Power shaft system bearing fault detection method and system

A fault detection and power shafting technology, applied in the field of signal processing and deep learning, can solve problems such as abnormal mechanical equipment, casualties, and it is difficult to take into account the time-frequency characteristics of non-stationary signals.

Inactive Publication Date: 2021-04-02
中国船舶工业综合技术经济研究院
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Bearing failure will cause abnormalities in mechanical equipment, and even cause casualties in severe cases
[0003] When a rolling bearing fails, its vibration signal often exhibits non-stationary and nonlinear characteristics, and the fault characteristics are easily overwhelmed by strong background noise. It is difficult to take into account the time-frequency characteristics of non-stationary signals by using traditional signal analysis methods
Time-frequency domain analysis methods such as wavelet analysis, Wigner-Ville distribution, and short-time Fourier transform emerged as the times require, but these signal processing methods lack adaptability

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
  • Power shaft system bearing fault detection method and system
  • Power shaft system bearing fault detection method and system
  • Power shaft system bearing fault detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] see figure 1 , the present embodiment provides a power shaft bearing fault detection method, the method includes the following steps:

[0051] Step 101: Obtain the vibration signal of the bearing.

[0052] Step 102: Using singular spectrum decomposition to decompose the vibration signal into singular spectral components of several frequency scales. The specific decomposition process can be as follows:

[0053] (1) Construct a new trajectory matrix. Suppose x(n) is a time series, its embedding dimension is M, and the data length is N, and x(n) is constructed into a matrix X of size M×N, then the i-th row of matrix X can be expressed as x i =(x(i),...,x(N),x(1),...,x(i-1)), where i=1,...,M, namely

[0054] (2) Adaptively select the embedding dimension size M. The singular spectrum decomposition adopts the adaptive law to select the embedding dimension M at the jth iteration, and the specific process can be as follows:

[0055] a. Calculate the remaining component ...

Embodiment 2

[0095] see Figure 7 , the present embodiment provides a power shaft bearing fault detection system, the system includes:

[0096] A vibration signal acquisition module 701, configured to acquire a vibration signal of the bearing;

[0097] A singular spectrum decomposition module 702, configured to decompose the vibration signal into singular spectrum components of several frequency scales by employing singular spectrum decomposition;

[0098] A screening module 703, configured to calculate the kurtosis value of each of the singular spectral components, and select the singular spectral component whose kurtosis value is within a set threshold range as the target singular spectral component;

[0099] A reconstruction module 704, configured to reconstruct the vibration signal based on the target singular spectral component to obtain a reconstructed vibration signal;

[0100] Diagnosis module 705, configured to input the reconstructed vibration signal into the trained neural net...

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 power shaft system bearing fault detection method and system. The method comprises the following steps: decomposing an original vibration signal into singular spectrum components of a plurality of frequency scales by singular spectrum decomposition, and selecting effective singular spectrum components to reconstruct the signal according to a kurtosis criterion; and constructing a one-dimensional convolutional neural network structure, inputting the reconstructed signal into a model for training, fully extracting the characteristics of the signal, and outputting a diagnosis result through an output layer, thereby achieving the precise diagnosis of a fault bearing. The influence of background noise can be effectively reduced, the calculation efficiency of sparse representation is improved, and effective fault diagnosis is realized.

Description

technical field [0001] The invention relates to the field of signal processing and deep learning, in particular to a method and system for detecting faults of power shafting bearings. Background technique [0002] Rolling bearings are one of the important components of rotating mechanical equipment, used to support the rotating body and provide torque and power for the transmission system, so as to ensure its safe and stable operation. Bearing failures will cause abnormalities in mechanical equipment, and even cause casualties in severe cases. [0003] When a rolling bearing fails, its vibration signal often exhibits non-stationary and nonlinear characteristics, and the fault characteristics are easily overwhelmed by strong background noise. It is difficult to take into account the time-frequency characteristics of non-stationary signals by using traditional signal analysis methods. Time-frequency domain analysis methods such as wavelet analysis, Wigner-Ville distribution, ...

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): G01M13/045G06N3/04G06N3/08
CPCG01M13/045G06N3/08G06N3/045
Inventor 武朔晨刘柏方晓彤周旋唐庆李汉智田宏伟
Owner 中国船舶工业综合技术经济研究院
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