Method for identifying fault of variable-pitch bearing of wind turbine generator set

A technology for wind turbines and pitch bearings, applied in mechanical bearing testing, character and pattern recognition, computer components, etc., can solve problems such as high detection costs, high requirements for operators, and difficulties in accurate fault location, achieving high accuracy rate effect

Inactive Publication Date: 2019-10-22
ZHEJIANG WINDEY
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention aims to overcome the problems of high detection cost, difficulty in accurate fault location and high requirements for operators in the existing unit pitch bearing fault monitoring method in the prior art, and provides a utility model that can improve the monitoring accuracy. A method for fault identification of pitch bearings in wind turbines

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 identifying fault of variable-pitch bearing of wind turbine generator set
  • Method for identifying fault of variable-pitch bearing of wind turbine generator set
  • Method for identifying fault of variable-pitch bearing of wind turbine generator set

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0055] Example: as figure 1 A method for fault identification of a pitch bearing of a wind turbine generator shown in the figure includes the following steps:

[0056] (1-1) Offline modeling, collecting training sample sets:

[0057] Collect data including normal operating condition data of wind turbines and pitch bearing fault condition data, conduct variation coefficient analysis on training set data, select variables sensitive to pitch bearing faults as input variables of hidden Markov model HMM, and train hidden Markov model HMM. Markov model;

[0058] (1-1-1) Offline modeling:

[0059] Set the monitoring data collected during the operation of the wind turbine to form two data sets X={x m,1 x m,2 …x m,n }∈R m×n and where dataset X represents the data collected during normal operation, where m is the number of normal samples, n is the number of monitored variables, and dataset X f represents the data collected when the wind turbine pitch bearing fails, where m f...

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 method for identifying a fault of a variable-pitch bearing of a wind turbine generator set. The method comprises the steps of: 1, offline modeling, and training sample set acquisition, which are implemented by acquiring data containing normal operation working condition data and variable-pitch bearing faulty working condition data of the wind turbine generator set, performing variable coefficient analysis on the training set data, selecting variables sensitive to the fault of the variable-pitch bearing as input variables of a hidden Markov model (HMM), and training the hidden Markov model; 2, online data identification, which is implemented by carrying out online identification, namely, still adopting the variables selected by the training set as observation variables of the hidden Markov model, and performing variable-pitch bearing fault identification on the online data by means of the hidden Markov model. The method has higher precision in identifying the fault of the variable-pitch bearing of the wind turbine generator set.

Description

technical field [0001] The present invention relates to the technical field of wind power generation, and in particular, to a method for fault identification of pitch bearings of wind turbines that can improve monitoring accuracy. Background technique [0002] In the wind power generation system, the pitch control system is an important part of the wind turbine control system, and ensuring the safety and reliability of the pitch bearing is very important to ensure the normal operation of the entire pitch control system. Therefore, monitoring and diagnosing the faults of wind turbine bearings is of great practical significance for reducing economic losses caused by bearing faults. [0003] In recent years, the monitoring of turbine pitch bearing faults has received great attention in the field of wind power generation. The monitoring methods are mainly divided into the following categories: 1. Fault diagnosis technology based on vibration signal analysis, because when the bea...

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): G01M13/04G06K9/62
CPCG01M13/04G06F18/295G06F18/214
Inventor 王琳陈棋孙勇傅凌焜
Owner ZHEJIANG WINDEY
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