The deep learning algorithm in intelligent fault diagnosis and rapid recovery strategy of the power network
1
Inner Mongolia Power Digital Research Institute, Hohhot 010000, Inner Mongolia, China
Submission date: 2025-08-20
Final revision date: 2026-04-27
Acceptance date: 2026-06-15
Online publication date: 2026-06-17
Publication date: 2026-06-17
Corresponding author
KEYWORDS
TOPICS
ABSTRACT
With the expansion of smart grid scale and the complication of topological structure, traditional fault diagnosis and recovery methods have significant limitations in handling multimodal time-series data, anti-noise performance, and dynamic adaptability. To this end, this study applies the proposed deep learning (DL) algorithm to intelligent fault diagnosis and rapid recovery strategies in the power network. In the fault recovery stage, it combines the model's secondary judgment of fault status and reconstruction information completion to assist in generating dynamic recovery strategies, forming an integrated solution. Experimental results demonstrate that the proposed model achieves a fault diagnosis accuracy of 97.8%, with an average diagnosis time of 11.3 milliseconds, and the recognition accuracy for typical faults exceeds 93%. In a 5-decibel strong noise environment, its accuracy still reaches 78.4%, showing excellent anti-noise performance. The research results confirm that the integrated application of a DL algorithm can effectively improve the accuracy and efficiency of power network fault diagnosis. Moreover, it can optimize the generation of recovery strategies and provide technical support for the safe and stable operation of smart grids.
FUNDING
This research received no external funding.
REFERENCES (32)
1.
Singh RA, Sujatha SM, Kadu DA, Addis HK, Sarada K. A deep learning and IoT-driven framework for real-time adaptive resource allocation and grid optimization in smart energy systems. Sci Rep. 2025;15(1):19309. https://doi.org/10.1038/s41598....
2.
Sinneh SI, Sun Y. Optimizing smart nano grid control strategies through virtual environment and hybrid deep learning approaches. Renew Energy Focus. 2025;54:100712. https://doi.org/10.1016/j.ref.....
3.
Ciaramella G, Martinelli F, Santone A, Mercaldo F. A method for smart grid intrusion detection through explainable deep learning. J Comput Virol Hacking Tech. 2025;21(1):9. https://doi.org/10.1007/s11416....
4.
Goh HH, Xu H, Zhang D, et al. Classification and detection of direct current power quality disturbances for grid operation implications using deep learning models. Eng Appl Artif Intell. 2025;163(Pt 1):112644. https://doi.org/10.1016/j.enga....
5.
Ziad H, Al-Dujaili A, Humaidi AJ. Electrical faults classification in permanent magnet synchronous motor using ResNet neural network. Int Rev Appl Sci Eng. 2024;15(3):355-364. https://doi.org/10.1556/1848.2....
6.
Gao Z, Gao G, Liu C, et al. TNet: Power pole classification with deep learning for automated inspection in smart grids. Int J Pattern Recognit Artif Intell. 2025;39(10):25550134. https://doi.org/10.1142/S02180....
7.
Ziad H, Al-Dujaili AQ, Humaidi AJ. A comparative study of deep learning efficiency in the classification of electrical faults of permanent magnet synchronous motor. Int Rev Appl Sci Eng. 2025;16(2):292-302. https://doi.org/10.1556/1848.2....
8.
Niu B, Wei Y, Yu Z, et al. Acoustic signal augmentation for fault diagnosis of power transformers based on improved cycle generative adversarial networks. Expert Syst Appl. 2025;288:127997. https://doi.org/10.1016/j.eswa....
9.
Zhang J, Cheng L, Yang Z, et al. An enhanced semi-supervised learning method with self-supervised and adaptive threshold for fault detection and classification in urban power grids. Energy AI. 2024;17:100377. https://doi.org/10.1016/j.egya....
10.
Xue H, Yao N, Fan Q, et al. Analysis of power system signal processing method based on deep convolutional neural network. Int J High Speed Electron Syst. 2024;34:24540223. https://doi.org/10.1142/S01291....
11.
Alsamraee AS, Khanna S. Long-term electricity demand forecasting of a university campus based on advanced deep learning artificial neural network algorithms. Results Eng. 2025;27:106683. https://doi.org/10.1016/j.rine....
12.
Lee B, Kim Y, Lee H, et al. Bidirectional gated recurrent unit neural network for fault diagnosis and rapid maintenance in medium-voltage direct current systems. Sensors. 2025;25(3):693. https://doi.org/10.3390/s25030....
13.
Mei L. Improved system model for fault classification and diagnosis of power system based on artificial intelligence and BP neural network and its application. J Electr Eng Technol. 2025:1-16. https://doi.org/10.1007/s42835....
14.
Peter MV, Okpura IN, Udofia MK. Intelligent fault diagnosis in 330 kV power networks using SVM and ANN techniques: Case of the Onitsha-New Haven route. J Eng Res Rep. 2025;27(6):83-96. https://doi.org/10.9734/jerr/2....
15.
Jiang L, Li C, Qiu W, et al. Research on short-term line loss rate prediction method of distribution network based on RF-CNN-LSTM. Front Smart Grids. 2025;4:1612770. https://doi.org/10.3389/frsgr.....
16.
Liu J, Zang H, Ding T, et al. A principle-constrained wind field image generation framework for short-term wind power forecasting. IEEE Trans Power Syst. 2024. https://doi.org/10.1109/TPWRS.....
17.
Bedoui M, Berkani A, Negadi K, Marignetti F, Drias S. Practical measurement of automatic power factor detection and correction using smart Arduino in three-phase distribution networks. Instrum Mes Metrol. 2025;24(1):1-8. https://doi.org/10.18280/i2m.2....
18.
Alhanaf AS, Farsadi M, Balik HH. Fault detection and classification in ring power system with DG penetration using hybrid CNN-LSTM. IEEE Access. 2024;12:59953-59975. https://doi.org/10.1109/ACCESS....
19.
Vadivelan DS, Sethuramalingam P. A hybrid approach for EEG motor imagery classification using adaptive margin disparity and knowledge transfer in convolutional neural networks. Comput Biol Med. 2025;195:110675. https://doi.org/10.1016/j.comp....
20.
Adekunle AA, Fofana I, Picher P, et al. Multiclass fault diagnosis in power transformers using dissolved gas analysis and grid search-optimized machine learning. Energies. 2025;18(13):3535. https://doi.org/10.3390/en1813....
21.
Boutkhil M, Guemmour, Negadi K, Araria R, Bey M. Analysis and fault diagnosis in point absorber wave energy conversion systems using fault tree and Bayesian networks. Diagnostyka. 2025;26(2):2025209. https://doi.org/10.29354/diag/....
22.
Srividhya PJ, Prabha LEK, Jaisiva S, et al. Power quality enhancement in smart microgrid system using convolutional neural network integrated with interline power flow controller. Electr Eng. 2024;106(6):1-24. https://doi.org/10.1007/s00202....
23.
Zare A, Simab M, Nafar M, et al. A novel method for fault diagnosis in photovoltaic arrays used in distribution power systems. Energy Syst. 2024:1-35. https://doi.org/10.1007/s12667....
24.
Liang B, Sun Z, Yang Z, et al. Data augmentation and optimization method based on conditional generative adversarial network and convolutional neural network for transformer fault diagnosis. Measurement. 2025;254:117872. https://doi.org/10.1016/j.meas....
25.
Liu J, Cai Y. Comparative analysis of switching power supply fault diagnosis model based on particle swarm optimization and convolutional neural network. J Phys Conf Ser. 2024;2902(1):012018. https://doi.org/10.1088/1742-6....
26.
Poongothai K, Kumaresan M, Ananda M, et al. Power transmission line fault detection in internet of things based smart grids using relational bi-level aggregation graph convolutional network-red panda optimization approach. Measurement. 2025;256:118448. https://doi.org/10.1016/j.meas....
27.
Alkhanafseh Y, Akinci CT, Morales MAA, et al. MH-WMG: A multi-head wavelet-based MobileNet with gated linear attention for power grid fault diagnosis. Appl Sci. 2025;15(20):10878. https://doi.org/10.3390/app152....
28.
Mampilly JB, Sheeba SV. An empirical wavelet transform based fault detection and hybrid convolutional recurrent neural network for fault classification in distribution network integrated power system. Multimed Tools Appl. 2024;83(32):77445-77468. https://doi.org/10.1007/s11042....
29.
Hamid M, Ahmad K, Rahman D, et al. Deep learning-based fault location framework in power distribution grids employing convolutional neural network based on capsule network. Electr Power Syst Res. 2023;223:109529. https://doi.org/10.1016/j.epsr....
30.
Shaohua Q, Xiaopeng C, Zuowei P, et al. Deep learning techniques in intelligent fault diagnosis and prognosis for industrial systems: A review. Sensors. 2023;23(3):1305. https://doi.org/10.3390/S23031....
31.
Zouari F. Robust neural adaptive control for a class of uncertain nonlinear complex dynamical multivariable systems. Int Rev Model Simul. 2012;5:2075-2103.
32.
Kouraichi M, Mansouri M, Trabelsi M, et al. Deep learning for fault diagnosis in power transmission lines: Current trends, limitations, and future directions. IEEE Access. 2025;13:192105-192142. https://doi.org/10.1109/ACCESS....
| eISSN: | 2449-5220 |
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.
