Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A rolling bearing fault diagnosis method based on improved pso algorithm and optimized fsvm

A rolling bearing and fault diagnosis technology, which is applied in mechanical bearing testing, design optimization/simulation, calculation, etc., can solve the problems of reduced diagnostic accuracy and classification failure to achieve group optimization, so as to improve speed and accuracy, and make the fault diagnosis model reasonable Effective, clear and precise results

Active Publication Date: 2020-08-25
KUNMING UNIV OF SCI & TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although SVM has good classification ability and global generalization ability, due to the influence of environmental factors, the samples collected by SVM have fuzzy information such as noise points and isolated points, which eventually makes the classification unable to achieve group optimization and accurate diagnosis. rate is also significantly reduced

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
  • A rolling bearing fault diagnosis method based on improved pso algorithm and optimized fsvm
  • A rolling bearing fault diagnosis method based on improved pso algorithm and optimized fsvm
  • A rolling bearing fault diagnosis method based on improved pso algorithm and optimized fsvm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] Embodiment 1: as figure 1As shown, a rolling bearing fault diagnosis method based on the improved PSO algorithm to optimize the FSVM, firstly use the wavelet decomposition method to extract the feature vector of the rolling bearing fault data; then use the PSO algorithm to optimize the penalty coefficient and kernel function parameters of the FSVM, Build an optimized FSVM model; then input the extracted feature vectors into the optimized FSVM for training to obtain a rolling bearing fault diagnosis model, and finally use the rolling bearing fault diagnosis model for rolling bearing fault diagnosis model for fault diagnosis. In order to balance the global optimization advantages and local optimization advantages of the particle swarm optimization algorithm model to a greater extent, the present invention will add inertia factors in the process of algorithm optimization, and incorporate the IPSO-FSVM classification model with dynamically updated inertia weights to greatly ...

Embodiment 2

[0054] Embodiment 2: In this embodiment, the method as shown in Embodiment 1 is adopted to carry out the fault diagnosis of the bearing, and the specific implementation steps are as follows:

[0055] According to the wavelet three-layer decomposition principle, the energy characteristics of the bearing are extracted, and some experimental data are shown in Table 1. Four states of bearings (normal, inner ring fault, outer ring fault and rolling element fault) are selected in the experiment, and 30 sets of samples are selected for each type of fault as training samples, so a total of 120 feature vectors need to be selected, and the selected 120 sets of feature vectors The vectors are entered into the data samples in preparation for training. Then select 20 eigenvectors for each kind of fault, a total of 80 are stored in the data sample as the test sample set.

[0056] Table 1. Partial samples of bearing fault energy features extracted by wavelet

[0057]

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 relates to a rolling bearing fault diagnosis method for optimizing an FSVM based on an improved PSO algorithm, and belongs to the technical field of mechanical engineering automation. The rolling bearing fault diagnosis method comprises the steps that firstly, a wavelet decomposition method is utilized to extract feature vectors of fault data of a rolling bearing; then penalty coefficients and kernel function parameters of the FSVM are optimized by using the PSO algorithm, and an optimized FSVM model is constructed; the extracted feature vectors are input into the optimized FSVMfor training to obtain a rolling bearing fault diagnosis model, and lastly, fault diagnosis is carried out by using the rolling bearing fault diagnosis model. The rolling bearing fault diagnosis method for optimizing the FSVM based on the improved PSO algorithm can obtain the fault diagnosis precision rate as high as possible in a short time.

Description

technical field [0001] The invention relates to a rolling bearing fault diagnosis method based on an improved PSO algorithm to optimize FSVM, and belongs to the technical field of mechanical engineering automation. Background technique [0002] The tamping car is a large-scale maintenance machine, which is mainly used for the construction of new railway lines and troubleshooting during railway maintenance. Its purpose is to ensure the stable and efficient operation of trains. Therefore, fast and accurate judgments on various faults of tamping vehicles have engineering value that cannot be ignored. Rolling bearing is an important part of mechanical equipment, and it is also one of the parts with frequent failures. It determines whether the entire mechanical equipment can work normally with a high probability. Because the traditional fault diagnosis relying on personal experience not only wastes a lot of time and experience, but also its diagnostic accuracy is often unsatisfa...

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 Patents(China)
IPC IPC(8): G01M13/04G06F30/17G06F30/20G06N3/00
CPCG01M13/04G06F30/17G06F30/20G06N3/006
Inventor 王海瑞林雅慧靖婉婷
Owner KUNMING UNIV OF SCI & TECH
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
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