Sensitive feature selection and dimensionality reduction method for vibration signal analysis

A technology of sensitive features and vibration signals, used in instruments, character and pattern recognition, computer parts, etc., can solve problems affecting the accuracy of fault classification and high computational complexity

Inactive Publication Date: 2019-01-04
XUZHOU MEDICAL UNIV
View PDF2 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, if high-dimensional statistical features are directly used for fault classification, the computational complexity is high, and it will also affect the accuracy of fault classification

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
  • Sensitive feature selection and dimensionality reduction method for vibration signal analysis
  • Sensitive feature selection and dimensionality reduction method for vibration signal analysis
  • Sensitive feature selection and dimensionality reduction method for vibration signal analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0046] 1. Relevant theoretical basis

[0047] 1. Maximum overlapping wavelet packet transform (MODWPT)

[0048] The Maximum Overlap Discrete Wavelet Transform (MODWT) is improved on the basis of DWT. Walden et al. pointed out that the traditional discrete wavelet transform has the following limitations:

[0049] (1) When the length N of the analyzed signal sequence is an integer power of 2, the complete DWT can be performed; when the length N of the sequence is a multiple of the integer power of 2, the partial DWT can be performed.

[0050] (2) The result of DWT analysis will change due to cyclic...

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 sensitive feature selection and dimension reduction method for vibration signal analysis. The method comprises the following steps: the vibration signal is decomposed by MODWPT to obtain each frequency band coefficient and node signal; each node signal is reconstructed by a single branch and corresponding statistical features are calculated; the frequency band coefficientand node signal are decomposed by MODWPT. FSELM, a feature selection method based on extreme learning machine, is used to select the sensitive features, and NPEMMC is used to reduce the dimension ofthe selected sensitive features. The low-dimensional sensitive features are used as input space to train the classifier, and the trained classification model is used to complete the fault pattern recognition. The invention can achieve ideal rolling bearing fault state identification effect.

Description

technical field [0001] The invention belongs to the technical field of mechanical fault detection, in particular to a sensitive feature selection and dimension reduction method for vibration signal analysis. Background technique [0002] Rolling bearings are one of the key components of rotating machinery, and their failure will seriously affect the safe and stable operation of rotating machinery. If the failure is not found in time and effective measures are taken, it may cause serious casualties and property losses. Therefore, carry out Rolling bearing fault diagnosis is of great significance to ensure the continuous safety of equipment and reduce maintenance costs. In recent years, in terms of fault diagnosis technology, with the continuous development of signal processing, data mining and artificial intelligence technology, data-driven fault diagnosis methods are getting more and more attention. [0003] The vibration signals of rolling bearings during operation contain...

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): G06K9/00G06K9/62
CPCG06F2218/06G06F2218/08G06F2218/12G06F18/211G06F18/213G06F18/24147
Inventor 俞啸左海维董飞卞水荣张立
Owner XUZHOU MEDICAL UNIV
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