Unlock instant, AI-driven research and patent intelligence for your innovation.

A detection method for defective appearance of electronic components based on deep learning

A technology of electronic components and deep learning, applied in instruments, computer parts, image analysis, etc., can solve problems such as missed detection and detection limitations

Active Publication Date: 2021-09-14
HANGZHOU DIANZI UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this detection system is affected by the quality image setting standard. If the standard setting is too strict, there will be too many misjudgments, and if the standard setting is too wide, it will miss detection, resulting in detection limitations.

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
  • A detection method for defective appearance of electronic components based on deep learning
  • A detection method for defective appearance of electronic components based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] In order to illustrate the technical solution of the present invention more clearly, the specific implementation manners of the present invention will be described below with reference to the accompanying drawings.

[0024] Such as figure 1 As shown, firstly, the deep learning detection model is obtained through the offline training process, and then on the basis of obtaining the above deep learning detection model, online automatic detection of defective electronic components is realized. The specific design steps are as follows:

[0025] Step 1: Dataset collection and labeling. Collect a class of sample images of defective electronic components, classify and mark them according to surface pits, scratches, scratches, holes, stains, and burrs; at the same time collect a class of sample images of good electronic components containing characters or random noise to mark. Because characters are often printed on the surface of electronic components, this is normal, but the...

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 an automatic detection method for electronic components with defective appearance based on deep learning technology. The method includes: collection and labeling of data sets; data enhancement of images in the data set; construction of a simple and efficient convolutional neural network model; inputting sample pictures of the data set into the above-mentioned convolutional neural network model for iterative training to obtain the best The best detection model; the collected images are input into the deep learning detection model to identify the image category; the defective products identified by the deep learning detection model are automatically eliminated on the production line, thereby improving product quality.

Description

technical field [0001] The invention belongs to the field of detection of defective appearance of electronic components, and specifically relates to a method for detecting defective appearance of electronic components based on deep learning technology. Background technique [0002] Defective appearance of electronic components refers to products containing surface pits, scratches, abrasions, holes, stains, burrs, etc. In the manufacturing process, it is often difficult to completely avoid the appearance of these defective products, but this has a great negative impact on the performance and quality of electronic components. At present, the automatic detection method of electronic components with defective appearance is AOI automatic optical inspection system, which scans and collects images of target products through CCD / CMOS cameras, and then compares the images with the preset images of good products in the system. In order to identify the appearance of defective 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
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06K9/62G06N3/04
CPCG06T7/0004G06T2207/20084G06T2207/20081G06N3/045G06F18/214
Inventor 郑小青刘峰姚莉陈杰郑松孔亚广王洪成
Owner HANGZHOU DIANZI UNIV