Bearing fault degree identifying method based on flow diagram and non-nave Bayesian inference

An identification method and technology of failure degree, applied in mechanical bearing testing, mechanical component testing, machine/structural component testing, etc., can solve the problems of low diagnostic accuracy, weak classification and reasoning ability, high computational cost, etc. Computational complexity, overcoming conditional constraints, the effect of good diagnostic results

Active Publication Date: 2019-03-22
哈尔滨轴承制造有限公司
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problems of high computing cost and low diagnostic accuracy caused by redundant symptom attribute nodes in the flow graph and the weak classification reasoning ability of the flow graph, the present invention provides a method based on the flow graph and non-naive Bayesian reasoning Identification method of bearing fault degree

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
  • Bearing fault degree identifying method based on flow diagram and non-nave Bayesian inference
  • Bearing fault degree identifying method based on flow diagram and non-nave Bayesian inference
  • Bearing fault degree identifying method based on flow diagram and non-nave Bayesian inference

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0024] Specific implementation mode one: combine figure 1 This embodiment will be described. This embodiment provides a bearing fault degree identification method based on flow diagram and non-naive Bayesian reasoning, the method includes the following steps:

[0025] Step 1. Extract the fault diagnosis features of the roller bearings in the training samples to construct a standardized flow diagram;

[0026] Step 2, using the node reduction algorithm based on the importance of symptom attribute nodes to delete redundant symptom attribute nodes in the standardized flow graph, and obtain the node-reduced flow graph;

[0027] Step 3: Extract the fault diagnosis features of the roller bearings in the waiting samples, and use the non-naive Bayesian inference algorithm based on the flow graph to identify the state of the roller bearings in the waiting samples.

specific Embodiment approach 2

[0028] Specific implementation mode two: combination figure 2 This embodiment will be described. The difference between this embodiment and the specific embodiment one is: the specific steps of the node reduction algorithm based on the importance of symptom attribute nodes in the second step are as follows:

[0029] Step 21, calculating the information entropy H(G) of the standardized flow graph G;

[0030] Step 22: Calculate symptom attribute node set N C Relative to the decision attribute node set N D The mutual information H(N C ,N D );

[0031] Step two and three, calculate symptom attribute node x i ∈N C ,(i=1,...,m), m is the number of symptom attribute nodes, Sig(x i ,N D ) is relative to the decision attribute node set N D the importance of

[0032] Step 24, if symptom attribute node x i ∈N C The importance of Sig(x i ,N D )=0, then symptom attribute node x i is unnecessary, otherwise essential;

[0033] Step 25, repeat steps 23 and 24 for other sympt...

specific Embodiment approach 3

[0035] Specific embodiment three: the difference between this embodiment and specific embodiment two is: the symptom attribute node x∈N in the step two or three C Relative to the decision attribute node set N D The importance of Sig(x,N D ) is defined as follows:

[0036] Let the standardized flow graph G=(N,B,σ), N represents the node set, B represents the directed branch set, σ is the standardized flow function, N C and N D are symptom attribute node set and decision attribute node set respectively, then symptom attribute node x∈N C Relative to the decision attribute node set N D The importance is:

[0037] Sig(x,N D )=H(N C ,N D )-H(N C -{x},N D ) (1).

[0038] Among them, H(N C ,N D ) is symptom attribute node set N C Relative to the decision attribute node set N D The mutual information of H(N C -{x},N D ) is to remove symptom attribute node x∈N C Post symptom attribute node set N C - {x} relative to decision attribute node set N D mutual information. ...

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 bearing fault degree identifying method based on a flow diagram and a non-nave Bayesian inference. The identifying method comprises the following steps: step one, extractingfault diagnosis features of a roller bearing in a training sample, and used for constructing a standardized flow diagram; step two, deleting a redundant sign attribute node in the standardized flow diagram by using a node reduction algorithm based on sign attribute node importance, and acquiring the flow diagram after node reduction; and step three, extracting the fault diagnosis features of the roller bearing in a sample to be detected, and identifying a state of the roller bearing in the sample to be detected by using a non-nave Bayesian inference algorithm based on the flow diagram. The method is capable of intuitively and accurately identifying a fault degree of the roller bearing, and providing a novel solution idea for fault degree identification of the roller bearing.

Description

technical field [0001] The invention relates to a fault degree identification method, in particular to a bearing fault degree identification method based on flow graph and non-naive Bayesian reasoning. Background technique [0002] As a key component of rotating machinery, roller bearings directly affect the normal operation of mechanical equipment. However, due to long-term operation in complex and harsh working conditions such as high speed and heavy load, the inner and outer rings of roller bearings are prone to local failures such as cracks, pitting or peeling to varying degrees, which reduces the accuracy of the equipment and even endangers personal safety. accident happened. Therefore, the identification of the failure degree of roller bearings is of great significance to prevent the occurrence of potentially catastrophic accidents and ensure the safe operation of mechanical systems. [0003] In recent years, intelligent diagnosis technology has received widespread a...

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): G01M13/04G01M13/045
CPCG01M13/04G01M13/045
Inventor 于军于广滨
Owner 哈尔滨轴承制造有限公司
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