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

Automatic category rating method for microscopic particles in nodular cast iron

A nodular cast iron, automatic classification technology, applied in the direction of individual particle analysis, particle and sedimentation analysis, image data processing, etc., can solve the problems of inability to accurately identify and judge the name of the organization, lack of adaptability and accuracy, etc.

Inactive Publication Date: 2012-06-13
天津卓朗科技发展有限公司
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method cannot accurately identify and judge the name of the segmented tissue, and it lacks adaptability and accuracy to the processing of metallographic images containing various tissues.

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
  • Automatic category rating method for microscopic particles in nodular cast iron
  • Automatic category rating method for microscopic particles in nodular cast iron
  • Automatic category rating method for microscopic particles in nodular cast iron

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0070] Automatic Classification and Grading of Microscopic Particles in Ductile Iron Sample 1

[0071] The first step is to collect images

[0072] The metallographic image of the tested nodular cast iron is collected through an optical microscope and a CCD camera. The resolution of the CCD camera used is 2 million pixels, and the USB interface is used for communication. Frames are saved as images in BMP format.

[0073] In the second step, the customer enters the estimated number of microparticle categories for classification

[0074] Considering the quantification of the metallographic structure rating of nodular cast iron, the estimated value of the microscopic particle cluster number for the classification input by the customer is K=2.

[0075] The third step, image preprocessing

[0076] The image collected in the first step is subjected to image preprocessing. The operation process is to grayscale the image first, then convert the three-channel image into a single-cha...

Embodiment 2

[0118] Automatic Classification and Grading of Microscopic Particles in Ductile Iron Sample 2

[0119] The first step is to collect images

[0120] Collect the metallographic image of the tested nodular cast iron sample 2 through an optical microscope and a CCD camera. The resolution of the CCD camera used is 3 million pixels, and the USB interface is used for communication. The frame rate of video collection is 31 frames per second, and the capture effect is better. A frame is saved as an image in JPG format.

[0121] In the second step, the customer enters the estimated number of microparticle categories for classification

[0122] Considering the quantification of metallographic structure rating of nodular cast iron, the estimated value of microscopic particle cluster number for customer input classification is K=3.

[0123] The third step, image preprocessing

[0124] The image collected in the first step is subjected to image preprocessing. The operation process is to ...

Embodiment 3

[0166] Automatic Classification and Grading of Microscopic Particles in Ductile Iron Sample 3

[0167] The first step is to collect images

[0168] Collect the metallographic image of the tested nodular cast iron sample 3 through an optical microscope and a CCD camera. The resolution of the CCD camera used is 1.3 million pixels, and the USB interface is used for communication. The frame rate of the video collection is 11 frames per second, and the capture effect is better. A frame is saved as an image in BMP format.

[0169] In the second step, the customer enters the estimated number of microparticle categories for classification

[0170] Considering the quantification of metallographic structure rating of nodular cast iron, the estimated value of microscopic particle cluster number for customer input classification is K=3.

[0171] The third step, image preprocessing

[0172] The image collected in the first step is subjected to image preprocessing. The operation process ...

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 category rating method for microscopic particles in nodular cast iron, which relates to metallographic microscopic image data processing and includes the steps: acquiring images; inputting the estimation value of the category number of the categorical microscopic particles by a client; preprocessing the images; clustering and categorizing the images; and extracting and computing morphological characteristics of the microscopic particles in the images, and distinguishing and rating categories of the microscopic particles in the nodular cast iron according to corresponding national standards. By integrally applying improved K-means clustering algorithm and image partitioning algorithm and by combining metallographic characteristic values, the images are partitioned into the corresponding number of sample images according the categories of the microscopic particles in the images, each partitioned image only contains one category of microscopic particles, and a user can select proper microscopic particles for category rating as needed, so that the automatic category rating method overcomes the shortcoming that processing for metallographic images by means of existing metallographic microscopic analysis technology, particularly processing for the metallographic images containing various textures lacks accuracy and authority of inspection.

Description

technical field [0001] The technical scheme of the invention relates to metallographic microscopic image data processing, in particular to an automatic classification and grading method for microscopic particles in ductile iron. Background technique [0002] Metallographic microanalysis is a very important research method in the scientific research of metal materials. It can observe and study the structural details and defects in metals that cannot be observed by macroscopic analysis methods. Since the size of the metallographic geometric parameter has a great influence on the properties of the material, its detection plays an important role in the analysis of metal materials. [0003] In the existing metallographic microscopic analysis technology, the difference of the particles in the metallographic microscopic image is not big, it is difficult to distinguish and judge manually, and the judgment and inspection standards are not uniform, and human factors have a great influ...

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): G01N15/14G06T5/00
Inventor 张坤宇岳洋李旺
Owner 天津卓朗科技发展有限公司
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