Rolling bearing fault detection method based on actual measurement signal
A rolling bearing and fault detection technology, which is applied in the direction of measuring devices, testing of mechanical components, testing of machine/structural components, etc., can solve the problems of difficulty in extracting fault features of bearing signals and low recognition accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0126] The actual fan bearing fault vibration data is used to construct a bearing fault vibration signal test set sample, and the rolling bearing fault detection method of the present invention is used to identify the fault state. It is proved by experiments that the present invention can not only accurately identify the fault status of fan bearings, but also effectively identify unknown fault type data without training samples.
[0127] The one-class support vector machine can be trained only with negative samples, and can accurately identify non-negative samples. Suppose there are samples {z i ,i=1,2,…N}, through the kernel function ψ is mapped to the high-dimensional feature space, so that it has better aggregation, and can solve an optimal hyperplane in the feature space to achieve the target data and coordinates Maximum separation of origins. Its decision function fsign(z)=sign(u·Ψ(z)-ρ), try to separate the sample set used for training from the origin, so that the dist...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com