Intelligent Diagnosis Method for Partial Discharge of Substation Equipment Based on Multi-Source Sensor Data Fusion

View at publisher Summarise with VIRAT
Authors: Yongde Pan, Tuo Li, Hao Guo
Cited by: 0
References: 7

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Partial discharge (PD) is one of the key indicators reflecting the insulation degradation of substation equipment, and its accurate diagnosis is crucial to ensure the safe and stable operation of the power grid. Aiming at the problems of single sensor data limitation, low diagnosis accuracy and poor antiinterference ability in traditional PD diagnosis methods, an intelligent diagnosis method for PD of substation equipment based on multi-source sensor data fusion is proposed. First, multi-source sensors (ultrasonic, ultra-high frequency, transient earth voltage, etc.) are used to collect PD characteristic data, and a series of preprocessing operations such as denoising, normalization and feature extraction are performed on the original data to construct a multi-dimensional feature set. Then, a multi-level data fusion framework is designed, which integrates data-level fusion based on improved wavelet transform, feature-level fusion based on attention mechanism and decision-level fusion based on D-S evidence theory. Finally, a hybrid intelligent diagnosis model combining deep residual network (ResNet) and support vector machine (SVM) is established to realize the accurate identification of PD types. The experimental results show that compared with the traditional single-source data diagnosis method and single intelligent algorithm, the proposed method has higher diagnosis accuracy, stronger anti-interference ability and better generalization performance. It can effectively identify different types of PD defects of substation equipment, providing a reliable technical support for the condition-based maintenance of power systems.

Fields of Study & Subjects

High voltage insulation and dielectric phenomena Power Transformer Diagnostics and Insulation Electrical Fault Detection and Protection

Publication details

Journal / source
International Conference on Electrical Automation and Artificial Intelligence (ICEAAI)
Pages
1192–1196
Publication date
16 January 2026
Language
EN