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

An Online Fault Diagnosis Method for Rolling Bearings under Variable Load Based on Transfer Learning

A rolling bearing and fault diagnosis technology, which is applied in the field of online fault diagnosis of rolling bearings under variable load of transfer learning, can solve the problems such as the inability to effectively guarantee the modeling efficiency and accuracy of online fault diagnosis of rolling bearings under variable load, so as to solve the problem of online fault diagnosis, The effect of high recognition accuracy and good generalization

Active Publication Date: 2022-05-27
HARBIN UNIV OF SCI & TECH
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In view of the above problems, the present invention proposes a transfer learning online fault diagnosis method for rolling bearings under variable loads, which is used to solve the problem that the deep migration method of the existing offline training method cannot effectively ensure the modeling efficiency and accuracy in the online fault diagnosis of rolling bearings under variable loads. rate problem

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
  • An Online Fault Diagnosis Method for Rolling Bearings under Variable Load Based on Transfer Learning
  • An Online Fault Diagnosis Method for Rolling Bearings under Variable Load Based on Transfer Learning
  • An Online Fault Diagnosis Method for Rolling Bearings under Variable Load Based on Transfer Learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0086] In order to verify the validity and accuracy of the method of the present invention, the bearing data set of Case Western Reserve University in the United States is used for experimental verification. [23] . Bearing test benches such as Figure 4 As shown, these data were collected by the accelerometer under 4 load conditions and the sampling frequency was 12kHz.

[0087] Load types include 0hp, 1hp, 2hp and 3hp, and the motor speed varies between 1730rpm and 1797rpm depending on the load. Under each load, there are 3 fault damage degrees including normal state (N) and inner ring fault (IR), outer ring fault (OR), and rolling element fault (B). The damage diameters are 0.1778mm, 0.3556mm, 0.5334mm respectively mm, there is no damage to the rolling bearing under normal conditions, so there is no fault location and degree of fault damage. The normal state of the rolling bearing, inner ring, outer ring, rolling element failure and 10 states of different failure damage l...

specific Embodiment 2

[0115] In order to better verify the efficiency of the method of the present invention, the time consumption and accuracy of the three methods are compared, wherein the settings of the online data set are consistent with Table 5, and the experimental results are shown in Table 7.

[0116] Table 7 Time consumption and accuracy comparison of three methods

[0117]

[0118] In the experiment, Method 1 and Method 2 use offline training methods, that is, the model is retrained each time to process the newly added online data; Method 3 is an online training method, which only needs to update the model for the newly added online data. Method 1 is the combination of CNN and Softmax for back-propagation optimization training CNN model; Method 2 is to extract features from the fault data with the CNN model trained in Method 1, and then input SVM for fault classification; Method 3 is the CNN proposed by the present invention. - ISVM rolling bearing multi-state identification method. ...

specific Embodiment 3

[0120] In order to further prove that the method of the present invention has obvious advantages in the online fault diagnosis of rolling bearings under variable load, ISVM, OS-ELM are selected. [28] And the online learning method proposed in the literature [29] to conduct a comparative experimental study. Among them, ISVM and OS-ELM methods use the feature extraction method of literature [30] to extract 10 kinds of time-domain features and 4 kinds of frequency-domain features, and then input the extracted features into the diagnosis algorithm to complete the fault diagnosis. During the experiment, the same source domain and target domain datasets were used. The time comparison results are shown in Table 8, and the accuracy comparison results are shown in Table 8. Figure 11 shown.

[0121] Table 8 Time comparison with other methods

[0122]

[0123] It can be seen from Table 8 that the average online learning time of the method proposed in the present invention is 16.97s...

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

An online fault diagnosis method for rolling bearings under variable loads based on transfer learning, which belongs to the field of fault diagnosis technology. It is used to solve the problem that the deep migration method of the existing offline training method cannot effectively guarantee the modeling efficiency and accuracy in the online fault diagnosis of rolling bearings under variable loads. question. The technical points of the present invention include: first, STFT processing the original time-domain vibration signal to construct a two-dimensional spectrum data set; then use the source domain data to train the source domain CNN-ISVM model, obtain the source domain classification model, save the model parameters and Migrate to the target domain CNN-ISVM training process; finally update and correct the ISVM classifier in the target domain CNN-ISVM model through online data to realize multi-state online recognition of rolling bearings under variable loads. The method of the invention greatly reduces the model training time and calculation amount, has high modeling efficiency, and has high accuracy and good generalization; it has the advantages of online monitoring and rapid diagnosis of rolling bearing faults in actual work important guiding significance.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis, in particular to an on-line fault diagnosis method of a rolling bearing under variable load based on migration learning. Background technique [0002] As a key component in industrial production equipment, rolling bearings will directly affect the safe operation of the entire mechanical equipment once a failure occurs. [1] . Under the condition of variable load, the running state of rolling bearing is complex and changeable, and the distribution of data characteristics is quite different. In practice, the target domain data collection is often obtained online in a sequential manner, which cannot meet the completeness assumption of the test data in the model training process, which poses new challenges for the existing transfer learning methods. [2] . Therefore, it is of great significance to carry out multi-state online fault diagnosis of rolling bearings under variable loads. [0003...

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 Patents(China)
IPC IPC(8): G01M13/045G06N3/04G06N3/08G06K9/62G06V10/764G06V10/82
CPCG01M13/045G06N3/084G06N3/047G06N3/045G06F18/2411G06F18/2415
Inventor 康守强刘旺辉王玉静王庆岩梁欣涛谢金宝
Owner HARBIN UNIV OF SCI & TECH
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