Wind turbine generator set bearing mechanical fault diagnosis method considering multi-class objectives

A technology for wind turbines and bearing machinery, applied in mechanical bearing testing, complex mathematical operations, etc., can solve problems such as errors, misidentification of fault samples without training, and impact on equipment reliability, so as to prevent false modals and modal aliasing Effects with low impact and few modalities

Active Publication Date: 2018-06-19
国电投河南新能源有限公司
View PDF8 Cites 64 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the absence of fault training data, multi-class classifiers such as support vector machines are easy to misident

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
  • Wind turbine generator set bearing mechanical fault diagnosis method considering multi-class objectives
  • Wind turbine generator set bearing mechanical fault diagnosis method considering multi-class objectives
  • Wind turbine generator set bearing mechanical fault diagnosis method considering multi-class objectives

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0086] The present invention is a method for diagnosing mechanical faults of bearings of wind turbines considering multi-classification targets, comprising the following steps:

[0087] 2) Wind turbine bearing vibration signal acquisition

[0088] The normal state signal of the wind turbine bearing, the rolling element fault vibration signal, the inner ring fault vibration signal and the outer ring fault signal are collected through the acceleration sensor, and the above signals are recorded by a 16-channel data recorder. The signal sampling frequency is 12kHz and the signal length is 4096 sampling points;

[0089] 2) Wind turbine bearing vibration signal processing

[0090] In order to extract effective fault feature information and consider the modulation characteristics of bearing vibration signal, empirical wavelet transform is used for bearing fault diagnosis. The interval is divided, and then a set of orthogonal filter banks are constructed based on the divided interva...

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 wind turbine generator set bearing mechanical fault diagnosis method considering multi-class objectives. The method is characterized by comprising the steps of wind turbine generator set bearing vibration signal acquisition, wind turbine generator set bearing vibration signal processing, wind turbine generator set bearing vibration signal feature extraction, wind turbine generator set bearing vibration signal feature selection and recognition of the circuit breaker state through the hierarchical hybrid classifier. The method is scientific and reasonable, high in applicability and high in practical value and can accurately recognize the fault so that the situation that the present method is liable to misrecognize the new fault degree or the new fault type of samplewhich is not included in the training samples as the normal state can be avoided.

Description

[0001] The invention is a mechanical fault diagnosis method for wind turbine bearings in consideration of multi-category targets, which is applied to online diagnosis of mechanical fault states of wind turbine bearings. Background technique [0002] Bearings are key components of rotating machinery, and their failure affects the reliable operation of many types of electrical equipment, including wind turbines. Non-bearing failures such as gearboxes and blades in the mechanical transmission system of wind turbines are mostly caused by bearing failures, and the same is true for other mechanical equipment failures. Therefore, the research on bearing condition monitoring technology and fault diagnosis method is of great significance. The existing bearing fault diagnosis process mainly includes two steps of feature extraction and fault classification. [0003] Commonly used signal processing methods include empirical mode decomposition, wavelet decomposition, ensemble empirical mo...

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): G01M13/04G06F17/14
Inventor 黄南天王斌王达蔡国伟杨冬锋黄大为方立华杨学航刘博张良孔令国王燕涛
Owner 国电投河南新能源有限公司
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