Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Onshore wind turbine generator blade icing diagnosis method based on migration component analysis

A wind turbine and component analysis technology, applied to wind power generation, wind turbines, engines, etc., can solve problems such as poor generalization ability and failure to identify blade icing faults

Active Publication Date: 2020-10-20
DATANG CHIFENG NEW ENERGY
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above method has a relatively accurate diagnosis ability for wind turbines with the same or similar SCADA data distribution, and can accurately identify blade icing faults. Accurate identification of faults

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Onshore wind turbine generator blade icing diagnosis method based on migration component analysis
  • Onshore wind turbine generator blade icing diagnosis method based on migration component analysis
  • Onshore wind turbine generator blade icing diagnosis method based on migration component analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] This embodiment relates to a method for diagnosing icing on the blades of an onshore wind turbine based on migration component analysis, and the specific steps are as follows:

[0049] Step 1: Monitor and record the icing status of wind turbines, add icing labels and time continuity labels to the corresponding SCADA data to form a model training data set;

[0050] Step 11: Select a wind turbine in good operating condition in the icing period to form a reference set for training the model;

[0051] Step 12: Observing and recording the icing period and normal period of each unit in the reference unit set during the icing period;

[0052]Step 13: Select 26 characteristic variables from the original SCADA data that are highly correlated with blade icing, including: wind speed, generator speed, grid-side active power, wind angle, average wind direction angle, yaw position, yaw Speed, blade angle, pitch motor temperature, blade speed, ng5 temperature, x-direction acceleratio...

Embodiment 2

[0085] First, the icing diagnosis model based on the Naive Bayesian algorithm is obtained by using the training set data combined with the Naive Bayesian algorithm through multiple iterations, and the test set data is input into the trained model to obtain the diagnostic accuracy index; then, using the implementation The migration component analysis method described in Example 1 adjusts the data distribution difference between the training set and the test set to obtain the post-migration training set and the post-migration test set, and uses the post-migration training set data combined with the Naive Bayes algorithm to obtain the Naive Bayes-based The icing diagnosis model of the Adams algorithm is used to input the transferred training set data into the trained model to obtain the diagnostic accuracy index.

Embodiment 3

[0086] Embodiment 3: First, the icing diagnosis model based on the linear discriminant analysis algorithm is obtained through multiple iterations by using the training set data combined with the linear discriminant analysis algorithm, and the test set data is input into the trained model to obtain the diagnostic accuracy index; then, Use the migration component analysis method described in Example 1 to adjust the data distribution difference between the training set and the test set to obtain the training set after migration and the test set after migration, and use the training set data after migration in combination with the linear discriminant algorithm to obtain the linear discriminant algorithm based on multiple iterations. The icing diagnosis model is used, and the transferred training set data is input into the trained model to obtain the diagnostic accuracy index.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an onshore wind turbine generator blade icing diagnosis method based on migration component analysis. The method comprises the steps that S1, a model training data set is formed; S2, feature selection is carried out; S3, multiple iterations are carried out on the data processed through a migration component analysis method by adopting a machine learning algorithm to train awind turbine generator blade icing state diagnosis model; and S4, the online blade icing state diagnosis model is deployed and applied. According to the onshore wind turbine generator blade icing diagnosis method based on the migration component analysis, the migration component analysis method is adopted, so that edge probability distribution between a modeling unit and a target unit is minimized, and the distribution difference between data is reduced. The method is strong in generalization ability, can effectively reduce the difference between icing data of different units, and improves the diagnosis accuracy of wind turbine generator blade icing.

Description

Technical field: [0001] The invention relates to the field of state monitoring and fault diagnosis of onshore wind turbines, in particular to a method for diagnosing icing of blades of onshore wind turbines based on migration component analysis. Background technique: [0002] Because of its abundant reserves, clean and pollution-free, green and sustainable characteristics, wind energy has attracted widespread attention worldwide. In actual operation, the power generation efficiency of wind turbines is often restricted by environmental factors, and the problem of blade icing in low temperature and humid environments is particularly prominent. When the blades freeze, it will cause different degrees of harm. At the slightest, it will reduce the power generation efficiency of the wind turbine and affect the income of the wind farm; if it is serious, it will induce blade breakage and endanger the safety of the wind turbine and the operation and maintenance personnel of the wind f...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): F03D80/40
CPCF03D80/40Y02E10/72
Inventor 丛智慧阎洁李硕刘永前马亮陶涛韩爽李莉
Owner DATANG CHIFENG NEW ENERGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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