Industrial data classification method based on model migration

A technology of industrial data and classification methods, applied in neural learning methods, biological neural network models, character and pattern recognition, etc., can solve the problem of less application of transfer learning methods

Active Publication Date: 2019-12-10
青岛奥利普奇智智能工业技术有限公司
View PDF16 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, transfer learning methods are rarely used in various defect detection fields of industrial products.

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
  • Industrial data classification method based on model migration
  • Industrial data classification method based on model migration
  • Industrial data classification method based on model migration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be described in further detail below in conjunction with the examples.

[0051] The invention discloses a method for classifying industrial data based on model migration, which includes the following steps (taking welding defects as an example):

[0052] Step A: Collect a large number of welding defect data sets A of different types of products in the industry as source domain data sets, and divide them into different folders according to the type of welding defects and number them (such as: 1-surface cracks 2-surface pores 3-undercut 4-welding bump);

[0053] Step B: Collect defect data to be classified of a small number of products to be tested (hundreds of pieces) as target domain data;

[0054] Step C: Perform data enhancement on the source domain data, expand the training set, increase the data feature density, and avoid overfitting;

[0055] Step D: Construct a convolutional neural network with a residual structure;

[0056] Step E: E...

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 an industrial data classification method based on model migration. The method comprises: collecting source domain data and target domain data respectively; performing data enhancement on the source domain data; constructing a convolutional neural network with a residual structure; establishing a loss function to minimize the difference of cross-domain learning feature covariances, and minimizing domain displacement by aligning second-order statistics of distribution of source domain data and target domain data on a feature level; and training and predicting the model.According to the method, other similar data are used for learning to carry out feature migration under the conditions that the target data are few and the data are difficult to obtain, and then the target domains are classified, so that the method has a relatively high application value.

Description

technical field [0001] This patent application belongs to the technical field of surface defect detection of industrial products in machine vision, more specifically, it relates to a method for classifying industrial data based on model migration, and also involves machine learning and deep learning, data enhancement, domain self-adaptation, and model-based Migrating the field of industrial defect detection classification. Background technique [0002] Product surface defect detection is an extremely important link in the industrial manufacturing production line. Enterprises spend a lot of money every year to recruit workers to use human eyes to detect product defects, such as surface cracks, surface pores, undercuts, welding tumors and other defects in welding defects. These defective products need to be accurately identified. However, in the actual production environment, most of them are detected manually. Because the detection method by naked eyes not only has a huge mis...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/241G06F18/214
Inventor 张发恩袁智超孙天齐陆强
Owner 青岛奥利普奇智智能工业技术有限公司
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