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

Self-learning-based on-line detection method for machine running faults in strong noise environment

A technology for machine operation and detection methods, applied in the field of online monitoring, can solve problems such as affecting the timeliness of fault monitoring, weak signal online detection defects, etc., and achieve the effect of stable online fault detection

Inactive Publication Date: 2019-09-03
CHENGDU UNIV +1
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is that the existing technology can be divided into offline and online from the immediacy of samples, mainly for machine operation failures in strong interference environments, most of which adopt relatively complicated offline methods, which seriously affect the timeliness of fault monitoring , There are serious defects in the online detection of weak signals. The purpose of the present invention is to provide a method for online detection of machine operation faults in a strong noise environment based on self-learning, so as to solve the above-mentioned problems

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
  • Self-learning-based on-line detection method for machine running faults in strong noise environment
  • Self-learning-based on-line detection method for machine running faults in strong noise environment
  • Self-learning-based on-line detection method for machine running faults in strong noise environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] like figure 1 As shown, the present invention is based on a self-learning strong noise environment machine operation fault online detection method, characterized in that, the method comprises the following steps: S1: during the operation of the machine, collect the vibration signal generated during the operation of the machine, and The collected vibration signal is detected by the FFT algorithm; S2: after the vibration signal is collected for the nth time and the FFT spectrum detection is performed, the FFT(n) spectrum detection is weighted; S3: after the FFT(n) spectrum detection is weighted , optimize the signal spectrum through the nonlinear threshold evolution method, and suppress the noise generated by the machine operation; S4: output the FFT(n) spectrum after the nonlinear threshold is performed to the fault recording terminal, and record the fault data; S5 : After completing the fault record, update the FFT data and feed it back to the acquisition terminal when ...

Embodiment 2

[0060] like Figure 2-5 As shown, this embodiment is specifically described on the basis of Embodiment 1, and compared through experiments, experiment: x(n)=exp(0.2πnj)+exp(0.4πnj)+exp(0.5πnj)*f( n)+w(n); Among them, the noise variance is 20, and the data window is 200.

[0061] pass figure 2 , 3 It can be seen that direct FFT analysis is almost impossible to detect machine fault signals online in a strong interference environment.

[0062] pass Figure 4 , 5 It can be seen that after the system is started, after a few cycles of self-learning, the system spectrum tends to be stable, and the natural vibration signal and fault signal of the system are clearly visible, which has a strong inhibitory effect on random noise.

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 self-learning-based on-line detection method for machine running faults in a strong noise environment. The method is characterized by comprising the following steps: S1, during the machine running process, collecting vibration signals generated in the machine running process and carrying out spectrum detection on the collected vibration signals based on an FFT algorithm;S2, after nth vibration signal collection and FFT spectrum detection, carrying out weighting on FFT (n) spectrum detection; S3, after FFT(n) spectrum detection weighting, optimizing a signal spectrumby means of nonlinear threshold evolution, and suppressing noises generated by machine running; S4, outputting the FFT(n) spectrum after the nonlinear threshold processing to a fault record terminal and recording fault data; and S5, after fault recording completion, updating FFT data and feeding back the data to a collecting terminal in machine running.

Description

technical field [0001] The invention relates to an on-line monitoring method, in particular to an on-line detection method for machine operation faults in a strong noise environment based on self-learning. Background technique [0002] With the development of society and the advancement of science and technology, the degree of automation of modern mass production is getting higher and higher, the structure of modern equipment is becoming more and more complex, the functions are becoming more and more perfect, and the connection between the internal parts of the equipment is getting closer. For dynamic systems, such as cyber-physical systems, power systems, aerospace systems, etc., due to internal failures, the system’s operating state is unstable or its performance is out of balance, which has a huge impact on production and even serious catastrophic accidents. SUMMARY OF THE INVENTION [0003] The technical problem to be solved by the present invention is that the existin...

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): G01M99/00G06F17/14G06F17/15G06N20/00
CPCG01M99/005G06F17/142G06F17/156G06N20/00
Inventor 蒋毅
Owner CHENGDU 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