Wind turbine generator gearbox fault early warning method based on fusion model
A fusion model and fault early warning technology, applied in the field of data analysis, can solve problems such as failure to provide early warning information for operation and maintenance personnel, low model prediction accuracy, wind turbine fault early warning, etc., to control model complexity and reduce training time. , the effect of preventing overfitting phenomenon
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0024] like figure 1 Shown is a wind turbine gearbox fault early warning method based on fusion model, which specifically includes the following contents:
[0025] Step 1: Select the historical data of SCADA for one month, remove the variables containing "no data" and all state variables are "0", and then use the quartile principle to remove noise to obtain the data set;
[0026] Step 2: Normalize the data set, use the Pearson correlation coefficient to calculate the correlation with the gearbox temperature, remove redundant features, and obtain a sample set;
[0027] Step 3: First randomly select 80% of the data in the sample set to train the XGBoost model for the first time, optimize the parameters of the XGBoost model through grid search and cross-validation, and obtain the temperature prediction value y1;
[0028] Step 4: Input the training data into the LSTM model for training, and iteratively update the weights and offsets to minimize the error, obtain the gearbox tempe...
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