Fault diagnosis method and system for converter transformer on-load tap changer
By processing the vibration signal of the on-load tap changer of the converter transformer using a stochastic resonance model and the Cuckoo optimization algorithm, converting it into a three-dimensional Hilbert spectrum and calculating the distortion rate, the problem of insufficient diagnostic accuracy and physical interpretability in the existing technology is solved, and efficient fault identification and differentiation are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- STATE GRID ANHUI ULTRA HIGH VOLTAGE CO
- Filing Date
- 2026-04-24
- Publication Date
- 2026-07-21
AI Technical Summary
Existing technologies lack sufficient physical interpretability and diagnostic accuracy in the fault diagnosis of on-load tap changers in converter transformers, making it difficult to effectively distinguish between similar faults.
The vibration signal is denoised using a stochastic resonance model and converted into a three-dimensional Hilbert spectrum. The Gaussian curvature and normal vector are calculated, and fault diagnosis is performed using the distortion rate. The stochastic resonance model parameters are optimized using the Cuckoo optimization algorithm.
It improves the accuracy and physical interpretability of fault diagnosis, enables more precise identification of fault types in on-load tap changers, and enhances adaptability to non-stationary transient signals and noise interference resistance.
Smart Images

Figure CN122430680A_ABST
Abstract
Citation Information
Patent Citations
Mechanical fault diagnosis method for on-load tap-changer of transformer
CN113553930A
Mechanical fault diagnosis method based on minimum entropy deconvolution and stochastic resonance
CN115655706A
Bearing fault diagnosis method based on adaptive fractional order stochastic resonance
CN115931356A