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

Injection product defect classification method based on machine learning

A technology for classification of injection molding products and defects, which is applied to instruments, computer parts, calculations, etc., can solve problems such as single classification, inability to classify, increase time cost, etc., and achieve effective classification, improve accuracy, and enhance connectivity.

Active Publication Date: 2020-03-17
GUANGDONG UNIV OF TECH
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this injection molding product detection method, although the secondary detection of unqualified products helps to improve the detection accuracy, it increases the time cost
Another type of classification for injection molding products is based on physical judgment of whether the shapes are consistent. Therefore, there is a shortcoming of too single classification. When there are cases where the classified products have the same shape, effective classification cannot be carried out.

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
  • Injection product defect classification method based on machine learning
  • Injection product defect classification method based on machine learning
  • Injection product defect classification method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] This embodiment proposes a method for classifying defects of injection molding products based on machine learning, such as figure 1 As shown, it is a flow chart of a method for classifying defects of injection molded products based on machine learning in this embodiment.

[0041] In the method for classifying defects of injection molding products based on machine learning proposed in this embodiment, the following steps are included:

[0042] S1: Collect images of injection molded products with various types of defects as training samples and preprocess them.

[0043] In this step, the steps of preprocessing the training samples include:

[0044] S11: Manually label the images [t1, t2, ..., tn] in the training samples to obtain an image label set [s1, s2, ..., sn];

[0045] S12: Grayscale the images [t1, t2, ..., tn] in the training samples, and perform parameter transformation on the two-dimensional domain, and the transformation formula is as follows:

[0046] tn'=...

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 injection product defect classification method based on machine learning. The method comprises the following steps: collecting a training sample; inputting the training sample into a classifier for training to obtain a trained classifier; presetting a shooting time period for the shooting device, acquiring an image of the to-be-classified product and preprocessing the image; inputting an image of a to-be-classified product into the trained classifier to obtain a classification label, and obtaining a label matrix through one-hot coding and transcoding; stacking the label matrix to obtain a stacking matrix containing label information; performing data separation on the stacking matrix to obtain a low-rank matrix and a sparse matrix, and decomposing the sparse matrixinto noise of a training sample and noise of an image of a to-be-classified product; iterating the low-rank matrix, and taking a label matrix corresponding to the iterated optimal solution as an optimized label matrix; and the injection product system converting the optimized label matrix into a machine signal, so that a machine on a production line can control defect classification of injectionproducts.

Description

technical field [0001] The present invention relates to the technical field of product defect classification, and more specifically, relates to a method for classifying defects of injection molding products based on machine learning. Background technique [0002] At present, the defects of injection molding machine products are mainly caused by the design of the mold, the manufacturing accuracy and the degree of wear. Since the injection molding cycle itself is very short, if the process conditions are not well grasped, a large amount of waste products will be generated. [0003] There is an existing intelligent secondary detection method for injection molding products, which mainly judges whether the product is qualified by comparing preset image information, and then performs secondary detection on unqualified products to avoid false subtraction or missed detection. In this injection molding product detection method, although the secondary detection of unqualified products...

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): G06K9/62
CPCG06F18/214G06F18/241Y02P90/30
Inventor 谭淇李建中潘嘉伟吴宗泽
Owner GUANGDONG 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