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

Analysis method of gear train noise based on ensemble empirical mode decomposition and support vector machine

A technology that integrates empirical modes and support vector machines, and is applied in machine gear/transmission mechanism testing, mechanical component testing, machine/structural component testing, etc., and can solve problems such as inability to characterize local characteristics of signals

Inactive Publication Date: 2017-05-31
BEIJING UNIV OF TECH
View PDF5 Cites 35 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The gear transmission noise signal exhibits energy aggregation characteristics in a specific fractional Fourier transform domain, which can retain useful signal components related to faults; although this method has many unique properties, it cannot characterize the local characteristics of the signal, which is very important for gear faults. The feature extraction of the signal poses certain limitations

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
  • Analysis method of gear train noise based on ensemble empirical mode decomposition and support vector machine
  • Analysis method of gear train noise based on ensemble empirical mode decomposition and support vector machine
  • Analysis method of gear train noise based on ensemble empirical mode decomposition and support vector machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0088] The present invention will be further described in detail below in conjunction with the accompanying drawings, so that those skilled in the art can implement it with reference to the description.

[0089] In the experiment, the attached image 3 The experimental bench shown is used to collect gear transmission noise. The transmission noise signals of normal gears, pitting gears of driving wheels, and gears with damaged gears on all tooth surfaces of driving wheels are as follows: Figures 4a-4c As shown, the illustration shows that the three kinds of defective gears cannot be distinguished by observing the noise signal waveform or spectral line, so the analysis is carried out through the following steps:

[0090] Step 1: Collect the mixed signal s(t) containing the background noise w(t) and the gear transmission noise signal x(t) by using the acceleration sensor, where t is the sampling time. For the transmission noise mixed signal of gears with driving wheel pitting, t...

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 an analysis method of gear train noise based on ensemble empirical mode decomposition and support vector machine. Firstly, the method of ensemble empirical mode decomposition stepwise decomposes the different time scale wave or trend of gear train noise signals and a set of intrinsic mode functions IMF. Gear train noise useful signals are extracted and the signals including mesh frequency are found from the result of ensemble empirical mode decomposition and conducted reconsitution. time synchronous averaging is operated according to gear rotation period and the signal irrelevant to gear rotation frequency is weaken through time expansion treatment. The characteristic parameter of treated gear train noise signals is calculated and a set of characteristic parameters with large differences is selected as characteristic vector. The characteristic vector as sample is divided into two groups, wherein the two groups have the same numbers and are used as a training sample and a testing sample. The method has little man-made operation and ensures the accuracy of analysis. The intelligent analysis method is based on support vector machine and has high and fast recognition accuracy of gear train prosperity.

Description

technical field [0001] The invention relates to a gear transmission noise analysis method, in particular to a gear transmission noise analysis method based on ensemble empirical mode decomposition (EEMD) and support vector machine (SVM). The invention belongs to the field of gear transmission noise measurement and fault diagnosis. Background technique [0002] Gear transmission noise signal analysis is mainly used for gear fault diagnosis. The analysis process is applied to the fields of non-stationary signal denoising, useful signal extraction, feature analysis and intelligent recognition. Signal denoising and useful signal extraction are directly related to the correctness of feature analysis and intelligent recognition. [0003] Traditional signal spectrum analysis methods are mainly based on fast Fourier transform, or spectrum analysis based on time series model. The preconditions of these two methods assume that the signal is stationary. However, for the gear transmi...

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): G06K9/00G06K9/62G01M13/02
CPCG01M13/021G01M13/028G06F2218/08G06F2218/12G06F18/2411
Inventor 陈洪芳孙衍强石照耀王亚韦
Owner BEIJING UNIV OF TECH
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