Titanium alloy surface defect treatment method
By constructing a titanium alloy defect recognition model based on image data, identifying and processing various types of defects on the surface of titanium alloy, the problems of poor treatment effect of multiple defects and limited recognition ability in the prior art are solved, and titanium is improved Alloy surface quality and service life.
Patent Information
- Application Number
- CN202411014792.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-25
- Publication Date
- 2024-11-12
AI Technical Summary
The existing titanium alloy surface defect treatment technology cannot effectively deal with multiple types of defects, and the image recognition technology has limited accuracy and efficiency in identifying small defects, so it is impossible to accurately evaluate the usability, safety and quality of defects.
By obtaining defect image data of titanium alloy products, a defect recognition model based on scrap, history and scrap product images is constructed, the defect degree of the product to be tested is identified, and the treatment plan is determined based on the defect degree, including polishing, grinding, welding, heat treatment or cutting, etc. Wait for operations.
It realizes effective treatment of various types of defects, improves the accuracy and efficiency of identification, especially the ability to identify small defects, can evaluate its usability and safety according to the degree of defects, and extends the service life of titanium alloy.
Smart Images

Figure CN118941931A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of titanium alloy surface defect treatment, and in particular to a titanium alloy surface defect treatment method. Background Art
[0002] Titanium alloy is a high-performance structural material. It is widely used in aerospace, automobile, medical equipment and other fields due to its advantages such as high strength, low density, good corrosion resistance and biocompatibility. However, titanium alloy may produce surface defects such as cracks, pores, inclusions, etc. due to various reasons during the manufacturing and use process. These defects may affect the performance and service life of titanium alloy. Therefore, it is crucial to effectively detect and treat the surface of titanium alloy to ensure its quality and safety.
[0003] Existing titanium alloy surface defect treatment technologies mainly include mechanical processing, chemical treatment, heat treatment and other methods, which can effectively improve the surface quality of titanium alloy and increase its service life. In addition, with the development of computer technology, image recognition technology based on deep learning has also been applied to the detection of titanium alloy surface defects, which can realize the automatic identification and positioning of defects.
[0004] Although the existing titanium alloy surface defect treatment technology and image recognition technology have solved the problem of titanium alloy surface defects to a certain extent, there are still some problems and shortcomings. First, the existing surface treatment technology can often only target specific types of defects, and the treatment effect on multiple types of defects is not good. Secondly, although the existing image recognition technology can realize the automatic recognition of defects, its recognition accuracy and efficiency need to be improved, especially for the limited recognition ability of minor defects. In addition, the existing technology is often unable to analyze its usability, safety and quality issues according to the degree of defects, which brings certain difficulties to practical applications. Summary of the invention
[0005] In view of the above problems, the present application is proposed to provide a titanium alloy surface defect treatment method that overcomes the above problems or at least partially solves the above problems, comprising:
[0006] A method for treating surface defects of a titanium alloy, the method comprising:
[0007] Acquire defect image data of titanium alloy products, wherein the defect image data includes images of scrap titanium alloy products, images of historical titanium alloy products, and images of scrapped titanium alloy products;
[0008] Constructing a defect recognition model based on the scrap titanium alloy product image, the historical titanium alloy product image and the scrap titanium alloy product image;
[0009] Determine the degree of defects corresponding to the titanium alloy product to be tested by performing defect identification based on the defect identification model and the titanium alloy product to be tested;
[0010] A treatment plan corresponding to the titanium alloy product to be tested is determined according to the defect degree.
[0011] Furthermore, the step of obtaining defect image data of the titanium alloy product includes:
[0012] Acquiring a surface image of the titanium alloy product;
[0013] Performing image recognition on the surface image to determine product types, wherein the product types include waste products and finished products;
[0014] Screening a target titanium alloy product corresponding to the product type as the scrap product;
[0015] Obtaining a defect area of the target titanium alloy product;
[0016] generating a first target surface image according to the defect area;
[0017] The defect image data is generated based on the first target surface image and the second target surface image corresponding to the historical problem product.
[0018] Furthermore, the step of obtaining the defective region of the target titanium alloy product comprises:
[0019] Collect the grayscale image of the target titanium alloy product;
[0020] Perform pixel segmentation according to the grayscale image to obtain a plurality of super pixel blocks;
[0021] Determine the gradient magnitude of each superpixel block corresponding to a pixel point;
[0022] Determining the grayscale uniformity of each superpixel block according to the grayscale value difference and gradient amplitude difference of the pixel points in each superpixel block;
[0023] Generating texture information according to the grayscale uniformity, the gradient assignment and the edge pixel points of each super pixel block;
[0024] Determining gloss regularity information corresponding to each of the superpixel blocks according to the texture information;
[0025] Determine the glossiness corresponding to each superpixel block according to the gloss regularity information and the grayscale distribution difference between the superpixel block and other superpixel blocks;
[0026] Determining the pixel grayscale value of each pixel point according to the glossiness of each superpixel block;
[0027] Generating a suspected defect area according to the pixel grayscale value of each of the pixel points and the edge pixel points;
[0028] Layering the suspected defect areas to generate various suspected areas;
[0029] The defect area is determined according to each of the suspected areas, target pixels corresponding to the suspected defect areas, and local pixels corresponding to the target pixels.
[0030] Furthermore, the step of constructing a defect recognition model based on the scrap titanium alloy product image, the historical titanium alloy product image and the scrapped titanium alloy product image includes:
[0031] Performing convolutional neural network learning to generate a preliminary prediction model based on the scrap titanium alloy product image, the historical titanium alloy product image, and the scrapped titanium alloy product image;
[0032] Generating preliminary prediction results corresponding to the titanium alloy product according to the preliminary prediction model;
[0033] The preliminary prediction model is adjusted according to the error between the preliminary prediction result and the actual result to generate the defect recognition model.
[0034] Furthermore, the step of performing defect identification based on the defect identification model and the titanium alloy product to be tested to determine the defect degree corresponding to the titanium alloy product to be tested includes:
[0035] Collecting image information of the titanium alloy product to be tested;
[0036] Determining defect information corresponding to the titanium alloy product to be tested according to the image information and the defect recognition model, wherein the defect information includes defect type, defect location, defect morphology and defect range;
[0037] A defect degree corresponding to the titanium alloy product to be tested is generated according to the defect type, the defect position, the defect morphology and the defect range.
[0038] Furthermore, the step of determining defect information corresponding to the titanium alloy product to be tested based on the image information and the defect recognition model includes:
[0039] Obtaining the grayscale and gradient corresponding to each pixel in the image information;
[0040] Determining the possibility that each of the pixel points is a defect according to the grayscale and the gradient of each of the pixel points;
[0041] Determining location information of a defective area based on the possibility of the defect;
[0042] Determining an impact weight based on the location information and the likelihood of the defect;
[0043] The defect information is determined according to the influence weight and a grayscale image corresponding to the image information.
[0044] Furthermore, the step of determining a treatment solution corresponding to the titanium alloy product to be tested according to the defect degree includes:
[0045] Determining a target defect type corresponding to the titanium alloy product to be tested according to the defect degree;
[0046] When the target defect type is a surface scratch, a first processing scheme is generated, wherein the first processing scheme is to process the titanium alloy product to be tested by polishing or grinding; and / or,
[0047] When the target defect type is a surface crack, a second processing scheme is generated, wherein the second processing scheme is to process the titanium alloy product to be tested by welding or heat treatment; and / or,
[0048] When the target defect type is surface depression, a third processing scheme is generated, and the third processing scheme is to reprocess the titanium alloy product to be tested; and / or,
[0049] When the target defect type is the presence of inclusions on the surface, a fourth processing scheme is generated, and the fourth processing scheme is to cut off the inclusions from the titanium alloy product to be tested and then perform processing.
[0050] An embodiment of the present application further discloses a titanium alloy surface defect treatment system, the system comprising:
[0051] An acquisition module, used to acquire defect image data of titanium alloy products, wherein the defect image data includes images of scrap titanium alloy products, images of historical titanium alloy products and images of scrapped titanium alloy products;
[0052] A construction module, used to construct a defect recognition model based on the scrap titanium alloy product image, the historical titanium alloy product image and the scrap titanium alloy product image;
[0053] A first determination module is used to perform defect identification based on the defect identification model and the titanium alloy product to be tested to determine the defect degree corresponding to the titanium alloy product to be tested;
[0054] The second determination module is used to determine a treatment plan corresponding to the titanium alloy product to be tested according to the defect degree.
[0055] An embodiment of the present application also discloses a computer device, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the steps of the titanium alloy surface defect treatment method as described above when executed by the processor.
[0056] An embodiment of the present application further discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the titanium alloy surface defect treatment method as described above are implemented.
[0057] This application has the following advantages:
[0058] In the embodiments of the present application, compared with the prior art that "existing surface treatment technologies can often only target specific types of defects, and are not effective for multiple types of defects. Secondly, although existing image recognition technologies can realize automatic recognition of defects, their recognition accuracy and efficiency need to be improved, especially the limited recognition ability for minor defects", the present application provides a solution for "a titanium alloy surface defect treatment method", specifically: "a titanium alloy surface defect treatment method, the method comprising: obtaining defect image data of a titanium alloy product, wherein the defect image data comprises images of waste titanium alloy products, images of historical titanium alloy products, and images of scrapped titanium alloy products; constructing a defect recognition model based on the images of waste titanium alloy products, the images of historical titanium alloy products, and the images of scrapped titanium alloy products; performing defect recognition based on the defect recognition model and the titanium alloy product to be tested to determine the defect degree corresponding to the titanium alloy product to be tested; determining a treatment plan corresponding to the titanium alloy product to be tested based on the defect degree". By "defect identification based on the defect identification model and the titanium alloy product to be tested to determine the degree of defects corresponding to the titanium alloy product to be tested", the problem of "existing surface treatment technology can often only target specific types of defects, and the treatment effect on multiple types of defects is not good. Secondly, although the existing image recognition technology can realize automatic recognition of defects, its recognition accuracy and efficiency need to be improved, especially the limited recognition ability for minor defects" is solved, and the effect of "being able to handle common surface defects, such as cracks, pores, inclusions, etc., and being able to effectively handle multiple types of defects, improving the comprehensiveness of the treatment; being able to accurately identify defects on the surface of titanium alloys, not only improving the accuracy of recognition, but also improving the efficiency of recognition, especially the recognition ability for minor defects has been significantly improved; being able to determine its usability, safety and quality issues according to the degree of defects, providing a more reliable basis for practical applications, and solving the problem that defects cannot be accurately evaluated in the existing technology; by effectively treating the surface of titanium alloys, not only the surface quality of titanium alloys can be improved, but also its service life can be improved, achieving a double improvement in performance and life" is achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0059] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the description of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0060] Figure 1 This is a flow chart of the steps of a titanium alloy surface defect treatment method provided in one embodiment of the present application;
[0061] Figure 2 It is a structural block diagram of a titanium alloy surface defect treatment method system provided by an embodiment of the present application;
[0062] Figure 3 It is a structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0063] In order to make the objects, features and advantages of the present application more obvious and understandable, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.
[0064] Reference Figure 1 , showing a flow chart of steps of a titanium alloy surface defect treatment method provided by an embodiment of the present application;
[0065] A method for treating surface defects of a titanium alloy, the method comprising:
[0066] S110, acquiring defect image data of titanium alloy products, wherein the defect image data includes images of scrap titanium alloy products, images of historical titanium alloy products, and images of scrapped titanium alloy products;
[0067] S120, constructing a defect recognition model based on the scrap titanium alloy product image, the historical titanium alloy product image and the scrap titanium alloy product image;
[0068] S130, performing defect identification according to the defect identification model and the titanium alloy product to be tested to determine the defect degree corresponding to the titanium alloy product to be tested;
[0069] S140, determining a treatment plan corresponding to the titanium alloy product to be tested according to the defect degree.
[0070] In the embodiments of the present application, compared with the prior art that "existing surface treatment technologies can often only target specific types of defects, and are not effective for multiple types of defects. Secondly, although the existing image recognition technology can realize automatic recognition of defects, its recognition accuracy and efficiency need to be improved, especially the limited recognition ability for minor defects", the present application provides a solution for "a titanium alloy surface defect treatment method", specifically: "a titanium alloy surface defect treatment method, the method comprising: S110, obtaining defect image data of a titanium alloy product, wherein the defect image data comprises images of scrap titanium alloy products, images of historical titanium alloy products, and images of scrapped titanium alloy products; S120, constructing a defect recognition model based on the images of scrap titanium alloy products, the images of historical titanium alloy products, and the images of scrapped titanium alloy products; S130, performing defect recognition based on the defect recognition model and the titanium alloy product to be tested to determine the defect degree corresponding to the titanium alloy product to be tested; S140, determining a treatment plan corresponding to the titanium alloy product to be tested based on the defect degree". By "defect identification based on the defect identification model and the titanium alloy product to be tested to determine the degree of defects corresponding to the titanium alloy product to be tested", the problem of "existing surface treatment technology can often only target specific types of defects, and the treatment effect on multiple types of defects is not good. Secondly, although the existing image recognition technology can realize automatic recognition of defects, its recognition accuracy and efficiency need to be improved, especially the limited recognition ability for minor defects" is solved, and the effect of "being able to handle common surface defects, such as cracks, pores, inclusions, etc., and being able to effectively handle multiple types of defects, improving the comprehensiveness of the treatment; being able to accurately identify defects on the surface of titanium alloys, not only improving the accuracy of recognition, but also improving the efficiency of recognition, especially the recognition ability for minor defects has been significantly improved; being able to determine its usability, safety and quality issues according to the degree of defects, providing a more reliable basis for practical applications, and solving the problem that defects cannot be accurately evaluated in the existing technology; by effectively treating the surface of titanium alloys, not only the surface quality of titanium alloys can be improved, but also its service life can be improved, achieving a double improvement in performance and life" is achieved.
[0071] Next, a method for treating surface defects of a titanium alloy in this exemplary embodiment will be further described.
[0072] As described in step S110, defect image data of the titanium alloy product is acquired, wherein the defect image data includes images of waste titanium alloy products, images of historical titanium alloy products, and images of scrapped titanium alloy products.
[0073] In one embodiment of the present invention, the specific process of "obtaining defect image data of titanium alloy products, wherein the defect image data includes images of waste titanium alloy products, images of historical titanium alloy products and images of scrapped titanium alloy products" described in step S110 can be further explained in combination with the following description.
[0074] As described in the following steps,
[0075] S210, acquiring a surface image of the titanium alloy product;
[0076] S220, performing image recognition on the surface image to determine product types, wherein the product types include waste products and finished products;
[0077] S230, screening the target titanium alloy product corresponding to the product type being the waste product;
[0078] S240, obtaining a defect area of the target titanium alloy product;
[0079] S250, generating a first target surface image according to the defect area;
[0080] S260: Generate the defect image data based on the first target surface image and the second target surface image corresponding to the historical problem product.
[0081] It should be noted that waste products include scrapped products and failed products. Scrapped products are titanium alloy products that cannot be used due to quality problems, and failed products are defective products that do not meet the standards due to problems during the processing. Finished products are complete titanium alloy products that meet the quality requirements.
[0082] As an example, titanium alloy products are classified and problematic titanium alloy products are selected, and then the corresponding defective areas in the problematic titanium alloy products are determined; first surface images of the defective areas are obtained one by one, and second surface images of historical problematic products are obtained by combining historical processing or handling data, and the first surface image and the second surface image are combined to obtain defective image data.
[0083] In a specific implementation, titanium alloy products are screened, good titanium alloy products are filtered out, and scrap titanium alloy products are obtained. After unified processing based on the surface images of the scrap products, defect image data is obtained and used to construct a defect recognition model.
[0084] As described in step S240, the defect area of the target titanium alloy product is obtained.
[0085] In one embodiment of the present invention, the specific process of "obtaining the defect region of the target titanium alloy product" in step S240 may be further explained in combination with the following description.
[0086] As described in the following steps,
[0087] S3001. Collect a grayscale image of the target titanium alloy product;
[0088] S3002, performing pixel segmentation according to the grayscale image to obtain a plurality of super pixel blocks;
[0089] S3003, determining the gradient amplitude of each superpixel block corresponding to a pixel point;
[0090] S3004, determining the grayscale uniformity of each superpixel block according to the grayscale value difference and gradient amplitude difference of the pixel points in each superpixel block;
[0091] S3005, generating texture information according to the grayscale uniformity, the gradient assignment and the edge pixel points of each super pixel block;
[0092] S3006, determining gloss regularity information corresponding to each of the superpixel blocks according to the texture information;
[0093] S3007, determining the gloss dispersion corresponding to each superpixel block according to the gloss regularity information and the grayscale distribution difference between the superpixel block and other superpixel blocks;
[0094] S3008, determining the pixel grayscale value of each pixel point according to the glossiness of each superpixel block;
[0095] S3009, generating a suspected defect area according to the pixel grayscale value of each of the pixel points and the edge pixel points;
[0096] S3010, layering the suspected defect regions to generate various suspected regions;
[0097] S3011, determining the defect area according to each of the suspected areas, the target pixel points corresponding to the suspected defect area, and the local pixel points corresponding to the target pixel points.
[0098] It should be noted that grayscale images are also called grayscale images; the relationship between white and black is divided into several levels according to the logarithmic relationship, which is called grayscale. Grayscale is divided into 256 levels. An image represented by grayscale is called a grayscale image.
[0099] It should be noted that superpixels divide images into small blocks between pixels and image objects; the size of these small blocks has the following characteristics: larger than pixels: larger than a single pixel in the image, or a superpixel is composed of several pixels. Smaller than objects: smaller than the content presented in the image for specific objects; pixels in the same block have a high degree of similarity.
[0100] It should be noted that the superpixel block segmentation is obtained by a graph theory segmentation algorithm or a gradient ascent segmentation algorithm; wherein, graph theory is to define the rough center and size of the kernel starting from the pre-segmentation kernel, map the elliptical boundary in the Cartesian coordinate system to the line in the polar coordinate system, and use dynamic programming and an iterative method to ensure the best closed contour to identify the global optimal path in the constructed graph; gradient ascent is a relatively rough clustering starting calculation, and the clustering is continuously iterated and modified through gradient ascent until a specific convergence criterion is met to form a superpixel.
[0101] It should be noted that the gradient amplitude is mainly used to represent the brightness information of each pixel in the image. The image gradient describes the degree and direction of brightness change. The larger the gradient, the more drastic the brightness change, and there may be features such as edges or textures; the smaller the gradient, the gentler the brightness change, belonging to a flat area or background; the image gradient R is calculated by the first-order derivative operator; among them, the first-order derivative operator includes the Sobel operator, the Schar operator, the Reber operator and the Prewitt operator. The Sobel operator is divided into two convolution kernels in the horizontal and vertical directions, which are used to calculate the gradient of the image in the x and v directions respectively; the gradient components in the two directions are squared and then squared to get the gradient amplitude. The Rebert operator mainly calculates the gradient in the diagonal direction of the adjacent 4 fields to obtain the edge information of the image.
[0102] It should be noted that when there are no defects on the surface of the titanium alloy product, the texture distribution on the surface of the titanium alloy product is relatively regular, so that the light reflected by the surface is also reflected in a regular manner, so that the corresponding reflective area is distributed more evenly and concentrated, and the grayscale changes are also relatively similar, and the gloss of the corresponding titanium alloy product is good; when there are defects on the surface of the titanium alloy product, defective texture areas of different sizes, shapes, and distribution positions will be produced on the surface of the titanium alloy product. These defective texture areas will destroy the relatively regular normal texture distribution of the titanium alloy product surface itself, making the corresponding reflective areas more unevenly dispersed and the grayscale changes are relatively different; the texture information can be obtained by analyzing the changing trend of the texture direction corresponding to the pixel points in different areas, and the gloss regularity information can be further analyzed through the texture information; the gloss dispersion can be obtained by combining the analysis of the distribution of the corresponding reflective areas in the defective texture areas.
[0103] In a specific implementation, a grayscale image of the target titanium alloy product is collected, and the surface contour surface of the target titanium alloy product is mapped to a two-dimensional plane to obtain a grayscale image corresponding to the surface contour surface of the target alloy product; pixel segmentation is performed based on the grayscale image to obtain a number of superpixel blocks; the gradient amplitude of each superpixel block corresponding to the pixel point is determined; the grayscale uniformity of each superpixel block is determined based on the grayscale value difference and gradient amplitude difference of the pixel points in each superpixel block, by obtaining the gradient amplitude of each pixel point in the surface image of the target titanium alloy product; a first cumulative index and a second cumulative index are obtained based on the grayscale value difference and gradient amplitude difference of the pixel points in each superpixel block; the grayscale uniformity of each superpixel block is determined based on the first cumulative index and the second cumulative index; the grayscale uniformity of each superpixel block is determined based on the grayscale uniformity, the Generate texture information by assigning gradients and edge pixels; determine gloss regularity information corresponding to each of the superpixel blocks based on the texture information; determine gloss dispersion corresponding to each of the superpixel blocks based on the gloss regularity information and the difference in grayscale distribution between the superpixel block and other superpixel blocks; determine the pixel grayscale value of each pixel point based on the gloss dispersion of each superpixel block; generate suspected defect areas based on the pixel grayscale value of each pixel point and the edge pixels; layer the suspected defect areas to generate various suspected areas; determine the defect area based on each of the suspected areas, the target pixels corresponding to the suspected defect areas, and the local pixels corresponding to the target pixels; determine the accurate defect area of the titanium alloy product through multiple analyses of the surface image data, so as to facilitate the subsequent construction of a defect recognition model.
[0104] As described in step S120, a defect recognition model is constructed based on the waste titanium alloy product image, the historical titanium alloy product image and the scrapped titanium alloy product image.
[0105] In one embodiment of the present invention, the specific process of "building a defect recognition model based on the scrap titanium alloy product image, the historical titanium alloy product image and the scrapped titanium alloy product image" in step S120 can be further explained in combination with the following description.
[0106] As described in the following steps,
[0107] S410, performing convolutional neural network learning to generate a preliminary prediction model based on the scrap titanium alloy product image, the historical titanium alloy product image and the scrapped titanium alloy product image;
[0108] S420, generating a preliminary prediction result corresponding to the titanium alloy product according to the preliminary prediction model;
[0109] S430, adjusting the preliminary prediction model according to the error between the preliminary prediction result and the actual result to generate the defect recognition model.
[0110] It should be noted that convolutional neural networks are a type of feedforward neural network that includes convolution calculations and has a deep structure. They are the representative algorithm of deep learning. Convolutional neural networks have representation learning capabilities and can perform translation-invariant classification of input information according to their hierarchical structure.
[0111] As an example, the preliminary prediction model is used to predict the defect type and location of the input image; the defect recognition model adjusts the parameters on the basis of the preliminary prediction model to improve its prediction accuracy.
[0112] In a specific implementation, the preliminary prediction model is debugged by matching the error between the preliminary prediction result and the actual result until the success rate between the preliminary prediction result and the actual result is not less than 90%, and a defect recognition model is obtained after completion.
[0113] As described in step S130, defect identification is performed based on the defect identification model and the titanium alloy product to be tested to determine the defect degree corresponding to the titanium alloy product to be tested.
[0114] In one embodiment of the present invention, the specific process of "performing defect identification based on the defect identification model and the titanium alloy product to be tested to determine the defect degree corresponding to the titanium alloy product to be tested" in step S130 can be further explained in combination with the following description.
[0115] As described in the following steps,
[0116] S510, collecting image information of the titanium alloy product to be tested;
[0117] S520, determining defect information corresponding to the titanium alloy product to be tested according to the image information and the defect recognition model, wherein the defect information includes defect type, defect location, defect morphology and defect range;
[0118] S530: Generate a defect degree corresponding to the titanium alloy product to be tested according to the defect type, the defect position, the defect morphology and the defect range.
[0119] As an example, a test area is set up, and an eddy current sensing terminal and at least one image acquisition terminal are provided in the test area; when it is recognized that the titanium alloy product to be tested enters the test area, image acquisition is performed on the titanium alloy product to be tested based on the eddy current sensing terminal in combination with the image acquisition terminal to obtain a surface image of the titanium alloy product to be tested, and the obtained surface image of the titanium alloy product to be tested is used as an input of a defect recognition model to obtain defect information.
[0120] In a specific implementation, defect types include surface scratches, surface cracks, surface depressions, surface inclusions and other surface conditions; the defect location is used to indicate where the defect exists in the titanium alloy product; the defect morphology is used to indicate whether there is deformation at the defect site of the titanium alloy product; and the defect range is used to indicate the area size of the defect site of the titanium alloy product.
[0121] As described in step S520, defect information corresponding to the titanium alloy product to be tested is determined based on the image information and the defect recognition model.
[0122] In an embodiment of the present invention, the specific process of "determining the defect information corresponding to the titanium alloy product to be tested based on the image information and the defect recognition model" in step S520 can be further explained in combination with the following description.
[0123] As described in the following steps,
[0124] S610, obtaining the grayscale and gradient corresponding to each pixel in the image information;
[0125] S620, determining the possibility that each pixel is a defect according to the grayscale and the gradient of each pixel;
[0126] S630, determining the location information of the defect area according to the possibility of the defect;
[0127] S640, determining an impact weight according to the location information and the possibility of the defect;
[0128] S650: Determine the defect information according to the influence weight and a grayscale image corresponding to the image information.
[0129] As an example, the grayscale and gradient corresponding to each pixel in the image information are obtained; the possibility of each pixel being a defect is determined based on the grayscale and gradient of each pixel; the gradient of each pixel in the image information is obtained by the image gradient R calculation method; the total gradient of all pixels in the image information is determined by summing the gradients of all pixels in the image information; the first gradient direction is obtained from the total gradient, and the second gradient direction is obtained by combining the texture information; the reciprocal of the grayscale value of any pixel in the image information is marked as the first target number; the reciprocal of the minimum angle between the first gradient direction and the second gradient direction is marked as the second target number; the first target number is multiplied by the second target number to obtain a normalized value, and the normalized value is marked as the possibility of any pixel in the titanium alloy product being a defect; the position information of the defect area is determined based on the possibility of the defect; the influence weight is determined based on the position information and the possibility of the defect, wherein the influence weight is used to make the judgment of the degree of defect in the defect area more accurate; the defect information is determined based on the influence weight and the grayscale image corresponding to the image information, wherein the defect information includes defect type, defect location, defect morphology and defect range.
[0130] In a specific implementation, the defective areas are filtered, and the comprehensive defect degree of each defective area is calculated based on the shape defect degree, area defect degree and position defect degree of each defective area; if the preset comprehensive defect degree threshold is greater than the comprehensive defect degree threshold, the defective area is a defect and is recorded.
[0131] As described in step S140, a treatment solution corresponding to the titanium alloy product to be tested is determined according to the defect degree.
[0132] In one embodiment of the present invention, the specific process of "determining a treatment solution corresponding to the titanium alloy product to be tested according to the defect degree" in step S140 can be further explained in combination with the following description.
[0133] As described in the following steps,
[0134] S710, determining a target defect type corresponding to the titanium alloy product to be tested according to the defect degree;
[0135] S720, when the target defect type is a surface scratch, generating a first processing scheme, wherein the first processing scheme is to process the titanium alloy product to be tested by polishing or grinding; and / or,
[0136] S730, when the target defect type is a surface crack, a second processing scheme is generated, wherein the second processing scheme is to process the titanium alloy product to be tested by welding or heat treatment; and / or,
[0137] S740, when the target defect type is surface depression, a third processing scheme is generated, wherein the third processing scheme is to reprocess the titanium alloy product to be tested; and / or,
[0138] S750. When the target defect type is the presence of inclusions on the surface, a fourth processing scheme is generated. The fourth processing scheme is to cut off the inclusions from the titanium alloy product to be tested and then perform processing.
[0139] It should be noted that different surface treatment technologies are used for different defect types.
[0140] As an example, for surface scratches, polishing, grinding and other technologies can be used for processing. As an example, for surface cracks, welding, heat treatment and other technologies can be used for repair. As an example, for surface depressions, additional processing can be used to form new titanium alloy products, such as perforated titanium alloy products. As an example, for the presence of inclusions on the surface, a cutting tool can be used to cut off the inclusions, and then the cut parts can be reprocessed to form new titanium alloy products.
[0141] In a specific implementation, in actual application, the above steps can be appropriately modified and adjusted according to actual conditions.
[0142] Embodiment 1
[0143] Collect a large number of different types of titanium alloy surface image data, which should cover various possible defect types, such as surface scratches, surface cracks, surface depressions, etc. These image data will be used as training data for the deep learning model. To build a deep learning model, the convolutional neural network model is selected here because it has a wide range of applications and excellent performance in the field of image recognition. The input of the model is the image of the titanium alloy surface, and the output is the type and location of the defect. The training process of the model includes two stages: forward propagation and back propagation. In the forward propagation stage, the model predicts the defect type and location of the input image; in the back propagation stage, the model parameters are adjusted according to the error between the predicted result and the actual result to improve the prediction accuracy of the model. Use the trained deep learning model to identify defects on new titanium alloy surface images. The model outputs the type and location of the defect, and also evaluates the severity of the defect based on the shape, size and other characteristics of the defect. According to the degree of the defect, its usability, safety and quality issues are determined. For example, if the degree of the defect is relatively minor, it may not affect the usability and safety of the titanium alloy, but it may affect its quality; if the degree of the defect is relatively severe, it may affect the usability and safety of the titanium alloy. Different surface treatment technologies are used for different types of defects. For example, for surface scratches, polishing, grinding and other technologies can be used for treatment; for surface cracks, welding, heat treatment and other technologies can be used for repair. In practical applications, the above steps can be appropriately modified and adjusted according to actual conditions.
[0144] This application can be widely used in aerospace, automobile, medical equipment and other application fields. First, titanium alloys are widely used in the aerospace field due to their advantages such as high strength, low density, good corrosion resistance and biocompatibility, and this technical solution can effectively improve the surface quality of titanium alloys and ensure their safety and reliability in extreme environments. Secondly, the automotive industry also uses a large number of titanium alloys to reduce vehicle weight and improve fuel efficiency. This technical solution can improve the use efficiency of titanium alloys and reduce production costs. In addition, the demand for titanium alloys in the field of medical devices is also increasing, because titanium alloys have good biocompatibility and will not produce adverse reactions to the human body, and this technical solution can ensure the safety and quality of titanium alloys and meet the high standards of the medical device industry. This technical solution meets market demand and has good application prospects.
[0145] As for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0146] Reference Figure 2 , showing a structural block diagram of a titanium alloy surface defect treatment system provided by an embodiment of the present application;
[0147] A titanium alloy surface defect treatment system, the system comprising:
[0148] An acquisition module 210 is used to acquire defect image data of a titanium alloy product, wherein the defect image data includes images of scrap titanium alloy products, images of historical titanium alloy products, and images of scrapped titanium alloy products;
[0149] A construction module 220, configured to construct a defect recognition model based on the scrap titanium alloy product image, the historical titanium alloy product image, and the scrap titanium alloy product image;
[0150] A first determination module 230, configured to perform defect identification based on the defect identification model and the titanium alloy product to be tested to determine the defect degree corresponding to the titanium alloy product to be tested;
[0151] The second determination module 240 is used to determine a treatment solution corresponding to the titanium alloy product to be tested according to the defect degree.
[0152] In one embodiment of the present invention, the acquisition module 210 includes:
[0153] A first acquisition submodule is used to acquire a surface image of the titanium alloy product;
[0154] A first determination submodule is used to perform image recognition on the surface image to determine the product type, wherein the product type includes waste products and finished products;
[0155] A first screening submodule is used to screen the target titanium alloy product corresponding to the product type being the waste product;
[0156] A second acquisition submodule is used to acquire the defect area of the target titanium alloy product;
[0157] A first generating submodule, used for generating a first target surface image according to the defect area;
[0158] The second generating submodule is used to generate the defect image data based on the first target surface image and the second target surface image corresponding to the historical problem product.
[0159] In one embodiment of the present invention, the second acquisition submodule includes:
[0160] A first acquisition unit is used to acquire a grayscale image of a target titanium alloy product;
[0161] A first segmentation unit, configured to perform pixel segmentation according to the grayscale image to obtain a plurality of super pixel blocks;
[0162] A first determining unit, configured to determine a gradient magnitude of each superpixel block corresponding to a pixel point;
[0163] A second determining unit, configured to determine the grayscale uniformity of each superpixel block according to the grayscale value difference and gradient amplitude difference of the pixel points in each superpixel block;
[0164] A first generating unit, configured to generate texture information according to the grayscale uniformity, the gradient value and the edge pixel points of each super pixel block;
[0165] A third determining unit, configured to determine gloss regularity information corresponding to each of the superpixel blocks according to the texture information;
[0166] A fourth determining unit, configured to determine the glossiness corresponding to each of the superpixel blocks according to the gloss law information and the grayscale distribution difference between the superpixel block and other superpixel blocks;
[0167] A fifth determining unit, configured to determine a pixel grayscale value of each pixel point according to the glossiness of each superpixel block;
[0168] A second generating unit, configured to generate a suspected defect area according to the pixel grayscale value of each of the pixel points and the edge pixel points;
[0169] A third generating unit, used for generating various suspected regions by layering the suspected defect regions;
[0170] A sixth determining unit is used to determine the defect area according to each of the suspected areas, the target pixel points corresponding to the suspected defect area, and the local pixel points corresponding to the target pixel points.
[0171] In one embodiment of the present invention, the construction module 220 includes:
[0172] A third generation submodule is used to generate a preliminary prediction model by performing convolutional neural network learning based on the scrap titanium alloy product image, the historical titanium alloy product image and the scrapped titanium alloy product image;
[0173] A fourth generation submodule, used to generate a preliminary prediction result corresponding to the titanium alloy product according to the preliminary prediction model;
[0174] The fifth generating submodule is used to adjust the preliminary prediction model according to the error between the preliminary prediction result and the actual result to generate the defect recognition model.
[0175] In one embodiment of the present invention, the first determining module 230 includes:
[0176] A first acquisition submodule is used to acquire image information of the titanium alloy product to be tested;
[0177] A second determination submodule is used to determine defect information corresponding to the titanium alloy product to be tested according to the image information and the defect recognition model, wherein the defect information includes defect type, defect location, defect morphology and defect range;
[0178] The sixth generation submodule is used to generate a defect degree corresponding to the titanium alloy product to be tested according to the defect type, the defect position, the defect morphology and the defect range.
[0179] In one embodiment of the present invention, the second determining submodule includes:
[0180] A first acquisition unit, used to acquire the grayscale and gradient corresponding to each pixel in the image information;
[0181] A seventh determining unit, configured to determine the possibility that each pixel is a defect according to the grayscale and the gradient of each pixel;
[0182] An eighth determining unit, configured to determine location information of a defective area according to the possibility of the defect;
[0183] A ninth determining unit, configured to determine an impact weight according to the location information and the possibility of the defect;
[0184] A tenth determining unit is used to determine the defect information according to the influence weight and a grayscale image corresponding to the image information.
[0185] In one embodiment of the present invention, the second determining module 240 includes:
[0186] A third determination submodule is used to determine a target defect type corresponding to the titanium alloy product to be tested according to the defect degree;
[0187] a first processing submodule, for generating a first processing scheme when the target defect type is a surface scratch, wherein the first processing scheme is to process the titanium alloy product to be tested by polishing or grinding; and / or,
[0188] A second processing submodule is used to generate a second processing scheme when the target defect type is a surface crack, wherein the second processing scheme is to process the titanium alloy product to be tested by welding or heat treatment; and / or,
[0189] a third processing submodule, for generating a third processing scheme when the target defect type is a surface depression, wherein the third processing scheme is to reprocess the titanium alloy product to be tested; and / or,
[0190] The fourth processing submodule is used to generate a fourth processing scheme when the target defect type is the presence of inclusions on the surface. The fourth processing scheme is to cut off the inclusions from the titanium alloy product to be tested and then perform processing.
[0191] Reference Figure 3 , showing a computer device of a titanium alloy surface defect treatment method of the present invention, which may specifically include the following:
[0192] The computer device 12 is in the form of a general-purpose computing device, and the components of the computer device 12 may include but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).
[0193] The bus 18 represents one or more of several types of bus 18 structures, including a memory bus 18 or memory controller, a peripheral bus 18, an accelerated graphics port, a processor or a local bus 18 using any of a variety of bus 18 architectures. These architectures include, by way of example, but are not limited to, an Industry Standard Architecture (ISA) bus 18, a Micro Channel Architecture (MAC) bus 18, an Enhanced ISA bus 18, an Audio Video Electronics Standards Association (VESA) local bus 18, and a Peripheral Component Interconnect (PCI) bus 18.
[0194] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.
[0195] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (commonly referred to as a "hard drive"). Although Figure 3 Not shown, a disk drive for reading and writing to a removable non-volatile disk (such as a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM or other optical medium) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory may include at least one program product having a set (e.g., at least one) of program modules 42, which are configured to perform the functions of various embodiments of the present invention.
[0196] A program / utility 40 having a set (at least one) of program modules 42 may be stored in, for example, a memory, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules 42, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.
[0197] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, cameras, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., local area networks (LANs)), wide area networks (WANs), and / or public networks (e.g., the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 via the bus 18. It should be understood that although Figure 3 Not shown, other hardware and / or software modules may be used in conjunction with the computer device 12, including but not limited to: microcode, device drivers, redundant processing units 16, external disk drive arrays, RAID systems, tape drives, and data backup storage systems 34, etc.
[0198] The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28, such as implementing a titanium alloy surface defect processing method provided in an embodiment of the present invention.
[0199] That is, when the processing unit 16 executes the program, the following is achieved: S110, acquiring defect image data of titanium alloy products, wherein the defect image data includes images of scrap titanium alloy products, images of historical titanium alloy products and images of scrapped titanium alloy products; S120, constructing a defect recognition model based on the images of scrap titanium alloy products, the images of historical titanium alloy products and the images of scrapped titanium alloy products; S130, performing defect recognition based on the defect recognition model and the titanium alloy product to be tested to determine the defect degree corresponding to the titanium alloy product to be tested; S140, determining a treatment plan corresponding to the titanium alloy product to be tested based on the defect degree.
[0200] In an embodiment of the present invention, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a titanium alloy surface defect treatment method as provided in all embodiments of the present application:
[0201] That is, when the program is executed by the processor, it is implemented as follows: S110, acquiring defect image data of titanium alloy products, wherein the defect image data includes images of waste titanium alloy products, images of historical titanium alloy products and images of scrapped titanium alloy products; S120, constructing a defect recognition model based on the images of waste titanium alloy products, the images of historical titanium alloy products and the images of scrapped titanium alloy products; S130, performing defect recognition based on the defect recognition model and the titanium alloy product to be tested to determine the defect degree corresponding to the titanium alloy product to be tested; S140, determining a processing plan corresponding to the titanium alloy product to be tested based on the defect degree.
[0202] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device or device.
[0203] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0204] The computer program code for performing the operation of the present invention can be written in one or more programming languages or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other.
[0205] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.
[0206] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.
[0207] The above is a detailed introduction to a titanium alloy surface defect treatment method provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
Claims
1. A method for treating surface defects of titanium alloy, characterized in that: The method comprises: Acquire defect image data of titanium alloy products, wherein the defect image data includes images of scrap titanium alloy products, images of historical titanium alloy products, and images of scrapped titanium alloy products; Constructing a defect recognition model based on the scrap titanium alloy product image, the historical titanium alloy product image and the scrap titanium alloy product image; Determine the degree of defects corresponding to the titanium alloy product to be tested by performing defect identification based on the defect identification model and the titanium alloy product to be tested; A treatment plan corresponding to the titanium alloy product to be tested is determined according to the defect degree.
2. The method according to claim 1, characterized in that The step of obtaining defect image data of the titanium alloy product comprises: Acquiring a surface image of the titanium alloy product; Performing image recognition on the surface image to determine product types, wherein the product types include waste products and finished products; Screening a target titanium alloy product corresponding to the product type as the scrap product; Obtaining a defect area of the target titanium alloy product; generating a first target surface image according to the defect area; The defect image data is generated based on the first target surface image and the second target surface image corresponding to the historical problem product.
3. The method according to claim 2, characterized in that The step of obtaining the defect area of the target titanium alloy product comprises: Collect the grayscale image of the target titanium alloy product; Perform pixel segmentation according to the grayscale image to obtain a plurality of super pixel blocks; Determine the gradient magnitude of each superpixel block corresponding to a pixel point; Determining the grayscale uniformity of each superpixel block according to the grayscale value difference and gradient amplitude difference of the pixel points in each superpixel block; Generating texture information according to the grayscale uniformity, the gradient assignment and the edge pixel points of each super pixel block; Determining gloss regularity information corresponding to each of the superpixel blocks according to the texture information; Determine the glossiness corresponding to each superpixel block according to the gloss regularity information and the grayscale distribution difference between the superpixel block and other superpixel blocks; Determining the pixel grayscale value of each pixel point according to the glossiness of each superpixel block; Generating a suspected defect area according to the pixel grayscale value of each of the pixel points and the edge pixel points; Layering the suspected defect areas to generate various suspected areas; The defect area is determined according to each of the suspected areas, target pixels corresponding to the suspected defect areas, and local pixels corresponding to the target pixels.
4. The method according to claim 1, characterized in that The step of constructing a defect recognition model based on the scrap titanium alloy product image, the historical titanium alloy product image and the scrap titanium alloy product image comprises: Performing convolutional neural network learning to generate a preliminary prediction model based on the scrap titanium alloy product image, the historical titanium alloy product image, and the scrapped titanium alloy product image; Generating preliminary prediction results corresponding to the titanium alloy product according to the preliminary prediction model; The preliminary prediction model is adjusted according to the error between the preliminary prediction result and the actual result to generate the defect recognition model.
5. The method according to claim 1, characterized in that The step of performing defect identification based on the defect identification model and the titanium alloy product to be tested to determine the defect degree corresponding to the titanium alloy product to be tested comprises: Collecting image information of the titanium alloy product to be tested; Determining defect information corresponding to the titanium alloy product to be tested according to the image information and the defect recognition model, wherein the defect information includes defect type, defect location, defect morphology and defect range; A defect degree corresponding to the titanium alloy product to be tested is generated according to the defect type, the defect position, the defect morphology and the defect range.
6. The method according to claim 5, characterized in that The step of determining defect information corresponding to the titanium alloy product to be tested based on the image information and the defect recognition model comprises: Obtaining the grayscale and gradient corresponding to each pixel in the image information; Determining the possibility that each of the pixel points is a defect according to the grayscale and the gradient of each of the pixel points; Determining location information of a defective area based on the possibility of the defect; Determining an impact weight based on the location information and the likelihood of the defect; The defect information is determined according to the influence weight and a grayscale image corresponding to the image information.
7. The method according to claim 1, characterized in that The step of determining a treatment solution corresponding to the titanium alloy product to be tested according to the defect degree comprises: Determining a target defect type corresponding to the titanium alloy product to be tested according to the defect degree; When the target defect type is a surface scratch, a first processing scheme is generated, wherein the first processing scheme is to process the titanium alloy product to be tested by polishing or grinding; and / or, When the target defect type is a surface crack, a second processing scheme is generated, wherein the second processing scheme is to process the titanium alloy product to be tested by welding or heat treatment; and / or, When the target defect type is surface depression, a third processing scheme is generated, and the third processing scheme is to reprocess the titanium alloy product to be tested; and / or, When the target defect type is the presence of inclusions on the surface, a fourth processing scheme is generated, and the fourth processing scheme is to cut off the inclusions from the titanium alloy product to be tested and then perform processing.
8. A titanium alloy surface defect treatment system, characterized in that: The system comprises: An acquisition module, used to acquire defect image data of titanium alloy products, wherein the defect image data includes images of scrap titanium alloy products, images of historical titanium alloy products and images of scrapped titanium alloy products; A construction module, used to construct a defect recognition model based on the scrap titanium alloy product image, the historical titanium alloy product image and the scrap titanium alloy product image; A first determination module is used to perform defect identification based on the defect identification model and the titanium alloy product to be tested to determine the defect degree corresponding to the titanium alloy product to be tested; The second determination module is used to determine a treatment plan corresponding to the titanium alloy product to be tested according to the defect degree.
9. A computer device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the method according to any one of claims 1 to 7 when executed by the processor.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Steel surface defect detection method and equipment based on artificial intelligence image recognition
CN113781456A
Banknote printing quality inspection method based on deep learning algorithm
CN114445365A
Titanium plate surface defect detection method based on image processing
CN117764986A
Method and system for rapidly detecting glossiness of titanium rod
CN118115498A
Titanium alloy casting defect intelligent detection and repair method and system
CN118237842A
Cited By
Surface cleaning identification method for titanium alloy bar rolling
CN119399567A
A method for identifying surface cleanliness during rolling of titanium alloy bars
CN119399567B
