Mechanical equipment abnormal sound detection method based on self-supervised feature extraction

A technology for mechanical equipment and feature extraction, which is applied in the testing of mechanical components, neural learning methods, testing of machine/structural components, etc., can solve the problems of low accuracy and poor correlation of abnormal sound detection of mechanical equipment, and achieve high accuracy , the effect of improving the accuracy rate

Pending Publication Date: 2021-12-14
INST OF INTELLIGENT MFG GUANGDONG ACAD OF SCI
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, in order to solve the problem in the prior art that when the training data only has normal sound samples, the manual extraction of sound features may be poorly correlated with the next step of abnormal detection, resulting in low accuracy of abnormal sound detection of mechanical equipment. The invention proposes a method for detecting abnormal sounds of mechanical equipment based on self-supervised feature extraction

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
  • Mechanical equipment abnormal sound detection method based on self-supervised feature extraction
  • Mechanical equipment abnormal sound detection method based on self-supervised feature extraction
  • Mechanical equipment abnormal sound detection method based on self-supervised feature extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] Such as figure 1 with figure 2 As shown, the present invention proposes a method for detecting abnormal sound of mechanical equipment based on self-supervised feature extraction, including the following steps:

[0049] S1. Acquisition of normal operation sound data set D of mechanical equipment 1 ;

[0050] S2. Perform preprocessing and short-time Fourier transform (STFT) on all data samples to obtain normal sample time spectrum data set D 3 ;

[0051] S3. Spectrum data set D when using normal samples 2 Spectrum dataset D when abnormal samples are generated 3 ;

[0052] S4. The normal sample time spectrum data set D 2 and the generated abnormal sample time spectrum data set D 3 Combined into training data set D 4 , using D 4 Train a deep convolutional network to generate a self-supervised feature extraction model Z1;

[0053] S5. Use the self-supervised feature extraction model Z1 to extract D 2 feature T 1 , then use T 1 Train the autoencoder network to ...

Embodiment 2

[0081] Such as Figure 5 As shown, the present invention provides a mechanical equipment abnormal sound detection system based on self-supervised feature extraction, including a normal operation sound data set acquisition module, a normal sample time spectrum data set acquisition module, an abnormal sample time frequency spectrum data set acquisition module, and a self-supervised Feature extraction model generation module, abnormal detection model generation module and abnormal sound detection module;

[0082] The normal operation sound data set acquisition module is used to collect the normal operation sound data set D of mechanical equipment 1 ;

[0083] The normal sample time spectrum data set acquisition module is used to preprocess and short-time Fourier transform all data samples to obtain the normal sample time spectrum data set D 2 ;

[0084] The frequency spectrum data set acquisition module for the abnormal samples is used to use the normal sample time spectrum da...

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 discloses a mechanical equipment abnormal sound detection method based on self-supervised feature extraction, solves the problems of large influence of human factors, weak universality of an artificial extraction method, and the like, which are caused by the fact that mechanical equipment abnormal sound detection mainly extracts sound signal features based on an artificial construction algorithm, and then performs abnormal detection based on the features, and improves the abnormal sound detection accuracy of the mechanical equipment. The method comprises the following implementation steps: collecting sound of the mechanical equipment; preprocessing data; manufacturing an abnormal sound sample; using a normal sound sample and the manufactured abnormal sound sample to train a convolutional network as a self-supervised feature extractor; training an auto-encoder network by using extracted normal sound sample features; judging whether the sound of the mechanical equipment to be detected is abnormal or not by using a trained self-supervised feature extractor and a self-encoder network. According to the method, results show that the features extracted based on self-supervised learning are more suitable for anomaly detection, the accuracy is high, and the method can be applied to real factory mechanical equipment anomaly detection tasks.

Description

technical field [0001] The invention relates to the technical field of abnormal sound detection, in particular to a method for detecting abnormal sound of mechanical equipment based on self-supervised feature extraction. Background technique [0002] With the rapid development of industrial production automation, the normal operation of mechanical equipment in factories plays an important role in industrial production, but the high complexity of industrial equipment makes it difficult for humans to detect early equipment failures, resulting in major economic losses. It is of great significance to study the abnormal diagnosis. At present, abnormal detection of mechanical equipment based on vibration signals has been widely used. Similar to vibration signals, sound signals are an important source of information to reflect the operating status of equipment, and sound signals have the advantages of convenient collection, non-contact measurement, and fast processing speed. The ...

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
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08G01M13/045
CPCG06N3/08G01M13/045G06N3/045G06F2218/08G06F2218/12G06F18/241
Inventor 刘忆森周松斌薛英杰
Owner INST OF INTELLIGENT MFG GUANGDONG ACAD OF SCI
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