Circuit breaker voiceprint and vibration entropy feature fusion fault diagnosis method
A technology of feature fusion and fault diagnosis, applied in the testing of machines/structural components, instruments, genetic rules, etc., can solve the problem of insufficient diagnostic accuracy, improve generalization performance, reduce misdiagnosis and missed diagnosis, and improve accuracy Effect
- Application Information
AI Technical Summary
Problems solved by technology
 see figure 1 , figure 1 It is a schematic flow chart of a fault diagnosis method for fusion of circuit breaker voiceprint and vibration entropy features in the implementation of the present invention.
 Such as figure 1 As shown, a fault diagnosis method for circuit breaker voiceprint and vibration entropy feature fusion, the method includes:
 S11: Perform band-pass filtering on the sound signal, and obtain roughness, box dimension, directionality, contrast, linearity and regularity reflecting time-frequency texture characteristics through generalized S-transformation;
 In the specific implementation process of the present invention, the band-pass filtering is carried out to the sound signal, and through the generalized S transform, the roughness, box dimension, directionality, contrast, linearity and regularity reflecting the time-frequency texture characteristics include: According to the frequency band characteristics of the sound signal of ...
specific Embodiment approach
 In the specific implementation, taking the ZN65-12 circuit breaker as an example, the fault diagnosis process is as follows figure 2 shown, with figure 2 Show the circuit breaker fault diagnosis flowchart in the implementation of the present invention; The specific embodiment of the present invention is as follows:
 Step 1, use AC144 piezoelectric acceleration sensor (0.6-10000Hz) and NVL-AF-aduio to embed waterproof (storm) high-fidelity pickup (20-20000Hz), in which the vibration sensor is adsorbed to the circuit breaker body, and the sound sensor is placed 50cm away from the sound source; collect multiple sets of sound wave and vibration sample signals under the circuit breaker mechanism jamming, loose base, connecting rod falling off, voltage fluctuation and normal state;
 In the second step, the frequency band noise of the sound signal below 3kHz and above 15kHz is filtered out by a finite-length unit impulse response (FIR) bandpass filter, and t...
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction