Leakage sound emission signal identification method based on multi-scale morphological decomposition energy spectrum entropy and support vector machine
An acoustic emission signal and support vector machine technology, which is applied in character and pattern recognition, computer parts, instruments, etc., can solve the problems of detection and classification of leaked acoustic emission signals, leaked acoustic emission signals, etc., and achieves strong resolution ability and correct identification. high rate effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0038] Example 1: Such as Figure 1-7 As shown, a method for identifying leakage acoustic emission signals based on multi-scale morphological decomposition energy spectrum entropy and support vector machine, first adopts a digital acoustic emission system to collect experimental data; performs multi-scale morphological decomposition on the collected analog leakage acoustic emission signals, respectively Calculate its spectral energy on different scales, and calculate the energy spectrum entropy; then calculate the proportion of energy spectrum entropy that each scale occupies, and compose the feature vector; finally use the support vector machine to train and test the feature vector.
[0039] The specific steps of the method are as follows:
[0040] Step1. Acoustic emission signal acquisition: N groups of analog leakage acoustic emission signals are collected through the digital acoustic emission system, and the signals are denoted as f(x);
[0041] Step2. The structure element adop...
Example Embodiment
[0046] Example 2: Such as Figure 1-7 As shown, a method for identifying leakage acoustic emission signals based on multi-scale morphological decomposition energy spectrum entropy and support vector machine, first uses a digital acoustic emission system for experimental data collection; performs multi-scale morphological decomposition on the collected analog leakage acoustic emission signals, respectively Calculate its spectral energy on different scales, and calculate the energy spectrum entropy; then calculate the proportion of energy spectrum entropy that each scale occupies, and compose the feature vector; finally, use the support vector machine to train and test the feature vector.
[0047] The specific steps of the method are as follows:
[0048] Step1. Acoustic emission signal acquisition: N groups of analog leakage acoustic emission signals are collected through the digital acoustic emission system, and the signals are denoted as f(x);
[0049] Step2. The structure element a...
Example Embodiment
[0053] Example 3: Such as Figure 1-7 As shown, a method for identifying leakage acoustic emission signals based on multi-scale morphological decomposition energy spectrum entropy and support vector machine, first uses a digital acoustic emission system for experimental data collection; performs multi-scale morphological decomposition on the collected analog leakage acoustic emission signals, respectively Calculate its spectral energy on different scales, and calculate the energy spectrum entropy; then calculate the proportion of energy spectrum entropy that each scale occupies, and compose the feature vector; finally use the support vector machine to train and test the feature vector.
[0054] The simulated leakage acoustic emission signal selects any two or more of the simulated leakage acoustic emission signals of percussion, sandpaper and lead breaking.
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.
© 2023 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap