Method for detecting PCB electronic component based on ERFAM-YOLOV3 network structure

A technology of electronic components and network structure, applied in the direction of biological neural network model, neural architecture, computer components, etc., can solve the problems of large number of detection network parameters, low detection efficiency, slow operation speed, etc. The effect of fast speed and few parameters

Pending Publication Date: 2021-10-01
FOSHAN NANHAI GUANGDONG TECH UNIV CNC EQUIP COOP INNOVATION INST +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Due to technical reasons, most manufacturers still use the traditional detection method, but the traditional detection method has the following problems: (1) Low detection efficiency and low precision
(2) The detection network involved in the traditional detection method has many parameters and slow operation speed

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
  • Method for detecting PCB electronic component based on ERFAM-YOLOV3 network structure
  • Method for detecting PCB electronic component based on ERFAM-YOLOV3 network structure
  • Method for detecting PCB electronic component based on ERFAM-YOLOV3 network structure

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] A kind of detection method that the present invention provides based on the PCB electronic component of ERFAM-YOLOV3 network structure, is characterized in that, comprises the following concrete steps:

[0052] S1, there are 1,000 images, 29 instrument categories and 182,900 electronic components in the PCB electronic component dataset. The PCB electronic component dataset is divided into 8:2, that is, 8 pieces of data are randomly selected for training, and 2 pieces of data are used for detection. data.

[0053] S2, the ERFAM-YOLOV3 network is designed using the modular design strategy and the matching algorithm between the anchor size and the effective receptive field size. Further specific steps related to S2 are as follows:

[0054] S201, first load the YOLOV3 model, each convolution layer has two parameters: weight and bias. We will set the weights of each layer to random values ​​and the bias to 0. The BN layer has four parameters - weight, bias, running mean a...

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 PCB electronic component detection method based on an ERFAM-YOLOV3 network structure, and the method comprises the steps: S1, taking YOLOV3 as a basic network, taking an electronic component on a PCB as a detection object, and carrying out the preprocessing of data; s2, loading the network model of the effective receptive field, and solving the size of the effective receptive field by using gradient back propagation; s3, defining a module according to the operation sequence in the YOLOV3, and presetting the modularization of the ERFAM-YOLOV3; s4, designing an effective receptive field size-anchor size corresponding matching algorithm and the size of the receptive field corresponding to the pixel of the layer where the anchor is located, and detecting the target by using the receptive field size-anchor size corresponding matching algorithm; s5, detecting the electronic components on the images respectively, and outputting the detection results. Compared with a traditional detection method, the method has the advantages of being high in detection precision and efficiency, the designed network has the advantages of being small in parameter quantity and high in operation speed, and therefore the detection cost is reduced.

Description

technical field [0001] The invention relates to the technical field of automatic visual inspection, in particular to a method for detecting PCB electronic components based on the ERFAM-YOLOV3 network structure. Background technique [0002] As an indispensable part of electronic information products, electronic components must be assembled according to the rules of correct category and correct position during the manufacturing process of electronic products. With the continuous improvement of the design and production process, the electronic components on the printed circuit board present the characteristics of small size and similar appearance, which brings great challenges to the visual inspection of the target. Therefore, it is particularly important to develop a set of efficient and effective electronic component detection technology. [0003] Due to technical reasons, most manufacturers still adopt the traditional detection method, but the traditional detection method ...

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): G06T7/00G06K9/62G06N3/04
CPCG06T7/0004G06T2207/30141G06N3/045G06F18/22G06F18/214
Inventor 王华龙杨海东李泽辉吴均城
Owner FOSHAN NANHAI GUANGDONG TECH UNIV CNC EQUIP COOP INNOVATION INST
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