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

Unsupervised domain adaptive fault diagnosis method

A fault diagnosis and unsupervised technology, applied in the field of fault diagnosis, can solve the problem of fault diagnosis performance degradation, achieve good intra-class compactness and inter-class separability, and improve performance

Active Publication Date: 2020-03-31
YANCHENG INST OF TECH
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the problem of performance degradation of fault diagnosis in the above-mentioned existing unsupervised domain adaptive fault diagnosis method, the present invention is proposed

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
  • Unsupervised domain adaptive fault diagnosis method
  • Unsupervised domain adaptive fault diagnosis method
  • Unsupervised domain adaptive fault diagnosis method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] refer to figure 1 , which provides a schematic diagram of the overall structure of an unsupervised domain adaptive fault diagnosis method, as shown in Figure 4. An unsupervised domain adaptive fault diagnosis method includes,

[0061] The objective function of the model proposed by the present invention includes the cross-entropy classification loss of the source domain, the discriminative loss based on the center and the relative alignment loss based on the features of the source domain and the target domain. The latter two losses are performed in the last fully connected layer. After model training, not only The representation learned in the source domain can be applied to the target domain, and the extracted domain-invariant features can be guaranteed to have better intra-class compactness and inter-class separability, and the extracted features can effectively improve the performance of cross-domain testing. performance.

[0062] Specifically, the main structure of...

Embodiment 2

[0109] In order to verify the effectiveness and feasibility of the proposed method, the bearing test device includes a motor, a torque sensor, a power tester and an electronic controller. An acceleration sensor is placed on the bearing seat of the motor drive end and the fan end. The data is collected by the acceleration sensor placed above the bearing seat of the motor drive end. The sampling frequency includes 12KHz and 48KHz, which are collected under 4 different loads (0-3HP) respectively; this bearing test system simulates the bearing There are 4 types of normal state (N), outer ring fault (OF), inner ring fault (IF) and rolling element fault (RF), and each type of fault has 3 fault degrees, including damage diameter of 0.007inch, 0.014 inch, 0.021inch, you can get 10 kinds of health status.

[0110] In this example, the sampling frequency of the driving end of the rolling bearing is 12kHz for different fault locations and vibration signals of different health states for ...

Embodiment 3

[0118] For each fault detection type, in order to further analyze the sensitivity of the proposed CACD-1DCNN model, this method introduces three new evaluation indicators, namely Precision (precision), Recall (recall rate) and F value. Called precision, recall is also called recall.

[0119] In the fault diagnosis multi-classification problem, the definitions for each fault category c are:

[0120] Accuracy (c)=TP / TP+FP

[0121] Recall (c)=TP / TP+FN

[0122] Among them, true positives (TP) represent the number of faults that are correctly identified as fault category c, false positives (FP) represent the number of faults that are incorrectly identified as fault category c, and false negatives (FN) represent the number of faults that are incorrectly identified as not belonging to c, i.e. no The number of faults that were correctly labeled.

[0123] The failure category c has an accuracy of 1, which means that when each sample is marked as belonging to a certain failure class ...

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 an unsupervised domain adaptive fault diagnosis method, which comprises the steps of obtaining bearing source vibration data, and dividing the bearing source vibration data into a training sample and a test sample; constructing a CACD-1 DCNN model, training the model, determining model parameters, and performing the fault diagnosis; the source vibration data comprises target data without labels and source domain data with labels; the acquired bearing source vibration data is acquired through a sensor; an objective function of the model provided by the invention comprises cross entropy classification loss of a source domain, based on center discrimination loss and related alignment loss based on source domain and target domain features, the last two losses are executed in the last full connection layer, representation learned in a source domain can be applied to a target domain after model training, it can be guaranteed that the extracted domain invariant features have better intra-class compactness and inter-class separability, and meanwhile the extracted features can effectively improve the performance of cross-domain testing.

Description

technical field [0001] The present invention relates to the technical field of fault diagnosis, in particular to an unsupervised domain adaptive fault diagnosis method. Background technique [0002] Deep learning is to learn the inherent laws and representation levels of sample data. The information obtained in these learning processes is of great help to the interpretation of data such as text, images and sounds; its ultimate goal is to enable machines to have the same analytical capabilities as humans. Learning ability, capable of recognizing data such as text, images and sounds; deep learning is a complex machine learning algorithm, and the effect achieved in speech and image recognition far exceeds the previous related technologies. [0003] Deep learning techniques have been widely used in fault diagnosis and achieved good results. However, in many practical fault diagnosis applications, the labeled training data (source domain) and unlabeled test data (target domain) ...

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
IPC IPC(8): G01M13/045G06K9/62G06N3/04G06N3/08
CPCG01M13/045G06N3/08G06N3/045G06F18/241
Inventor 安晶艾萍李青祝黄曙荣刘聪刘大琨
Owner YANCHENG INST OF 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