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

A method and device for detecting abnormal noise of window motors based on MFCC and SVM

A technology of abnormal noise and detection method, which is applied in the direction of measuring devices, electric devices, and electromagnetic means, etc., can solve the problems that hinder the realization of full automation of window motors, cannot accurately estimate the degree of noise contribution, and cannot distinguish abnormal noise motors, etc. Achieve the effect of realizing fully automatic online detection, reducing sensor installation links, and ensuring acoustic quality

Active Publication Date: 2019-07-02
CENT SOUTH UNIV
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In the above method (1), the detection of motor noise by manual auscultation has the disadvantage of strong subjectivity, that is, different people will have different feelings when hearing the same sound. Fatigue is prone to problems such as false detection and missed detection. At the same time, manual detection hinders the realization of full automation of window motor production
[0007] In the method (2) above, the total sound pressure level can identify the window motor that is too loud, but cannot identify the motor with abnormal noise
The analysis method based on the sound spectrum can identify abnormal noise motors to a certain extent, but the frequency spectrum in Hz cannot accurately estimate the contribution of each frequency component to the noise, which makes these methods have limitations in practical applications

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
  • A method and device for detecting abnormal noise of window motors based on MFCC and SVM
  • A method and device for detecting abnormal noise of window motors based on MFCC and SVM
  • A method and device for detecting abnormal noise of window motors based on MFCC and SVM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0066] Such as figure 1 As shown, a method for detecting abnormal noise of a window motor based on MFCC and SVM includes the following steps:

[0067] Step 1: Fix the motor and get the sound signal of the motor.

[0068] The motor is positioned through the positioning bolts on the equipment replacement plate and the positioning holes of the motor, and is clamped and fixed by manual clamps. The microphone (model G.R.A.S 46AE) used for motor sound signal collection is installed at 100-110mm directly above the output shaft of the window motor reducer gear. The data acquisition card model (NI PCI 4462) is connected to the industrial computer through the PCI slot of the industrial computer. The sampling rate of motor sound signal collection is 51200, the sampling time is 4.5s, and the data is saved in WAV. format.

[0069] Step 2: Read the collected WAV ...

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 of this article discloses an abnormal noise detection method and device based on MFCC and SVM. The sound signal is collected when the motor is carried out and the signal is prepared.During the pre -processing stage, the second -order Hanning self -voltage window is used as a window function to intercept the sound signal.After pre -processing the data extract MFCC parameter and enter the SVM for abnormal noise judgment.Save MFCC feature values and judgment results Label into the historical database.In order to improve the accuracy of SVM's judgment, the artificial bee colony algorithm is used to achieve automatic adjustment and update of SVM parameters; the method has high reliability and strong practicality, and can effectively judge the abnormal noise of the motor in actual production applications.

Description

technical field [0001] The invention relates to an on-line detection technology for motor abnormal noise at a production site of an automobile window motor, in particular to a method and device for detecting abnormal noise of a window motor based on MFCC and SVM. Background technique [0002] As people put forward higher requirements for the comfort of the automotive acoustic environment, NVH (Noise, Vibration, Harshness) has become an important indicator for evaluating the overall performance of automotive motors. The window motor of the car is close to the driver, and the unpleasant sound brought by the window motor will affect the acoustic comfort in the car and bring people an unpleasant acoustic experience, and the motor noise reflects the running state of the motor, and the motor with abnormal noise is often accompanied by Internal structural defects. Before leaving the factory, automotive window motors must undergo strict vibration and noise tests in accordance with ...

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 Patents(China)
IPC IPC(8): G01H11/06G06K9/62G10L25/24G10L25/51
CPCG10L25/24G10L25/51G01H11/06G06F18/2411
Inventor 谭建平刘思思李锋黄涛
Owner CENT SOUTH 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