A rolling bearing fault identification method under variable working conditions based on ATT-CNN

An ATT-CNN, rolling bearing technology, used in mechanical bearing testing, instruments, biological neural network models, etc., can solve problems such as generalization ability constraints

Active Publication Date: 2019-06-18
HARBIN UNIV OF SCI & TECH
View PDF11 Cites 65 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to solve the problem that the feature extraction in the existing rolling bearing fault identification method under variable working conditions relies too much on prior knowledge and expert experience due to the use of time-domain features, frequency-domain features or time-frequency domain features, and the feature extraction and model establishment are carried out in isolation , so that its generalization ability is limited for complex classification problems, and then provides a rolling bearing fault identification method based on ATT-CNN (attention mechanism CNN) under variable working conditions

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
  • A rolling bearing fault identification method under variable working conditions based on ATT-CNN
  • A rolling bearing fault identification method under variable working conditions based on ATT-CNN
  • A rolling bearing fault identification method under variable working conditions based on ATT-CNN

Examples

Experimental program
Comparison scheme
Effect test

experiment approach 2

[0140] In order to verify the generalization ability of the algorithm proposed in this paper, experiments are carried out on the data of all load types. All state data sets under two loads are used as the training set, and the data under the other two different loads are used as the test set. The data settings and experimental results are shown in Table 4. The structure of multi-working condition data is more complex and diverse, and it is more difficult to identify the fault state when testing and diagnosing single working condition data.

[0141] Table 4 Experimental Scheme 2 Dataset Settings and Accuracy Comparison

[0142]

[0143] Through the analysis of multiple groups of experiments, the average test accuracy of the ATT-CNN model is 96.48%, which is 3.3% higher than that of CNN. It shows that under more complex working conditions, the data structure and distribution of the test set and the training set are quite different, and the ATT-CNN model can well adapt to the...

experiment approach 3

[0146] In order to further verify the robustness of the model, the data under one load is used as the training set, and the data under the other three loads are used as the test set. The data settings and experimental results are shown in Table 5. It is well known that for deep neural networks, a more robust model can be obtained by using a large amount of training data. However, in practical applications, some working condition data are difficult to obtain or unknown working condition data will appear, so it is hoped that small data sets can be used to realize fault diagnosis under variable working conditions.

[0147] Table 5 Experimental scheme three data set settings and accuracy comparison

[0148]

[0149]

[0150] The average test accuracy based on the ATT-CNN model is 83.40%, while the unimproved CNN model is only 77.98%, which is 5.5% higher. The overall performance of the proposed algorithm on the data set set by scheme three is not as good as that of the firs...

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 rolling bearing fault identification method under variable working conditions based on ATT-CNN, and relates to a rolling bearing fault identification technology. The problemthat the generalization ability of an existing rolling bearing fault recognition method under variable working conditions is limited to a certain extent for a complex classification problem is solved.The method comprises the following steps: firstly, mapping vibration data to a nonlinear space domain through a convolutional neural network (CNN), and adaptively extracting rolling bearing fault characteristics under variable working conditions by utilizing the characteristic that the CNN has invariance on micro displacement, scaling and other distortion forms of an input signal; Secondly, an attention mechanism (ATT) thought is put forward to be fused into a CNN structure, and the sensitivity of bearing vibration characteristics under variable working conditions is further improved; And meanwhile, more abundant and diverse training samples are obtained through a data enhancement method, so that the network can be learned more fully, and the robustness is improved. The proposed fault diagnosis model based on the attention mechanism CNN (ATT-CNN) can realize multi-state recognition and classification of the rolling bearing under variable working conditions, and compared with other methods, higher accuracy can be obtained.

Description

technical field [0001] The invention relates to a rolling bearing fault identification method under variable working conditions, and relates to a rolling bearing fault identification technology. Background technique [0002] The status of rolling bearings in industrial production is light, and they often work in the state of changing load and speed. Therefore, it is important to effectively diagnose the performance state of rolling bearings during the evolution of rolling bearing faults under variable working conditions and improve the reliability of mechanical equipment. significance [1] . In the field of fault diagnosis, the use of condition monitoring data combined with artificial intelligence methods has gradually become a research hotspot in recent years. In particular, rolling bearing fault signals under variable working conditions contain richer vibration characteristic information [2] , the dynamic nature of its fault development also poses new challenges for degr...

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): G06F17/50G01M13/04G06N3/04
Inventor 梁欣涛康守强李艺伟王玉静王庆岩
Owner HARBIN UNIV OF SCI & TECH
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