Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Flutter signal analysis method based on convolutional neural network and short-time Fourier transform

A convolutional neural network and short-time Fourier technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as processing methods that have not yet been formed, and achieve good reliability and accuracy

Pending Publication Date: 2020-03-06
NORTHWESTERN POLYTECHNICAL UNIV
View PDF9 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the ideal conditions or simplified models in its derivation, a stable, general and accurate processing method has not yet been formed under complex working conditions.

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
  • Flutter signal analysis method based on convolutional neural network and short-time Fourier transform
  • Flutter signal analysis method based on convolutional neural network and short-time Fourier transform
  • Flutter signal analysis method based on convolutional neural network and short-time Fourier transform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Now in conjunction with embodiment, accompanying drawing, the present invention will be further described:

[0035] Steps of the present invention:

[0036] 1) Integrate the convolutional neural network with the short-time Fourier transform, and perform operations such as preprocessing and downsampling on the obtained time-frequency map;

[0037] 2) Structure design of convolutional neural network for flutter analysis, construction of network framework, adjustment of hyperparameters such as penalty factor, kernel function, hidden layer neurons, stop point of backpropagation algorithm, optimal network depth, etc. ;

[0038] 3) Preliminary classification, data preparation, and data cleaning are performed on the multivariate signals measured by flutter to generate training sets, test sets, and verification sets required for network research.

[0039] Specific implementation:

[0040] 1) Time-frequency analysis

[0041] Time-frequency analysis provides the joint distrib...

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 relates to a flutter signal analysis method based on a convolutional neural network and short-time Fourier transform. The flutter signal analysis method comprises the following steps: performing time-frequency analysis on an actually measured flutter signal by using short-time Fourier transform to obtain a time-frequency graph of the flutter signal, mining image features by using thepowerful image processing capability of a convolutional neural network, and realizing flutter feature extraction and subsequent signal analysis through calculation of a full connection layer and a loss function. According to the flutter signal analysis method, the convolutional neural network is combined with the short-time Fourier transform of the flutter signals, so that the flutter signal analysis method has good reliability and accuracy for analysis of actually measured flutter data, lays a certain foundation for further development of research on combination of artificial intelligence and air elasticity, and has practical engineering application value.

Description

technical field [0001] The invention belongs to a flutter signal analysis method, and relates to a flutter signal analysis method based on a convolutional neural network and a short-time Fourier transform. Background technique [0002] Flutter is a very dangerous aeroelastic instability phenomenon produced by an elastic structure under the coupled action of aerodynamic force, elastic force and inertial force, which often leads to disastrous consequences. However, due to the deficiencies in the theoretical analysis and calculation of flutter at the present stage, in order to supplement and verify the flutter design, the flutter test in engineering has become an unavoidable important link in the aircraft development process, and the flutter signal can be analyzed and processed accurately and effectively. It is an important task of this kind of experimental data processing. [0003] In the flutter test, the structural response signal most directly reflects the process of mode ...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F2218/00G06F2218/12
Inventor 郑华段世强赵东柱尚亚飞
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com