Fault early warning method for wind power generator

A wind turbine and fault early warning technology, which is applied to wind turbines, wind turbine monitoring, engines, etc., can solve problems such as difficult model maintenance, low accuracy, and long time consumption, and achieve fault early warning and predictive stability High, high fault tolerance effect

Active Publication Date: 2018-02-16
SHANGHAI ELECTRIC POWER DESIGN INST
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the traditional expert system-based fault early warning method is aimed at complex systems such as DFIG with mechanical-electrical-thermal coupling, its knowledge source is not enough to express and reflect the characteristics of things, and the accuracy rate is not high; Fault warning method, modeling takes a long time, the selection of learning samples is also lack of basis, and model maintenance is difficult

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
  • Fault early warning method for wind power generator
  • Fault early warning method for wind power generator
  • Fault early warning method for wind power generator

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] figure 1 This is a flowchart of a wind turbine fault early warning method provided in the first embodiment of the present invention, which specifically includes the following steps:

[0042] Step S101: Extract observation parameters;

[0043] The observation parameters are the observation data of multiple observation points in different time periods, which are extracted and constructed by the SCADA system to form an initial observation parameter matrix. Each column vector (called column sample) in the initial observation parameter matrix is ​​collected at a certain time The values ​​of parameters at different observation points of the wind turbine; each row vector (called a row sample) in the initial observation parameter matrix is ​​the value of the parameters collected at different times for the same observation point of the wind turbine.

[0044] Step S102: Observation parameter cluster analysis, the construction of the state matrix can be classified as a clustering proble...

Embodiment 2

[0052] figure 2 It is a flowchart of a wind turbine fault early warning method provided in the second embodiment of the present invention. The second embodiment of the present invention specifically describes the data processing after the observation parameters are extracted based on the first embodiment.

[0053] Further, as figure 2 As shown, after the observation parameters are extracted in step S201, the operations of rough set attribute reduction in step S202 and observation parameter preprocessing in step S203 can also be performed. Step S202 rough set attribute reduction and step S203 observation parameter preprocessing are in the actual sense of sorting out historical operating data, reducing the scale of data processing, and improving the accuracy of fault early warning. After processing the historical operating data, step S204 observes parameter clustering analysis, step S205 "centroid" extraction construction state matrix and step S206 similarity modeling state estim...

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 fault early warning method for a wind power generator. The method comprises the steps that observation parameters are extracted; clustering analysis is carried out on the observation parameters, and the observation parameters are classified by adopting a Ward system clustering analysis method; centroids are extracted to construct a state matrix, each classified centroid is calculated according to the shortest distance principle, and the state matrix representing the normal operation situation of the wind power generator is formed through a centroid set; and an estimated value of the generating state of the state matrix is calculated in a similarity modeling mode, and whether the early warning is triggered or not is judged in a residual analysis mode. The fault early warning method for the wind power generator has the advantages that the fault of the wind power generator can be quickly and effectively predicted.

Description

Technical field [0001] The embodiment of the present invention relates to the field of wind power generation, and in particular to a method for early warning of a wind generator failure. Background technique [0002] The harsh operating environment of the wind power system, coupled with the sluggish domestic development of the wind power tertiary industry, has caused high frequency of wind turbine equipment failures. As the core equipment for variable-speed constant-frequency wind power system implementation, doubly-fed wind turbines are also at the boundary between the power generation side of the wind farm and the grid side. Its importance is self-evident. Therefore, regardless of economic or safety considerations, wind power generation It is indeed necessary for the aircraft to carry out fault early warning research. [0003] The occurrence of failures of wind turbine components does not happen overnight. Its generation and development generally require several processes such a...

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): F03D17/00
Inventor 肖礼沈彬孙雷邓宇
Owner SHANGHAI ELECTRIC POWER DESIGN INST
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