Detection method, device and equipment for inclusions in steel and storage medium

Abstract

The invention is suitable for the technical field of steel detection, and provides a method, device and equipment for detecting inclusions in steel and a storage medium. The method comprises the following steps: performing ultrasonic detection on to-be-detected steel to obtain first ultrasonic reflection information; inputting the first ultrasonic reflection information into a trained detection model to obtain the position, shape and size of the target inclusion in the to-be-detected steel output by the detection model; the detection model is obtained through training according to ultrasonic reflection information obtained through ultrasonic detection on the steel, the position, obtained based on the ultrasonic reflection information, of the target inclusion in the steel and the shape and size, obtained through scanning electron microscope detection on the steel and matched with the ultrasonic reflection information, of the target inclusion in the steel. According to the method, the distribution condition and the morphology characteristics of the target inclusions in the to-be-detected steel can be obtained only based on the ultrasonic reflection information, and the efficiency, the accuracy and the comprehensiveness of detection of the target inclusions in the steel are improved.

Description

Technical Field

[0001] The present application relates to the technical field of steel detection, and in particular to a method, device, equipment and storage medium for detecting inclusions in steel. Background Art

[0002] Steels such as manganese steel are widely used in many industrial fields. Inclusions in steel such as titanium nitride (TiN) have a significant impact on the performance and quality of steel, so it is very important to accurately detect the distribution and characteristics of inclusions in steel.

[0003] However, related technologies usually only detect the distribution of inclusions in steel, which has certain limitations in terms of detection accuracy, efficiency and comprehensiveness, and cannot meet the needs of accurate and comprehensive detection of inclusions in steel. Summary of the invention

[0004] In view of this, the embodiments of the present application provide a method, device, equipment and storage medium for detecting inclusions in steel to solve the technical problems that related methods have certain limitations in detection accuracy, efficiency and comprehensiveness.

[0005] In a first aspect, an embodiment of the present application provides a method for detecting inclusions in steel, comprising: Performing ultrasonic testing on the steel to be tested to obtain first ultrasonic reflection information; Inputting the first ultrasonic reflection information into a trained detection model to obtain the position, shape and size of the target inclusions in the steel to be detected output by the detection model; The detection model is trained based on ultrasonic reflection information obtained by ultrasonic testing of steel, the position of target inclusions in the steel obtained based on the ultrasonic reflection information, and the shape and size of target inclusions in the steel obtained by scanning electron microscope testing of steel and matching the ultrasonic reflection information; the detection model inputs the ultrasonic reflection information and outputs the position, shape and size of the target inclusions.

[0006] In a possible implementation manner of the first aspect, before inputting the first ultrasonic reflection information into a trained detection model, the method further includes: Performing ultrasonic testing on steel samples to obtain second ultrasonic reflection information; determining a target position of a target inclusion in the steel sample according to the second ultrasonic reflection information; Based on the target position, a scanning electron microscope is performed on the target inclusion in the steel sample to obtain morphological information of the target inclusion; the morphological information includes the shape and size of the target inclusion in the steel sample; According to the target position of the target inclusion, matching the second ultrasonic reflection information with the morphology information, and constructing a training set according to the matched second ultrasonic reflection information and morphology information; The preset detection model is trained based on the training set to obtain a trained detection model.

[0007] In a possible implementation manner of the first aspect, the ultrasonic reflection information includes the reflection time, reflection amplitude, reflection frequency and reflection speed of the ultrasonic wave; The step of determining the target position of the target inclusion in the steel sample according to the second ultrasonic reflection information includes: determining target inclusions in the steel sample according to the reflection time, reflection amplitude and reflection frequency of the ultrasonic wave in the second ultrasonic reflection information; For each target inclusion in the steel sample, a target position of the target inclusion in the steel sample is determined according to the reflection time and reflection speed of the ultrasonic wave corresponding to the target inclusion in the second ultrasonic wave reflection information.

[0008] In a possible implementation manner of the first aspect, determining the target inclusions in the steel sample according to the reflection time, reflection amplitude, and reflection frequency of the ultrasonic wave in the second ultrasonic wave reflection information includes: For each ultrasonic wave in the second ultrasonic wave reflection information, if the reflection time of the ultrasonic wave is within a preset time range, the reflection amplitude is within a preset amplitude range, and the reflection frequency is within a preset frequency range, it is determined that the inclusion corresponding to the ultrasonic wave is the target inclusion in the steel sample.

[0009] In a possible implementation of the first aspect, based on the target position, performing scanning electron microscope detection on the target inclusion in the steel sample to obtain morphology information of the target inclusion includes: Based on the target position, cutting the steel sample to expose the target inclusions in the steel sample; The target inclusions exposed in the cut steel sample are detected by scanning electron microscopy to obtain the morphological information of the target inclusions.

[0010] In a possible implementation manner of the first aspect, matching the second ultrasonic reflection information with the morphology information according to the target position of the target inclusion, and constructing a training set according to the matched second ultrasonic reflection information and morphology information, includes: matching the second ultrasonic reflection information corresponding to the same target position with the topographic information; A training set is constructed based on the matched second ultrasonic reflection information and morphological information.

[0011] In a possible implementation manner of the first aspect, after performing scanning electron microscope detection on the target inclusions in the steel sample based on the target position, the method further includes: Performing energy spectrum detection on each target inclusion in the steel sample to obtain the element type and element content of the target inclusion; Determining whether the target inclusion is a preset inclusion according to the element type and the element content; If the target inclusion is not the preset inclusion, the target inclusion is removed from the target inclusions.

[0012] In a second aspect, an embodiment of the present application provides a device for detecting inclusions in steel, comprising: A detection module, used to perform ultrasonic detection on the steel to be detected and obtain first ultrasonic reflection information; An obtaining module, used for inputting the first ultrasonic reflection information into a trained detection model to obtain the position, shape and size of the target inclusions in the steel to be detected output by the detection model; The detection model is trained based on ultrasonic reflection information obtained by ultrasonic testing of steel, the position of target inclusions in the steel obtained based on the ultrasonic reflection information, and the shape and size of target inclusions in the steel obtained by scanning electron microscope testing of steel and matching the ultrasonic reflection information; the detection model inputs the ultrasonic reflection information and outputs the position, shape and size of the target inclusions.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the method for detecting inclusions in steel as described in any one of the first aspects is implemented.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for detecting inclusions in steel as described in any one of the first aspects is implemented.

[0015] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0016] The detection method, device, equipment and storage medium for inclusions in steel provided in the embodiments of the present application perform ultrasonic detection on the steel to be detected to obtain first ultrasonic reflection information, and then input the first ultrasonic reflection information into a trained detection model, thereby obtaining the position, shape and size of the target inclusions in the steel to be detected output by the detection model. Among them, the detection model is trained based on the ultrasonic reflection information obtained by ultrasonic detection of the steel, the position of the target inclusions in the steel obtained based on the ultrasonic reflection information, and the shape and size of the target inclusions in the steel that match the ultrasonic reflection information obtained by scanning electron microscope detection of the steel. The present application can obtain the distribution and morphological characteristics of the target inclusions in the steel to be detected based only on the ultrasonic reflection information obtained by ultrasonic detection of the steel to be detected and the trained detection model, thereby improving the efficiency, accuracy and comprehensiveness of the detection of target inclusions in the steel.

[0017] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art 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 work.

[0019] Figure 1 It is a schematic diagram of an application scenario provided by an embodiment of the present application; Figure 2 It is a schematic flow chart of a method for detecting inclusions in steel provided in one embodiment of the present application; Figure 3 It is a schematic diagram of the structure of a detection device for inclusions in steel provided in one embodiment of the present application; Figure 4 It is a schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0020] The present application is described more clearly below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the effects of the present application, but are not intended to limit the present application in any form. It should be noted that, for those of ordinary skill in the art, several variations and improvements may be made without departing from the concept of the present application. These all fall within the scope of protection of the present application.

[0021] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0022] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0023] In the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0024] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0025] In addition, the “plurality” mentioned in the embodiments of the present application should be interpreted as two or more.

[0026] In order to accurately, efficiently and comprehensively detect target inclusions in steel, the present application performs ultrasonic testing on the steel to be tested to obtain first ultrasonic reflection information, and then inputs the first ultrasonic reflection information into a trained detection model, thereby obtaining the position, shape and size of the target inclusions in the steel to be tested output by the detection model. Among them, the detection model is trained based on the ultrasonic reflection information obtained by ultrasonic testing of steel, the position of the target inclusions in the steel obtained based on the ultrasonic reflection information, and the shape and size of the target inclusions in the steel obtained by scanning electron microscopy testing of steel that match the ultrasonic reflection information, so that the detection model can input ultrasonic reflection information and output the position, shape and size of the target inclusions.

[0027] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0028] First reference Figure 1 , Figure 1An application scenario of the present application is schematically illustrated, in which an electronic device is included, and a trained detection model is provided on the electronic device.

[0029] The electronic device performs ultrasonic testing on the steel to be tested, obtains first ultrasonic reflection information, and inputs the first ultrasonic reflection information into a trained detection model to obtain the position, shape and size of the target inclusions in the steel to be tested output by the detection model.

[0030] Among them, the detection model is trained based on the ultrasonic reflection information obtained by ultrasonic testing of steel, the position of the target inclusions in the steel based on the ultrasonic reflection information, and the shape and size of the target inclusions in the steel obtained by scanning electron microscope testing of steel and matching the ultrasonic reflection information; the detection model inputs the ultrasonic reflection information and outputs the position, shape and size of the target inclusions.

[0031] The application scenario may also include an ultrasonic detection device, and the electronic device controls the ultrasonic detection device to perform ultrasonic detection on the steel to be detected, thereby obtaining first ultrasonic reflection information. The electronic device may be a hardware device with data storage, processing and analysis functions, such as a controller or a computer.

[0032] Combine the following Figure 1 ,refer to Figure 2 A method for detecting inclusions in steel provided according to an exemplary embodiment of the present application will be described.

[0033] Figure 2 FIG. 1 is a flow chart of a method for detecting inclusions in steel provided in an embodiment of the present application. Figure 2 As shown, the method in the embodiment of the present application may include: Step 201: Perform ultrasonic testing on the steel material to be tested to obtain first ultrasonic reflection information.

[0034] Exemplarily, the steel to be tested may be manganese steel. In this embodiment, ultrasonic testing equipment is used to perform ultrasonic testing on the steel to be tested. Ultrasonic testing is a testing method that uses the propagation characteristics of ultrasonic waves in materials to detect defects in materials. Here, the ultrasonic testing equipment is controlled to emit ultrasonic waves to the steel to be tested. The ultrasonic waves propagate in the steel to be tested and are reflected after encountering inclusions in the steel to be tested. Thus, information about the inclusions in the steel to be tested can be determined based on the first ultrasonic reflection information received by the ultrasonic testing equipment.

[0035] In this embodiment, the ultrasonic reflection information includes the ultrasonic reflection time, reflection amplitude, reflection frequency and reflection speed. The reflection time refers to the time it takes for the ultrasonic wave to return to the probe of the ultrasonic detection device after it is emitted from the ultrasonic detection device and encounters the inclusion. The reflection amplitude refers to the amplitude of the ultrasonic wave when it returns to the probe. The reflection frequency refers to the frequency of the ultrasonic wave when it returns to the probe. The reflection speed refers to the propagation speed of the ultrasonic wave in the steel.

[0036] Step 202: input the first ultrasonic reflection information into the trained detection model to obtain the position, shape and size of the target inclusions in the steel to be detected output by the detection model.

[0037] Among them, the detection model is trained based on the ultrasonic reflection information obtained by ultrasonic testing of steel, the position of the target inclusions in the steel based on the ultrasonic reflection information, and the shape and size of the target inclusions in the steel obtained by scanning electron microscope testing of steel and matching the ultrasonic reflection information; the detection model inputs the ultrasonic reflection information and outputs the position, shape and size of the target inclusions.

[0038] In this embodiment, the target inclusion is the inclusion to be detected in the steel to be detected, such as the inclusions in the steel to be detected may be TiN and / or MnS, etc., wherein the target inclusion may be TiN. The first ultrasonic reflection information is input into the trained detection model, and the position, shape and size of the target inclusion in the steel to be detected output by the detection model can be obtained. The position of the target inclusion can be represented by a three-dimensional coordinate.

[0039] In a possible implementation manner, before inputting the first ultrasonic wave reflection information into the trained detection model, the present embodiment may further train the detection model. Specifically, the present embodiment may further include steps S1 to S5.

[0040] S1. Perform ultrasonic testing on a steel sample to obtain second ultrasonic reflection information.

[0041] S2. Determine a target position of a target inclusion in the steel sample according to the second ultrasonic reflection information.

[0042] S3. Based on the target position, the target inclusions in the steel sample are detected by scanning electron microscopy to obtain the morphological information of the target inclusions; the morphological information includes the shape and size of the target inclusions in the steel sample.

[0043] S4. Match the second ultrasonic reflection information with the morphology information according to the target position of the target inclusion, and construct a training set according to the matched second ultrasonic reflection information and the morphology information.

[0044] S5. Train the preset detection model based on the training set to obtain a trained detection model.

[0045] For example, the steel sample in this embodiment has precise size, neat edges, smooth and flat surface without obvious scratches, so as to ensure that an accurate three-dimensional coordinate system can be constructed based on the steel sample in the future to improve the accuracy of ultrasonic testing and scanning electron microscope testing. For example, the steel ingot can be accurately cut by laser cutting technology to obtain a steel sample, and the length, width and height of the steel sample can be 10mm×10mm×5mm. The steel sample can specifically be a manganese steel sample.

[0046] Optionally, in this embodiment, the steel sample is ultrasonically cleaned to remove impurities and contaminants on the surface of the steel sample to improve the accuracy of subsequent ultrasonic testing and scanning electron microscope testing, such as controlling an ultrasonic cleaning device to ultrasonically clean the steel sample. Afterwards, the steel sample is ultrasonically tested to obtain second ultrasonic reflection information.

[0047] It should be noted that in the part of the detection model training in this embodiment, the target inclusions refer to the target inclusions in the steel sample. When the steel to be detected is subjected to inclusion detection, the target inclusions refer to the target inclusions in the steel to be detected, and it should be noted that the distinction should be made.

[0048] In some embodiments, when determining the target position of a target inclusion in a steel sample, the target inclusion in the steel sample can be determined based on the reflection time, reflection amplitude and reflection frequency of the ultrasonic wave in the second ultrasonic reflection information. For each target inclusion in the steel sample, the target position of the target inclusion in the steel sample is determined based on the reflection time and reflection speed of the ultrasonic wave corresponding to the target inclusion in the second ultrasonic reflection information.

[0049] Here, as mentioned above, there may be multiple types of inclusions in the steel sample. After the ultrasonic wave encounters different inclusions and reflects, the ultrasonic wave reflection information corresponding to different inclusions is different. Therefore, in this embodiment, the target inclusions in the steel sample can be determined according to the reflection time, reflection amplitude and reflection frequency of the ultrasonic wave in the second ultrasonic wave reflection information. For example, when the ultrasonic wave propagates in an area containing more TiN in the steel sample, phenomena such as prolonged reflection time and attenuated reflection amplitude may occur.

[0050] Exemplarily, for each ultrasonic wave in the second ultrasonic reflection information, if the reflection time of the ultrasonic wave is within a preset time range, the reflection amplitude is within a preset amplitude range, and the reflection frequency is within a preset frequency range, it is determined that the inclusion corresponding to the ultrasonic wave is the target inclusion in the steel sample.

[0051] Here, the preset time range can be determined based on the time it takes for the ultrasonic wave to return to the probe after encountering the target inclusion in the steel sample. For example, when the target inclusion is TiN, the preset time range can be determined based on the time it takes for the ultrasonic wave to return to the probe after encountering TiN in the steel sample. Similarly, the preset reflection amplitude can be determined based on the amplitude of the ultrasonic wave when it returns to the probe after encountering TiN in the steel sample, and the preset frequency range can be determined based on the frequency of the ultrasonic wave when it returns to the probe after encountering TiN in the steel sample.

[0052] Optionally, in this embodiment, a three-dimensional coordinate system can be constructed according to the size of the steel sample, so that after determining the target inclusion in the steel sample, the target position of the target inclusion in the steel sample can be determined according to the reflection time and reflection speed of the ultrasonic wave corresponding to the target inclusion in the second ultrasonic wave reflection information. Here, the target position can be represented by the three-dimensional coordinates of the target inclusion in the three-dimensional coordinate system of the steel sample.

[0053] In some embodiments, when obtaining the morphological information of the target inclusions, the steel sample can be cut based on the target position to expose the target inclusions in the steel sample, and then the exposed target inclusions in the cut steel sample are subjected to scanning electron microscopy detection to obtain the morphological information of the target inclusions.

[0054] Here, scanning electron microscope detection refers to scanning electron microscope (SEM) detection. By performing scanning electron microscope detection on target inclusions in steel samples, the morphological characteristics of the target inclusions can be obtained.

[0055] Exemplarily, after determining the target inclusions and the target positions of the target inclusions in the steel sample, this embodiment positions and cuts the steel sample according to the target positions, so that the target inclusions corresponding to the target positions can be exposed, facilitating the scanning electron microscope detection of the exposed target inclusions. For example, the steel sample is cut according to the target position to obtain a sub-steel sample containing the exposed target inclusions corresponding to the target position, and the exposed target inclusions in the sub-steel sample are subjected to scanning electron microscope detection, thereby obtaining the morphological information of the target inclusions.

[0056] This embodiment can control the cutting equipment to cut the steel sample, and can control the SEM to perform scanning electron microscope detection on the exposed target inclusions. Specifically, when performing scanning electron microscope detection on the exposed target inclusions, the magnification of the SEM can be set to 1000 times and the working distance to 10 mm.

[0057] In some embodiments, when constructing a training set, the second ultrasonic reflection information corresponding to the same target position may be matched with the morphology information, and the training set may be constructed based on the matched second ultrasonic reflection information and morphology information.

[0058] In this embodiment, according to the target position, the second ultrasonic reflection information corresponding to the same target position is matched with the morphology information, that is, the second ultrasonic reflection information corresponding to the same target inclusion in the steel sample is matched with the corresponding morphology information and the target position, and the obtained matched second ultrasonic reflection information is used as a training sample, and the morphology information and the target position are used as labels to construct a training set. As mentioned above, the morphology information includes the shape and size of the target inclusion.

[0059] Exemplarily, after constructing the training set, the preset detection model is trained based on the constructed training set and the machine learning algorithm, so that the trained detection model can input ultrasonic reflection information and output the location, shape and size of the target inclusion. In this embodiment, the detection model can be a neural network model, such as a convolutional neural network (CNN) model.

[0060] In this way, by matching the second ultrasonic reflection information of the target inclusion in the steel sample with the corresponding morphological information and the target position, the ultrasonic reflection information corresponding to the target inclusion can be matched with the position, shape and size of the target inclusion, and then the detection model is subsequently trained according to the matched second ultrasonic reflection information, target position and morphological information to obtain a trained detection model. Therefore, when the target inclusion in the steel to be detected is subsequently detected, only the steel to be detected is ultrasonically detected, and the position, shape and size of the target inclusion in the steel to be detected can be obtained according to the obtained first ultrasonic reflection information and the trained detection model, so that the distribution and morphological characteristics of the target inclusion in the steel to be detected can be obtained by only performing ultrasonic detection on the steel to be detected, thereby improving the efficiency, accuracy and comprehensiveness of the detection of the target inclusion.

[0061] Optionally, as mentioned above, the position of the target inclusion can be represented by three-dimensional coordinates, and then a three-dimensional distribution image of the target inclusion can be obtained based on the three-dimensional coordinates, which more intuitively displays the distribution of the target inclusions in the steel to be tested.

[0062] In some embodiments, after performing scanning electron microscope detection on the target inclusions in the steel sample based on the target position, energy spectrum detection can also be performed on each target inclusion in the steel sample to obtain the element type and element content of the target inclusion, and determine whether the target inclusion is a preset inclusion based on the element type and element content, and when the target inclusion is not a preset inclusion, remove the target inclusion from the target inclusions.

[0063] In this embodiment, in order to avoid possible identification errors when ultrasonic testing identifies target inclusions, the target inclusions in the steel sample determined by ultrasonic testing are further determined. Specifically, after the target inclusions in the steel sample are detected by scanning electron microscope, the target inclusions in the steel sample can also be detected by energy spectrum, that is, by energy spectrum analyzer (EDS), so as to obtain the element type and element content of the target inclusions in the steel sample, and then determine whether the target inclusion is a preset inclusion according to the element type and element content of the target inclusion. Here, the preset inclusion is determined according to the target inclusion.

[0064] For example, when the target inclusion is TiN, the preset inclusion is set to TiN, and the element types of the target inclusion should include two elements, Ti and N, and the atomic ratio of Ti and N is close to 1:1. If the element types of the target inclusions in the steel sample obtained by energy spectrum detection are Ti and N, and the atomic ratio of Ti and N is within the preset atomic ratio range, the target inclusion is determined to be TiN, otherwise it is considered that there is a problem with the ultrasonic detection, and the target inclusion is not TiN. The target inclusion is removed from the target inclusions determined by the ultrasonic detection, and the remaining target inclusions are all TiN, so the morphological information of the target inclusions obtained is all morphological information of TiN.

[0065] The preset atomic ratio range may be determined according to the elements included in the target inclusions. For example, when the target inclusion is TiN, the preset atomic ratio range may be determined according to 1: 1. This embodiment may control EDS to perform energy spectrum detection on the target inclusions in the steel sample.

[0066] The method for detecting inclusions in steel provided in the embodiment of the present application performs ultrasonic testing on the steel to be tested to obtain first ultrasonic reflection information, and then inputs the first ultrasonic reflection information into a trained detection model, thereby obtaining the position, shape and size of the target inclusions in the steel to be tested output by the detection model. Among them, the detection model is trained based on the ultrasonic reflection information obtained by ultrasonic testing of the steel, the position of the target inclusions in the steel obtained based on the ultrasonic reflection information, and the shape and size of the target inclusions in the steel that match the ultrasonic reflection information obtained by scanning electron microscope testing of the steel. The present application can obtain the distribution and morphological characteristics of the target inclusions in the steel to be tested based only on the ultrasonic reflection information obtained by ultrasonic testing of the steel to be tested and the trained detection model, thereby improving the efficiency, accuracy and comprehensiveness of the detection of target inclusions in the steel.

[0067] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0068] Figure 3 Schematic diagram of the structure of a device for detecting inclusions in steel provided in one embodiment of the present application. Figure 3 As shown, the device for detecting inclusions in steel provided in this embodiment may include: a detection module 301 and an obtaining module 302 .

[0069] The detection module 301 is used to perform ultrasonic detection on the steel to be detected to obtain first ultrasonic reflection information.

[0070] An obtaining module 302 is used to input the first ultrasonic reflection information into a trained detection model to obtain the position, shape and size of the target inclusion in the steel to be detected output by the detection model; The detection model is trained based on ultrasonic reflection information obtained by ultrasonic testing of steel, the position of target inclusions in the steel obtained based on the ultrasonic reflection information, and the shape and size of target inclusions in the steel obtained by scanning electron microscope testing of steel and matching the ultrasonic reflection information; the detection model inputs the ultrasonic reflection information and outputs the position, shape and size of the target inclusions.

[0071] Optionally, the obtaining module 302 is further used for: Performing ultrasonic testing on the steel sample to obtain second ultrasonic reflection information; determining a target position of a target inclusion in the steel sample according to the second ultrasonic reflection information; Based on the target position, a scanning electron microscope is performed on the target inclusion in the steel sample to obtain morphological information of the target inclusion; the morphological information includes the shape and size of the target inclusion in the steel sample; According to the target position of the target inclusion, matching the second ultrasonic reflection information with the morphology information, and constructing a training set according to the matched second ultrasonic reflection information and morphology information; The preset detection model is trained based on the training set to obtain a trained detection model.

[0072] Optionally, the ultrasonic reflection information includes the ultrasonic reflection time, reflection amplitude, reflection frequency and reflection speed; the obtaining module 302 is further used for: determining target inclusions in the steel sample according to the reflection time, reflection amplitude and reflection frequency of the ultrasonic wave in the second ultrasonic reflection information; For each target inclusion in the steel sample, a target position of the target inclusion in the steel sample is determined according to the reflection time and reflection speed of the ultrasonic wave corresponding to the target inclusion in the second ultrasonic wave reflection information.

[0073] Optionally, the obtaining module 302 is further used for: For each ultrasonic wave in the second ultrasonic wave reflection information, if the reflection time of the ultrasonic wave is within a preset time range, the reflection amplitude is within a preset amplitude range, and the reflection frequency is within a preset frequency range, it is determined that the inclusion corresponding to the ultrasonic wave is the target inclusion in the steel sample.

[0074] Optionally, the obtaining module 302 is further used for: Based on the target position, cutting the steel sample to expose the target inclusions in the steel sample; The target inclusions exposed in the cut steel sample are detected by scanning electron microscopy to obtain the morphological information of the target inclusions.

[0075] Optionally, the obtaining module 302 is further used for: matching the second ultrasonic reflection information corresponding to the same target position with the topographic information; A training set is constructed based on the matched second ultrasonic reflection information and morphological information.

[0076] Optionally, the obtaining module 302 is further used for: Performing energy spectrum detection on each target inclusion in the steel sample to obtain the element type and element content of the target inclusion; Determining whether the target inclusion is a preset inclusion according to the element type and the element content; If the target inclusion is not the preset inclusion, the target inclusion is removed from the target inclusions.

[0077] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0078] Figure 4 Schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 4 As shown, the electronic device 400 of this embodiment includes: a processor 410 and a memory 420, wherein the memory 420 stores a computer program 421 that can be run on the processor 410. When the processor 410 executes the computer program 421, the steps in any of the above method embodiments are implemented, for example Figure 2 Alternatively, when the processor 410 executes the computer program 421, the functions of each module / unit in the above-mentioned device embodiments are implemented, for example Figure 3 Functions of modules 301 to 302 are shown.

[0079] Exemplarily, the computer program 421 may be divided into one or more modules / units, one or more modules / units are stored in the memory 420, and are executed by the processor 410 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 421 in the electronic device 400.

[0080] Those skilled in the art will understand that Figure 4 These are merely examples of electronic devices and do not constitute a limitation of the electronic device. The electronic device may include more or fewer components than those shown in the figure, or a combination of certain components, or different components, such as input and output devices, network access devices, buses, etc.

[0081] The processor 410 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0082] The memory 420 may be an internal storage unit of the electronic device, such as a hard disk or memory of the electronic device, or an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. The above-mentioned memory 420 may also include both an internal storage unit of the electronic device and an external storage device. The above-mentioned memory 420 is used to store computer programs and other programs and data required by the electronic device. The memory 420 may also be used to temporarily store data that has been output or is to be output.

[0083] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0084] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0085] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0086] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0087] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0088] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0089] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0090] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for detecting inclusions in steel, characterized in that: include: Performing ultrasonic testing on the steel to be tested to obtain first ultrasonic reflection information; Inputting the first ultrasonic reflection information into a trained detection model to obtain the position, shape and size of the target inclusions in the steel to be detected output by the detection model; The detection model is trained based on ultrasonic reflection information obtained by ultrasonic testing of steel, the position of target inclusions in the steel obtained based on the ultrasonic reflection information, and the shape and size of target inclusions in the steel obtained by scanning electron microscope testing of steel and matching the ultrasonic reflection information; the detection model inputs the ultrasonic reflection information and outputs the position, shape and size of the target inclusions.

2. The method for detecting inclusions in steel according to claim 1, characterized in that: Before inputting the first ultrasonic reflection information into the trained detection model, the method further includes: Performing ultrasonic testing on the steel sample to obtain second ultrasonic reflection information; determining a target position of a target inclusion in the steel sample according to the second ultrasonic reflection information; Based on the target position, a scanning electron microscope is performed on the target inclusion in the steel sample to obtain morphological information of the target inclusion; the morphological information includes the shape and size of the target inclusion in the steel sample; According to the target position of the target inclusion, matching the second ultrasonic reflection information with the morphology information, and constructing a training set according to the matched second ultrasonic reflection information and morphology information; The preset detection model is trained based on the training set to obtain a trained detection model.

3. The method for detecting inclusions in steel according to claim 2, characterized in that: Ultrasonic reflection information includes ultrasonic reflection time, reflection amplitude, reflection frequency and reflection speed; The step of determining the target position of the target inclusion in the steel sample according to the second ultrasonic reflection information includes: determining target inclusions in the steel sample according to the reflection time, reflection amplitude and reflection frequency of the ultrasonic wave in the second ultrasonic reflection information; For each target inclusion in the steel sample, a target position of the target inclusion in the steel sample is determined according to the reflection time and reflection speed of the ultrasonic wave corresponding to the target inclusion in the second ultrasonic wave reflection information.

4. The method for detecting inclusions in steel according to claim 3, characterized in that: The step of determining the target inclusions in the steel sample according to the reflection time, reflection amplitude and reflection frequency of the ultrasonic wave in the second ultrasonic wave reflection information comprises: For each ultrasonic wave in the second ultrasonic wave reflection information, if the reflection time of the ultrasonic wave is within a preset time range, the reflection amplitude is within a preset amplitude range, and the reflection frequency is within a preset frequency range, it is determined that the inclusion corresponding to the ultrasonic wave is the target inclusion in the steel sample.

5. The method for detecting inclusions in steel according to any one of claims 2 to 4, characterized in that: The method of performing scanning electron microscope detection on the target inclusions in the steel sample based on the target position to obtain the morphology information of the target inclusions includes: Based on the target position, cutting the steel sample to expose the target inclusions in the steel sample; The target inclusions exposed in the cut steel sample are detected by scanning electron microscopy to obtain the morphological information of the target inclusions.

6. The method for detecting inclusions in steel according to any one of claims 2 to 4, characterized in that: The matching of the second ultrasonic reflection information with the morphology information according to the target position of the target inclusion, and constructing a training set according to the matched second ultrasonic reflection information and morphology information, comprises: matching the second ultrasonic reflection information corresponding to the same target position with the topographic information; A training set is constructed based on the matched second ultrasonic reflection information and morphological information.

7. The method for detecting inclusions in steel according to any one of claims 2 to 4, characterized in that: After the target inclusions in the steel sample are detected by scanning electron microscope based on the target position, the method further includes: Performing energy spectrum detection on each target inclusion in the steel sample to obtain the element type and element content of the target inclusion; Determining whether the target inclusion is a preset inclusion according to the element type and the element content; If the target inclusion is not the preset inclusion, the target inclusion is removed from the target inclusions.

8. A device for detecting inclusions in steel, characterized in that: include: A detection module, used to perform ultrasonic detection on the steel to be detected and obtain first ultrasonic reflection information; An obtaining module, used for inputting the first ultrasonic reflection information into a trained detection model to obtain the position, shape and size of the target inclusions in the steel to be detected output by the detection model; The detection model is trained based on ultrasonic reflection information obtained by ultrasonic testing of steel, the position of target inclusions in the steel obtained based on the ultrasonic reflection information, and the shape and size of target inclusions in the steel obtained by scanning electron microscope testing of steel and matching the ultrasonic reflection information; the detection model inputs the ultrasonic reflection information and outputs the position, shape and size of the target inclusions.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the method for detecting inclusions in steel as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for detecting inclusions in steel according to any one of claims 1 to 7 is implemented.

Images