Convolutional neural network adversarial transfer learning method based on Waserstein distance and application thereof

A convolutional neural network and transfer learning technology, applied in the field of industrial process fault diagnosis, can solve problems such as difficult application and high requirements for neural network structure, improve judgment accuracy, high accuracy, and solve the waste of computing resources and training time Effect

Inactive Publication Date: 2019-11-05
HUAZHONG UNIV OF SCI & TECH
View PDF4 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The present invention provides a convolutional neural network anti-migration learning method based on Wasserstein distance and its application to solve the requirements of the existing deep transfer learning method on actual sample data and / or neural network structure while ensuring the ability to diagnose industrial process faults High technical problems that lead to difficulty in applying to practical industrial processes

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
  • Convolutional neural network adversarial transfer learning method based on Waserstein distance and application thereof
  • Convolutional neural network adversarial transfer learning method based on Waserstein distance and application thereof
  • Convolutional neural network adversarial transfer learning method based on Waserstein distance and application thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] A Convolutional Neural Network Adversarial Migration Learning Method 100 Based on Wasserstein Distance, Such as figure 1 shown, including:

[0049] Step 110, from the source domain labeled data set and the target domain data set, determine the source domain labeled sample set and the target domain sample set;

[0050] Step 120, using the convolutional neural network to be transferred to learn, obtain the source domain feature set and source domain fault judgment set of the source domain labeled sample set and the target feature set of the target domain sample set;

[0051] Step 130, with the goal of maximizing the Wasserstein distance between the source domain feature set and the target feature set and minimizing the sum of the Wasserstein distance and the judgment loss value of the source domain fault judgment set, adjusting the parameters of the convolutional neural network, based on the convergence Criterion, repeat step 110, or complete the adversarial transfer lea...

Embodiment 2

[0083] A convolutional neural network for industrial process fault diagnosis, obtained by training with any Wasserstein distance-based convolutional neural network confrontation transfer learning method as described in the first embodiment.

[0084] Based on the correlation between tasks, the convolutional neural network obtained by using any of the above-mentioned convolutional neural network adversarial transfer learning methods based on the Wasserstein distance can be used to learn the deep adversarial transfer learning of the convolutional neural network corresponding to the source domain. The convolutional neural network with high precision in the source domain and the target domain solves to a certain extent the waste of computing resources and training time caused by the need to rebuild the deep learning model from scratch in the face of new fault diagnosis tasks in the existing technology and the lack of Technical issues with sufficient sample data in the target domain....

Embodiment 3

[0086] An industrial process fault diagnosis method, based on any industrial process fault diagnosis convolutional neural network as described in the second embodiment above, when any convolutional neural network based on the Wasserstein distance described in the first embodiment above is received against When transferring a new sample of the target domain in the learning method, the industrial process fault judgment result corresponding to the new sample is obtained.

[0087] The convolutional neural network trained by any of the above-mentioned Wasserstein distance-based convolutional neural networks against transfer learning methods is used for industrial process fault diagnosis. On the premise of ensuring safety and high efficiency, the fault diagnosis accuracy is higher.

[0088] In order to verify the effectiveness of the above-mentioned deep adversarial transfer learning on the problem of fault diagnosis, this example introduces the benchmark bearing fault data set obtai...

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 relates to a convolutional neural network adversarial transfer learning method based on Waserstein distance and application thereof and the method comprises the steps: employing a to-be-migrated convolutional neural network to obtain a source domain feature set and a source domain fault judgment set of a source domain mark sample set and a target feature set of a target domain sampleset; and with maximization of a Wasserstein distance between the source domain feature set and the target feature set and minimization of the sum of the Wasserstein distance and a judgment loss valueof the source domain fault judgment set as a target, realizing adversarial migration learning of the convolutional neural network based on a convergence criterion. According to the invention, the Wasserstein distance is introduced into the transfer learning of the convolutional neural network. The maximum Wasserstein distance is used as a target; the distinguishing sensitivity of the features extracted from the two sample sets is improved; and the minimum sum of the Wasserstein distance and the loss value of the source domain fault judgment set is taken as a target, so that the judgment precision of the convolutional neural network is improved, the requirements on sample data and a network structure are low while the fault diagnosis capability is ensured, and the invention can be suitablefor migration among multiple working conditions and is high in practical applicability.

Description

technical field [0001] The invention belongs to the field of industrial process fault diagnosis, and more specifically, relates to a convolutional neural network anti-migration learning method based on Wasserstein distance and its application. Background technique [0002] Fault diagnosis aims to isolate faults on the system by monitoring and analyzing the state of the machine using acquired measurement data and other information. To do this requires highly skilled and experienced experts, which increases the use of artificial intelligence technology. The need for fault diagnosis decisions. The deployment of a real-time fault diagnosis framework allows maintenance teams to take proactive action to replace or repair affected components, thereby increasing productivity and keeping operations safe. Therefore, accurate diagnosis of bearing faults is of critical significance to the reliability and safety of mechanical manufacturing systems. [0003] Many advanced signal process...

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): G06K9/00G06K9/62G06K9/66G06N3/04
CPCG06V30/194G06N3/045G06F2218/08G06F2218/12G06F18/22
Inventor 袁烨周倍同程骋李星毅马贵君
Owner HUAZHONG 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