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

Composite fault diagnosis method and device based on a multi-label classification convolutional neural network

A technology of convolutional neural network and composite faults, which is applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as increased model complexity, insufficient data volume of composite faults, and increased number of model parameters, achieving excellent results. Similarity of the same kind and difference of different kinds, good decoupling, and the effect of good feature learning ability

Active Publication Date: 2019-04-16
SOUTH CHINA UNIV OF TECH
View PDF9 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For a deep learning diagnosis model, if you want to model multiple possible composite faults in a system, the complexity of the model will increase, the number of model parameters will increase significantly, and it will also lead to insufficient data for some composite faults And other issues

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
  • Composite fault diagnosis method and device based on a multi-label classification convolutional neural network
  • Composite fault diagnosis method and device based on a multi-label classification convolutional neural network
  • Composite fault diagnosis method and device based on a multi-label classification convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0049] A one-dimensional convolutional neural network compound fault diagnosis method based on multi-label classifier, the algorithm flow is as follows figure 1As shown, the method uses the Margin Loss function to expand the distance between classes and reduce the distance between classes, and improves the cost function and activation function of the one-dimensional convolutional neural network. Output multiple labels. The method includes steps as follows:

[0050] Step 1: Collect vibration acceleration signals of rotating machinery under single fault and composite fault conditions, and set a certain sample length and sample overlap rate to truncate and extract a large number of samples;

[0051] Step 2: For each sample, a single label is given for a single fault, and multiple labels are given for a compound fault, and then the sample set is randomly divided into a training set and a test set according to a certain proportion;

[0052] Step 3: Use Keras to build a deep one-d...

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 composite fault diagnosis method and device based on a multi-label classification convolutional neural network. The method comprises: steps 1, collecting and extracting vibration acceleration signal samples under single fault and composite fault working conditions; step 2, giving a label to each sample according to the type, and dividing the sample into a training set anda test set; step 3, establishing a deep one-dimensional convolutional neural network, and setting a Sigmoid activation function and a boundary loss function Margin Loss; step 4, directly inputting the vibration data of the training set into the built deep one-dimensional convolutional neural network for training; and step 5, selecting an optimal model through Grid Search, and applying the optimalmodel to the test set to obtain a fault state classification result. The method enables the classifier to adaptively output a plurality of labels for the composite fault, is high in fault diagnosis precision, can overcome the limitation that a traditional classifier can only output one label, and achieves the diagnosis of the composite fault.

Description

technical field [0001] The invention belongs to the technical field of mechanical manufacturing and relates to a mechanical fault diagnosis technology, in particular to a composite fault diagnosis method and device based on a multi-label classification convolutional neural network. Background technique [0002] Rotating parts such as bearings and gears are an essential general-purpose component in mechanical equipment and play an important role in modern industrial equipment. The fault diagnosis of rotating machinery is an important part of the preventive maintenance system, which is of great significance to prolong the service life of mechanical equipment, reduce maintenance costs and increase the safety of equipment operation. [0003] The fault diagnosis method based on artificial intelligence has been widely used in the fault diagnosis of rotating machinery and achieved good results. Generally, fault diagnosis of rotating machinery can be completed through vibration sig...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06N3/048G06N3/045G06F2218/08G06F2218/12
Inventor 李巍华刘龙灿黄如意
Owner SOUTH CHINA UNIV 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