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

Lower fan blade icing prediction method based on unbalanced data set condition

A prediction method and data set technology, applied in computer parts, instruments, characters and pattern recognition, etc., can solve the problem of insufficient accuracy of fan blade icing prediction, and achieve the effect of avoiding overlapping redundancy and increasing randomness.

Active Publication Date: 2019-07-05
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Purpose of the invention: The present invention proposes a wind turbine blade icing prediction method based on unbalanced data sets to solve the problem of insufficient accuracy of wind turbine blade icing prediction under unbalanced data and conditions

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
  • Lower fan blade icing prediction method based on unbalanced data set condition
  • Lower fan blade icing prediction method based on unbalanced data set condition
  • Lower fan blade icing prediction method based on unbalanced data set condition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] Such as figure 1 As shown, the wind turbine blade icing prediction method based on the unbalanced data set includes the following steps:

[0041] Step 1) Collect and organize the historical meteorological data and wind turbine operating status data of the wind farm, and finally store the sorted data in the database, which is convenient for use in forecasting; among them, the historical meteorological data of the wind farm and the fan operating status data and forecast The target (whether the wind turbine is icing) can constitute a wind turbine historical data training vector; the wind turbine historical data training vector specifically includes the following dimensions: wind speed, wind power generation speed, wind power generation speed, ambient temperature, generator internal temperature, whether wind turbine blades are frozen The ice phenomenon can be expressed as:

[0042] X=[v w ,v g ,p,t e ,t i ,f]

[0043] where v w Indicates the wind speed; v g Indicate...

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 a lower fan blade icing prediction method based on an unbalanced data set condition, and the method enables the distribution of data samples in an unbalanced data set to be balanced, and predicts a fan blade icing event in combination with a random forest algorithm (RF). The algorithm comprises the following steps: firstly, carrying out BIRCH hierarchical clustering operation on a small number of original samples, and dividing different concentration regions in each clustering region according to the density of sample points; the lower the concentration is, the more thesamples to be synthesized are, and the fewer the samples to be synthesized are in the higher the concentration is. In order to follow the original distribution situation of a few types of samples, new samples are synthesized in different concentration areas in each cluster. Also, a BIRCH-SMOTE algorithm improves linear interpolation operation, randomness is increased in the interpolation process,and the overlapping redundancy problem of synthetic samples is effectively avoided. Finally, the random forest model is trained by using the balanced data set, and a fan blade icing prediction resultis obtained.

Description

technical field [0001] The invention relates to the technical field of short-term wind power generation, in particular to a method for predicting icing of blades of a wind power generator based on an unbalanced data set. Background technique [0002] Wind energy is a typical renewable clean energy. Due to its abundant reserves and the conditions for large-scale development, it has received widespread attention worldwide. In the installed capacity of renewable energy power generation in the world, wind power has an overwhelming advantage. Wind energy accounts for more than half of the utilized renewable energy, and wind power is also the most mature utilization technology of all renewable resources. In recent years, the world's wind power generation has grown rapidly and has a bright future. As of December 2012, the installed capacity of wind power in the world has increased from 60GW in 2000 to 282.578GW. At present, China is the country with the largest installed wind po...

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): G06K9/62
CPCG06F18/231G06F18/2148G06F18/24147G06F18/24323
Inventor 岳东葛阳鸣卜阳宋星星
Owner NANJING UNIV OF POSTS & TELECOMM
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