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

Bearing fault diagnosis method based on average multi-granularity decision rough set and NNBC

A fault diagnosis, multi-granularity technology, applied in mechanical bearing testing, measuring devices, instruments, etc., can solve problems such as inappropriate selection of constraints, improve clustering effect, reduce computational complexity, and reduce the number of input variables. Effect

Active Publication Date: 2018-08-17
哈尔滨力哈智能科技有限公司 +1
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem of inappropriate selection of limiting conditions in the process of bearing fault diagnosis based on multi-granularity rough sets, and to provide a novel solution for the fault diagnosis of rolling bearings, and propose a rough set based on average multi-granularity decision-making and NNBC Bearing Fault Diagnosis Method

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 diagnosis method based on average multi-granularity decision rough set and NNBC
  • Bearing fault diagnosis method based on average multi-granularity decision rough set and NNBC
  • Bearing fault diagnosis method based on average multi-granularity decision rough set and NNBC

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0033] Specific implementation mode one: combine figure 1 Illustrate this embodiment, based on average multi-granularity decision-making rough set and NNBC bearing fault diagnosis method, it is characterized in that the method comprises the following steps:

[0034] Step 1, extracting the fault diagnosis features of rolling bearings in the training samples to construct a fault symptom attribute set;

[0035] Step 2. Using the attribute reduction algorithm based on the average multi-granularity decision-making rough set to reduce the dimensionality of the symptom attribute set in the training sample;

[0036] Step 3: Construct NNBC based on the reduced training samples, and use the NNBC-based pattern recognition algorithm to judge the rolling bearing status of the samples to be diagnosed.

specific Embodiment approach 2

[0037] Specific embodiment two: the difference between this embodiment and specific embodiment one is: the attribute reduction algorithm based on the average multi-granularity decision-making rough set in the step two, combined with figure 2 Describe this implementation mode:

[0038] Step 21. According to the risk price λ p,q (p,q=1,2,3), calculate the threshold α; where

[0039] Step 22. Calculate the classification quality S of the symptom attribute set C with respect to the decision attribute D C (D);

[0040] Step two and three, in turn for each symptom attribute c i ,i=1,2,...,n perform the following operations;

[0041] Step 24: Calculate symptom attribute c i In the symptom attribute set C, the importance Sig(c i ,C,D);

[0042] Step 25, if the symptom attribute c i The importance of Sig(c i ,C,D)=0, then the symptom attribute c i is redundant, otherwise essential;

[0043] Step 26. Repeat steps 24 and 25 for other symptom attributes until the last sympto...

specific Embodiment approach 3

[0045] Embodiment 3: The difference between this embodiment and Embodiment 1 or 2 is: the classification quality S of the symptom attribute set C with respect to the decision attribute D in the step 22 C (D) is defined as follows:

[0046] For the information system S=(U,A=C∪D,V,f), U is the instance set, A is the attribute set, C is the symptom attribute set, D is the decision attribute set, V is the range of A, f is Mapping function, let B={B 1 ,B 2 ,...,B m} are m attribute subsets of symptom attribute set C, then the classification quality of symptom attribute set C with respect to decision attribute D is:

[0047]

[0048] in, is the lower approximate set of the average multi-granularity decision rough set of set X about B, and α is the threshold.

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 provides a bearing fault diagnosis method based on an average multi-granularity decision rough set and NNBC. The bearing fault diagnosis method based on an average multi-granularity decision rough set and NNBC aims at solving the problem that selection of the restriction conditions is not appropriate during the bearing fault diagnosis process based on the multi-granularity rough set.The bearing fault diagnosis method based on an average multi-granularity decision rough set and NNBC includes the steps: 1) extracting the fault diagnosis characteristics of an antifriction bearing in a training sample for constructing a fault symptom attribute set; 2) by means of an attribute reduction algorithm based on the average multi-granularity decision rough set, reducing the dimensions of the symptom attribute set in the training sample; and 3) according to the training sample after reduction, constructing NNBC, and determining the antifriction bearing state of the sample to be diagnosed by means of an algorithm for pattern recognition based on NNBC. The result of the embodiment shows that the bearing fault diagnosis method based on an average multi-granularity decision rough setand NNBC can accurately determine the fault type and the fault degree of the antifriction bearing and can reduce the calculating complexity.

Description

technical field [0001] The invention relates to a fault diagnosis method, in particular to a fault diagnosis method based on average multi-granularity decision-making rough sets and NNBC bearings. Background technique [0002] As the core component of rotating machinery, rolling bearings have been widely used in the transmission systems of wind turbines, transportation vehicles and precision machine tools. However, due to long-term operation in complex and harsh working conditions such as high speed and heavy load, the inner ring, outer ring, and rolling elements of rolling bearings are prone to cracks, pitting, or peeling off; thereby reducing equipment accuracy and even causing serious casualties. as a result of. Therefore, research on fault diagnosis of rolling bearings is of great significance. [0003] In recent years, artificial intelligence technology has been widely used in fault diagnosis methods of rolling bearings, such as deep neural network (deep neural networ...

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): G01M13/04
CPCG01M13/045
Inventor 于军
Owner 哈尔滨力哈智能科技有限公司
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