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

One-way valve fault feature extraction method based on improved permutation entropy

A technology of fault features and extraction methods, which is used in mechanical valve testing, pattern recognition in signals, complex mathematical operations, etc. It can solve problems such as loss of information and affecting diagnostic efficiency.

Inactive Publication Date: 2020-07-07
KUNMING UNIV OF SCI & TECH
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, PE is sensitive to noise, and usually needs to be used in combination with filtering noise reduction, modal decomposition and other methods, which affects the diagnostic efficiency; moreover, when extracting mechanical fault features, PE only considers the order of the signals and ignores the signal amplitude interval. difference, losing the information contained in the signal amplitude

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
  • One-way valve fault feature extraction method based on improved permutation entropy
  • One-way valve fault feature extraction method based on improved permutation entropy
  • One-way valve fault feature extraction method based on improved permutation entropy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Embodiment 1: as figure 1 As shown, a check valve fault feature extraction method based on improved permutation entropy, the specific steps are:

[0057] Step1: Use the acceleration sensor to sample when the check valve is normal, the valve is stuck, and the wear is faulty, and the vibration data of the check valve is obtained in each state;

[0058] Step2: Improve the permutation entropy by adding a weighted coefficient to the reconstruction component of the permutation entropy, and propose an improved permutation entropy algorithm;

[0059] Step3: Use the improved permutation entropy to directly extract the fault features of the check valve under the background of strong noise, and realize the fault diagnosis of the check valve.

[0060] The specific steps of the permutation entropy algorithm in the Step2 are:

[0061] Step2.1: The discrete time series of length T Perform phase space reconstruction to obtain the reconstruction matrix Where m is the embedding di...

Embodiment 2

[0075] Embodiment 2: The present invention uses simulation signals to verify the effectiveness and superiority of improving permutation entropy from the aspects of detecting signal mutations, measuring signal complexity and anti-noise ability.

[0076] First, use the simulation signal 1 to verify the advantages of the improved permutation entropy in detecting signal mutations. The simulation signals are Gaussian white noise signals and shock signals, such as image 3 shown. In the figure, the amplitude of the shock signal is 50, the mean of Gaussian white noise is 0, and the standard deviation is 1. Calculate the PE and IPE of the simulated signal 1, Figure 4 It is the average value of 50 calculation results for the simulated signal. In the calculation process, a sliding window is constructed with 100 data points, and the sliding step is 10.

[0077] from Figure 4 It can be seen from the figure that when the sliding window only contains Gaussian white noise, the randomne...

Embodiment 3

[0082] Embodiment 3: The experimental data of this example comes from the rolling bearing data of the electrical engineering laboratory of Case Western Reserve University in the United States, select 25 groups of data of rolling bearing normal state, inner ring fault, outer ring fault, and rolling element fault, and the length of the data for 2400. Because the data is the data of laboratory simulated faults, the data is almost free of noise and relatively regular. Using improved permutation entropy to directly extract fault features, the experimental results are as follows Figure 8 shown.

[0083] Depend on Figure 8 It can be seen that since the data of rolling bearings contains almost no noise, the fault characteristics of bearings can be extracted effectively by directly using the improved permutation entropy. The IPE in the normal state is between 0.5-0.6, the outer ring fault is between 0.6-0.7, the rolling element fault is between 0.7-0.8, the inner ring fault is bet...

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 one-way valve fault feature extraction method based on improved permutation entropy, and belongs to the technical field of mechanical fault diagnosis and signal processing.The method comprises the following steps: firstly, aiming at the problem that the permutation entropy algorithm only considers the permutation sequence of signals and ignores the signal amplitude, adding a weighting coefficient to a reconstructed component to improve the permutation entropy, and further proposing an improved permutation entropy algorithm; directly adopting an improved permutationentropy algorithm to extract one-way valve fault features under a strong noise background, and completing fault diagnosis of the one-way valve. According to the method, the fault characteristics of the one-way valve are extracted by utilizing the permutation entropy, improvement is carried out aiming at the defects of the permutation entropy, the noise interference resistance is improved, the signal preprocessing step is omitted, the program running time is shortened, and the diagnosis efficiency is improved.

Description

technical field [0001] The invention relates to a check valve fault feature extraction method based on improved permutation entropy, which belongs to the technical field of mechanical fault diagnosis and signal processing. Background technique [0002] The high-pressure diaphragm pump is the core equipment for slurry pipeline transportation, and is used to transport high-concentration and highly corrosive slurry materials. As the main component of the diaphragm pump, the check valve is the most prone to failure in actual work, and its failure directly affects the operating status of the entire diaphragm pump system. Therefore, the fault diagnosis of the check valve is particularly important. However, due to the complexity of the mechanical system of the diaphragm pump, there are many excitation sources of the signal, and there is strong background noise in the signal of the check valve, which makes it difficult to extract the fault features of the check valve. [0003] In ...

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): G01M13/003G06F17/16G06K9/00
CPCG01M13/003G06F17/16G06F2218/10G06F2218/08
Inventor 黄国勇潘震吴建德冯早范玉刚
Owner KUNMING 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