Window motor abnormal noise detection method and apparatus based on MFCC and SVM

A technology of abnormal noise and detection method, which is applied to measurement devices, electrical devices, computer parts, etc., can solve problems such as hindering the realization of full automation of window motors, inability to distinguish abnormal noise motors, and inability to accurately estimate the degree of noise contribution.
CN105841797AActive Publication Date: 2016-08-10CENT SOUTH UNIV
12 Cites 23 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Current Assignee / Owner
CENT SOUTH UNIV
Publication Date
2016-08-10

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a window motor abnormal noise detection method and apparatus based on an MFCC and an SVM. Sound signals during no-load running of a motor are acquired and pre-processed. In the pre-processing stage, a second order Hanning self-convolution window is used as a window function for interception of the sound signals. After pre-processing, data extraction of MFCC parameters is conducted and an SVM is entered for abnormal noise determination. An MFCC feature value and a determination result Label are stored in a historical database. To improve the SVM discriminant accuracy, the invention adopts an artificial bee colony algorithm for SVM parameter automatic adjustment and updating; and the method has the characteristics of high reliability, practicality, and the like, and can be used for effectively distinguishing abnormal motor noises in practical applications.
Need to check novelty before this filing date? Find Prior Art

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