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

Bearing fault diagnosis method capable of recovering missing data of back propagation neural network estimation values

A BP neural network and missing data technology, applied in the field of missing data bearing fault diagnosis, can solve problems such as accuracy limitation, incomplete data clustering, missing data set health evaluation method, etc.

Active Publication Date: 2015-07-01
LIAONING UNIVERSITY
View PDF2 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In actual industrial production, due to the limitation of the accuracy of the acquisition equipment, the influence of noise or data omission and other reasons, the data collected by the bearing is missing and an incomplete data set is generated.
But the fuzzy C-means clustering algorithm cannot directly cluster incomplete data
Currently, there is no health evaluation method for missing bearing datasets

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 capable of recovering missing data of back propagation neural network estimation values
  • Bearing fault diagnosis method capable of recovering missing data of back propagation neural network estimation values
  • Bearing fault diagnosis method capable of recovering missing data of back propagation neural network estimation values

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] 1、BP神经网络

[0055] BP神经网络通常是由输入层、隐含层和输出层这三层组成,层与层之间全互连,但每层节点之间不相连。 Such as figure 1 所示,为一个具有单隐含层的BP神经网络模型。 该BP网络由输入层,隐含层和输出层构成。 每个圆圈表示一个节点,每层各包含n,l,m个节点。 节点之间的链接用箭头来表示,每个箭头表示一个权重。 w ij 表示输入层和隐含层之间的连接权值,w jk 表示隐含层和输出层得连接权值。数据的处理和计算将有隐含层和输出层的每个节点执行,隐含层节点的具体数目将在实验中确定。

[0056] 2、改进BP神经网络

[0057] 基本的BP神经网络的训练样本都必须是完整的数据样本,而本方法中对每个缺失属性的训练样本都是缺失样本集。 因而,基本BP神经网络是不能直接使用的,需要对其进行改进。 Such as figure 2 所示,假设一个输入样本中的第三个属性是缺失的,用“?”来表示。则在计算隐含层输出时缺失属性不参与计算隐含层的值,而是有其余完整属性进行计算。训练过程中需要通过误差的反向传播更新网络的权值和阈值,因此在计算网络预测输出和期望输出的误差时,缺失属性不参与误差的计算,以免影响网络的权值和阈值的更新。经过多次迭代学习,可以得到网络的权值和阈值,即训练好的网络。

[0058] 3、模糊C均值(FCM)聚类算法

[0059] 模糊C均值聚类算法(Bezdek,1981)将s维的数据集 中的数据样本分为c类,且c(2≤c≤n),聚类中心为V=[v 1 ,v 2 ,...,v c ],第j类的聚类中心用v j ∈ R s express. 它的基本思想是:建立基于隶属度和聚类中心的目标函数,通过对隶属度矩阵以及聚类中心的迭代优化,达到目标函数极小化的目的,从而实现对样本的聚类。 聚类结果用隶属度矩阵U (c×n) 表示,其中,n表示聚类数据集中的样本数目,c表示聚类中心数目,隶属度矩阵中的元素u ij 表示第j个数据样本隶属于第i类的程度,并且满足以下条件:

[0060] u ik ∈[0,1],i=1,2,...,c;k=1,2,...,n; (18)

[0061] ...

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

A bearing fault diagnosis method capable of recovering missing data of back propagation neural network estimation values includes the steps of 1) bearing data preprocessing; 2) training sample determining and optimizing; 3) network initializing; 4) training based on a back propagation neural network after recovering; 5) missing attribute estimating; 6) clustering analyzing of data sets. The bearing fault diagnosis method capable of recovering the missing data of the back propagation neural network estimation values has the advantages that bearing data with the missing data can be processed, integral data obtained after recovering can be subjected to clustering by the aid of a fuzzy c-means clustering algorithm, and accordingly health of a bearing can be evaluated.

Description

technical field [0001] The invention relates to a method for diagnosing bearing faults with missing data by improving BP neural network evaluation. Background technique [0002] In modern production, rolling bearings are widely used in rotating machinery, and the health of rolling bearings is one of the important influences on the operation of the entire machinery. Rolling bearings need to have high reliability, and the occurrence of bearing faults during mechanical operation may lead to fatal mechanical failures. Therefore, the evaluation technology of rolling bearing health is extremely important. [0003] In recent years, health evaluation technology has developed rapidly, and research results have emerged continuously, and various methods have been adopted. The most widely used is the fuzzy C-means clustering algorithm. In actual industrial production, due to the limitation of the accuracy of the acquisition equipment, the influence of noise or data omission and other ...

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): G06N3/08
Inventor 张利王蓓蕾刘萌萌夏天王鹭王军孙颖
Owner LIAONING UNIVERSITY
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