A method and device for detecting non-metallic inclusions in metal materials

Abstract

The present invention relates to a method for detecting non-metallic inclusions in metal materials based on image recognition. The method first performs a magnet adsorption operation on the metal material, obtains feature points of a motion region of the metal material image based on pixel statistics, uses motion position difference as a basic difference feature of the non-metallic inclusion, and extracts instantaneous difference features of the motion state of a material fragment based on the position difference of a difference block between two consecutive frames, thereby detecting abnormalities of the material fragment. The non-metallic inclusion detection method can not only effectively reduce the number of acquired motion feature points to avoid subsequent processing of some meaningless feature points, but also reflect the texture features of a foreground motion region to reflect the distribution of the density of the material fragment, so that the extracted motion feature points are more representative and uniform; both the response speed when detecting the occurrence of non-metallic inclusions and the description of the change in the motion state of the material fragment show outstanding superiority.

Description

Technical Field

[0001] The present application belongs to the field of metal materials, and specifically relates to a method, device and electronic equipment for detecting non-metallic inclusions in metal materials. Background Art

[0002] Non-metallic inclusions in steel (usually oxides, sulfides, nitrides and silicates, etc.) are usually generated during the deoxidation, solidification and subsequent reactions of molten steel. Non-metallic inclusions have many effects on the properties of steel, so the study of non-metallic inclusions in steel has always been an important topic in steelmaking. Using a scanning electron microscope equipped with a characteristic X-ray spectrometer and an automatic image analysis program, a comprehensive statistical analysis of the distribution, morphology, composition and size of inclusions can be performed.

[0003] Conventional non-metallic inclusions in steel are oxides, sulfides, nitrides and silicates formed by metal elements lighter than iron, such as aluminum oxide, calcium sulfide, etc. Their sources are deoxidizers, refractory materials and other micro-alloying elements. In the backscattering mode of the scanning electron microscope, these inclusions are darker than the grayscale of the iron matrix. Using the image automatic analysis program, particles can be selected by grayscale difference, that is, a threshold is set between the grayscale of the inclusions and the iron matrix, and particles with grayscale below the threshold are selected for analysis. In special cases, in order to obtain certain special properties (such as free cutting performance), it is necessary to add some elements heavier than iron to the steel. For example, inclusions formed by adding cerium, lead, bismuth, etc. have a lighter grayscale than the iron matrix. When selecting particles using the image automatic analysis program, it is necessary to set a threshold between the grayscale of the iron matrix and the grayscale of the heavy element inclusions, and select particles with grayscale above the threshold for analysis. When two types of inclusions need to be analyzed at the same time, the double threshold method is generally required. Since the grayscale of light element inclusions is the darkest, the iron matrix is ​​in the middle, and the heavy element inclusions are the lightest, two thresholds are set between the grayscale of light element inclusions and the iron matrix, and between the grayscale of iron matrix and heavy element inclusions, and particles with grayscale lower than the first threshold or higher than the second threshold are selected for analysis. In the actual operation process, the system scanned twice, selecting light element inclusions and heavy element inclusions respectively.

[0004] The identification of non-metallic inclusions can generally be processed by magnet adsorption operation. However, due to the close binding of atoms inside the microscopic structure, the purity of the metal material cannot be accurately determined by naked eye observation after macroscopic magnet treatment. Therefore, a method that can accurately detect non-metallic inclusions in metal materials is urgently needed. Summary of the invention

[0005] In view of this, the present application aims to propose a method, device and electronic equipment for detecting non-metallic inclusions in metal materials.

[0006] In the first aspect, the embodiment of the present application provides a method for detecting non-metallic inclusions in a metal material, wherein the non-metallic inclusions are composed of multi-order atomic copolymers, and the method comprises:

[0007] Obtaining the property values ​​of non-metallic inclusions, cleaning and configuring the property values, and obtaining the property values ​​after cleaning;

[0008] The metal material is constructed in a world space coordinate system for magnet adsorption operation, and a random exhaustive algorithm is used in the world space coordinate system to obtain the initial coordinate value and the initial target coordinate value of the initial atomic copolymer of the non-metallic inclusion;

[0009] The primary coordinate value and the primary target coordinate value are bridged to obtain the primary atomic copolymer of the non-metallic inclusion;

[0010] According to the initial atomic copolymer, the initial current non-metallic inclusion density of the non-metallic inclusion is obtained;

[0011] The initial current non-metallic inclusion density is matched with the attribute value after cleaning, and the non-metallic inclusions are detected based on the matching result.

[0012] In a possible implementation of the above first aspect, the method further includes:

[0013] The property values ​​at least include the length and width of each atomic copolymer, the size of the density of non-metallic inclusions, the discrete atomic diameter and the order of the discrete atoms of non-metallic inclusions;

[0014] Perform cleansing configuration on the attribute value to obtain the cleansed attribute value, including:

[0015] According to the specific requirements of the detection, the length, width, size of non-metallic inclusion density, discrete atom diameter and order of discrete atoms of non-metallic inclusions of each order of atomic copolymers are configured with preset values, and the cleaned attribute values ​​of the length, width, size of non-metallic inclusion density, discrete atom diameter and order of discrete atoms of non-metallic inclusions of each order of atomic copolymers are obtained;

[0016] After obtaining the cleaned attribute value, it also includes:

[0017] Store the cleaned attribute values ​​into the preset linked list.

[0018] In a possible implementation of the above first aspect, the method further includes:

[0019] The initial coordinate values ​​and initial target coordinate values ​​of the initial atomic copolymer of the non-metallic inclusions are obtained, specifically including:

[0020] The initial coordinate values ​​and the initial target coordinate values ​​of the initial atomic copolymer of the non-metallic inclusions are generated by using a random exhaustive algorithm;

[0021] The coordinates of the initial coordinate value and the initial target coordinate value are (x 1 ,y 1 ,z 1 ) and (x 2 ,y 2 ,z 2 );

[0022] The coordinates of the initial coordinate value and the initial target coordinate value are related to the post-cleaning attribute value.

[0023] In a possible implementation of the above first aspect, the method further includes:

[0024] Obtain the initial discrete atoms of non-metallic inclusions, including:

[0025] Preset the mapping size range of non-metallic inclusions in the world space coordinate system;

[0026] The mapping size range is set according to the length and width of the atomic copolymer;

[0027] The initial coordinate value and the initial target coordinate value are bridged to obtain the initial candidate atomic copolymer;

[0028] The parts of the primary candidate atomic copolymers that exceed the mapping size range are removed to obtain the primary atomic copolymers;

[0029] According to the discrete atomic diameter of the atomic copolymer, the primary atomic copolymer is scattered and expanded to obtain the primary discrete atoms of the non-metallic inclusions.

[0030] In a possible implementation of the above first aspect, the method further includes:

[0031] According to the initial atomic copolymer, the initial current non-metallic inclusion density of the non-metallic inclusion is obtained, which specifically includes:

[0032] According to the initial discrete atoms, the current total length of the discrete atoms of the initial atomic copolymer is obtained;

[0033] According to the current total length of discrete atoms of the primary atomic copolymer, the current total volume of the primary atomic copolymer is obtained;

[0034] According to the current total volume of the primary atomic copolymer, the primary current non-metallic inclusion density of the primary atomic copolymer is obtained.

[0035] In a possible implementation of the above first aspect, the method further includes:

[0036] The initial current non-metallic inclusion density is matched by the attribute value after cleaning, and the non-metallic inclusions are tested according to the matching results, including:

[0037] Matching the initial current non-metallic inclusion density with the size of the non-metallic inclusion density of the atomic copolymer required for the specific detection;

[0038] When the matching result indicates that the two are matched, the system automatically jumps to the primary target atomic copolymer of the non-metallic inclusion for detection, constructs the metal material in the world space coordinate system for magnet adsorption operation, and uses a random exhaustive algorithm in the world space coordinate system to obtain the coordinate value of the primary target atomic copolymer of the non-metallic inclusion;

[0039] When the matching result indicates that the two do not match, the metal material is constructed in a world space coordinate system for magnet adsorption operation, and a random exhaustive algorithm is used in the world space coordinate system to obtain a secondary coordinate value and a secondary target coordinate value of the primary atomic copolymer of the non-metallic inclusion;

[0040] The secondary coordinate value and the secondary target coordinate value are bridged to obtain the primary target discrete atoms of the non-metallic inclusions;

[0041] According to the initial target discrete atoms, the initial current non-metallic inclusion density is updated to obtain the initial target current non-metallic inclusion density of the non-metallic inclusions;

[0042] Matching the current non-metallic inclusion density of the initial target with the non-metallic inclusion density of the atomic copolymer required for the specific detection, if the matching result shows that the two do not match, re-constructing the metal material in the world space coordinate system based on the obtained discrete atoms to perform a magnet adsorption operation, using a random exhaustive algorithm in the world space coordinate system to obtain the coordinate value of the atomic copolymer of the non-metallic inclusion and update the current non-metallic inclusion density until the updated current non-metallic inclusion density matches the non-metallic inclusion density of the atomic copolymer required for the specific detection;

[0043] After each atomic copolymer of non-metallic inclusions is detected, if the current non-metallic inclusion density of each atomic copolymer matches the size of the non-metallic inclusion density of each atomic copolymer required for the specific detection, the detection of non-metallic inclusions is completed.

[0044] In terms of the primary objective, the embodiment of the present application provides a detection device for non-metallic inclusions in a metal material, wherein the non-metallic inclusions are composed of multi-order atomic copolymers, and the device comprises:

[0045] A cleaning module obtains the property values ​​of non-metallic inclusions, performs cleaning configuration on the property values, and obtains the property values ​​after cleaning;

[0046] A data point acquisition module is used to construct the metal material in a world space coordinate system to perform a magnet adsorption operation, and to use a random exhaustive algorithm in the world space coordinate system to obtain a primary coordinate value and a primary target coordinate value of a primary atomic copolymer of non-metallic inclusions;

[0047] The expansion module bridges the initial coordinate value and the initial target coordinate value to obtain the initial atomic copolymer of the non-metallic inclusion;

[0048] The first-order analysis module obtains the first current non-metallic inclusion density of non-metallic inclusions based on the first atomic copolymer;

[0049] The detection module matches the initial current non-metallic inclusion density through the attribute value after cleaning, and detects the non-metallic inclusions based on the matching result.

[0050] In one possible implementation of the above primary objective, the method further includes:

[0051] The property values ​​at least include the length and width of each atomic copolymer, the size of the density of non-metallic inclusions, the discrete atomic diameter and the order of the discrete atoms of non-metallic inclusions;

[0052] Perform cleansing configuration on the attribute value to obtain the cleansed attribute value, including:

[0053] According to the specific requirements of the detection, the length, width, size of non-metallic inclusion density, discrete atom diameter and order of discrete atoms of non-metallic inclusions of each order of atomic copolymers are configured with preset values, and the cleaned attribute values ​​of the length, width, size of non-metallic inclusion density, discrete atom diameter and order of discrete atoms of non-metallic inclusions of each order of atomic copolymers are obtained;

[0054] After obtaining the cleaned attribute value, it also includes:

[0055] Store the cleaned attribute values ​​into the preset linked list;

[0056] Data point acquisition module, specifically including:

[0057] The initial coordinate values ​​and the initial target coordinate values ​​of the initial atomic copolymer of the non-metallic inclusions are generated by using a random exhaustive algorithm;

[0058] The coordinates of the initial coordinate value and the initial target coordinate value are (x 1 ,y 1 ,z 1 ) and (x 2 ,y2 ,z 2 );

[0059] The coordinates of the initial coordinate value and the initial target coordinate value are related to the post-cleaning attribute value.

[0060] In one possible implementation of the above primary objective, the method further includes:

[0061] Extension modules include:

[0062] Preset the mapping size range of non-metallic inclusions in the world space coordinate system;

[0063] The mapping size range is set according to the length and width of the atomic copolymer;

[0064] The initial coordinate value and the initial target coordinate value are bridged to obtain the initial candidate atomic copolymer;

[0065] The parts of the primary candidate atomic copolymers that exceed the mapping size range are removed to obtain the primary atomic copolymers;

[0066] According to the discrete atomic diameter of the atomic copolymer, the primary atomic copolymer is scattered and expanded to obtain the primary discrete atoms of the non-metallic inclusions;

[0067] The first-order analysis module includes:

[0068] According to the initial discrete atoms, the current total length of the discrete atoms of the initial atomic copolymer is obtained;

[0069] According to the current total length of discrete atoms of the primary atomic copolymer, the current total volume of the primary atomic copolymer is obtained;

[0070] According to the current total volume of the primary atomic copolymer, the primary current non-metallic inclusion density of the primary atomic copolymer is obtained;

[0071] Detection module, including:

[0072] Matching the initial current non-metallic inclusion density with the size of the non-metallic inclusion density of the atomic copolymer required for the specific detection;

[0073] When the matching result indicates that the two are matched, the system automatically jumps to the primary target atomic copolymer of the non-metallic inclusion for detection, constructs the metal material in the world space coordinate system for magnet adsorption operation, and uses a random exhaustive algorithm in the world space coordinate system to obtain the coordinate value of the primary target atomic copolymer of the non-metallic inclusion;

[0074] When the matching result indicates that the two do not match, the metal material is constructed in a world space coordinate system for magnet adsorption operation, and a random exhaustive algorithm is used in the world space coordinate system to obtain a secondary coordinate value and a secondary target coordinate value of the primary atomic copolymer of the non-metallic inclusion;

[0075] The secondary coordinate value and the secondary target coordinate value are bridged to obtain the primary target discrete atoms of the non-metallic inclusions;

[0076] According to the initial target discrete atoms, the initial current non-metallic inclusion density is updated to obtain the initial target current non-metallic inclusion density of the non-metallic inclusions;

[0077] Matching the current non-metallic inclusion density of the initial target with the non-metallic inclusion density of the atomic copolymer required for the specific detection, if the matching result shows that the two do not match, re-constructing the metal material in the world space coordinate system based on the obtained discrete atoms to perform a magnet adsorption operation, using a random exhaustive algorithm in the world space coordinate system to obtain the coordinate value of the atomic copolymer of the non-metallic inclusion and update the current non-metallic inclusion density until the updated current non-metallic inclusion density matches the non-metallic inclusion density of the atomic copolymer required for the specific detection;

[0078] After each atomic copolymer of non-metallic inclusions is detected, if the current non-metallic inclusion density of each atomic copolymer matches the size of the non-metallic inclusion density of each atomic copolymer required for the specific detection, the detection of non-metallic inclusions is completed.

[0079] In a secondary aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor, wherein the memory is set to store a computer executable program, and the processor reads part or all of the computer executable program from the memory and executes it. When the processor executes part or all of the computer executable program, a method for detecting non-metallic inclusions in a metal material of the present application can be implemented.

[0080] The present invention relates to a method for detecting non-metallic inclusions in metal materials based on image recognition. The method first performs a magnet adsorption operation on the metal material, obtains feature points of a motion region of the metal material image based on pixel statistics, uses motion position difference as a basic difference feature of the non-metallic inclusion, and extracts instantaneous difference features of the motion state of a material fragment based on the position difference of a difference block between two consecutive frames, thereby detecting abnormalities of the material fragment. The non-metallic inclusion detection method can not only effectively reduce the number of acquired motion feature points to avoid subsequent processing of some meaningless feature points, but also reflect the texture features of a foreground motion region to reflect the distribution of the density of the material fragment, so that the extracted motion feature points are more representative and uniform; both the response speed when detecting the occurrence of non-metallic inclusions and the description of the change in the motion state of the material fragment show outstanding superiority. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 It is a workflow diagram of a method for detecting non-metallic inclusions in a metal material according to an embodiment of the present application;

[0082] Figure 2 This is a workflow diagram of Example 1 of a method for detecting non-metallic inclusions in a metal material according to an embodiment of the present application;

[0083] Figure 3 This is a work flow chart of Example 2 of a method for detecting non-metallic inclusions in a metal material according to an embodiment of the present application;

[0084] Figure 4 This is a workflow diagram of Example 3 of a method for detecting non-metallic inclusions in a metal material according to an embodiment of the present application;

[0085] Figure 5 This is a work flow chart of a fourth embodiment of a method for detecting non-metallic inclusions in a metal material according to an embodiment of the present application;

[0086] Figure 6 It is a structural module diagram of a device for detecting non-metallic inclusions in a metal material according to an embodiment of the present application. DETAILED DESCRIPTION

[0087] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. It will be understood that the terms "for the first time", "initial target", etc. used in this application may be used in this text to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish one element from another element for the first time. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure, and to be able to fully convey the scope of the present disclosure to those skilled in the art.

[0088] Some existing detection methods mainly include the use of simulation methods to optimize the design of non-metallic inclusion structures and the exploration of transport characteristics, which require the detection and reproduction of their three-dimensional porous structures. The first method is to use X-CT technology (X-ray computed tomography), which can penetrate non-transparent entities to obtain their internal structural characteristics. The first target method is a random detection method. Its principle is to use known parameter characteristics (such as discrete atomic diameters) combined with the statistical characteristics of target parameters (such as non-metallic inclusion density, thickness, etc.) to generate metal atomic structures through random detection methods. In this process, all key parameters can be adjusted according to target requirements.

[0089] However, since the characteristics of non-metallic inclusions in different directions are anisotropic, the characteristics of the geometric model obtained by X-CT technology are also limited by the characteristics of the sample. At the same time, due to the time and economic cost of X-CT, the use of X-CT method to explore the influence of key parameters on the performance of non-metallic inclusions is not ideal, which requires a large number of sample models to be converted. At the same time, the problem with existing random detection methods is that most of them rely on computational grids for generation and feedback control, which reduces the applicability of the method. In addition, some methods use step-by-step generation, and then manually stack according to the density of each order of non-metallic inclusions, resulting in a cumbersome detection process and non-integrated control.

[0090] The non-metallic inclusion detection scheme of the present application has better overcome the various defects of the existing detection schemes. The embodiments of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0091] Refer to the attached Figure 1 The first embodiment of the present application provides a method for detecting non-metallic inclusions in a metal material, wherein the non-metallic inclusions are composed of multi-order atomic copolymers, and comprises the following steps:

[0092] Step 1: Obtain the attribute values ​​of non-metallic inclusions, clean and configure the attribute values, and obtain the attribute values ​​after cleaning;

[0093] Step 2: construct the metal material in a world space coordinate system to perform a magnet adsorption operation, and use a random exhaustive algorithm in the world space coordinate system to obtain the initial coordinate value and the initial target coordinate value of the initial atomic copolymer of the non-metallic inclusion;

[0094] Step 3: bridge the initial coordinate value and the initial target coordinate value to obtain the initial atomic copolymer of the non-metallic inclusion;

[0095] Step 4: According to the initial atomic copolymer, the initial current non-metallic inclusion density of the non-metallic inclusion is obtained;

[0096] Step 5: Match the initial current non-metallic inclusion density with the attribute value after cleaning, and detect the non-metallic inclusions based on the matching result.

[0097] Carbon paper-type non-metallic inclusions are formed by the interlacing of randomly distributed discrete atoms.

[0098] For details, please refer to the attached Figure 2 , in step 1:

[0099] The property values ​​at least include the length and width of each atomic copolymer, the size of the density of non-metallic inclusions, the discrete atomic diameter and the order of the discrete atoms of non-metallic inclusions;

[0100] Perform cleansing configuration on the attribute value to obtain the cleansed attribute value, including:

[0101] According to the specific requirements of the detection, the length, width, size of non-metallic inclusion density, discrete atom diameter and order of discrete atoms of non-metallic inclusions of each order of atomic copolymers are configured with preset values, and the cleaned attribute values ​​of the length, width, size of non-metallic inclusion density, discrete atom diameter and order of discrete atoms of non-metallic inclusions of each order of atomic copolymers are obtained;

[0102] After obtaining the cleaned attribute value, it also includes:

[0103] Store the cleaned attribute values ​​into the preset linked list.

[0104] In this embodiment, the size of the non-metallic inclusion density of each order of atomic copolymers is stored in the linked list Porous[] in order; the size of the discrete atomic diameter of each order of atomic copolymers is stored in the linked list D[].

[0105] First, the number of atomic copolymers of non-metallic inclusions in the metal material used in this embodiment is 24 orders, and the discrete atomic diameters of each order of atomic copolymers are the same, all 8 μm. The detection size is selected as 800 μm×800 μm, that is, L=800 μm, W=800 μm.

[0106] Secondly, the distribution of the density of non-metallic inclusions of each atomic copolymer is set according to the density of non-metallic inclusions obtained by X-ray technology in the comparison result diagram of non-metallic inclusions and X-ray technology. That is, the chain list D

[24] of discrete atomic diameters of each order = {8,8,8,8…8,8}; the chain list Porous

[24] representing the size of the density of non-metallic inclusions of each atomic copolymer is = {0.94,0.81,0.64,0.59,0.61,0.69,0.75,0.75,0.77, 0.82,0.84,0.81,0.82,0.80,0.75,0.74,0.73,0.65,0.57,0.56,0.66,0.79,0.94,0.96}.

[0107] Specific, reference Figure 3 , in step 2:

[0108] The initial coordinate values ​​and the initial target coordinate values ​​of the initial atomic copolymer of the non-metallic inclusions are generated by using a random exhaustive algorithm;

[0109] The coordinates of the initial coordinate value and the initial target coordinate value are (x 1 ,y 1 ,z 1 ) and (x 2 ,y 2 ,z 2 );

[0110] The coordinates of the initial coordinate value and the initial target coordinate value are related to the post-cleaning attribute value.

[0111] Among them, the two initial coordinate values ​​(x 1 ,y 1 ,z 1 ), initial target coordinate value (x 2 ,y 2 ,z 2 ). The expression is as follows:

[0112] x 1 =L·Rand_x+(L+W) (1-1)

[0113] x 2 =L·Rand_x-(L+W) (1-2)

[0114]

[0115]

[0116] z 1=(L+W)tan(π·Rand_θ)+W·Rand_z (1-5)

[0117] z 2 =-(L+W)tan(π·Rand_θ)+W·Rand_z (1-6)

[0118] Among them, Rand_x and Rand_z represent the values ​​generated by the random function for calculating the coordinates, Rand_θ represents the value generated by the random function for calculating the radian (need to be limited to the domain of the function), and i represents the order of the discrete atom.

[0119] In this solution, a random exhaustive algorithm is used to generate two coordinate values ​​and radians. At this time, the value generated by the random function is a value between 0 and 1.

[0120] At the same time, when using a random function to generate coordinate values, you need to add a time seed to ensure that the random number generated is different each time, otherwise the coordinate value generated by the random function will remain unchanged each time.

[0121] According to formulas (1-1) to (1-6), two random coordinate values ​​generated by combining radians can be obtained.

[0122] In this scheme, the coordinate value is generated by a random exhaustive algorithm to ensure the adaptability of atomic copolymers, so that the detection of atomic copolymers can be adaptively adjusted according to the diverse needs of non-metallic inclusions, and a time seed is added to ensure that the random number generated each time is different, further improving the reliability of the basic data of discrete atom detection.

[0123] Specifically, refer to Figure 4 , in step 3:

[0124] Preset the mapping size range of non-metallic inclusions in the world space coordinate system;

[0125] The mapping size range is set according to the length and width of the atomic copolymer;

[0126] The initial coordinate value and the initial target coordinate value are bridged to obtain the initial candidate atomic copolymer;

[0127] The parts of the primary candidate atomic copolymers that exceed the mapping size range are removed to obtain the primary atomic copolymers;

[0128] According to the discrete atomic diameter of the atomic copolymer, the primary atomic copolymer is scattered and expanded to obtain the primary discrete atoms of the non-metallic inclusions.

[0129] The normal mapping size of the non-metallic inclusions ranges from (0,0) to (L,W).

[0130] In this embodiment, the order of generating discrete atoms is from the bottom to the top step by step along the thickness direction (0μm~192μm). Combined with the mapping range (0,0)~(800,800), the coordinate range of the overall atomic copolymer is (0,0,0)μm~(800,800,192)μm. Therefore, the generated discrete atoms are only retained within this range, and the rest are discarded.

[0131] In this embodiment, the generated initial coordinate value and the initial target coordinate value are bridged, and the part exceeding the length and width of the non-metallic inclusion is discarded, and the corresponding value in the linked list D

[24] where the discrete atomic diameter of this order is located is read, and a discrete atom is generated based on the discrete atomic diameter scattering expansion of the atomic copolymer.

[0132] In this scheme, the effective length of discrete atoms is extracted to ensure the accuracy of discrete atom extraction data for detecting non-metallic inclusions, and the atomic copolymers are scattered and expanded based on the discrete atomic diameters of the atomic copolymers to obtain discrete atoms of this order, thereby enhancing the matching of detection with product requirements.

[0133] Specifically, refer to Figure 5 , in step 4:

[0134] According to the initial discrete atoms, the current total length of the discrete atoms of the initial atomic copolymer is obtained;

[0135] According to the current total length of discrete atoms of the primary atomic copolymer, the current total volume of the primary atomic copolymer is obtained;

[0136] According to the current total volume of the primary atomic copolymer, the primary current non-metallic inclusion density of the primary atomic copolymer is obtained.

[0137] As the number of discrete atoms increases, the current non-metallic inclusion density of the order is calculated synchronously and compared with the target non-metallic inclusion density.

[0138] The current calculation method for the density of non-metallic inclusions is to remove the volume of discrete atoms and divide it by the total volume of the order. The expression is as follows:

[0139] Get the length L of the first discrete atom of each discrete atom f :

[0140] According to the current determination of the density of discrete atomic non-metallic inclusions, the total length L of the discrete atoms of this order is obtained by summing up fs ; Then the current total volume V of the discrete atoms of this order f It can be calculated by the following expression:

[0141]

[0142] Then the current non-metallic inclusion density ε of this order can be obtained by the following expression:

[0143]

[0144]

[0145] In this embodiment, the length of the initial discrete atoms is calculated according to the method shown in formula (3-3), and the current non-metallic inclusion density is calculated according to formulas (3-1) and (3-2).

[0146] This scheme adds up the current judgment of the density of discrete atomic non-metallic inclusions to obtain the current total length of the discrete atoms of this order. It takes into account the specific spatial placement forms of various discrete atoms in the atomic copolymer of this order, and performs multi-scenario configuration according to the discrete atomic coordinate values ​​to obtain the corresponding length, thereby ensuring the accuracy of the discrete atomic length, volume, and non-metallic inclusion density results to the greatest extent, and ensuring that the deviation of the subsequent detection model is minimized.

[0147] Specifically, in step 5:

[0148] Matching the initial current non-metallic inclusion density with the size of the non-metallic inclusion density of the atomic copolymer required for the specific detection;

[0149] When the matching result indicates that the two are matched, the system automatically jumps to the primary target atomic copolymer of the non-metallic inclusion for detection, constructs the metal material in the world space coordinate system for magnet adsorption operation, and uses a random exhaustive algorithm in the world space coordinate system to obtain the coordinate value of the primary target atomic copolymer of the non-metallic inclusion;

[0150] When the matching result indicates that the two do not match, the metal material is constructed in a world space coordinate system for magnet adsorption operation, and a random exhaustive algorithm is used in the world space coordinate system to obtain a secondary coordinate value and a secondary target coordinate value of the primary atomic copolymer of the non-metallic inclusion;

[0151] The secondary coordinate value and the secondary target coordinate value are bridged to obtain the primary target discrete atoms of the non-metallic inclusions;

[0152] According to the initial target discrete atoms, the initial current non-metallic inclusion density is updated to obtain the initial target current non-metallic inclusion density of the non-metallic inclusions;

[0153] Matching the current non-metallic inclusion density of the initial target with the non-metallic inclusion density of the atomic copolymer required for the specific detection, if the matching result shows that the two do not match, re-constructing the metal material in the world space coordinate system based on the obtained discrete atoms to perform a magnet adsorption operation, using a random exhaustive algorithm in the world space coordinate system to obtain the coordinate value of the atomic copolymer of the non-metallic inclusion and update the current non-metallic inclusion density until the updated current non-metallic inclusion density matches the non-metallic inclusion density of the atomic copolymer required for the specific detection;

[0154] After each atomic copolymer of non-metallic inclusions is detected, if the current non-metallic inclusion density of each atomic copolymer matches the size of the non-metallic inclusion density of each atomic copolymer required for the specific detection, the detection of non-metallic inclusions is completed.

[0155] Among them, the current atomic copolymer non-metallic inclusion density ε is compared with the target non-metallic inclusion density Porous[i] of this order. When the target non-metallic inclusion density of this order is reached, a logical judgment program is used to jump to the next order for generation, and the target non-metallic inclusion density Porous[i] and discrete atomic diameter D[i] of this order are called for control.

[0156] In this embodiment, the current non-metallic inclusion density is compared with the size in the non-metallic inclusion density linked list Porous

[24] . When it is less than the target non-metallic inclusion density, a discrete atom is generated until it is satisfied. Then, the next step is repeated to construct the metal material in the world space coordinate system for magnet adsorption operation. A random exhaustive algorithm is used in the world space coordinate system to obtain the coordinate value of the next-order atomic copolymer of the non-metallic inclusion until all atomic copolymers are completed.

[0157] This scheme improves the shortcomings of the existing technology of manual step-by-step generation and superposition, and adopts a scheme for automatic matching of non-metallic inclusion density. It has the advantages of automatic process cycle control and integrated detection. In addition, the detection method of this scheme has strong universality and does not rely on numerical calculation grid generation. It can be widely used in the performance evaluation and optimization of non-metallic inclusions.

[0158] According to the difference in the density of non-metallic inclusions, the number of discrete atoms in each order is also different. The comparison of the density of non-metallic inclusions obtained by the method of the present invention and the X-ray technology shows a high degree of agreement, reflecting the reliability of the method of the present invention. In this embodiment, the thickness of each atomic copolymer is normalized from bottom to top, with the value of the bottom being 0 and the value of the top being 1.

[0159] Furthermore, the detection method of non-metallic inclusions in metal materials of the present invention can also be applied to the detection of non-metallic inclusions with various types of non-metallic inclusion density distributions, such as a stepped non-metallic inclusion density structure. This structure represents a development direction of non-metallic inclusion optimization design.

[0160] This embodiment provides the detection results of several types of non-metallic inclusions with uniform and linear distribution of non-metallic inclusion density under the same discrete atomic diameter.

[0161] At this time, the diameter of discrete atoms of each atomic copolymer is 8 μm, the size is L = 200 μm, W = 200 μm, the order of discrete atoms of non-metallic inclusions is 24, and the coordinate range of the overall atomic copolymer is (0,0,0) ~ (200,200,192). The density of non-metallic inclusions of the three non-metallic inclusions from the bottom to the top is kept constant at 0.7, linearly increased, and linearly decreased, which is reflected in the control chain table as follows: Porous

[24] = {0.7,0.7,0.7...0.7,0.7}; Porous

[24] = {0.5,0.517,0.535,0.552,0.57,0.587,0.604,0.622,0.639,0.657,0.674,0.691, 0.709,0.726,0.743,0.761,0.778,0.796,0.813,0.83,0.848,0.865,0.883,0.9} ;Porous

[24] ={0.9,0.883,0.865,0.848,0.83,0.813,0.796,0.778,0.761,0.743, 0.726,0.709,0.691,0.674,0.657,0.639,0.622,0.604,0.587,0.57,0.552,0.535, 0.517,0.5}.

[0162] See attached Figure 6 , a structural module diagram of a detection device for non-metallic inclusions in a metal material for which protection is sought by the present invention, wherein the non-metallic inclusions are composed of multi-order atomic copolymers, and wherein the device comprises:

[0163] A cleaning module obtains the property values ​​of non-metallic inclusions, performs cleaning configuration on the property values, and obtains the property values ​​after cleaning;

[0164] A data point acquisition module is used to construct the metal material in a world space coordinate system to perform a magnet adsorption operation, and to use a random exhaustive algorithm in the world space coordinate system to obtain a primary coordinate value and a primary target coordinate value of a primary atomic copolymer of non-metallic inclusions;

[0165] The expansion module bridges the initial coordinate value and the initial target coordinate value to obtain the initial atomic copolymer of the non-metallic inclusion;

[0166] The first-order analysis module obtains the first current non-metallic inclusion density of non-metallic inclusions based on the first atomic copolymer;

[0167] The detection module matches the initial current non-metallic inclusion density through the attribute value after cleaning, and detects the non-metallic inclusions based on the matching result.

[0168] Flowcharts are used in this disclosure to illustrate the steps of the method according to the embodiments of the present disclosure. It should be understood that the previous or subsequent steps are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously. At the same time, other operations can also be added to these processes.

[0169] Those skilled in the art will appreciate that the contents disclosed in this disclosure may be subject to various modifications and improvements. For example, the various devices or components described above may be implemented by hardware, or by software, firmware, or a combination of some or all of the three.

[0170] Those skilled in the art will appreciate that all or part of the steps in the above method can be completed by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits. Accordingly, each module / unit in the above embodiment can be implemented in the form of hardware or in the form of a software functional module. The present disclosure is not limited to any particular form of combination of hardware and software.

[0171] Unless otherwise defined, all terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present disclosure belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having meanings that match their meanings in the context of the relevant technology, and should not be interpreted in an idealized or highly formal sense, unless explicitly defined as such herein.

[0172] The above is an explanation of the present disclosure and should not be considered as a limitation thereof. Although several exemplary embodiments of the present disclosure are described, it will be readily understood by those skilled in the art that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present disclosure. Therefore, all such modifications are intended to be included within the scope of the present disclosure as defined in the claims. It should be understood that the above is an explanation of the present disclosure and should not be considered to be limited to the specific embodiments disclosed, and modifications to the disclosed embodiments and other embodiments are intended to be included within the scope of the appended claims. The present disclosure is defined by the claims and their equivalents.

[0173] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0174] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

Claims

1. A method for detecting non-metallic inclusions in a metal material, wherein the non-metallic inclusions are composed of multi-order atomic copolymers, characterized in that: The method comprises: Acquire the property value of the non-metallic inclusion, and perform cleaning configuration on the property value to obtain the property value after cleaning; The metal material is constructed in a world space coordinate system to perform a magnet adsorption operation, and a random exhaustive algorithm is used in the world space coordinate system to obtain the initial coordinate values ​​and the initial target coordinate values ​​of the initial discrete atoms of the non-metallic inclusions; The primary coordinate value and the primary target coordinate value are bridged to obtain the primary atomic copolymer of the non-metallic inclusion; According to the primary atomic copolymer, obtaining the primary current non-metallic inclusion density of the non-metallic inclusion; Matching the initial current non-metallic inclusion density with the post-cleaning attribute value, and detecting the non-metallic inclusion according to the matching result; The property values ​​at least include the length, width, density of non-metallic inclusions, discrete atomic diameter and order of discrete atoms of the non-metallic inclusions of each order of the atomic copolymer; The step of cleaning the attribute value to obtain the cleaned attribute value includes: According to the specific requirements of the detection, the length, width, size of non-metallic inclusion density, discrete atomic diameter and order of discrete atoms of the non-metallic inclusions of each order of the atomic copolymer are configured with preset values, and the cleaned attribute values ​​of the length, width, size of non-metallic inclusion density, discrete atomic diameter and order of discrete atoms of the non-metallic inclusions of each order of the atomic copolymer are obtained; After obtaining the cleaned attribute value, the method further includes: Storing the cleaned attribute values ​​in a preset linked list; The obtaining of the initial coordinate values ​​and the initial target coordinate values ​​of the initial discrete atoms of the non-metallic inclusions specifically includes: Generate the initial coordinate values ​​and initial target coordinate values ​​of the initial discrete atoms of the non-metallic inclusions by using a random exhaustive algorithm; The coordinates of the initial coordinate value and the initial target coordinate value are (x1, y1, z1) and (x2, y2, z2) respectively; The coordinates of the initial coordinate value and the initial target coordinate value are related to the post-cleaning property value.

2. The method for detecting non-metallic inclusions in a metal material according to claim 1, characterized in that: The method of obtaining the primary atomic copolymer of the non-metallic inclusions specifically comprises: Presetting a mapping size range of the non-metallic inclusions in the world space coordinate system; The mapping size range is set according to the length and width of the atomic copolymer; the initial coordinate value and the initial target coordinate value are bridged to obtain a primary candidate atomic copolymer; removing the portion of the primary candidate atomic copolymer that exceeds the mapping size range to obtain a primary atomic copolymer; According to the discrete atomic diameter of the atomic copolymer of this order, the primary atomic copolymer is scattered and expanded to obtain the primary atomic copolymer set of the non-metallic inclusions.

3. The method for detecting non-metallic inclusions in a metal material according to claim 1, characterized in that: The step of obtaining the initial current non-metallic inclusion density of the non-metallic inclusion according to the initial atomic copolymer specifically comprises: According to the initial discrete atoms, a current total length of discrete atoms of the initial atomic copolymer is obtained; Obtaining a current total volume of the primary atomic copolymer according to a current total length of discrete atoms of the primary atomic copolymer; According to the current total volume of the primary atomic copolymer, the primary current non-metallic inclusion density of the primary atomic copolymer is obtained.

4. The method for detecting non-metallic inclusions in a metal material according to claim 1, characterized in that: The matching of the initial current non-metallic inclusion density with the post-cleaning attribute value and detecting the non-metallic inclusions according to the matching result specifically includes: Matching the initial current non-metallic inclusion density with the non-metallic inclusion density of the atomic copolymer required for the specific detection; When the matching result indicates that the two are matched, the method automatically jumps to the primary target atomic copolymer of the non-metallic inclusion for detection, constructs the metal material in the world space coordinate system for magnet adsorption operation, and uses a random exhaustive algorithm in the world space coordinate system to obtain the coordinate value of the primary discrete atom of the next order of the non-metallic inclusion; When the matching result indicates that the two do not match, the metal material is constructed in a world space coordinate system to perform a magnet adsorption operation, and a random exhaustive algorithm is used in the world space coordinate system to obtain a secondary coordinate value and a secondary target coordinate value of a secondary discrete atom of the order of the non-metallic inclusion; The secondary coordinate value and the secondary target coordinate value are bridged to obtain a secondary atomic copolymer of the non-metallic inclusion; According to the secondary atomic copolymer, updating the initial current non-metallic inclusion density to obtain the initial target current non-metallic inclusion density of the non-metallic inclusion; Matching the current non-metallic inclusion density of the initial target with the size of the non-metallic inclusion density of the atomic copolymer required by the detection. If the matching result shows that the two do not match, re-constructing the metal material in the world space coordinate system based on the obtained discrete atoms to perform a magnet adsorption operation, using a random exhaustive algorithm in the world space coordinate system to obtain the coordinate value of the atomic copolymer of the non-metallic inclusion and update the current non-metallic inclusion density until the updated current non-metallic inclusion density matches the size of the non-metallic inclusion density of the atomic copolymer required by the detection; After each order of atomic copolymers of the non-metallic inclusions is detected, if the current non-metallic inclusion density of each order of atomic copolymers matches the size of the non-metallic inclusion density of each order of the atomic copolymers required for the specific detection, the detection of the non-metallic inclusions is completed.

5. A detection device for non-metallic inclusions in a metal material, wherein the non-metallic inclusions are composed of multi-order atomic copolymers, characterized in that: The device comprises: A cleaning module, which obtains the property value of the non-metallic inclusions, performs cleaning configuration on the property value, and obtains the property value after cleaning; A data point acquisition module constructs the metal material in a world space coordinate system to perform a magnet adsorption operation, and uses a random exhaustive algorithm in the world space coordinate system to obtain the initial coordinate value and the initial target coordinate value of the initial discrete atoms of the non-metallic inclusion; An expansion module is used to bridge the initial coordinate value and the initial target coordinate value to obtain the initial atomic copolymer of the non-metallic inclusion; An order analysis module obtains the primary current non-metallic inclusion density of the non-metallic inclusion according to the primary atomic copolymer; A detection module matches the initial current non-metallic inclusion density through the cleaned attribute value, and detects the non-metallic inclusion according to the matching result; and further includes: The property values ​​at least include the length, width, density of non-metallic inclusions, discrete atomic diameter and order of discrete atoms of the non-metallic inclusions of each order of the atomic copolymer; The step of cleaning the attribute value to obtain the cleaned attribute value includes: According to the specific requirements of the detection, the length, width, size of non-metallic inclusion density, discrete atomic diameter and order of discrete atoms of the non-metallic inclusions of each order of the atomic copolymer are configured with preset values, and the cleaned attribute values ​​of the length, width, size of non-metallic inclusion density, discrete atomic diameter and order of discrete atoms of the non-metallic inclusions of each order of the atomic copolymer are obtained; After obtaining the cleaned attribute value, the method further includes: Storing the cleaned attribute values ​​in a preset linked list; The data point acquisition module specifically includes: Generate the initial coordinate value and the initial target coordinate value of the initial atomic copolymer of the non-metallic inclusion by using a random exhaustive algorithm; The coordinates of the initial coordinate value and the initial target coordinate value are (x1, y1, z1) and (x2, y2, z2) respectively; The coordinates of the initial coordinate value and the initial target coordinate value are related to the post-cleaning property value.

6. A device for detecting non-metallic inclusions in a metal material as claimed in claim 5, characterized in that: Also includes: The expansion module specifically includes: Presetting a mapping size range of the non-metallic inclusions in the world space coordinate system; The mapping size range is set according to the length and width of the atomic copolymer; the initial coordinate value and the initial target coordinate value are bridged to obtain a primary candidate atomic copolymer; removing the portion of the primary candidate atomic copolymer that exceeds the mapping size range to obtain a primary atomic copolymer; According to the discrete atomic diameter of the atomic copolymer, the primary atomic copolymer is scattered and expanded to obtain the primary discrete atoms of the non-metallic inclusion; The order analysis module specifically includes: According to the initial discrete atoms, a current total length of discrete atoms of the initial atomic copolymer is obtained; Obtaining a current total volume of the primary atomic copolymer according to a current total length of discrete atoms of the primary atomic copolymer; Obtaining the initial current non-metallic inclusion density of the initial atomic copolymer according to the current total volume of the initial atomic copolymer; The detection module specifically includes: Matching the initial current non-metallic inclusion density with the non-metallic inclusion density of the atomic copolymer required for the specific detection; When the matching result indicates that the two are matched, the detection is automatically jumped to the primary target atomic copolymer of the non-metallic inclusion, the metal material is constructed in the world space coordinate system for magnet adsorption operation, and a random exhaustive algorithm is used in the world space coordinate system to obtain the coordinate value of the primary target atomic copolymer of the non-metallic inclusion; When the matching result indicates that the two do not match, the metal material is constructed in a world space coordinate system to perform a magnet adsorption operation, and a random exhaustive algorithm is used in the world space coordinate system to obtain a secondary coordinate value and a secondary target coordinate value of the primary atomic copolymer of the non-metallic inclusion; Bridge processing is performed on the secondary coordinate value and the secondary target coordinate value to obtain the primary target discrete atoms of the non-metallic inclusion; According to the initial target discrete atoms, the initial current non-metallic inclusion density is updated to obtain the initial target current non-metallic inclusion density of the non-metallic inclusion; Matching the current non-metallic inclusion density of the initial target with the size of the non-metallic inclusion density of the atomic copolymer required by the detection. If the matching result shows that the two do not match, re-constructing the metal material in the world space coordinate system based on the obtained discrete atoms to perform a magnet adsorption operation, using a random exhaustive algorithm in the world space coordinate system to obtain the coordinate value of the atomic copolymer of the non-metallic inclusion and update the current non-metallic inclusion density until the updated current non-metallic inclusion density matches the size of the non-metallic inclusion density of the atomic copolymer required by the detection; After each order of atomic copolymers of the non-metallic inclusions is detected, if the current non-metallic inclusion density of each order of atomic copolymers matches the size of the non-metallic inclusion density of each order of the atomic copolymers required for the specific detection, the detection of the non-metallic inclusions is completed.

Images