Method for diagnosing hub bearing fault of automobile based on Hankel matrix

A Hankel matrix, automobile wheel technology, applied in the field of bearing fault diagnosis, can solve the problems of large original vibration signal dimension, affecting the success of fault diagnosis, information dispersion, etc., to achieve the effect of improving correlation

Inactive Publication Date: 2018-12-07
WENZHOU UNIVERSITY
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the original vibration signal has a large dimension and scatt

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 diagnosing hub bearing fault of automobile based on Hankel matrix
  • Method for diagnosing hub bearing fault of automobile based on Hankel matrix
  • Method for diagnosing hub bearing fault of automobile based on Hankel matrix

Examples

Experimental program
Comparison scheme
Effect test

Embodiment example 1

[0090] In this case, the vibration data for simulating the failure of an automobile hub bearing is used. The bearing model is: NSK / 38BWD12, the number of rolling elements is double row, the number of rolling elements is 30, the thickness of the bearing is 36mm, and the inner diameter of the bearing is 38mm, the outer diameter of the bearing is 72mm. The fault types of bearings are: (1) normal bearing, which is predefined as failure mode 1; (2) 0.1mm inner ring fault, which is predefined as failure mode 2; (3) 0.1mm rolling element fault, which is predefined as failure mode Mode 2; (4) 0.1mm outer ring fault, predefined as failure mode 4; (5) 0.3mm inner ring fault, predefined as failure mode 5; (6) 0.3mm rolling element fault, predefined as Failure mode 6; (7) 0.3mm outer ring failure, predefined as failure mode 7; (8) 0.5mm inner ring failure, predefined as failure mode 8; (9) 0.5mm rolling element failure, predefined It is failure mode 9; (10) 0.5mm outer ring failure is pr...

Embodiment example 2

[0097] Take the fault data of a wheel hub bearing in an automobile transmission system. The bearing model is: SKF / DAC30600037. The diameter is 60mm. The fault types of bearings are: (1) normal bearing, which is predefined as failure mode 1; (2) 0.2mm inner ring fault, which is predefined as failure mode 2; (3) 0.2mm outer ring fault, which is predefined as fault Mode 3; (4) 0.2mm rolling element failure, predefined as failure mode 4; (5) 0.3mm inner ring failure, predefined as failure mode 5; (6) 0.3mm outer ring failure, predefined as failure mode 6. The bearing rotation frequency is 25Hz, and the sampling frequency is 12k Hz.

[0098] The original vibration signal waveform is as Figure 9 Shown: (a) failure mode 1; (b) failure mode 2; (c) failure mode 3; (d) failure mode 4; (e) failure mode 5; (f) failure mode 6. It can be seen from the figure that each type of fault signal has some differences except for the amplitude, and it is difficult to observe the fault characteri...

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

PropertyMeasurementUnit
Thicknessaaaaaaaaaa
The inside diameter ofaaaaaaaaaa
Outer diameteraaaaaaaaaa
Login to view more

Abstract

The invention relates to a method for diagnosing the hub bearing fault of an automobile based on a Hankel matrix. The method comprises steps of firstly constructing the Hankel matrix to achieve the two-dimensional matrix representation of an original vibration signal and to improve signal correlation; secondly, establishing a convolutional neural network (CNN) of a known fault mode to enhance a hidden Markov model; and finally, diagnosing a fault mode of an unknown fault type by using the model. The CNN is a data-driven feature learning method, can perform convolution and sub-sampling operations on a two-dimensional signal represented by the Hankel matrix from the original data by using the CNN model, completely retains a part of representing the features of the signal, reduces the high-dimensional interference components in the signal, solves the feature automatic learning problem of the fault signals, and finally establishes the hidden Markov model of the known fault mode by using the self-learned feature. On the one hand, the method uses the CNN to automatically learn the features and reduce data dimension so as to obtain the distributed feature representation of the data; and on the other hand, determines the fault type by using the dynamic sequence modeling capability and the timing sequence mode classification ability of the Hidden Markov Model.

Description

technical field [0001] The invention belongs to the field of bearing fault diagnosis, and specifically refers to a method for diagnosing the fault of an automobile hub bearing based on a Hankel matrix, in particular to a method for diagnosing an automobile hub based on a convolutional neural network enhanced hidden Markov model based on a Hankel matrix approach to bearing failure. Background technique [0002] Automobile hub bearing is one of the key components of the automobile chassis system, which has the function of carrying the weight of the vehicle body and guiding the steering of the wheel hub. Automobile hub bearings are usually installed between the suspension and the hub to connect the hub and tires, and their operating status directly affects the comfort and safety of the car when driving. Once a failure occurs, it will cause increased vibration and noise, resulting in strong bumps and sharp noises during driving, posing a huge safety hazard. Therefore, real-tim...

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
IPC IPC(8): G06K9/62G01M13/04
CPCG01M13/04G06F18/2415G06F18/295
Inventor 向家伟王淑慧蒋勇英钟永腾
Owner WENZHOU UNIVERSITY
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