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

Method for optimizing multi-kernel multi-feature fusion support vector machine and identifying bearing fault

A support vector machine and multi-feature fusion technology, applied in the field of self-adjusting particle swarm optimization multi-core multi-feature fusion support vector machine, can solve the problems of cumbersome sensor installation and lack of multiple measurement positions, and achieve high fault identification accuracy , Reasonable design, high precision effect

Active Publication Date: 2018-05-22
INNER MONGOLIA UNIV OF SCI & TECH
View PDF9 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Multiple sensor installations are cumbersome and often do not have multiple measurement locations available

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
  • Method for optimizing multi-kernel multi-feature fusion support vector machine and identifying bearing fault
  • Method for optimizing multi-kernel multi-feature fusion support vector machine and identifying bearing fault
  • Method for optimizing multi-kernel multi-feature fusion support vector machine and identifying bearing fault

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] see figure 1 , figure 2 , image 3 , the present invention optimizes the multi-core multi-feature fusion support vector machine method for bearing fault identification, the steps are as follows: S1. Select the bearing vibration signal collected under a single sensor;

[0040] S2. Decompose the bearing vibration signals at different speeds through EMD (full name Empirical Mode Decomposition, empirical mode decomposition algorithm) to obtain IMF (full name Intrinsic Mode Function, eigenmode component) energy entropy and IMF permutation entropy;

[0041] S3. Fusion of IMF energy entropy and IMF permutation entropy under different rotational speeds is extracted to obtain fusion features containing different rotational speed information, which are used as support vector machine training samples to obtain multi-core multi-feature fusion support vector machines suitable for fault identification under different rotational speeds ;

[0042] S4. Integrating the performance of...

Embodiment 2

[0046] The optimized multi-core multi-feature fusion support vector machine of the present embodiment is used for the method of bearing fault identification, and the difference with embodiment 1 is: in step S4, multi-core least squares support vector machine construction process and parameter optimization process are as follows:

[0047] Select the appropriate Gaussian radial basis function kernel parameter g, polynomial kernel parameter c and combined kernel coefficient p, Gaussian radial basis function kernel: K g =exp(-g·||x-x i || 2 ); the polynomial kernel is defined as: K d =(x T x i +1) c ; Combined kernel function: K=p·(x T x i +1) c +(1-p)·exp(-g·||x-x i || 2 ); through SRPSO optimization parameters p, c, g, support vector machine identification accuracy as the fitness index, the greater the fitness index, the higher the fault identification accuracy; set parameters p, c, g as SRPSO particles, the optimization steps are as follows:

[0048] 1) Initialize the...

Embodiment 3

[0054] In this embodiment, the multi-core multi-feature fusion support vector machine is optimized, and the process for bearing fault identification is as follows: figure 1 shown. The essence of self-adjusting particle swarm optimization multi-core multi-feature fusion support vector machine used in support vector machine is the linear regression that maps samples from nonlinear function space to high-dimensional space, so that samples can be classified according to different characteristics, such as figure 2 shown. Support vector machines are used in pattern recognition processes such as image 3 It can be seen that the important indicators of the difference in recognition accuracy of support vector machines are feature selection and parameter selection.

[0055] For feature selection, S1. Select the bearing vibration signal collected under a single sensor; S2. Decompose the bearing vibration signal at different speeds through EMD to obtain IMF energy entropy and IMF arran...

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 method for optimizing a multi-kernel multi-feature fusion support vector machine and identifying a bearing fault. The method comprises a step of selecting bearing vibrationsignals collected under a single sensor, a step of decomposing bearing vibration signals at different rotational speeds by EMD to obtain IMF energy entropy and IMF permutation entropy, a step of extracting IMF energy entropy and IMF permutation entropy at different rotation speeds and fusing the IMF energy entropy and IMF permutation entropy to obtain fusion features including different rotationalspeed information for support vector machine training samples so as to obtain the multi-kernel multi-feature fusion support vector machine which is adapted to fault identification at different rotation speeds, a step of integrating Gaussian radial basis function kernel and polynomial function kernel performance, allowing the training samples to be in linear regression from a nonlinear function space to high-dimensional space mapping such that the training samples are classified according to different characteristics, forming a multi-kernel least square support vector machine, and enabling thesupport vector machine to identify a fault feature under a variable load, and a step of carrying out parameter optimization on the training samples with a self-adjusting particle swarm algorithm withstrong convergence, comparing the training samples and a test sample, and identifying the bearing fault.

Description

technical field [0001] The invention relates to a fault identification method for rotating machinery, in particular to a self-regulating particle swarm optimization multi-core multi-feature fusion support vector machine for high-precision bearing fault identification. Background technique [0002] Large-scale rotating machinery is usually placed in harsh environments and sparsely populated areas. General fault detection methods require personnel to regularly obtain feature information and perform complex analysis and processing, which consumes a lot of manpower and material resources. As an intelligent pattern recognition method, support vector machine does not require personnel to stay for a long time or manually analyze the fault location, so it is widely used in the fault diagnosis of rotating machinery. For example, the invention patent with publication number CN107065568A proposes a transformer fault diagnosis method based on particle swarm support vector machine, and t...

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): G06K9/62G06N3/00
CPCG06N3/006G06F18/2411G06F18/253G06F18/214
Inventor 张超范业锐石炜杨柳王建国何园园朱腾飞
Owner INNER MONGOLIA UNIV OF SCI & TECH
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