Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Fan multi-fault diagnosis method based on deep metric network difficult for sample mining

A diagnostic method and multi-fault technology, applied in neural learning methods, biological neural network models, computer components, etc., can solve problems such as poor performance and limited number of fault types

Active Publication Date: 2019-12-10
NORTHEASTERN UNIV
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, existing methods for single-model diagnosis of multiple faults have poor performance, and these methods rely heavily on wind turbine domain knowledge, so the number of fault types that can be detected is limited

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
  • Fan multi-fault diagnosis method based on deep metric network difficult for sample mining
  • Fan multi-fault diagnosis method based on deep metric network difficult for sample mining
  • Fan multi-fault diagnosis method based on deep metric network difficult for sample mining

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0048] Multi-fault diagnosis method for wind turbines based on deep metric network of hard sample mining, such as figure 1 shown, including the following steps:

[0049] Step 1: Build a difficult training sample mining model; for a wind turbine z different types of SCADA (Supervisory Control And Data Acquisition, that is, data acquisition and monitoring control system data) data sets, D = [D 1 ,D 2 ,...,D z ] T , where each type includes normal data R n , abnormal data R f ; In order to select a sample set with high training accuracy, the abnormal data R f Divided into early failure data S ef and fault data S f , sample equalization is performed on normal data and...

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 provides a fan multi-fault diagnosis method based on a deep metric network difficult for sample mining, and relates to the technical field of wind turbine fault diagnosis. The method comprises the following steps: firstly, constructing a difficult sample data set for z different types of SCADA data of a wind turbine; subjecting the constructed difficult sample data set to imaging processing, optimizing various SCADA data variables so that arrangement of the data variables is made to be continuous in time and space, finally acquiring optimized training samples, and creating a depth measurement network model based on an improved triple training sample set loss function; and finally, taking a feature vector obtained by mapping the triple sample through a depth measurement network as a training set and inputting the training set into an SVM model to carry out wind turbine fault diagnosis. Sample generation is carried out on the basis of a triple model so that a method for diagnosing multiple faults by using a single model is provided, and an improved triple loss function training model is used, so that the accuracy of multi-fault diagnosis is improved.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis of wind turbines, in particular to a multi-fault diagnosis method of wind turbines based on a deep metric network of difficult sample mining. Background technique [0002] In recent years, due to the depletion of minerals, oil and other resources, it is unable to meet the growing demand of human beings for energy. The green and sustainable wind energy has become the main force of renewable resources, and its position in the entire energy system is also growing. According to the data released by the Global Wind Energy Council (GWEC), in 2018, the newly installed capacity in the world was 51.3GW, and the total installed capacity was 591GW, an increase of 9% compared with 2017. It is estimated that by 2023, new onshore and offshore The installed capacity will exceed 55GW per year. [0003] With the rapid development of wind power technology, more and more wind farms and wind turbines are put...

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): G06K9/62G06N3/04G06N3/08G01M13/02
CPCG06N3/08G01M13/02G06N3/045G06F18/2411G06F18/214
Inventor 刘金海刘晓媛曲福明
Owner NORTHEASTERN 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
Eureka Blog
Learn More
PatSnap group products