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

Method for fault diagnosis of wind turbine bear

A wind turbine, fault diagnosis technology, applied in the direction of mechanical bearing testing, neural learning methods, special data processing applications, etc., can solve problems such as bearings that have not been processed, and achieve the effects of suppressing noise, improving signal-to-noise ratio, and high accuracy

Active Publication Date: 2018-12-18
温州大学苍南研究院
View PDF3 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, there is no diagnostic method to effectively test the presence or absence of turbine engine faults by processing the vibration signals of the bearings

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
  • Method for fault diagnosis of wind turbine bear
  • Method for fault diagnosis of wind turbine bear
  • Method for fault diagnosis of wind turbine bear

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0138] Example: Fault Diagnosis of Bearing Inner and Outer Rings of Wind Turbines

[0139] A set of known bearing data is used for fault diagnosis, where the input shaft frequency is 25Hz, the sampling rate is 48828sps, the roller diameter is 0.235mm, the pitch diameter is 1.245mm, the number of elements is 8, and the contact angle is 0. This paper selects six types of fault data, which are the fault data of the inner ring at 0 lb, 150 lb, and 300 lb load and the outer ring at 25 lb, 150 lb, and 300 lb load.

[0140] First, the six types of data are decomposed by the method described in the invention. After the decomposition, according to the calculated correlation coefficient between the PF component and the original signal, the first three layers are selected for index calculation, and 18 new sets of data samples are obtained.

[0141] Then, the number of samples of the inner circle data is 120000, and divided into 50 segments, each segment has 2400 points, forming X1 50×24...

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 wind turbine bearing fault diagnosis method. Firstly, an optimal filter is designed by using the principle of minimum entropy, and the impulse impact in the signal is highlighted. Secondly, the fault signal is decomposed by local mean decomposition, and the PF component which is highly correlated with the original signal is extracted to compute the parameter index, and then the feature vector set is formed. Finally, a fault classification model of wind turbine bearing based on improved extreme learning machine is established, and the set of eigenvectors is inputted into the improved extreme learning machine to diagnose the fault. As the method of the invention utilizes the minimum entropy deconvolution to effectively improve the signal-to-noise ratio, the fault characteristics of the wind turbine bear are obvious; on the other hand, the complete time-frequency distribution of the original signal is obtained by using the local mean decomposition method, and thefault types of the wind turbine bearing can be directly detected from the fault model of the improved limit learning machine.

Description

technical field [0001] The invention relates to the field of turbine engine maintenance, in particular to a turbine engine bearing fault diagnosis method based on an improved extreme learning machine. Background technique [0002] As a renewable energy, wind energy is green, energy-saving and efficient, and it is the key development direction of energy science in the future. With the rapid development of wind power plants, the maintenance of wind turbines is becoming more and more important. People have higher and higher requirements for the reliable shape and safe operation of wind turbines, and bearings are a key part of wind turbines, and their performance has a crucial impact on the reliable operation of the entire system. Bearing failures may lead to sudden shutdown of wind turbines, leading to paralysis of the entire system, resulting in huge economic losses and even casualties. Therefore, fault diagnosis of wind turbine bearings is of great significance in industria...

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
IPC IPC(8): G06F17/50G06N3/08G01M13/04
CPCG06N3/084G01M13/04G06F30/17Y04S10/50Y02E10/72
Inventor 向家伟高云
Owner 温州大学苍南研究院
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