Method for diagnosing wind turbine main bearing fault based on temporal sequence clustering

A technology for wind turbines and time series, which is applied to the monitoring of wind turbines, wind turbines, and combinations of wind turbines, etc., can solve the problems of lack of maintenance of main bearings, low reliability of diagnosis and monitoring results, and inconvenience, so as to improve the power generation rate. and economic benefits, improve early warning capabilities, and reduce damage rates

Active Publication Date: 2017-06-20
GUODIAN UNITED POWER TECH
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the diagnosis method of the main bearing fault of the wind turbine is mainly through vibration monitoring, but the lack of maintenance and grease problems of the main bearing of the wind turbine due to vibration, the assembly problem of the main bearing and the damage of the main bearing have many i

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 diagnosing wind turbine main bearing fault based on temporal sequence clustering
  • Method for diagnosing wind turbine main bearing fault based on temporal sequence clustering
  • Method for diagnosing wind turbine main bearing fault based on temporal sequence clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] At present, there are several wind turbines in the wind farm. These wind turbines are of the same model and have the same components. This provides a broad possibility for the clustering method to identify faults. Assuming that the wind generator is a black box, the input to this box is only the wind and the external environment (temperature and humidity, etc.). Because the external environment has the same influence on all wind turbines in a wind farm at the same time. Therefore, through time series clustering, dimensionality reduction of multiple environmental independent variables can be achieved.

[0025] In view of this, the present invention proposes a method for diagnosing main bearing faults of wind power generators based on a time series clustering algorithm, so as to realize fast and intelligent diagnosis of main bearing faults.

[0026] combine figure 1 Shown, the method of the present invention is concretely realized as follows:

[0027] The first step, d...

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 diagnosing a wind turbine main bearing fault based on temporal sequence clustering. The method comprises the following steps that step one, data (power data and main bearing temperature data) are collected, screened and calculated; step two, different power intervals are divided according power clustering, and all the power intervals are subjected to the flowing steps from step three to step seven; step three, fitness is evaluated; step four, good individual groups are selected; step five, a temperature datum line is obtained; step six, a temperature warning line is obtained; and step seven, the data are substituted for detection and early warning. According to the method, the wind turbine main bearing temperature is subjected temporal sequence power clustering and good individual group selection, whether a main bearing has an abnormal operation state or not is distinguished for diagnosis, the diagnosis result is reliable, the early warning capacity of the main bearing can be improved, manual troubleshooting is replaced by the data, targeted maintenance and defect elimination are achieved, the damage rate of the main bearing is decreased, the power generation rate and economic benefits of a wind turbine are increased.

Description

technical field [0001] The invention relates to the field of operation and maintenance of wind power generators, in particular to a method for diagnosing faults of main bearings of wind power generators based on time series clustering. Background technique [0002] The main bearing is an important part of the wind turbine, which transmits the wind energy absorbed by the impeller to the gearbox, and is an important energy transmission mechanism of the wind turbine drive chain. While my country's wind power industry is booming, it is facing frequent failures of wind turbines. However, among all failures, failures of major components such as main bearings, gearboxes, generators, and blades are particularly serious, which will cause serious economic losses to wind farms. loss. The failure of many of these large components is due to lack of maintenance and oversight. If it can be diagnosed when maintenance is required or at an early stage of failure, this is an effective way to ...

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): F03D17/00F03D9/25F03D80/70G06F17/50
CPCF05B2260/80G06F30/20G06F2119/08Y02E10/72
Inventor 李永战杜国柱刘昊董健
Owner GUODIAN UNITED POWER TECH
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