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

Bearing fault diagnosis based on pseudo-tag semi-supervised kernel local Fisher discriminant analysis

A Fisher discrimination and fault diagnosis technology, applied in the testing of computer parts, mechanical parts, character and pattern recognition, etc., can solve problems such as long-term local optimal solutions

Inactive Publication Date: 2019-04-05
NORTHEAST FORESTRY UNIVERSITY
View PDF4 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above method requires more parameters to be trained, which leads to a longer time and is easy to fall into a local optimal solution.

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 based on pseudo-tag semi-supervised kernel local Fisher discriminant analysis
  • Bearing fault diagnosis based on pseudo-tag semi-supervised kernel local Fisher discriminant analysis
  • Bearing fault diagnosis based on pseudo-tag semi-supervised kernel local Fisher discriminant analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] Based on pseudo-label semi-supervised nuclear local Fisher discriminant analysis for bearing fault diagnosis, the local Fisher discriminant analysis algorithm includes the following specific steps:

[0075] Let x i ∈R d Represents the i-th sample vector, and its corresponding class label is y i ∈{1,2,...,c}, c is the number of categories. Let X n ={x 1 , X 2 ,..., x i ,..., x n }∈R d×n Represents the labeled sample data matrix, X m ={x 1 , X 2 ,..., x i ,..., x m }∈R d×m Represents the overall sample data matrix, where m represents the number of training samples, n is the number of labeled samples, and m>n. Let X m ={X n , X u }, X u Is a collection of unlabeled samples. Suppose z i ∈R r (1≤r≤d) is through the matrix T ∈ R d×r The projection representation of the transformed low-dimensional subspace: z i = T T x i .

[0076] The local Fisher discriminant analysis algorithm (LFDA) can be expressed by the following optimization problem:

[0077]

[0078] Here, S lb , S lw ∈...

Embodiment 2

[0106] Based on pseudo-label semi-supervised nuclear local Fisher discriminant analysis for bearing fault diagnosis, the density peak clustering algorithm used for pseudo-label generation includes the following specific steps:

[0107] Given data set X m ={x 1 , X2,..., x i ,..., x m }∈R d×m , Where x i ∈R d Represents the i-th sample vector, for each sample point x i Firstly calculate its local density value ρ quantitatively i Distance δ from the sample point with higher distance density i , And their definitions are as follows:

[0108]

[0109] Here parameter d c To cut off distance need to be specified in advance, d ij Represents x i And x j Euclidean distance.

[0110] Further set Means A descending sequence of, which satisfies:

[0111]

[0112]

[0113] Obviously, it is not difficult to find from the above formula that for the sample points whose density value is the local or global maximum, their δ i Will be lower than the δ of other sample points j The value is much larger...

Embodiment 3

[0126] Based on the pseudo-label semi-supervised nuclear local Fisher discriminant analysis bearing fault diagnosis, the pseudo-label semi-supervised nuclear local Fisher discriminant analysis bearing fault diagnosis method includes the following specific steps:

[0127] Use the density peak clustering algorithm to analyze all sample sets X m Perform cluster analysis to get the cluster label set of sample points And whether it is an identification set of boundary points What needs to be explained here is the number of clusters n c It does not need to be the same as the number of categories, which makes it better to adapt to multi-modal data distribution. Construct local inter-cluster divergence S according to the above information ulb And local clustering divergence S ulw The regularization term is specifically expressed as follows:

[0128]

[0129]

[0130] Here W ulb , W ulw Is an m×m matrix, and

[0131]

[0132]

[0133] Represented in cluster c i ∈{1, 2,..., n c } The number...

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

Bearing fault diagnosis based on pseudo-tag semi-supervised kernel local Fisher discriminant analysis is provided. The method is characterized in comprising the following steps: (1) collecting vibration signals of bearings under different working conditions to form a training sample; (2) performing feature extraction on the training sample obtained in (1); (3) performing normalization processing on features obtained in (2); (4) obtaining a clustering tag set by using density peak clustering for the entire feature set obtained in (3); (5) using clustering pseudo-tags obtained in (4) to construct local inter-cluster divergence and intra-cluster divergence regularization terms, and combining the regularization terms with the inter-class divergence and intra-class divergence with tag samples in the FDA to determine a final projection vector; (6) using the final projection vector obtained in (5) to solve a projection set of the tagged feature set in the dimensionality reduction space; (7) using the projection set obtained in (6) to train an extreme learning machine; and (8) performing processing of (2), (3) and (5) on the collected vibration signals, and inputting the processed vibration signals to determine the working conditions. The technical scheme of the present invention is applied to the problem of fault identification of bearing equipment.

Description

Technical field: [0001] The application of the present invention relates to the field of fault diagnosis of bearing equipment, in particular to a bearing fault diagnosis based on pseudo-label semi-supervised nuclear local Fisher discriminant analysis. Background technique: [0002] In the industrial field, in order to increase the reliability of equipment performance and reduce the probability of a decrease in output due to machine failures, the monitoring of machine operating status has attracted more and more attention. Rotating machinery is the most widely used type of machinery in the industrial sector. Many machinery such as steam turbines, compressors, fans and rolling mills belong to this category. However, its core component bearings often affect its normal operation due to various types of failures, and sometimes even cause serious machine crashes and deaths due to certain failures, and cause significant economic losses. Therefore, it is very important to carry out fault...

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): G05B23/02G01M13/045G06K9/62
CPCG05B23/0262G01M13/045G05B2219/24065G06F18/23G06F18/2411
Inventor 陶新民任超姜述杰郭文杰李青刘锐
Owner NORTHEAST FORESTRY UNIVERSITY
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