Wind turbine generator bearing early warning method based on feature fusion
A generator bearing and feature fusion technology, applied in the testing of mechanical components, testing of machine/structural components, instruments, etc., can solve problems such as inaccurate fault judgment, weak generalization ability, and single fault identification method
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0086] Embodiment: A kind of wind turbine generator bearing early warning method based on feature fusion in this embodiment, such as figure 1 shown, including the following steps
[0087] Step 1: Feature Fusion. Preprocess the CMS data, screen the data of the stable operation of the generator, and eliminate the low-precision and unstable data to obtain the effective data of the unit operation. From the four dimensions of vibration trend, time-domain features, frequency-domain features, and envelope features, the characteristics of the generator's operating state can be characterized. A total of 25 features form a feature vector for fusion. Mark the eigenvectors according to the normal, generator bearing damage, and generator bearing loose running circles;
[0088] Step 2: Fault warning. The Extreme Gradient Boosting (XGBoost) algorithm is used to train the generator bearing case data to obtain the XGBoost early warning model. For the data collected online, the feature fusi...
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