Abnormal sound detection system and method based on time-frequency domain characteristics

A detection method and technology in the time-frequency domain, which are applied to measuring devices, processing response signals of detection, and analyzing solids using sonic/ultrasonic/infrasonic waves, can solve the problems of low detection and recognition rate of abnormal sound, and improve the recognition rate of abnormal sound. Effect

Inactive Publication Date: 2020-04-10
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF10 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to propose a system and method for abnormal sound detection based on time-frequency domain characteristics, so as to solve the problem of low identification rate of abnormal sound detection in the traditional technology

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
  • Abnormal sound detection system and method based on time-frequency domain characteristics
  • Abnormal sound detection system and method based on time-frequency domain characteristics
  • Abnormal sound detection system and method based on time-frequency domain characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Such as figure 1 As shown, the abnormal sound detection system based on time-frequency domain features in this embodiment includes:

[0041] A preprocessing module, configured to extract effective sound segments in the sound data of the collected device, the effective sound segments at least including the smooth rotation sound segment of the collected device;

[0042] The abnormal time domain identification module is used to determine the range of the different tone band, obtain the feature components containing the different tone segments through frequency band decomposition, perform windowing and frame division on the feature components to calculate the time domain features, and then identify the sound abnormal frame through the threshold threshold;

[0043] The abnormal sound domain classification module is used to calculate the frequency domain features based on the recognition results of abnormal sound frames and input the pre-trained machine learning model for cla...

Embodiment 2

[0045] Based on the system in Embodiment 1 above, this embodiment provides a corresponding abnormal sound detection method based on time-frequency domain features, and its process is as follows figure 2 shown, including:

[0046] (1) Preprocessing steps:

[0047] An effective sound segment of the sound data of the collected device is extracted, and the effective sound segment at least includes information about a smooth rotating sound segment of the collected device.

[0048] The method of extracting the effective sound segment of the collected sound data at least includes: determining the start position and end position of the device, intercepting the sound data of the collected device through a rectangular window, and extracting the effective sound segment.

[0049] The conventional method is to ensure that when data is collected, the device and the recording are started at the same time, and the start position and end position of each device are the same. The result is as...

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 belongs to the field of sound signal processing, discloses an abnormal sound detection system and method based on time-frequency domain characteristics, and solves the problem of low abnormal sound detection and recognition rate in the prior art. The method comprises the steps of a, extracting an effective sound segment in sound data of collected equipment, wherein the effective sound segment at least comprises a stable rotation sound segment of the collected equipment; b, determining an abnormal audio frequency band range, obtaining a characteristic component containing a abnormal audio frequency band through frequency band decomposition, performing windowing framing calculation on the characteristic component to calculate time domain characteristics, and identifying a soundabnormal frame through a threshold value; and c, based on the recognition result of the sound abnormal frame, calculating frequency domain characteristics, inputting the frequency domain characteristics into a pre-trained machine learning model for classification, scoring according to a classification result, and determining an equipment abnormal sound detection result.

Description

technical field [0001] The invention belongs to the field of sound signal processing, in particular to a system and method for detecting abnormal sound based on time-frequency domain characteristics. Background technique [0002] In recent years, with the gradual maturity of artificial intelligence technology, it has greatly promoted the rapid development of all walks of life, and industrial automation is moving towards industrial intelligence. Among them, industrial defect detection has become one of the current research hotspots. Using machines instead of humans for identification and detection can greatly save manpower and material resources. The greater advantage is that it can standardize detection and eliminate human subjective influence. Adapt to industry standard requirements. [0003] In industrial defect detection, conventional abnormal sound detection is based on signal frequency domain information, and then uses machine learning methods to classify and identify ...

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): G01N29/04G01N29/44
CPCG01N29/04G01N29/4454G01N2291/023
Inventor 刘杨展华益伍强
Owner SICHUAN CHANGHONG ELECTRIC CO LTD
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