Research on Application and Optimization of Intelligent Diagnosis Technology in Power Line Loss Management
DOI:
https://doi.org/10.13052/dgaej2156-3306.4111Keywords:
Intelligent diagnosis, Power line loss management, Distributed computing, Federated Learning, Digital TwinAbstract
Power line loss management faces challenges such as massive data processing, real-time diagnosis accuracy, data security guarantee and system adaptive optimisation. It is urgent to improve diagnosis efficiency and management effect by applying and optimising intelligent diagnosis technology. This paper systematically studies the application and optimization of intelligent diagnosis technology in power line loss management. It constructs a multi-level diagnosis system integrating multiple technologies, where distributed streaming computing enables real-time processing of massive time-series data from smart meters and SCADA systems; trusted computing mechanism ensures data security through hardware-level authentication; spatiotemporal graph neural network models the spatiotemporal correlation of power grid nodes; federated learning realizes collaborative model optimization without data sharing; multi-objective evolutionary optimization improves parameter tuning efficiency; and digital twin achieves dynamic mapping of physical grid operations for continuous learning. According to the data of 200 monitoring points in this area, through the analysis of the intelligent diagnosis system, it is found that 23.5% of monitoring points have abnormal line loss fluctuations in varying degrees, 78.2% of the fluctuations are due to poor contact caused by equipment ageing, and normal equipment loss accounts for only 45%. After accurate positioning using intelligent diagnosis technology and targeted repair, the power line loss rate in this area decreased by 67.89%. In comparison, the meter reading accuracy increased from 32.1% to 90.5%, and the processing efficiency of abnormal work orders increased by 12.34 times, effectively reducing manual operation and maintenance costs, saving about 56.7% of operation and maintenance time, and providing strong data support and technical support for power line loss management.
Downloads
References
A. R. Abbasi, “Statistical techniques in power systems fault diagnostic: Classifications, challenges, and strategic recommendations,” Electric Power Systems Research, vol. 239, 2025.
M. E. Abed, H. Hadi, M. E. Slama, A. W. Belarbi, and N. Zekri, “Experimental investigation on dielectric/electric properties of aged polymeric insulator: correlation of permittivity and dielectric loss tangent with surface hydrophobicity,” Electrical Engineering, vol. 104, no. 3, pp. 1539–1552, 2022.
O. A. Alimi, K. Ouahada, A. M. Abu-Mahfouz, and S. Rimer, “Power system events classification using genetic algorithm based feature weighting technique for support vector machine,” Heliyon, vol. 7, no. 1, 2021.
F. M. Almasoudi, “Enhancing Power Grid Resilience through Real-Time Fault Detection and Remediation Using Advanced Hybrid Machine Learning Models,” Sustainability, vol. 15, no. 10, 2023.
I. Austrup, C. H. van der Broeck, S. Kalker, T. B. Albert, F. Janoth, and R. W. De Doncker, “Diagnosing Thermal-Interface Aging of Power Devices Using Self-Sensing,” Ieee Transactions on Power Electronics, vol. 40, no. 3, pp. 4386–4398, 2025.
I. V. Bryakin, I. V. Bochkarev, V. R. Khramshin, V. R. Gasiyarov, and I. V. Liubimov, “Power Transformer Condition Monitoring Based on Evaluating Oil Properties,” Machines, vol. 10, no. 8, 2022.
W. Cheng et al., “Diagnostics and Prognostics in Power Plants: A systematic review,” Reliability Engineering & System Safety, vol. 255, 2025.
P. Chi, R. Liang, C. C. Hao, G. C. Li, and M. Xin, “Cable fault diagnosis with generalization capability using incremental learning and deep convolutional neural network,” Electric Power Systems Research, vol. 241, 2025.
M. Dhimish, “Defining the best-fit machine learning classifier to early diagnose photovoltaic solar cells hot-spots,” Case Studies in Thermal Engineering, vol. 25, 2021.
R. El Abbadi, M. Aatabe, and A. E. Bouzid, “Wireless Diagnosis and Control of DC-DC Converter for Off-Grid Photovoltaic Systems,” Sustainability, vol. 16, no. 8, 2024.
K. H. Fanchiang, Y. C. Huang, and C. C. Kuo, “Power Electric Transformer Fault Diagnosis Based on Infrared Thermal Images Using Wasserstein Generative Adversarial Networks and Deep Learning Classifier,” Electronics, vol. 10, no. 10, 2021.
J. D. Gotz, J. R. Galvao, S. H. Werlich, A. M. da Silveira, F. C. Correa, and M. Borsato, “Reducing the Capacity Loss of Lithium-Ion Batteries with Machine Learning in Real-Time-A Study Case,” Machines, vol. 10, no. 12, 2022.
M. Hadizadeh-Bazaz, I. J. Navarro, and V. Yepes, “Power spectral density method performance in detecting damages by chloride attack on coastal RC bridge,” Structural Engineering and Mechanics, vol. 85, no. 2, pp. 197–206, 2023.
D. Hyun, T. J. Kang, and J. Kim, “Fault Diagnosis of Belt Driving Power Transfer Facility Using Vibration Analysis,” Journal of Electrical Engineering & Technology, vol. 16, no. 4, pp. 2257–2264, 2021.
Z. Y. Kang, S. M. Alia, M. Carmo, and G. Bender, “In-situ and in-operando analysis of voltage losses using sense wires for proton exchange membrane water electrolyzers,” Journal of Power Sources, vol. 481, 2021.
G. G. Kim, W. Lee, B. G. Bhang, J. H. Choi, and H. K. Ahn, “Fault Detection for Photovoltaic Systems Using Multivariate Analysis With Electrical and Environmental Variables,” Ieee Journal of Photovoltaics, vol. 11, no. 1, pp. 202–212, 2021.
J. Kim, S. H. Lee, and K. Park, “Numerical modelling of an air operated valve assembly for virtual diagnosis based on experimental diagnosis in nuclear power plants,” Nuclear Engineering and Technology, vol. 57, no. 6, 2025.
M. Kim, J. U. Ko, J. Lee, B. D. Youn, J. H. Jung, and K. H. Sun, “A Domain Adaptation with Semantic Clustering (DASC) method for fault diagnosis of rotating machinery,” Isa Transactions, vol. 120, pp. 372–382, 2022.
X. M. Li and J. Y. Sun, “A novel method for diagnosing rolling bearing faults based on the frequency spectrum distribution of the modulation signal,” Measurement Science and Technology, vol. 33, no. 8, 2022.
Z. Y. Li, K. Ryu, and S. Sohn, “Diagnostic Test of the 400-m 22.9-kV 3-Phase YBCO Cable through Single-Phase Transport Method,” Ieee Transactions on Applied Superconductivity, vol. 35, no. 2, 2025.
T. Lin, X. J. Li, Z. C. Zhu, J. Xie, Y. Li, and H. Yang, “Application of enstrophy dissipation to analyze energy loss in a centrifugal pump as turbine,” Renewable Energy, vol. 163, pp. 41–55, 2021.
K. Y. Liu, D. L. Jia, Z. J. Kang, and L. Luo, “Anomaly Detection Method of Distribution Network Line Loss Based on Hybrid Clustering and LSTM,” Journal of Electrical Engineering & Technology, vol. 17, no. 2, pp. 1131–1141, 2022.
B. C. Mateus, J. T. Farinha, and M. Mendes, “Fault Detection and Prediction for Power Transformers Using Fuzzy Logic and Neural Networks,” Energies, vol. 17, no. 2, 2024.
H. Mou, Y. Z. Jin, J. Yang, X. Xia, and Y. L. Fu, “Interaction between plasma and electromagnetic field in ion source of 10 cm ECR ion thruster,” Chinese Physics B, vol. 31, no. 7, 2022.
A. M. Mwaura and Y. K. Liu, “Prediction of the Loss of Feed Water Fault Signatures Using Machine Learning Techniques,” Science and Technology of Nuclear Installations, vol. 2021, 2021.
L. Ning and D. F. Pei, “Power line fault diagnosis based on convolutional neural networks,” Heliyon, vol. 10, no. 8, 2024.
J. Obra and S. Miwa, “Loss of coolant accident monitoring and pipe break diagnosis in pressurized water reactors using Bayesian-optimized long short-term memory models,” Engineering Applications of Artificial Intelligence, vol. 149, 2025.
S. Praveena and K. Senthilnathan, “Ultra Low Loss Dual Square Groove Incorporated SPR-Based PCF Sensor for Malaria Diagnosis,” Plasmonics, 2024.
R. Prosser, G. Offer, and Y. Patel, “Lithium-Ion Diagnostics: The First Quantitative In-Operando Technique for Diagnosing Lithium Ion Battery Degradation Modes under Load with Realistic Thermal Boundary Conditions,” Journal of the Electrochemical Society, vol. 168, no. 3, 2021.
S. Rajamand, “Analysis of effect of physical parameters on the performance of lead acid battery as efficient storage unit in power systems using new finite-element-method-based model,” Journal of Energy Storage, vol. 47, 2022.
