault diagnostics in power distribution systems. IEEE access 2023; 11: 46039-50. https://doi.org/10.1109/ACCESS....
Share
RELATED ARTICLE
| eISSN: | 2956-3860 |
| ISSN: | 1507-2711 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
