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

Product quality detection method based on deep neural network transfer learning

A deep neural network and transfer learning technology, applied in the field of data collection and analysis, can solve problems such as inability to train, and achieve the effect of simple algorithm, high accuracy and high accuracy

Pending Publication Date: 2020-10-09
海克斯康制造智能技术(青岛)有限公司
View PDF21 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In summary, there is an urgent need to design a product quality detection method based on deep neural network transfer learning, and apply the face recognition model to the product quality detection model, which can solve the problem that it cannot be trained without bad samples

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
  • Product quality detection method based on deep neural network transfer learning
  • Product quality detection method based on deep neural network transfer learning
  • Product quality detection method based on deep neural network transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] This embodiment proposes to use the sensor data collected during the production process of the product as the identification information of the product, and puts forward a hypothesis that the sensor information of the same product produced by the same equipment under the same external conditions is similar. In this way, the sensor information of the product can be used as a brief evaluation standard of product quality. The sensor data collected during the product production process is high-frequency data, and the data dimension may be as high as one million or more. Similarity processing is performed directly. Due to the large spatial dimension, the accuracy is poor. This is similar to face recognition, where the face is directly processed. For comparison, since the face image has a large dimension, it is difficult to distinguish it in Euclidean space. Therefore, a deep convolutional neural network is used to reduce the dimension of the face image and map it in a low-dim...

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 product quality detection method based on deep neural network transfer learning. The method comprises the following steps: S1, acquiring data of a sensor and performing normalization processing to obtain a grey-scale map; S2, carrying out transfer learning on the face recognition model to construct a sensor feature extraction network, performing dimension reduction processing on the grey-scale map in the step S1 by utilizing the sensor feature extraction network to obtain a sensor feature vector; and S3, comparing the sensor feature vector in the step S2 with a vectorin a product feature library, and judging the quality of the to-be-tested product. According to the invention, firstly, in product quality detection in which a face recognition model is applied through transfer learning, due to the fact that key features are reserved after the face recognition model passes through a face feature model, the calculation speed is higher, and the accuracy is higher;and meanwhile, model training can also be carried out under the condition of no difference sample.

Description

technical field [0001] The invention relates to the field of data collection and analysis, in particular to a product quality detection method based on deep neural network migration learning. Background technique [0002] With the vigorous development of global industrialization and artificial intelligence technology, artificial intelligence technology is more and more applied in the field of industrial production. The new industrial Internet development plans of various countries also use artificial intelligence technology as a key promotion technology. At present, in terms of quality control in the field of industrial production, it mainly relies on manual spot checks of products and the use of measuring equipment for measurement. Manual spot checks and equipment measurements take a lot of manpower, material resources and time. For some products that need to check the internal quality of a closed space, manual spot checks mean destroying the product. [0003] Prior art C...

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): G06K9/62G06N3/04G06N3/08G06Q10/06
CPCG06N3/08G06Q10/06395G06N3/045G06F18/24147
Inventor 谢德威李尚勇王雪涛惠伟
Owner 海克斯康制造智能技术(青岛)有限公司
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