Gear Performance Degradation Evaluation Method Based on AR Model and Dictionary Learning
An AR model and dictionary learning technology, applied in design optimization/simulation, character and pattern recognition, instruments, etc., can solve problems such as premature saturation, complex probabilistic similarity measurement evaluation method model, etc., to reduce data dimension and prevent major Sudden accidents, the effect of reducing the cost of downtime
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0042] Such as figure 1It is an evaluation flow chart of the present invention, a gear performance degradation evaluation method based on AR model and dictionary learning, and the specific steps are:
[0043] (1) Feature extraction: the first 35 non-fault samples are expanded by cyclic shifting to expand the sample data, and each reference sample segment is expanded to 10 sample segments after being cyclically shifted 10 times, and 350 sample segments are obtained after expansion. Trouble-free samples. 350 fault-free samples and 120 samples to be tested in the whole life cycle of gears are used to establish an AR model, and the AR model is used to extract autoregressive coefficients and residuals. The order of the AR model is determined to be 80 by the BIC criterion, and the coefficients of the AR model are used as input features vector.
[0044] (2) Modeling: the main parameters of dictionary learning are set to be: dictionary atom dimension n=80, dictionary atom number K=2...
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