Prediction method for early freezing fault of fan blade

A technology for fault prediction and wind turbine blades, which is used in prediction, wind turbines, engines, etc., and can solve problems such as the inability to obtain the best feature attributes, the complex feature process of key parameter data, and the low accuracy and detection efficiency of early prediction results of blade icing. problems, to achieve the effect of improving the accuracy of results and detection efficiency, reducing losses, and reducing their own costs

Pending Publication Date: 2021-05-25
SHANGHAI DIANJI UNIV
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the process of collecting data characteristics of key parameters is complicated, and the best characteristic attributes cannot be obtained by this method, and the accuracy and detection efficiency of early prediction results for blade icing are not high.

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
  • Prediction method for early freezing fault of fan blade
  • Prediction method for early freezing fault of fan blade
  • Prediction method for early freezing fault of fan blade

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0040] Such as figure 1 As shown, the present invention provides a method for predicting early icing faults of fan blades, comprising the following steps:

[0041] S1: Obtain prediction parameter data, construct a sample set and perform data preprocessing;

[0042] S2: Perform feature selection through the Relief-F algorithm to obtain the optimal feature subset;

[0043] S3: Perform PCA feature transformation on the optimal feature subset to obtain the best features;

[0044] S4: Build an early icing fault prediction model and use the best features for model training;

[0045] S5: Use the trained icing failure early prediction model to determine whether the fan blades have an early icing failure.

[0046] The specific implementation process is as follows:

[0047] Step 1: Data Acquisition. Use the data collected by the SCADA system as a sample set, including wind speed, ambient temperature, humidity, generator speed, yaw speed, grid-side active power, blade angle, etc.; ...

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 relates to a prediction method for an early freezing fault of a fan blade comprising the following steps: S1, obtaining prediction parameter data, constructing a sample set, and carrying out data preprocessing; S2, performing feature selection through a Relief-F algorithm to obtain an optimal feature subset; S3, carrying out PCA feature transformation on the optimal feature subset to obtain optimal features; S4, constructing an early freezing fault prediction model and performing model training by using the optimal features; and S5, judging whether the fan blade has an early icing fault or not by using the trained early icing fault prediction model, and compared with the prior art, the invention has the advantages of high efficiency, high precision and the like.

Description

technical field [0001] The invention relates to the field of wind power generation equipment, in particular to a method for predicting early icing faults of fan blades. Background technique [0002] With the goal of reaching carbon peak and carbon neutrality, the new energy represented by wind power and photovoltaic will show an explosive growth mode. As a clean, green and environmentally friendly renewable energy, wind power has a significant effect on reducing carbon emissions and is conducive to achieving the ambitious goals of carbon peaking and carbon neutrality. At present, many wind turbines are installed in the central and southern high-altitude areas with high humidity and low temperature. The special geographical location makes the wind turbines be affected by different degrees of natural environment during operation. Among them, the freezing of the blades of the wind turbines reduces the ability of the units to obtain wind energy. , resulting in a reduction in th...

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): G06F30/27G06K9/62G06Q10/04G06Q50/06F03D80/40G06F113/06G06F119/02
CPCG06F30/27G06Q10/04G06Q50/06F03D80/40G06F2113/06G06F2119/02G06F18/213G06F18/241G06F18/214Y02E10/72
Inventor 沈贺陈田李琼琼王海涛
Owner SHANGHAI DIANJI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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