Supercharge Your Innovation With Domain-Expert AI Agents!

Workpiece surface defect detection method and system based on SSD network model

A workpiece surface and network model technology, applied in the direction of instruments, scanning probe technology, etc., can solve the problem of reducing the workload of manual design features, and achieve the effect of strengthening network continuity, reducing workload, and increasing network complexity

Inactive Publication Date: 2020-11-03
QINGDAO TECHNOLOGICAL UNIVERSITY
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the deficiencies of the prior art, the present disclosure provides a workpiece surface defect detection method and system based on the SSD network model, which can process large-scale image data, reduce the huge workload of manual design features, and process a variety of different defects at the same time. Defect categories and the ability to obtain pixel-level defect area information

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
  • Workpiece surface defect detection method and system based on SSD network model
  • Workpiece surface defect detection method and system based on SSD network model
  • Workpiece surface defect detection method and system based on SSD network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] like figure 1 As shown, embodiment 1 of the present disclosure provides a method for detecting workpiece surface defects based on SSD network model, comprising the following steps:

[0048] Obtain image data of workpiece surface;

[0049] Input the acquired image data into the preset SSD network model to obtain the recognition result of workpiece surface defects;

[0050] Among them, the backbone network of the SSD network model adopts the MobileNet network combined with hole convolution and hierarchical feature fusion.

[0051] In detail, include the following:

[0052] S1: Image acquisition, using a scanning electron microscope to acquire images of workpiece surface defects at different positions, and then sending them to the image analysis stage.

[0053] SEM image acquisition involves the following steps:

[0054] S1.1: Put nitrogen into the sample exchange chamber until the light is on;

[0055] S1.2: Open the sample exchange chamber, put the sample stage with...

Embodiment 2

[0084] Embodiment 2 of the present disclosure provides a workpiece surface defect detection system based on an SSD network model, including:

[0085] The data acquisition module is configured to: acquire workpiece surface image data;

[0086] The defect recognition module is configured to: input the acquired image data into the preset SSD network model to obtain the recognition result of the workpiece surface defect;

[0087] Among them, the backbone network of the SSD network model adopts the MobileNet network combined with hole convolution and hierarchical feature fusion.

[0088] The working method of the system is the same as the method for detecting workpiece surface defects based on the SSD network model provided in Embodiment 1, and will not be repeated here.

Embodiment 3

[0090] Embodiment 3 of the present disclosure provides a workpiece surface defect detection system based on an SSD network model, including a scanning electron microscope, a high-performance server, and a control terminal;

[0091] The scanning electron microscope is configured to collect workpiece surface image data;

[0092] The high-performance server is configured to perform the following method:

[0093] Obtain image data of workpiece surface;

[0094] Input the acquired image data into the preset SSD network model to obtain the recognition result of workpiece surface defects;

[0095] Among them, the backbone network of the SSD network model adopts the MobileNet network combined with hole convolution and hierarchical feature fusion.

[0096] The detailed steps are the same as the SSD network model-based workpiece surface defect detection method provided in Embodiment 1, and will not be repeated here.

[0097] The control terminal includes input devices such as a keybo...

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 a workpiece surface defect detection method and system based on an SSD network model, and belongs to the technical field of workpiece surface defect detection, and the method comprises the following steps: obtaining workpiece surface image data; inputting the acquired image data into a preset SSD network model to obtain an identification result of the surface defects of theworkpiece, wherein a backbone network of the SSD network model adopts a MobileNet network combining hole convolution and hierarchical feature fusion; according to the invention, large-scale image datacan be processed, the huge workload of artificial design features can be reduced, various different defect types can be processed at the same time, and pixel-level defect area information can be obtained.

Description

technical field [0001] The present disclosure relates to the technical field of workpiece surface defect detection, in particular to a workpiece surface defect detection method and system based on an SSD network model. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] During the machining process, due to the influence of the type of tool or operation, various textures will be formed on the surface of the workpiece. In actual production, these textures are collectively referred to as surface defects of the workpiece. With the rapid development of modern industry, in the machinery manufacturing industry, the requirements for the quality of workpieces are gradually increasing. The size and type of defects on the surface of workpieces will directly affect the cost, performance and service life of mechanical equipment. Therefore, it is of grea...

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): G01Q30/02
CPCG01Q30/02
Inventor 李兰奚舒舒张才宝张洁
Owner QINGDAO TECHNOLOGICAL UNIVERSITY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com