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

Bearing fault diagnosis method based on cyclic correlation entropy and one-dimensional shallow convolutional neural network

A convolutional neural network and fault diagnosis technology, applied in the fields of deep learning and signal processing, can solve the problems of poor diagnosis effect and large amount of calculation of bearing signals processed by 1DCNN, so as to suppress non-Gaussian noise, simplify the structure, and avoid computational complexity. high effect

Pending Publication Date: 2021-12-31
TIANJIN UNIV OF TECH & EDUCATION TEACHER DEV CENT OF CHINA VOCATIONAL TRAINING & GUIDANCE
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a bearing fault diagnosis method based on cyclic correlation entropy and one-dimensional shallow convolutional neural network in view of the problems of large amount of calculation and poor diagnostic effect of 1D CNN processing bearing signals in the prior art

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
  • Bearing fault diagnosis method based on cyclic correlation entropy and one-dimensional shallow convolutional neural network
  • Bearing fault diagnosis method based on cyclic correlation entropy and one-dimensional shallow convolutional neural network
  • Bearing fault diagnosis method based on cyclic correlation entropy and one-dimensional shallow convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Such as figure 1As shown, the present invention discloses a bearing fault diagnosis method of cyclic correlation entropy and one-dimensional shallow convolutional neural network, comprising the following steps:

[0043] Step 1, collect N vibration signal samples Each sample signal x i The number of sampling points is M, and the sampling frequency is f s ;

[0044] Step 2, calculate each signal sample x i The time-varying correlation entropy matrix of The calculation formula is: Where τ is the delay variable, E(·) is the expectation operator, σ is the kernel length of the kernel function, κ σ ( ) is a kernel function that satisfies the Mercer condition, and the kernel function κ σ (·) Using Laplace kernel function, its calculation formula is: Where exp(·) is an exponential function, and ||·|| is a norm operator.

[0045] Step 3, calculate each signal sample x i The circular correlation entropy spectral density matrix of The formula is: Among them, FFT2[...

Embodiment 2

[0050] The experimental verification is carried out on the rolling bearing data set of Case Western Reserve University (CWRU). The sampling frequency of the motor vibration signal is 48kHz. The faulty bearing is the driving end deep groove ball bearing. The bearing model is SKF6205. The faulty defect of the bearing is processed by EDM . The patent of the present invention divides the fault categories into 10 types. According to the defect position, it is divided into bearing rolling body damage, inner ring damage and outer ring damage. The three different damage diameters of 0.007inch, 0.014inch and 0.021inch correspond to slight, moderate and Severe damage, using data sets A, B, and C of 3 different speeds and loads of 1hp (1772 rpm), 2hp (1750 rpm) and 3hp (1730 rpm), bearing rolling elements, inner rings , outer ring damage and normal state are marked as BF7, BF14, BF21, IF7, IF14, IF21, OF7, OF14, OF21 and NC, respectively, as shown in Table 1.

[0051] generalized cyclos...

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 bearing fault diagnosis method based on cyclic correlation entropy and a one-dimensional shallow convolutional neural network. The bearing fault diagnosis method comprises the following steps: collecting N vibration signal samples, and calculating a time-varying correlation entropy matrix, a cyclic correlation entropy spectral density matrix and generalized cyclostationarity DCS[sigma] of each signal sample xi; dividing the vibration signal samples into a training set, a verification set and a test set according to a certain proportion; and taking the generalized cyclostationarity DCS[sigma] as the input of the CCe-1D SCNN, performing one-dimensional shallow convolutional neural network parameter training and testing, and performing bearing fault mode classification. According to the method, the influence of Gaussian noise and non-Gaussian noise can be effectively suppressed, the fault features of the bearing are automatically extracted, the structure of the convolutional neural network is simplified, and the defects that the deep convolutional neural network is high in calculation complexity and prone to over-fitting and gradient disappearance are effectively overcome.

Description

technical field [0001] The invention relates to the technical fields of signal processing and deep learning, in particular to a bearing fault diagnosis method based on circular correlation entropy and one-dimensional shallow convolutional neural network. Background technique [0002] Since the convolutional neural network (CNN) can freely set the number of convolutional layers and pooling layers, it can effectively mine the fault features in mechanical signals through learning, and has been widely used in the field of electromechanical equipment fault diagnosis. However, since the original two-dimensional convolutional neural network (Two-dimensional Convolutional Neural Network, 2DCNN) is applied to the recognition of handwritten characters, the input layer is required to be a two-dimensional image. Therefore, when processing a 1D vibration signal, it is necessary to convert the 1D signal to As a 2D signal, it can then be used in the input layer of the convolutional neural ...

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): G06K9/62G01M13/045G06F17/16G06N3/04G06N3/08
CPCG06F17/16G06N3/08G01M13/045G06N3/045G06F18/2411G06F18/214
Inventor 李辉徐伟烝张寅
Owner TIANJIN UNIV OF TECH & EDUCATION TEACHER DEV CENT OF CHINA VOCATIONAL TRAINING & GUIDANCE
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