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

Object surface pattern screening method based on artificial neural network

A technology of artificial neural network and screening method, applied in the field of screening of object surface type, can solve the problems of uncontrollable yield rate of structural objects, prone to misjudgment, poor efficiency, etc.

Pending Publication Date: 2021-04-20
SHENXUN COMP KUNSHAN +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the efficiency of manually detecting whether a structural object has defects is low, and misjudgment is very easy to occur, which will cause the yield rate of the structural object to be uncontrollable

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
  • Object surface pattern screening method based on artificial neural network
  • Object surface pattern screening method based on artificial neural network
  • Object surface pattern screening method based on artificial neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The screening method of object surface type based on artificial neural network is suitable for an artificial neural network system. Here, the artificial neural network system can be implemented on a processor.

[0056] In some embodiments, referring to figure 1, in the learning phase, the processor can perform deep learning of multiple sub-neural network systems (that is, artificial neural networks that have not been trained) under different training conditions to respectively establish these sub-neural network systems for the prediction of the surface type of the recognition object model (that is, a trained artificial neural network) to obtain a trained sub-neural network system (step S01). Here, these object images may be images of surfaces of the same object at the same relative position. Furthermore, the artificial neural network system receives a plurality of object images with fixed imaging coordinate parameters. Moreover, the batch of object images can be obta...

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 provides an object surface pattern screening method based on an artificial neural network and is suitable for screening a plurality of objects. The object surface pattern screening method based on an artificial neural network comprises the following steps of: performing surface pattern identification of a plurality of object images by using a plurality of prediction models to obtain a judgment defect rate of each prediction model, wherein the object images correspond to the surface patterns of a part of objects; and connecting the prediction models in series to form an artificial neural network system according to the judgment defect rate of each prediction model so as to screen other objects. According to the object surface pattern screening method based on the artificial neural network, a plurality of neural networks with different training conditions are connected in series based on the judgment defect rates of the neural networks, so that an artificial neural network system for precisely and quickly classifying a large number of to-be-tested objects is provided, and meanwhile, a relatively good over-discharge rate is considered.

Description

【Technical field】 [0001] The invention relates to an artificial neural network training system, in particular to an artificial neural network-based object surface type screening method. 【Background technique】 [0002] Various safety protection measures are composed of many small structural objects, such as seat belts. If the strength of these small structural objects is insufficient, the protective effect of safety protection measures can be questioned. [0003] Due to various reasons during the manufacturing process of these structural objects, such as collisions, process errors, mold defects, etc., tiny defects on the surface, such as slots, cracks, bumps, and textures, etc., may occur on the surface. These tiny flaws are not easy to detect. One of the existing defect inspection methods is to manually observe the structural object to be inspected with naked eyes or touch with both hands to determine whether the structural object has defects, such as pits, scratches, colo...

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): G01N21/956
Inventor 蔡昆佑
Owner SHENXUN COMP KUNSHAN
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