CN113570703A - Three-dimensional digital model porosity calculation method based on image recognition technology - Google Patents
Three-dimensional digital model porosity calculation method based on image recognition technology Download PDFInfo
- Publication number
- CN113570703A CN113570703A CN202110846720.XA CN202110846720A CN113570703A CN 113570703 A CN113570703 A CN 113570703A CN 202110846720 A CN202110846720 A CN 202110846720A CN 113570703 A CN113570703 A CN 113570703A
- Authority
- CN
- China
- Prior art keywords
- image
- digital model
- calculating
- porosity
- dimensional digital
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
Abstract
The invention discloses a three-dimensional digital model porosity calculation method based on an image recognition technology, which comprises the following steps: s1, slicing the three-dimensional digital model; s2, carrying out binarization processing on the slice image; s3, calculating the pore information of the slice by using an image recognition method; s4, calculating the porosity of the three-dimensional digital entity; the invention has the advantages that: the three-dimensional digital model is sliced into a photo form, the porosity of a three-dimensional entity is approximately obtained through the information of a two-dimensional photo, the three-dimensional entity is insensitive to the complexity of the model, the porosity is directly obtained through an image, the result of theoretically calculating the porosity can be infinitely close to a true value under the condition that the precision of the digital model is enough and the resolution of the image is enough, the processing operation is simple and convenient, the applicability is high, and the calculation result meets the precision requirement.
Description
Technical Field
The invention relates to the technical field of porosity calculation, in particular to a three-dimensional digital model porosity calculation method based on an image recognition technology.
Background
In the post-processing analysis of numerical simulation, the quality evaluation of a workpiece is often involved, and since the existence of pores can cause a plurality of adverse effects in a printed product, the calculated porosity is an important ring in the quality evaluation process;
the existing numerical simulation post-processing software does not integrate a calculation module of porosity according to some problem requirements, and the porosity is often calculated by manually extracting result data and analyzing the result data; and if the operation calculation object is directly a three-dimensional digital object, the extracted data is often huge in information amount and may not be easily processed due to the high complexity of the model.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a three-dimensional digital model porosity calculation method based on an image recognition technology. The operation object is subjected to dimension reduction processing and then is analyzed and calculated, the porosity is directly obtained through the image, the sensitivity degree of the model is low, the calculation is rapid and accurate, and the application range is wide.
In order to realize the purpose, the technical scheme adopted by the invention is as follows:
a three-dimensional digital model porosity calculation method based on an image recognition technology comprises the following steps:
s1, slicing the three-dimensional digital model; extracting relevant information of the three-dimensional digital model from a calculation program solving output result file, wherein the relevant information specifically comprises but is not limited to a space coordinate of a node;
the specific process of slicing:
and S11, setting a proper implicit function to perform excision calculation on the digital model, and selecting an excision part of the three-dimensional digital model, wherein the excision part has the characteristics of the digital model, namely, the overall pore condition can be mapped through a part.
And S12, after the implicit function is set, traversing all the unit nodes in the input digital model, and removing the nodes of the cells outside the defined implicit function space. When a cell is crossed by a clipping plane defined by the implicit function, the cell will be clipped, by generating a new node on the clipping plane. The remaining nodes can form a graph outline through the node coordinates thereof, and an image with a specific resolution is output.
S2, carrying out binarization processing on the slice image;
according to the set threshold value, the image sets the pixel points with the gray values higher than the threshold value as 255, and the pixel points with the gray values lower than the threshold value as 0, and through the processing, a plurality of images are divided into entities with the gray values of 0, and the pore and background parts with the gray values of 255. In the binarized image, 0 represents an entity, and 1 represents a pore and a background. The threshold value may be the gray value of the selected entity.
S3, calculating the pore information of the slice by using an image recognition method;
s31, calculating the total pixel sum A of the slices;
a is the number of black and white pixels.
S32, calculating the pixel sum B of the slice hole and the boundary;
and B is the number of white pixel points in the binary image.
S33, removing the boundary of the binary image to obtain a new binary image;
the boundary removal is to remove all pixels connected with the image boundary, and the image boundary does not refer to the boundary of an object and a background in the image, but refers to the boundary of the actual image display. And setting the values of the pixel points of the pixel regions connected with the boundary pixel points to be 0, namely black pixel points.
S34, calculating the pixel sum C of the new binary image pore;
the sum of the pixels of the aperture is the white pixel point in the new binary image.
S35, calculating the number of pixels occupied by the material and the holes;
the number of material and hole pixels is A- (B-C).
S4, calculating the porosity of the three-dimensional digital entity;
an aperture of how many pixels are artificially specified in the calculation process is considered to be present here, and an appropriate threshold value is selected by screening.
The three-dimensional solid porosity calculation formula is as follows:
further, the implicit function in S11 may be selected to include: rectangular faces and triangular faces.
Further, in S12, the resolution selection selects the resolution meeting the result precision requirement through the result of experimental reverse-deduction or through the convergence result at different resolutions.
Compared with the prior art, the invention has the advantages that:
the three-dimensional digital model is sliced into a photo form, the porosity of a three-dimensional entity is approximately obtained through the information of a two-dimensional photo, the three-dimensional entity is insensitive to the complexity of the model, the porosity is directly obtained through an image, the result of theoretically calculating the porosity can be infinitely close to a true value under the condition that the precision of the digital model is enough and the resolution of the image is enough, the processing operation is simple and convenient, the applicability is high, and the calculation result meets the precision requirement.
Drawings
FIG. 1 is a flow chart of a method for calculating the porosity of a three-dimensional digital model according to an embodiment of the present invention;
FIG. 2 is a slice effect diagram of an embodiment of the invention;
FIG. 3 is a diagram of resolution selection changes according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating the effect of the binarization processing in the embodiment of the invention;
FIG. 5 is a diagram illustrating the effect of boundary removal processing according to an embodiment of the present invention;
FIG. 6 is a numerical model after additive manufacturing according to an embodiment of the invention;
FIG. 7 is a binary image of model slice derivation according to an embodiment of the present invention;
FIG. 8 is a plot of porosity results and error calculated for an example of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings by way of examples.
As shown in fig. 1, a method for calculating the porosity of a three-dimensional digital model based on an image recognition technology comprises the following steps:
s1, slicing the three-dimensional digital model;
and the related information of the three-dimensional digital model specifically comprises, but is not limited to, the spatial coordinates of the nodes, and for a cloud picture that further outputs stress strain and the like on the slice, the information of the stress strain and the like on the nodes can be further output. And extracting the solution from the output result file of the calculation program. The establishment of the related information such as the space coordinate and the like is the same as the coordinate system of the model established when the problem is solved. The specific process of slicing:
s11, setting proper implicit function to perform excision calculation on the digital model, and selecting the excision part of the three-dimensional digital model, wherein the excision part should have the characteristics of the digital model (i.e. the whole pore situation can be mapped through part). The implicit function can be selected from various forms, such as a rectangular surface, a triangular surface and the like.
And S12, after the implicit function is set, traversing all the unit nodes in the input digital model, and removing the nodes of the cells outside the defined implicit function space. When a cell is crossed by a clipping plane defined by the implicit function, the cell will be clipped, by generating a new node on the clipping plane. The remaining nodes can form a graph outline through the node coordinates thereof, and an image with a specific resolution is output.
The resolution selection can select the resolution meeting the result precision requirement through the result of experimental reverse deduction or through the convergence result under different resolutions. As shown in fig. 2, which shows the porosity trend with the resolution, the slice image may be selected to have a resolution satisfying the accuracy, as shown in fig. 3.
S2, carrying out binarization processing on the slice image;
according to the set threshold value, the image sets the pixel points with the gray values higher than the threshold value as 255, and the pixel points with the gray values lower than the threshold value as 0, and through the processing, a plurality of images are divided into entities with the gray values of 0, and the pore and background parts with the gray values of 255. In the binarized image, 0 represents an entity, and 1 represents a pore and a background. The threshold value may be selected as the gray level value of the entity, and the effect after the binarization processing is as shown in fig. 4.
S3, calculating the pore information of the slice by using an image recognition method;
s31, calculating the total pixel sum A of the slices;
a is the number of black and white pixels.
S32, calculating the pixel sum B of the slice hole and the boundary;
and B is the number of white pixel points in the binary image.
S33, removing the boundary of the binary image to obtain a new binary image;
the boundary removal is to remove all pixels connected with the image boundary, and the image boundary does not refer to the boundary of an object and a background in the image, but refers to the boundary of the actual image display. The values of the pixels in the pixel region connected to the boundary pixel are all set to 0 (i.e., black pixels), and the boundary removal effect is shown in fig. 5.
S34, calculating the pixel sum C of the new binary image pore
The sum of the pixels of the aperture is the white pixel point in the new binary image.
S35, calculating the number of pixels occupied by the material and the hole (integral area)
The number of material and hole pixels is A- (B-C)
S4, calculating the porosity of the three-dimensional digital entity;
in the calculation process, it can be artificially specified how many pores composed of pixels are considered as pores existing here, and an appropriate threshold value is selected through screening.
The three-dimensional solid porosity calculation formula is as follows:
example results show that:
fig. 6 is a result diagram after numerical simulation of a metal additive manufacturing process, in which porosity of a cladding layer under different laser speeds is to be calculated, fig. 7 is a binary diagram obtained by slicing a numerical model and deriving the porosity result, fig. 8 shows the porosity result obtained through calculation, X and Y in an image 8 indicate slicing in different directions, XYAVE is an average value of the porosities calculated by slicing in the X and Y directions, a porosity threshold value can be set in the calculation process, that is, the number of pores larger than a pixel point is considered to be counted, and an error diagram 8 right diagram is obtained. The advantage of this example is that the image resolution is improved under the conditions allowed by the equipment, and the calculated result will approach the true value in the simulation environment.
It will be appreciated by those of ordinary skill in the art that the examples described herein are intended to assist the reader in understanding the manner in which the invention is practiced, and it is to be understood that the scope of the invention is not limited to such specifically recited statements and examples. Those skilled in the art can make various other specific changes and combinations based on the teachings of the present invention without departing from the spirit of the invention, and these changes and combinations are within the scope of the invention.
Claims (3)
1. A three-dimensional digital model porosity calculation method based on an image recognition technology is characterized by comprising the following steps:
s1, slicing the three-dimensional digital model; extracting relevant information of the three-dimensional digital model from a calculation program solving output result file, wherein the relevant information specifically comprises but is not limited to a space coordinate of a node;
the specific process of slicing:
s11, setting a proper implicit function to perform excision calculation on the digital model, and selecting an excision part of the three-dimensional digital model, wherein the excision part has the characteristics of the digital model, namely, the overall pore condition can be mapped through part of the excision part;
s12, after the implicit function is set, traversing all the unit nodes in the input digital model, and removing the nodes of the cells outside the defined implicit function space; when the cells are crossed by a shearing surface defined by the implicit function, the cells are sheared, and new nodes are generated on the shearing surface; the left nodes can form a graph outline through the node coordinates of the nodes, and an image with a specific resolution is output;
s2, carrying out binarization processing on the slice image;
according to the set threshold value, the image sets the pixel points with the gray value higher than the threshold value as 255, the pixel points with the gray value lower than the threshold value as 0, and through the processing, a plurality of images are divided into entities with the gray value of 0, and the pore and background parts with the gray value of 255; 0 in the binarized image represents an entity, and 1 represents a pore and a background; selecting the gray value of the entity by the threshold value;
s3, calculating the pore information of the slice by using an image recognition method;
s31, calculating the total pixel sum A of the slices;
a is the number of black and white pixel points;
s32, calculating the pixel sum B of the slice hole and the boundary;
b is the number of white pixel points in the binary image;
s33, removing the boundary of the binary image to obtain a new binary image;
the step of removing the boundary is to completely remove pixels connected with the image boundary, wherein the image boundary does not refer to the boundary of an object and a background in the image, but refers to the boundary of the actual image display; setting all the values of the pixel points of the pixel region connected with the boundary pixel points to be 0, namely black pixel points;
s34, calculating the pixel sum C of the new binary image pore;
the sum of the pixels of the pores is a white pixel point in the new binary image;
s35, calculating the number of pixels occupied by the material and the holes;
the number of material and hole pixels is A- (B-C);
s4, calculating the porosity of the three-dimensional digital entity;
manually specifying the number of pores formed by pixels in the calculation process, determining that pores exist, and selecting a proper threshold value through screening;
the three-dimensional solid porosity calculation formula is as follows:
2. the method for calculating the porosity of the three-dimensional digital model according to claim 1, wherein: the implicit function in S11 may be selected to include: rectangular faces and triangular faces.
3. The method for calculating the porosity of the three-dimensional digital model according to claim 1, wherein: the resolution selection in S12 selects the resolution meeting the accuracy requirement of the result through the result of experimental reverse-deduction or through the convergence result at different resolutions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110846720.XA CN113570703B (en) | 2021-07-26 | 2021-07-26 | Three-dimensional digital model porosity calculation method based on image recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110846720.XA CN113570703B (en) | 2021-07-26 | 2021-07-26 | Three-dimensional digital model porosity calculation method based on image recognition technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113570703A true CN113570703A (en) | 2021-10-29 |
| CN113570703B CN113570703B (en) | 2023-05-16 |
Family
ID=78167606
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110846720.XA Active CN113570703B (en) | 2021-07-26 | 2021-07-26 | Three-dimensional digital model porosity calculation method based on image recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113570703B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120281883A1 (en) * | 2011-02-28 | 2012-11-08 | Hurley Neil F | Methods to build 3d digital models of porous media using a combination of high- and low-resolution data and multi-point statistics |
| CN104237103A (en) * | 2014-09-23 | 2014-12-24 | 中国石油天然气股份有限公司 | Quantitative characterization method and quantitative characterization device for pore connectivity |
| KR20160069379A (en) * | 2014-12-08 | 2016-06-16 | 공주대학교 산학협력단 | Apparatus and method for calculating permeability and porosity of rock using image of slice of rock |
| US20200132657A1 (en) * | 2018-10-31 | 2020-04-30 | Hubert E. King, JR. | Microanalysis of Fine Grained Rock for Reservoir Quality Analysis |
-
2021
- 2021-07-26 CN CN202110846720.XA patent/CN113570703B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120281883A1 (en) * | 2011-02-28 | 2012-11-08 | Hurley Neil F | Methods to build 3d digital models of porous media using a combination of high- and low-resolution data and multi-point statistics |
| CN104237103A (en) * | 2014-09-23 | 2014-12-24 | 中国石油天然气股份有限公司 | Quantitative characterization method and quantitative characterization device for pore connectivity |
| KR20160069379A (en) * | 2014-12-08 | 2016-06-16 | 공주대학교 산학협력단 | Apparatus and method for calculating permeability and porosity of rock using image of slice of rock |
| US20200132657A1 (en) * | 2018-10-31 | 2020-04-30 | Hubert E. King, JR. | Microanalysis of Fine Grained Rock for Reservoir Quality Analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113570703B (en) | 2023-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10510148B2 (en) | Systems and methods for block based edgel detection with false edge elimination | |
| CN110569899A (en) | Dam face defect classification model training method and device | |
| CN113109368B (en) | Glass crack detection method, device, equipment and medium | |
| KR20220058843A (en) | Method, device, device and storage medium for detecting the condition of a camera lens | |
| JP2016505186A (en) | Image processor with edge preservation and noise suppression functions | |
| CN110298858B (en) | Image clipping method and device | |
| CN110795978B (en) | Road surface point cloud data extraction method and device, storage medium and electronic equipment | |
| CN109461136B (en) | Method for detecting fiber distribution condition in mixed fiber product | |
| CN112070792B (en) | Edge growth connection method and device for image segmentation | |
| DE102021127403A1 (en) | DIE-LINE DEFECT QUALITY MONITORING SYSTEM AND DIE-LINE DEFECT MONITORING METHOD | |
| CN113570703B (en) | Three-dimensional digital model porosity calculation method based on image recognition technology | |
| CN114511862B (en) | Form identification method and device and electronic equipment | |
| CN110968835A (en) | Approximate quantile calculation method and device | |
| CN108109120B (en) | Illumination compensation method and device for dot matrix two-dimensional code | |
| CN115482239A (en) | Image positioning method, system, device and medium | |
| CN115830048A (en) | Image edge detection method and device and related equipment | |
| CN112084884A (en) | Scanning electron microscope image pore identification method, terminal device and storage medium | |
| CN111783648A (en) | Method and device for extracting guardrail in road point cloud | |
| CN112861874A (en) | Expert field denoising method and system based on multi-filter denoising result | |
| CN111932470A (en) | Image restoration method, device, equipment and medium based on visual selection fusion | |
| CN113382134B (en) | Focusing debugging method of linear array industrial camera | |
| CN114723748B (en) | Detection method, device and equipment of motor controller and storage medium | |
| CN117197036B (en) | Image detection method and device | |
| JP7028099B2 (en) | Candidate area estimation device, candidate area estimation method, and program | |
| Luo et al. | SMT stencil automatic registration method based on coordinates distribution analysis |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |