GIS fault diagnosis method and system based on voiceprint imaging

[0054] refer to figure 1 , a GIS fault diagnosis method based on voiceprint imaging, which comprises the following steps:

[0055] S1, collecting the acoustic signal radiated by the GIS;

[0056] S2. Perform time-frequency analysis and feature extraction on the acoustic signal radiated by the GIS collected in step S1, and locate the position of the abnormal sound source;

[0057] S3. EMD decomposition is performed on the collected acoustic signal, and the one-dimensional spectral entropy of the decomposed IMF component is obtained as a training sample and substituted into the SVM model module to obtain the fault type;

[0058] S4. Perform visual processing on the fault diagnosis results obtained in steps S2 and S3, and simultaneously store and alarm.

[0059] SVM (Support Vector Machine, Support Vector Machine) is a typical supervised learning method in machine learning algorithms. The premise of implementing this method is to prepare a large number of training samples and extr

[0100] refer to figure 2 , a GIS fault diagnosis system based on voiceprint imaging, including:

[0101] The collection module 1 is used to collect the acoustic signal radiated by the GIS;

[0102] The imaging positioning module 2 is used to perform time-frequency analysis and feature extraction on the collected GIS radiated acoustic signal, and locate the location of the abnormal sound source;

[0103] The fault diagnosis module 3 is used to perform EMD decomposition on the collected acoustic signal, and obtain the one-dimensional spectral entropy of the decomposed IMF component, and substitute it into the SVM model module as a training sample to obtain the fault type;

[0104] The PC module 4 includes a display screen 41, a memory 42 and an alarm 43. The diagnostic results are visualized, and the fault diagnosis results obtained by the imaging positioning module 2 and the fault diagnosis module 3 are stored in the memory. If the fault diagnosis module judges that the GIS If