Rolling bearing health condition evaluation method based on CFOA-MKHSVM
A rolling bearing and health state technology, applied in the field of rolling bearing health state assessment, can solve the problems of evaluating the rolling bearing health state, large overlapping range, and inability to correctly evaluate the bearing's deep degradation state.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0064] Specific implementation manner one: such as figure 1 As shown, the CFOA-MKHSVM-based rolling bearing health assessment method described in this embodiment is implemented according to the following steps:
[0065] Step 1. Obtain the vibration data of the rolling bearing's life cycle and divide it into two parts, one as the training sample and the other as the test sample, and the number of training samples is greater than the test sample;
[0066] Step 2: Build the CFOA-MKHSVM model:
[0067] Step 2: Feature extraction:
[0068] Extract time-domain statistical indicators, frequency-domain statistical indicators, and time-frequency indicators of wavelet packet-related frequency band spectrum energy entropy from the training samples (this technical means is the prior art, refer to the literature [19-21]) as feature indicators, each training sample The extracted feature indicators constitute the training feature vector, and all the training feature vectors form the training vector...
Example Embodiment
[0109] Specific implementation manner 2: This implementation manner is: in step 2, the chaotic sequence is based on the chaotic mapping iteration values generated by 5 one-dimensional chaotic systems of Logistic, Tent, Chebyshev, Circle, and Gauss, which are respectively mapped to CFOA Within the range of the optimized 5 parameters, the chaotic value after mapping is constructed into a 5×5 matrix, and then it is used for iterative optimization. The other steps are the same as in the first embodiment.
Example Embodiment
[0110] Specific implementation manner 3: This implementation manner is: in step two and four, the training accuracy rate is the accuracy rate obtained after 10-fold cross-validation of the training samples;
[0111] The calculation formula of its training accuracy rate:
[0112] The other steps are the same as the first or second embodiment.
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