Transformer fault detection method and device based on sound signal
By acquiring the target sound signal and leakage flux signal of the transformer, the phase deviation and frequency coupling relationship are determined, and fault detection is performed by combining time and frequency characteristics. This solves the problem of inaccurate transformer fault detection and realizes accurate analysis of transformer fault status.
CN122283537APending Publication Date: 2026-06-26STATE GRID BEIJING ELECTRIC POWER CO
View PDF 0 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN Β· China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- STATE GRID BEIJING ELECTRIC POWER CO
- Filing Date
- 2026-05-15
- Publication Date
- 2026-06-26
AI Technical Summary
Technical Problem
In existing technologies, fault detection of transformers using sound signals suffers from inaccurate fault detection.
Method used
By acquiring the target sound signal and leakage flux signal of the transformer, the phase deviation and frequency coupling relationship between the signals are determined. Fault detection is performed by combining time and frequency characteristics. Signal denoising and signal compensation are performed by using a multi-sensor array and noise sensor to obtain a high-fidelity, pure target sound signal.
Benefits of technology
It realizes multi-dimensional feature collaborative analysis of transformer fault detection, improves the accuracy of fault detection, and can comprehensively depict the fault state of transformer.
β¦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN122283537A_ABST
Abstract
This invention discloses a method and apparatus for transformer fault detection based on sound signals. The method includes: acquiring a target sound signal and a leakage flux signal of the transformer; determining the phase deviation between the target sound signal and the leakage flux signal based on the fundamental frequency of the target sound signal and the fundamental frequency of the leakage flux signal; determining the frequency coupling relationship between the leakage flux signal and the target sound signal; extracting the time-frequency features of the target sound signal; and determining the transformer fault detection result based on the phase deviation, frequency coupling relationship, and time-frequency features. This invention solves the technical problem of inaccurate fault detection in related technologies when using sound signals to detect transformer faults.
Need to check novelty before this filing date? Find Prior Art