journal article·2026-04-01Open access

The research on remote fault diagnosis system for substations based on deep learning

Ziqiang Guo, Tianyi Zhang, Qiang Song, Junwu Ma

AIP Advances· Volume 16· Issue 4

Abstract

Substation failures can trigger large-scale power outages and cause substantial economic losses. However, the scarcity of fault data forces existing substation failure detection methods to rely on single-modality information, thereby limiting their perceptual capabilities, while aggregating data from multiple substations for model training raises significant privacy concerns. To address these challenges, we propose a remote substation fault diagnosis framework. Specifically, we introduce S-informer, a model that integrates heterogeneous data modalities through a specialized encoder and a cross-modal attention mechanism for effective feature fusion. A multi-scale temporal attention module is incorporated to enhance the model’s ability to capture temporal dynamics. To tackle the class imbalance problem in fault data, we design a dual-path decoder architecture that performs normal-mode reconstruction and fault-mode classification. In addition, we develop a similarity-aware federated aggregation strategy that leverages inter-substation similarity metrics and incorporates differential privacy mechanisms, enabling privacy-preserving model training across distributed sites. Experimental results on a real-world dataset demonstrate that the proposed method achieves an accuracy improvement of 2.79% over the multimodal Informer, while reducing training time by 39.5% compared to FedAvg.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Power Systems Fault Detection · Smart Grid Security and Resilience · Advanced Data and IoT Technologies

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

State Grid Lanzhou Power Supply Company , Gansu Province, Lanzhou 730070,

References (17)

Show source-provided references
1. Solid-state power substations for future power grids10.1109/tia.2024.3477447 ↗
2. Integrated modeling for the transition pathway of China’s power system10.1039/d5ee00355e ↗
3. Real-time performance evaluation and optimization of electrical substation equipment inspection algorithm based on distributed computing10.1093/ijlct/ctae136 ↗
4. State-of-the-art fault detection and diagnosis in power transformers: A review of machine learning and hybrid methods10.1109/access.2025.3546861 ↗
5. Vision transformer-enhanced thermal anomaly detection in building facades through fusion of thermal and visible imagery10.1080/13467581.2024.2379866 ↗
6. A defect data compensation model for infrared thermal imaging based on Bi-LSTM with attention mechanism10.1007/s11837-024-06408-6 ↗
7. Graph autoencoder-based power attacks detection for resilient electrified transportation systems10.1109/tte.2024.3355094 ↗
8. An investigation of machine learning strategies for electric motor anomaly detection using vibration and audio signals10.1108/ec-03-2024-0206 ↗
9. Vibration signal-based fusion residual attention model for power transformer fault diagnosis10.1109/jsen.2024.3382811 ↗
10. Grid data analysis and load forecasting model based on federated learning technology and LSTM algorithm10.20532/cit.2025.1005946 ↗
11. Enhancing trust and privacy in distributed networks: A comprehensive survey on blockchain-based federated learning10.1007/s10115-024-02117-3 ↗
12. Accurate Fourier-space statistics for line intensity mapping: Cartesian grid sampling without aliased power10.1093/mnras/stae333 ↗
13. Short-term prediction of wind power based on temporal convolutional network and the informer model10.1049/gtd2.13064 ↗
14. Privacy-preserving distributed learning for residential short-term load forecasting10.1109/jiot.2024.3362587 ↗
15. Application of Hilbert transform for power quality indicators monitoring in general purpose grids10.15407/srenergy2024.02.071 ↗
16. Between privacy and utility: On differential privacy in theory and practice10.1145/3626494 ↗
17. Artificial neural network and support vector machine approach for locating faults in radial distribution systems10.1109/TPWRD.2005.844307 ↗