Rotating machine fault diagnosis method based on wavelet packet decomposition

A technology of wavelet packet decomposition and rotating machinery, applied in random CAD, computer parts, special data processing applications, etc., can solve the problems of mode aliasing, loss of original signal frequency components, low calculation efficiency, etc., and achieve good robustness , simplified classifier modeling, and the effect of removing redundant features

Pending Publication Date: 2021-02-09
CHINA SHIP DEV & DESIGN CENT
View PDF9 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above method still has some drawbacks
For example, EMD has disadvantages such as endpoint effects, mode aliasing, under-envelope and over-envelope, while LMD has disadvantages of mode aliasing and computational inefficiency
In addition, these methods are all based on "modes", and their sub-signals may lose some frequency components of the original signal

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
  • Rotating machine fault diagnosis method based on wavelet packet decomposition
  • Rotating machine fault diagnosis method based on wavelet packet decomposition
  • Rotating machine fault diagnosis method based on wavelet packet decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0105] Example 1: Effectiveness verification using the data of rotor and bearing mixed faults

[0106] In order to verify the effectiveness of the fault diagnosis method proposed in this intellectual achievement, this example uses the data set of mixed faults of rotor and bearing on the mechanical fault simulator platform to verify the effectiveness of the proposed method. The experimental platform is composed of AC motor, coupling, acceleration sensor, rotor, rolling bearing, centering adjustment disc, data acquisition box and inverter. The data set used contains nine types of faults, including shaft center bending, rotor warping, coupling bending, eccentric rotor, rotor unbalance, and rolling element faults of rolling bearings, inner ring faults, outer ring faults, and mixed inner and outer ring faults. type and a health status, as shown in Table 2. The data sampling frequency is 6kHz, and the motor speed is 2100rpm.

[0107] Specific steps are as follows:

[0108] (1) Da...

Embodiment 2

[0137] Example 2: Validation verification using gearbox data under complex working conditions

[0138] Since the mixed data set of the rotor and bearing in Example 1 has a single working condition, the gearbox data set with more complex working conditions is used to further verify the effectiveness of the method proposed in this intellectual achievement. The experimental platform is composed of electromagnetic brake, torque sensor, single-stage reducer, brake controller and servo motor. Gears with different crack lengths (including 0, 5, 10, 15 mm) were used and the sampling frequency was 5 kHz. In this intellectual achievement, ten data sets composed of data from twenty working conditions are used for experimental verification. The detailed information of the twenty working conditions and ten data sets are shown in Table 8 and Table 9, respectively.

[0139] Table 8

[0140]

[0141] Table 9

[0142]

[0143]

[0144] Data sets from A1 to A4 correspond to single-s...

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 rotating machine fault diagnosis method based on wavelet packet decomposition. The method comprises the following steps: 1) collecting vibration signals of a rotating machinein a normal state and a fault state; 2) selecting a wavelet basis function for fault feature extraction; 3) according to the selected wavelet basis function, obtaining sub-signals of different frequency bands of the vibration signal through wavelet packet decomposition; 4) calculating a fuzzy entropy value of the sub-signal to obtain a fault feature vector; 5) performing feature importance sorting according to the correlation, and selecting a set number of fault feature vectors with top sorting results according to the sorting results; 6) using a classifier to construct a fault diagnosis model, dividing the selected fault feature vector and the category label into a training set and a test set, and using the training set as the input of the model to train the model; and 7) inputting the test set into the fault diagnosis model to obtain a fault diagnosis result. According to the method, high-quality fault features can be effectively extracted, and the accuracy of fault diagnosis is improved.

Description

technical field [0001] The invention relates to mechanical fault diagnosis technology, in particular to a method for fault diagnosis of rotating machinery based on wavelet packet decomposition. Background technique [0002] As a key component in the transmission system, rotating machinery is widely used in industrial production such as motors, engines, bearings, and gearboxes. The key components of rotating machinery are prone to failure under harsh or complex working conditions, which directly affects the mechanical performance and even seriously affects production safety. Therefore, constructing a fault diagnosis scheme for rotating machinery under complex working conditions is of great significance to ensure the safe operation of equipment and reduce economic losses. [0003] In the field of rotating machinery fault diagnosis, vibration signal acquisition, feature extraction and fault mode recognition are three important aspects, and feature extraction directly affects 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): G06F30/17G06F30/27G06K9/00G06K9/62G06F111/08
CPCG06F30/17G06F30/27G06F2111/08G06F2218/08G06F18/22G06F18/214G06F18/24
Inventor 周涛涛陈志敏原宗张冬邹大程
Owner CHINA SHIP DEV & DESIGN CENT
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