Abstract
At present, research of cable fault diagnosis based on artificial intelligence mainly takes statistical characteristics as inputs, which means the appropriateness of statistical characteristic selection is directly related to the diagnosis accuracy and the identification results may have certain contingency. Further, most of these methods do not consider the correlation of signals in time. Therefore, this paper proposes a novel diagnosis method for 10 kV single-core cable based on Double-Layer Long Short Term Memory (D-LSTM) network considering timing relationship of multiple observable electrical quantities. Firstly, analysis object is expanded from single electrical quantity to multiple observable electrical quantities, and the relationships among these quantities are analyzed. Secondly, characteristic matrix of combined time series is constructed by time series pairs extracted from multiple observable electrical quantities. Thirdly, the D-LSTM network for processing sequenced input is established according to the features of characteristic matrix. Then, adaptive moment estimation (Adam) method is applied to model training under supervised learning and the model of fault diagnosis is obtained. Finally, recognition experiments are carried out by the proposed method with sample data obtained by simulation of three cable faults and load disturbance. Results show the diagnosis accuracy of proposed method can achieve 99.06%.
Similar content being viewed by others
References
Min SW, Nam SR, Kang SH, Park JK (2007) Fault location algorithm for cross-bonded cables using the singularity of the sheath impedance matrix. Electr Eng 89(7):525–533. https://doi.org/10.1007/s00202-006-0035-1
Metwally IA, Al-Badi AH, Al Farsi AS (2013) Factors influencing ampacity and temperature of underground power cables. Electr Eng 95(4):383–392. https://doi.org/10.1007/s00202-012-0271-5
Yang LF (2018) Fault location system for radial MV underground distribution cable networks. Ann Conf Protect Rel
Khond SV, Dhomane GA (2019) Optimum coordination of directional overcurrent relays for combined overhead/cable distribution system with linear programming technique. Protect Control Mod Power Syst 4(1):9. https://doi.org/10.1186/s41601-019-0124-6
Park JM, Jeon JC, Han GR (2019) New approach in partial discharge diagnosis and maintenance of 22.9 kV XLPE power cables in service. Electr Eng. https://doi.org/10.1007/s00202-019-00837-2
Xu ZH, Sidhu TS (2011) Fault location method based on single-end measurements for underground cables. IEEE Trans Power Deliv 26(4):2845–2854. https://doi.org/10.1109/Tpwrd.2011.2167721
Chen HC (2012) Fractal features-based pattern recognition of partial discharge in XLPE power cables using extension method. IET Gener Transm Distrib 6(11):1096–1103. https://doi.org/10.1049/iet-gtd.2012.0080
Sidhu TS, Xu ZH (2010) Detection of incipient faults in distribution underground cables. IEEE Trans Power Delivery 25(3):1363–1371. https://doi.org/10.1109/Tpwrd.2010.2041373
Zhang WH, Xiao XY, Zhou K, Xu W, Jing YD (2017) Multicycle incipient fault detection and location for medium voltage underground cable. IEEE Trans Power Delivery 32(3):1450–1459. https://doi.org/10.1109/Tpwrd.2016.2615886
Dong X, Yang Y, Zhou CK, Hepburn DM (2017) Online monitoring and diagnosis of HV cable faults by sheath system currents. IEEE Trans Power Deliv 32(5):2281–2290. https://doi.org/10.1109/Tpwrd.2017.2665818
Yuan YL, Zhong W, Dong J, Shi YC, Mu Y, Tang ZY, Zhou CK (2015) Sheath current in HV cable systems and its on-line monitoring for cable fault diagnosis. High Volt Eng 41(4):1194–1203. https://doi.org/10.13336/j.1003-6520.hve.2015.04.017
Zhang C, Kang XN, Ma XD, Jiang S, Qu XY (2016) On-line incipient faults detection in underground cables based on single-end sheath currents. Asia-Pac Power Energ:795–799
Kwon GY, Lee CK, Shin YJ (2019) Diagnosis of shielded cable faults via regression-based reflectometry. IEEE Trans Ind Electron 66(3):2122–2131. https://doi.org/10.1109/Tie.2018.2840529
Wang Y, Lu H, Yang XM, Xiao XY, Zhang WH (2018) Cable incipient fault identification based on stacked autoencoder and S-transform. Electric Power Autom Equip 38(8):117–124. https://doi.org/10.16081/j.issn.1006-6047.2018.08.017
Deng JY, Zhang WH, Yang XM (2019) Recognition and classification of incipient cable failures based on variational mode decomposition and a convolutional neural network. Energies 12 (10). https://doi.org/10.3390/en12102005
Chi P, Zhang Z, Liang R, Cheng C, Chen SK (2020) A CNN recognition method for early stage of 10 kV single core cable based on sheath current. Electric Power Syst Res. https://doi.org/10.1016/j.epsr.2020.106292
Qin XB, Zhang YZ, Mei W, Dong G, Gao J, Wang P, Deng J, Pan HG (2018) A cable fault recognition method based on a deep belief network. Comput Electr Eng 71:452–464. https://doi.org/10.1016/j.compeleceng.2018.07.043
Zhang S, Lin S, Tang J, He ZY (2016) Fault location of self-clearing fault in three phase single core cables based on double impedance model. Trans China Electrotech Soc 17(31):1–10. https://doi.org/10.3969/j.issn.1000-6753.2016.17.001
Zhou WJ, Yang Y, Wei LJ, Zhou CK et al (2016) Separation method of leakage current in cross-bonded cables and its application in on-line monitoring relative change of dielectric loss between phases. High Volt Eng 02(42):468–477. https://doi.org/10.13336/j.1003-6520.hve.2016.02.018
Jiao LC (2017) Deep learning, optimizations and recognition. Tsinghua University Press, Beijing
Wang Y, Gan DH, Sun MY, Zhang N, Lu ZX, Kang CQ (2019) Probabilistic individual load forecasting using pinball loss guided LSTM. Appl Energy 235:10–20. https://doi.org/10.1016/j.apenergy.2018.10.078
Zheng HT, Yuan JB, Chen L (2017) Short-term load forecasting using EMD-LSTM neural networks with a Xgboost algorithm for feature importance evaluation. Energies 10 (8). https://doi.org/10.3390/en10081168
Dai JJ, Song H, Sheng GH (2018) Prediction method for power transformer running state based on LSTM network. High Volt Eng 44:1099–1106
Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: The 3rd international conference for learning representations
Duan JD, Chen TX, Zhang BH, Yang XX (2005) Simulation of online monitoring of power cable insulation using grounding current method. High Volt Appar 41(1):29–31+35. https://doi.org/10.13296/j.1001-1609.hva.2005.01.011
Aloui T, Ben Amar F, Abdallah HH (2013) Fault prelocalization of underground single-phase cables: modeling and simulation. Int J Elect Power Energy Syst 44(1):514–519. https://doi.org/10.1016/j.ijepes.2012.07.067
Acknowledgements
This work was supported by Natural Science Foundation of Jiangsu Province (No. BK20201348) and the Postgraduate Research & Practice Innovation Program of Jiangsu Province.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no known competing financial interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chi, P., Zhang, Z., Liang, R. et al. A fault diagnosis method of double-layer LSTM for 10 kV single-core cable based on multiple observable electrical quantities. Electr Eng 104, 603–614 (2022). https://doi.org/10.1007/s00202-021-01324-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00202-021-01324-3