Substation equipment sound and voice identification method
A technology of power transformation equipment and recognition methods, applied in speech recognition, speech analysis, instruments, etc., to achieve the effect of ensuring life safety
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0059] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0060] The invention utilizes the principle of acoustics and combines the inherent properties of sound generation to extract the Fourier spectrum of the power frequency multiple of the sound to be tested and the equipment sound spectrum at the non-power frequency multiple to form a feature vector, and uses the SVM classifier to perform equipment sound and voice recognition analyze.
[0061] When the sound signal from the object is collected, the digital signal processing method can be used for signal analysis. When digitizing, the most intuitive way to understand a sound signal is to look at the signal's time-domain waveform. figure 2 and image 3 Time-domain waveform diagrams for substation sounds and voices. Although the time domain waveform is simple and intuitive, the complex sound signal cannot show its unique characteristics in the time domain...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap