CN115015266A - Image identification and evaluation method for area fraction of pores in metallographic structure of casting - Google Patents
Image identification and evaluation method for area fraction of pores in metallographic structure of casting Download PDFInfo
- Publication number
- CN115015266A CN115015266A CN202210531740.2A CN202210531740A CN115015266A CN 115015266 A CN115015266 A CN 115015266A CN 202210531740 A CN202210531740 A CN 202210531740A CN 115015266 A CN115015266 A CN 115015266A
- Authority
- CN
- China
- Prior art keywords
- metallographic structure
- picture
- casting
- metallographic
- area fraction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/693—Acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/695—Preprocessing, e.g. image segmentation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8858—Flaw counting
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Investigating And Analyzing Materials By Characteristic Methods (AREA)
Abstract
The invention discloses an image identification and evaluation method for the area fraction of pores in a metallographic structure of a casting. The technical scheme adopted by the invention is as follows: shooting a metallographic structure of a metallographic sample into a picture by using a metallographic microscope; importing the metallographic structure picture into ImageJ software, and setting the size proportion of the ImageJ software according to the size label of the metallographic structure picture; converting the metallographic structure picture into a bitmap; setting a proper threshold value, and converting the metallographic structure picture into a black and white picture in a binarization mode; filling possible gaps in the pores in the metallographic structure picture, and breaking possible overlapping parts between adjacent pores in the metallographic structure picture; and carrying out image intelligent analysis on the metallographic structure picture by using an analysis Particles algorithm of ImageJ software to obtain the average pore area fraction and the maximum pore area of the cast aluminum alloy casting. The method is based on the image identification method of the metallographic structure of the cast aluminum alloy casting, and can quantitatively, accurately and scientifically evaluate the degree of the pores of the cast aluminum alloy casting.
Description
Technical Field
The invention relates to the field of image identification and evaluation, in particular to an image identification and evaluation method for the area fraction of pores in a metallographic structure of a casting.
Background
Cast aluminum alloy is a metal material with large using amount, and is widely applied to various industries such as aviation, aerospace, machinery, electric power and the like due to the advantages of small density, high specific strength, good processing performance and the like. Generally, aluminum alloys suffer from thermal expansion and contraction, and the solubility of gases in liquid aluminum alloys tends to be much higher than in solid aluminum alloys. Therefore, in the process of solidification of the cast aluminum alloy, dispersed and fine pores are often formed in the aluminum alloy casting or in the thick part of the aluminum alloy casting due to the fact that the solidification volume of the aluminum alloy solution is difficult to timely compensate shrinkage, and gas overflowing from the solution is not ready to be discharged. The phenomenon of fine pores concentration is called shrinkage porosity. The shrinkage porosity is hidden in the casting and is difficult to find in appearance, but obviously damages the mechanical property of the casting and is a potential main quality threat of the casting. To assess the porosity of aluminum alloy castings, those skilled in the art have written the mechanical industry standard JB/T7946.3-2017 "cast aluminum alloy metallographic section 3: casting aluminum alloy pinholes. However, the standard still adopts the qualitative rating method of legend comparison and quantity framing which is used in the last century, the evaluation standard is fuzzy, quantification is difficult to achieve, artificial subjective judgment factors are obvious, and the development requirements of comprehensive intelligent manufacturing, accurate quantification and objective evaluation are difficult to adapt. Therefore, it is necessary to provide a new technology for analyzing the degree of casting porosity (shrinkage porosity) to achieve intelligent, quantitative and scientific evaluation of the degree of casting porosity (shrinkage porosity).
Image intelligent recognition technology has been around for many years and processes, analyzes and understands images by means of computer machine learning to recognize different targets and objects. The technology is widely applied to the fields of face recognition, commodity bar code recognition, hazard source identification and the like. By applying the principle of image recognition technology image acquisition, image preprocessing, feature extraction and image recognition to the analysis of the metallographic structure picture of the aluminum alloy casting, the intelligent analysis of the aluminum alloy casting pores (shrinkage porosity) can be better realized, and the efficiency, the accuracy and the quantification of the aluminum alloy casting pore (shrinkage porosity) degree evaluation can be greatly improved.
Disclosure of Invention
The invention aims to provide an image identification and evaluation method for the area fraction of pores in the metallographic structure of a cast aluminum alloy casting, so as to quantitatively, accurately and scientifically evaluate the pore degree of the casting.
Therefore, the invention is realized by adopting the following technical scheme: an image identification and evaluation method for the area fraction of pores in a metallographic structure of a casting comprises the following steps:
sampling a proper part of the cast aluminum alloy casting, preparing a metallographic sample, and then grinding and polishing;
shooting a metallographic structure of a metallographic sample into a picture by using a metallographic microscope;
importing the metallographic structure picture into ImageJ software, and setting the size proportion of the ImageJ software according to the size label of the metallographic structure picture;
converting the metallographic structure picture into a bitmap;
setting a proper threshold value, and converting the metallographic structure picture into a black and white picture in a binarization mode;
filling gaps possibly existing in the air Holes in the metallographic structure picture through a Fill Holes algorithm of ImageJ software, and then breaking overlapping parts possibly existing between adjacent air Holes in the metallographic structure picture through a watershed algorithm;
carrying out image intelligent analysis on the metallographic structure picture by using an Analyze partitions algorithm of ImageJ software;
and (4) carrying out statistical summary on the result of the image intelligent analysis to obtain the average pore area fraction and the maximum pore area of the cast aluminum alloy casting.
ImageJ is a public image analysis software, is mature in technology and meets the requirements of identifying and evaluating the air hole surface area number image of the cast aluminum alloy casting.
Furthermore, in order to ensure that the samples are representative, more than 2 metallographic samples are selected in the casting or in the thick part for analysis, the surface roughness Ra of the metallographic samples of the casting is not more than 1.0 mu m, and the surface of the metallographic samples does not generally need to be chemically corroded.
Furthermore, for each type of metallographic structure picture with the magnification, a picture with a size label is firstly taken for the ImageJ software to set the size ratio.
Furthermore, the metallographic structure picture is shot randomly, and at least 8 fields of view are selected for metallographic structure shooting.
Furthermore, the magnification of the metallographic structure picture is 25 times or 50 times, and the metallographic structure in the picture should fill the whole picture without any gap.
Further, the number of pores, the area of a single pore and the area fraction of pores in the metallographic structure picture of the casting are obtained by direct analysis, the average pore area fraction is obtained by averaging the pore area fraction of the metallographic structure picture of all samples of the casting, and the maximum pore area is obtained by comparing the maximum pore areas of the metallographic structure pictures of all samples of the casting.
Compared with the prior art, the invention has the beneficial effects that: according to the invention, the measurement efficiency and the measurement accuracy of parameters such as the pore area fraction, the number of pores, the area of a single pore, the maximum pore area and the like in the metallographic structure in the aluminum alloy casting are improved through image processing and image recognition technology. According to the invention, through the analysis Particles algorithm, the intelligent identification of the internal air hole characteristics of the aluminum alloy casting is realized, and the artificial identification is replaced.
Drawings
FIG. 1 is a flow chart of an image identification and evaluation method of the area fraction of pores in the metallographic structure of a casting according to the invention;
FIG. 2 is a metallographic structure diagram of a cast aluminum alloy power equipment clamp in an application example of the present invention;
FIG. 3 is a reference diagram of the pinhole degree class 1 in Table 1 according to the application example of the present invention;
FIG. 4 is a reference diagram of the pinhole degree grade of 2 in Table 1 according to the application example of the present invention;
FIG. 5 is a reference diagram of the pinhole degree grade of 3 in Table 1 according to the application example of the present invention;
FIG. 6 is a reference diagram of the pinhole degree scale of 4 in Table 1 according to the application example of the present invention;
fig. 7 is a reference diagram of the grade of pinhole degree of 5 in table 1 according to the application example of the present invention.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further described with the specific drawings.
An image identification and evaluation method for the pore area fraction of a cast aluminum alloy casting comprises the steps of firstly taking more than 2 samples in the interior or the large part of the cast aluminum alloy casting in a machining mode, then grinding and polishing the samples to prepare qualified metallographic samples, and then shooting the metallographic structure of the samples into pictures by using a metallographic microscope, as shown in figure 1.
The first step is as follows: and opening the ImageJ software, introducing a metallographic structure picture to be analyzed, drawing a straight line with the same length as the ruler along the ruler of the metallographic structure picture, and setting the length of the ruler.
The second step is that: and converting the metallographic structure picture into an 8-bit bitmap.
The third step: and selecting a proper threshold value according to the metallographic structure picture, ensuring that the air holes can be close to the actual condition as much as possible, and carrying out black-and-white binarization on the metallographic structure picture.
The fourth step: gaps possibly existing in the air Holes in the metallographic structure picture are filled through a Fill Holes algorithm of ImageJ software, and then overlapping parts possibly existing between adjacent air Holes in the metallographic structure picture are broken through a watershed algorithm, so that morphological optimization is carried out on the image.
The fifth step: and carrying out image intelligent analysis on the metallographic structure picture by using an analysis Particles algorithm of ImageJ software.
And a sixth step: and counting the intelligent analysis result of the image, and recording the pore area integral number and the maximum pore area of the metallographic structure picture.
And after all metallographic structure pictures shot by all samples are subjected to intelligent image analysis according to the method, average pore area fraction of the casting is obtained after pore area integral numerical calculation of all metallographic structure pictures is averaged, and the maximum pore area of the casting is obtained after the maximum pore areas of all metallographic structure pictures are compared.
Application example
An image identification and evaluation method for the area fraction of air holes of a cast aluminum alloy power equipment wire clamp casting comprises the following steps:
the wire clamp for the power equipment comprises ZL102 cast aluminum alloy, 10-13 wt.% of Si and the balance of Al. After smelting at 700 ℃ for 1h, pouring under the pressure of 0.1MPa, wherein the temperature of a mold is 350 ℃, the casting temperature is 700 ℃, and after filling, air cooling to room temperature is carried out. Taking 2 samples at the thick large part of the power equipment wire clamp to shoot metallographic structure pictures, as shown in figure 2. And then intelligently recognizing the image through ImageJ software. Through quantitative analysis, the maximum air hole area of the power equipment wire clamp is 0.122mm 2 The average pore area fraction was 5.37%.
According to the current JB/T7946.3-2017 cast aluminum alloy metallographic phase part 3: the pin hole degree rating of the cast aluminum alloy pin hole is shown in Table 1. The diameter of the maximum air hole of the power equipment wire clamp is about 0.74mm, the number of the air holes is large, and therefore the air hole grade of the wire clamp is rated as 4.
TABLE 1
The foregoing shows and describes the general principles, essential features, and advantages of the invention. The present invention is not limited by the above-described embodiments, which are described in the specification and drawings only for the principles of the present invention. Any simple modifications, changes and equivalent structural changes of the above embodiments according to the technical essence of the present invention are within the protection scope of the technical solution of the present invention.
Claims (6)
1. An image identification and evaluation method for the pore area fraction of a metallographic structure of a casting is characterized by comprising the following steps:
sampling a proper part of the cast aluminum alloy casting, preparing a metallographic sample, and then grinding and polishing;
shooting a metallographic structure of a metallographic sample into a picture by using a metallographic microscope;
importing the metallographic structure picture into ImageJ software, and setting the size proportion of the ImageJ software according to the size label of the metallographic structure picture;
converting the metallographic structure picture into a bitmap;
setting a proper threshold value, and converting the metallographic structure picture into a black and white picture in a binarization mode;
filling gaps possibly existing in the air Holes in the metallographic structure picture through a Fill Holes algorithm of ImageJ software, and then breaking overlapping parts possibly existing between adjacent air Holes in the metallographic structure picture through a watershed algorithm;
carrying out image intelligent analysis on the metallographic structure picture by using an Analyze partitions algorithm of ImageJ software;
and (4) carrying out statistical summary on the result of the image intelligent analysis to obtain the average pore area fraction and the maximum pore area of the cast aluminum alloy casting.
2. The image identification and evaluation method for the area fraction of the pores in the metallographic structure of the casting according to claim 1, wherein more than 2 metallographic samples are selected from the interior or the large part of the casting for analysis in order to ensure that the samples are representative, the surface roughness Ra of the metallographic samples of the casting is not more than 1.0 μm, and the surface of the metallographic samples does not generally need to be chemically corroded.
3. The image identification and evaluation method for the area fraction of the metallographic structure gas hole of the casting as claimed in claim 1, wherein for each type of the picture of the metallographic structure with the magnification, a picture with a size mark is taken first for the ImageJ software to set the size ratio.
4. The image identification and evaluation method for the area fraction of the metallographic structure gas hole of the casting according to claim 1, wherein the metallographic structure picture is randomly shot, and at least 8 fields of view are selected for shooting the metallographic structure.
5. The image identification and evaluation method for the pore area fraction of the metallographic structure of the casting according to claim 1, wherein the magnification of the picture of the metallographic structure is 25 times or 50 times, and the metallographic structure in the picture should fill the whole picture without leaving any gaps.
6. The image identification and evaluation method for the metallographic structure gas pore area fraction of the casting according to claim 1, wherein the number of gas pores, the area of a single gas pore, and the area fraction of gas pores in the metallographic structure picture of the casting are obtained by direct analysis, the average gas pore area fraction is obtained by averaging the gas pore area fractions of the metallographic structure pictures of all samples of the casting, and the maximum gas pore area is obtained by comparing the maximum gas pore areas of the metallographic structure pictures of all samples of the casting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210531740.2A CN115015266A (en) | 2022-05-16 | 2022-05-16 | Image identification and evaluation method for area fraction of pores in metallographic structure of casting |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210531740.2A CN115015266A (en) | 2022-05-16 | 2022-05-16 | Image identification and evaluation method for area fraction of pores in metallographic structure of casting |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115015266A true CN115015266A (en) | 2022-09-06 |
Family
ID=83069812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210531740.2A Pending CN115015266A (en) | 2022-05-16 | 2022-05-16 | Image identification and evaluation method for area fraction of pores in metallographic structure of casting |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115015266A (en) |
-
2022
- 2022-05-16 CN CN202210531740.2A patent/CN115015266A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11506650B2 (en) | Method for automatic quantitative statistical distribution characterization of dendrite structures in a full view field of metal materials | |
| CN111965183B (en) | Titanium alloy microstructure detection method based on deep learning | |
| CN111860176B (en) | Non-metal inclusion full-view-field quantitative statistical distribution characterization method | |
| JP2023511869A (en) | Method and system for automatic identification and grading of low multiplication acid etching defects by machine vision | |
| CN111738131B (en) | Method for extracting parameter characteristics of alloy two-phase microstructure | |
| CN106370565A (en) | Quantitative detection method for primary silicon phases in hypereutectic aluminum-silicon alloy | |
| CN108535105B (en) | Method for predicting fatigue strength of vermicular graphite cast iron | |
| CN109406524A (en) | Aluminium alloy impurity phase quantitative detecting method | |
| Dixon et al. | Quantification of the fatigue severity of porosity in aluminium alloy 7050-T7451 thick plate | |
| CN115015266A (en) | Image identification and evaluation method for area fraction of pores in metallographic structure of casting | |
| CN108830849B (en) | Hypereutectic/hypoeutectic Al-Si alloy modification grading method based on image processing technology | |
| CN111766237A (en) | Statistical calculation method for average distance of non-metallic inclusions in metal material | |
| CN114740030A (en) | Identification and in-situ quantitative statistical distribution characterization method for microcracks on surface of metal material | |
| Balasubramani et al. | Defect identification in casting surface using image processing techniques | |
| CN115170484A (en) | Characterization and classification method for surface defects of laser additive manufacturing workpiece | |
| Ling et al. | Research on segmentation features in visual detection of rust on bridge pier | |
| Bingan et al. | Research on Visual Inspection Algorithm of Crimping Appearance Defects for Wiring Harness Terminals | |
| Lin et al. | Alloy Cast Product Defect Detection Based on Object Detection | |
| CN111650096A (en) | Fisher-type particle size standard sample and preparation method and application thereof | |
| Bubonyi et al. | Comparison of CT and metallographic method for evaluation of microporosities of dye cast aluminum parts | |
| Bin et al. | Research on Surface Defect Detection System of Brake Disc | |
| Stachowicz et al. | Evaluation of 2D and 3D surface roughness of die castings from alloy AlSi9Cu3 | |
| Harris | Particle cracking damage evolution in 7075 wrought aluminum alloy under monotonic and cyclic loading conditions | |
| Femat-Diaz et al. | Microcrack parameters characterization in hard-coatings using moments for image processing | |
| Shirsat et al. | Metallographic Image Analysis for Quality Assurance of Metals: A Review |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |