Method, device, terminal and storage medium for removing raw material defects in a steel production line

Abstract

The present application is applicable to the technical field of steel production, and provides a method, device, terminal and storage medium for removing raw material defects in a steel production line, wherein the raw material defect removal method comprises: obtaining image acquisition information after the raw steel billet passes through a defect removal device; determining the defect type and defect shape of the raw steel billet according to the comparison result between the image acquisition information and the image information corresponding to each image in the steel billet database, wherein the steel billet database includes steel billet images corresponding to different defect types; determining the target device for defect removal according to the defect type and defect shape of the raw steel billet, wherein the target device is one of the at least one defect removal device; and controlling the target device to perform defect removal operations. The above-mentioned raw material defect removal method can improve the yield rate of steel production, so as to reduce the economic losses caused by defects in finished steel.

Description

Technical Field

[0001] The present application belongs to the technical field of steel production, and in particular, relates to a method, device, terminal and storage medium for removing raw material defects in a steel production line. Background Art

[0002] With the application and development of hot-rolled steel in various aspects, users' requirements for products are becoming more and more stringent. Besides, while users pay attention to the quality of steel, they also pay more attention to the appearance quality of products.

[0003] At present, during the production of hot-rolled steel, the raw steel billets have defects such as scars and heavy skin that are not cleaned up, which leads to the phenomenon that metal flakes with irregular shapes remaining on the surface of the steel after rolling are called scars. There are two types of scars. One is connected to the main body of the steel and folded onto the plate surface and is not easy to fall off; the other is not connected to the main body of the steel, but bonded to the plate surface, easy to fall off, and form smoother pits after falling off. Regardless of the defect, it will cause metal peeling or holes in the hot-rolled steel during the subsequent processing and use, and will cause great economic losses to the manufacturer.

[0004] Therefore, there is an urgent need to provide a method for removing raw material defects to reduce the economic losses caused by defects in finished steel products. Summary of the invention

[0005] The embodiments of the present application provide a method, device, terminal and storage medium for removing raw material defects in a steel production line, which can improve the yield rate of steel production and reduce the economic losses caused by defects in finished steel products.

[0006] A first aspect of an embodiment of the present application provides a method for removing raw material defects in a steel production line, the method comprising:

[0007] Acquire image acquisition information of the raw steel billet after it passes through a defect removal device;

[0008] determining the defect type and defect shape of the raw steel billet according to a comparison result between the image acquisition information and image information corresponding to each image in a steel billet database, wherein the steel billet database includes images of steel billets with different defects;

[0009] Determining a target device for defect removal according to the defect type and defect shape of the raw steel billet, wherein the target device is one of the at least one defect removal device;

[0010] The target device is controlled to perform a defect removal operation.

[0011] A second aspect of an embodiment of the present application provides a raw material defect removal device for a steel production line, the raw material defect removal device comprising:

[0012] An image acquisition module, used to acquire image acquisition information of the raw steel billet after it passes through a defect removal device;

[0013] a defect determination module, configured to determine the defect type and defect shape of the raw steel billet according to a comparison result between the image acquisition information and image information corresponding to each image in a steel billet database, wherein the steel billet database includes images of steel billets with different defects;

[0014] An equipment determination module, used to determine a target equipment for defect removal according to the defect type and defect shape of the raw steel billet, wherein the target equipment is one of at least one defect removal equipment;

[0015] The control module is used to control the target device to perform a defect removal operation.

[0016] A third aspect of an embodiment of the present application provides a terminal, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for removing raw material defects from a steel production line as described in the first aspect above is implemented.

[0017] A fourth aspect of 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 removing raw material defects from a steel production line described in the first aspect above is implemented.

[0018] A fifth aspect of an embodiment of the present application provides a computer program product. When the computer program product is run on a terminal, the terminal executes the method for removing raw material defects of a steel production line described in the first aspect.

[0019] Compared with the prior art, the embodiments of the present application have the following beneficial effects: the steel production line of the present application includes at least one defect removal device, and the operation process of the raw steel billet after passing through each defect removal device is the same as the following process. First, the image acquisition information of the raw steel billet after passing through a defect removal device is obtained. Secondly, since the steel billet database includes steel billet images corresponding to different defect types, the defect type and defect shape of the raw steel billet can be determined based on the comparison results of the image acquisition information and the image information corresponding to each image in the steel billet database. Finally, according to the defect type and defect shape of the raw steel billet, the target device for defect removal can be determined, and the target device can be controlled to perform the defect removal operation, correspondingly removing the defects on the raw steel billet, improving the yield rate of steel production, and reducing the economic losses caused by defects in the finished steel. Brief Description of the Drawings

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0021] Figure 1 is a schematic flowchart of a method for removing raw material defects provided in Embodiment 1 of the present application;

[0022] Figure 2 is an example diagram of an application scenario of the method for removing raw material defects;

[0023] Figure 3 is a schematic flowchart of a method for removing raw material defects provided in Embodiment 2 of the present application;

[0024] Figure 4 is a schematic structural diagram of a device for removing raw material defects provided in Embodiment 3 of the present application;

[0025] Figure 5 is a schematic structural diagram of a terminal provided in Embodiment 4 of the present application. Detailed Embodiments

[0026] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0027] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0028] It should also be understood that the term " / and" as used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0029] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0030] In addition, 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.

[0031] 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.

[0032] Research shows that in recent years, steel production technology has made significant progress. Taking the hot rolling production process as an example, when hot-rolled strip steel is being rolled, not only the product quality requirements for the strip steel are getting higher and higher, but also the appearance quality of the product is more valued and concerned. However, since the raw steel billet of hot-rolled strip steel may have defects such as scarring and heavy skin that are not cleaned up during production, it is easy to cause the phenomenon of residues on the surface of the steel after rolling, which in turn causes defects on the surface of the produced strip steel, which cannot fully meet the requirements of product appearance quality, resulting in a low yield rate of strip steel.

[0033] In view of the possible defects such as scarring and heavy skin in the raw steel billet, the present application provides a raw material defect removal method, which first obtains image acquisition information of the raw steel billet after passing through a defect removal device. Secondly, since the steel billet database includes steel billet images corresponding to different defect types, the defect type and defect shape of the raw steel billet can be determined based on the comparison results between the image acquisition information and the image information corresponding to each image in the steel billet database. Finally, based on the defect type and defect shape of the raw steel billet, the target device for defect removal can be determined, and the target device can be controlled to perform the defect removal operation, so as to remove the defects on the raw steel billet and improve the yield rate of steel production, so as to reduce the economic losses caused by defects in the finished steel.

[0034] It should be understood that the raw material defect removal method proposed in this application can be used to remove the surface defects of raw steel billets on various steel production lines. To illustrate the technical solution of this application, taking the hot-rolled strip production line as an example, it will be described below through specific embodiments.

[0035] It should also be understood that the magnitude of the sequence numbers of the steps in this embodiment does not mean the sequence of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of this application.

[0036] Referring to Figure 1 , a schematic flowchart of a raw material defect removal method provided in Embodiment 1 of this application is shown. As Figure 1 shown, the raw material defect removal method may include the following steps:

[0037] Step 101, obtain the image acquisition information of the raw steel billet after passing through a defect removal device.

[0038] In the embodiment of this application, taking the production of strip steel as an example, on the production line for producing strip steel, there is at least one defect removal device, and each defect removal device can be used to remove the defects existing on the raw steel billet. Among them, the defect removal device can be a high-pressure water descaling machine, a grinding wheel grinding machine, a torch grinding machine, a mechanical peeling machine, a laser grinding machine, etc.

[0039] Among them, the high-pressure water descaling machine uses the mechanical impact force of high-pressure water to remove the scale on the surface of the raw steel billet; the grinding wheel grinding machine uses a grinding wheel to grind the convex scars and other defects on the surface of the raw steel billet; the torch grinding machine uses a torch to remove the scars and other defects on the surface of the raw steel billet; the mechanical peeling machine is used to remove the double skin defects on the surface of the raw steel billet; the laser grinding machine uses a laser to grind the scars and other defects on the surface of the raw steel billet.

[0040] In the embodiment of this application, the acquisition image of the raw steel billet after passing through a defect removal device can be collected by an image acquisition device (such as a camera), and according to the obtained acquisition image, the corresponding image acquisition information can be obtained.

[0041] Exemplarily, a camera is used to obtain the acquisition image of the raw steel billet after passing through the high-pressure water descaling machine, the terminal obtains the acquisition image from the camera, and obtains the corresponding image acquisition information according to the acquisition image.

[0042] It should be understood that the image acquisition information may refer to the display information of each pixel point in the acquisition image.

[0043] Step 102, determine the defect type and defect shape of the raw steel billet according to the comparison result between the image acquisition information and the image information corresponding to each image in the steel billet database.

[0044] In the embodiments of the present application, the billet database includes billet images respectively corresponding to different defect types, such as billet images corresponding to the scab type, billet images corresponding to the double skin type, billet images corresponding to the residue type, etc.

[0045] It should be understood that a defect type can be refined into multiple subsets according to the granularity, and each subset includes multiple subtypes related to the defect type. For example, the scab type can be divided into the following multiple subsets, namely the leaf-shaped scab subset, the feather-shaped scab subset, the strip-shaped scab subset, the fish-scale-shaped scab subset, the tongue-tip-shaped scab subset, etc. And the leaf-shaped scab subset can also be divided into multiple subtypes according to different leaf shapes. In the embodiments of the present application, each subtype corresponds to a billet image.

[0046] In the embodiments of the present application, since the image acquisition information can refer to the display information of each pixel point, the comparison result can be obtained according to the pixel comparison between the acquired image of the raw material billet and each image in the billet database, so as to determine the defect type and defect shape of the raw material billet. The training data set composed of the billet images respectively corresponding to different defect types in the billet database can also be used to train a neural network to obtain a defect prediction model, and the defect type and defect shape of the raw material billet are output by the defect prediction model.

[0047] In a possible implementation manner, the billet database further includes the standard shapes corresponding to different models of billets. Determining the defect type and defect shape of the raw material billet according to the comparison result between the image acquisition information and the image information corresponding to each image in the billet database includes:

[0048] Comparing the image acquisition information with the image information corresponding to each image in the billet database;

[0049] Obtaining the image similarity between the image acquisition information and the image information corresponding to each image in the billet database to obtain multiple image similarities;

[0050] Determining that the defect type of the image corresponding to the maximum similarity is the defect type of the raw material billet, and comparing the raw material billet with the corresponding standard shape to obtain the defect shape of the raw material billet.

[0051] In the embodiments of the present application, the image acquisition information corresponding to the acquired image of the raw material billet can be the shape of the raw material billet and the display information of the pixel points. By comparing the shape of the raw material billet and the display information of the pixel points with the shape and the display information of the pixel points of each image in the billet database respectively, multiple image similarities can be obtained.

[0052] Among them, the calculation method of image similarity is not unique. The similarity can be calculated based on image features, and can also be calculated based on the display information and shape of pixel points. There are many algorithms for calculating similarity based on image features, such as artificial neural networks, cosine similarity calculation methods, etc. The average hashing algorithm can be used to calculate similarity based on the display information and shape of pixel points.

[0053] Taking the average hashing algorithm as an example, first, obtain the shape of the raw steel billet and the display information of pixel points after converting it into a grayscale image from the collected image of the raw steel billet. Secondly, calculate the average grayscale value of all pixels, and compare the grayscale value of each pixel in the collected image with the average value. If it is greater than or equal to the average value, record it as 1; if it is less than the average value, record it as 0. According to the comparison results of each pixel point, calculate the hash value of the collected image of the raw steel billet. Using the same method, obtain the hash value corresponding to each image according to the image information corresponding to each image in the steel billet database. Finally, calculate the difference between the hash value of the collected image of the raw steel billet and the hash value corresponding to each image in the steel billet database to obtain the image similarity between the image acquisition information and the image information corresponding to each image in the steel billet database.

[0054] Step 103: Determine the target device for defect removal according to the defect type and defect shape of the raw steel billet.

[0055] Among them, the target device is one of at least one defect removal device.

[0056] In the embodiment of the present application, for each defect type, there are applicable defect removal devices and inapplicable defect removal devices, and for each defect shape, there are also applicable defect removal devices and inapplicable defect removal devices. For example, if the defect shape is small, defect removal devices such as mechanical peeling machines for removing large defects do not need to be used. Therefore, the present application can combine the defect type and defect shape of the raw steel billet to determine the target device for defect removal.

[0057] In a possible implementation manner, determining the target device for defect removal according to the defect type and defect shape of the raw steel billet includes:

[0058] Screen at least one initial defect removal device corresponding to the defect type from all defect removal devices according to the defect type of the raw steel billet;

[0059] Obtain the removal time required for each of at least one initial defect removal device to remove the defect of the defect shape according to the volume information corresponding to the defect shape of the raw steel billet and at least one initial defect removal device corresponding to the defect type;

[0060] Determine the target device for defect removal based on multiple removal times and at least one initial defect removal device.

[0061] Exemplarily, assume that the defect type of the obtained raw steel billet is the leaf-shaped scab type, formed on the surface of the raw steel billet, forming a leaf-shaped protruding scab, with a corresponding volume of 0.3 cubic meters, which belongs to a defect with a small volume. The initial defect removal devices screened from all defect removal devices corresponding to the defect type can be a grinding wheel grinder, a gas gun grinder, and a laser grinder. Also, since the volume information corresponding to the defect shape is 0.3 cubic meters, the removal times required for the grinding wheel grinder, the gas gun grinder, and the laser grinder to remove the leaf-shaped scab can be obtained according to the unit workload of the grinding wheel grinder, the gas gun grinder, and the laser grinder. Assume the required removal times are T1, T2, and T3 respectively. Then, based on these three removal times, the target device for defect removal can be determined from the grinding wheel grinder, the gas gun grinder, and the laser grinder.

[0062] In a possible implementation manner, determining the target device for defect removal based on multiple removal times and at least one initial defect removal device includes:

[0063] Obtain the fitness of at least one initial defect removal device with respect to the defect type.

[0064] Based on the fitness, in combination with multiple removal times, determine the target device for defect removal.

[0065] In the embodiments of the present application, the fitness is used to measure the suitability of the initial defect removal device for removing the defects of the raw steel billet of the defect type. For example, it can be understood as the suitability of the grinding wheel grinder, the gas gun grinder, and the laser grinder for removing the leaf-shaped scab respectively. This fitness can be configured by the user and input into the terminal.

[0066] Among them, the target device for defect removal can be the initial defect removal device with the highest fitness for removing the defect type and a shorter removal time, or the initial defect removal device with the shortest removal time and a higher fitness. That is, when determining the target device for defect removal, the judgment priority of the fitness and the removal time can be set by the user independently, and the present application does not make any limitations in this regard.

[0067] In a possible implementation manner, determining the target device for defect removal based on multiple removal times and at least one initial defect removal device further includes:

[0068] Correspondingly display multiple removal times and at least one initial defect removal device on the display screen of the terminal for the user to view.

[0069] Based on the initially selected defect removal device by the user, determine the target device for defect removal.

[0070] Step 104, control the target device to perform the defect removal operation.

[0071] In the embodiments of the present application, controlling the target device to perform the defect removal operation may refer to controlling the target device to perform the defect removal operation according to the removal time corresponding to the target device and the defect position obtained from the image acquisition information.

[0072] In a possible implementation manner, before controlling the target device to perform the defect removal process, it further includes:

[0073] According to the image acquisition information, obtain the thickness information of each position on the raw steel billet;

[0074] According to the thickness information, obtain the position information for defect removal;

[0075] Correspondingly, controlling the target device to perform the defect removal operation includes:

[0076] Based on the position information for defect removal, control the target device to perform the defect removal operation at the position for defect removal.

[0077] In the embodiments of the present application, according to the thickness information, obtaining the position information for defect removal may refer to selecting the positions that are different from the thickness information of other positions from the thickness information of each position, and determining them as the positions for defect removal. For example, among the thickness information of each position, if there are two positions that are different from the thickness information of other positions, then these two positions can be determined as the defect removal positions, and then based on the position information for defect removal (which may refer to coordinates), control the target device to perform the defect removal operation at the position for defect removal.

[0078] In a possible implementation manner, the raw material defect removal method further includes:

[0079] According to the comparison result between the image acquisition information and the image information corresponding to each image in the steel billet database, when it is determined that the raw steel billet has defects, give a voice alarm prompt.

[0080] It should be understood that a voice alarm prompt is given to prompt the user to check the defects of the raw steel billet.

[0081] See Figure 2 , which shows an example diagram of an application scenario of the raw material defect removal method. The raw material defect removal method in the present application will be described below for this application scenario.

[0082] First, when the raw steel billet enters the production line, a high-pressure water dephosphorization machine is first used to remove the iron oxide scale on the surface of the raw steel billet. After removing the iron oxide scale on the surface, the camera installed on the production line is used to collect the image of the raw steel billet after passing through the high-pressure water dephosphorization machine, and the image collection information is obtained. According to the comparison result between the image collection information and the image information corresponding to each image in the steel billet database, the defect type and defect shape of the raw steel billet at this time are determined. If it is determined that there is no defect in the raw steel billet after passing through the high-pressure water dephosphorization machine, the process can be directly terminated. If the target device is determined to be a grinding wheel grinder based on the defect type and defect shape, the grinding wheel grinder is used to remove defects from the raw steel billet. After the defect removal operation is completed, another camera installed on the production line is used to capture an image of the steel billet after it passes through the grinding wheel grinder to obtain image acquisition information. The defect type and defect shape of the raw steel billet at this time are determined based on the comparison result between the image acquisition information and the image information corresponding to each image in the steel billet database. At this time, it is determined that the raw steel billet has no defects after passing through the grinding wheel grinder. The high-pressure water dephosphorization machine is used again to remove the iron oxide scale on the surface of the raw steel billet. If the captured image after passing through the high-pressure water dephosphorization machine again has no defects, the raw material defect removal process is terminated. If the captured image after passing through the high-pressure water dephosphorization machine again still has defects, the above process is continued until the defects of the raw steel billet are completely removed and the process is terminated.

[0083] It should be understood that the choice of defect removal equipment for defect removal after high-pressure water dephosphorization machine can be determined according to the actual application situation and the defect type and shape, and this application does not limit this.

[0084] In the embodiment of the present application, its steel production line includes at least one defect removal device, and the operation process of the raw steel billet after passing through each defect removal device is the same as the following process. First, the image acquisition information of the raw steel billet after passing through a defect removal device is obtained. Secondly, since the steel billet database includes steel billet images corresponding to different defect types, the defect type and defect shape of the raw steel billet can be determined according to the comparison result between the image acquisition information and the image information corresponding to each image in the steel billet database. Finally, according to the defect type and defect shape of the raw steel billet, the target device for defect removal can be determined, and the target device is controlled to perform the defect removal operation, so as to remove the defects on the raw steel billet, improve the yield rate of steel production, and reduce the economic losses caused by defects in the finished steel.

[0085] See also Figure 3 , shows a schematic flow chart of a method for removing raw material defects provided in Example 2 of the present application. Figure 3 As shown, the raw material defect removal method may include the following steps:

[0086] Step 301: Obtain the image acquisition information of the raw steel billet after passing through a defect removal device.

[0087] Step 301 of this embodiment is the same as step 101 of the foregoing embodiment and can be referred to each other. This embodiment will not be elaborated herein.

[0088] Step 302: Input the image acquisition information into the defect prediction model.

[0089] In the embodiment of the present application, the input of the defect prediction model can be the image acquisition information of the raw steel billet or the acquired image of the raw steel billet.

[0090] Step 303: Based on the image features, the defect prediction model outputs the defect type and defect shape of the raw steel billet.

[0091] In the embodiment of the present application, the defect prediction model is obtained by training a neural network with a training data set composed of steel billet images corresponding to different defect types. When training the neural network, the true defect type of the steel billet image is used as a label. Based on the image features of the steel billet image and the untrained neural network, the predicted defect type of the steel billet image is obtained. According to the loss value between the predicted defect type and the true defect type of the steel billet image, the neural network is trained. When the loss value meets the set requirements, the weight value of the neural network is obtained, and the trained prediction model is obtained.

[0092] It should be understood that the image features of the steel billet image can include color features, texture features, shape features, etc. The defect prediction model can determine and output the defect type and defect shape of the raw steel billet according to the above image features in the acquired image corresponding to the raw steel billet, and the defect shape can be obtained by extracting the shape features in the image features.

[0093] It should also be understood that the neural network model can predict the weights of each image feature, determine the importance of each image feature, and predict the defect type and defect shape of the raw steel billet based on the image features with higher importance, making the prediction more accurate.

[0094] Step 304: Determine the target device for defect removal according to the defect type and defect shape of the raw steel billet.

[0095] Step 305: Control the target device to perform the defect removal operation.

[0096] Steps 304-305 of this embodiment are the same as steps 103-104 of the foregoing embodiment and can be referred to each other. This embodiment will not be elaborated herein.

[0097] Compared with the first embodiment, the defect prediction model is obtained by training a neural network with a training data set composed of bloom images corresponding to different defect types respectively. During the training process, the importance of each image feature can be determined, and based on the image features with higher importance, the defect type and defect shape of the raw bloom can be predicted, making the predicted type and shape more accurate, thereby improving the accuracy of removing raw material defects.

[0098] See Figure 4 , which shows a schematic structural diagram of a raw material defect removal device provided in the third embodiment of the present application. For the sake of simplicity, only the parts related to the embodiments of the present application are shown.

[0099] The raw material defect removal device may specifically include the following modules:

[0100] An image acquisition module 401, configured to acquire image acquisition information of a raw bloom after passing through a defect removal device;

[0101] A defect determination module 402, configured to determine the defect type and defect shape of the raw bloom according to the comparison result between the image acquisition information and the image information corresponding to each image in the bloom database, where the bloom database includes bloom images corresponding to different defect types respectively;

[0102] A device determination module 403, configured to determine a target device for defect removal according to the defect type and defect shape of the raw bloom, where the target device is one of at least one defect removal device;

[0103] A control module 404, configured to control the target device to perform a defect removal operation.

[0104] In the embodiment of the present application, the device determination module 403 may specifically include the following sub-modules:

[0105] A screening sub-module, configured to screen at least one initial defect removal device corresponding to the defect type from all defect removal devices according to the defect type of the raw bloom;

[0106] A removal time determination sub-module, configured to obtain the removal time required for each of at least one initial defect removal device to remove the defect of the defect shape according to the volume information corresponding to the defect shape of the raw bloom and at least one initial defect removal device corresponding to the defect type;

[0107] A target device determination sub-module, configured to determine the target device for defect removal according to multiple removal times and at least one initial defect removal device.

[0108] In the embodiment of the present application, the target device determination sub-module may specifically include the following units:

[0109] An adaptability acquisition unit is configured to acquire the adaptability between at least one initial defect removal device and a defect type, where the adaptability is used to measure the suitability of the initial defect removal device for removing the raw billet defects of the defect type.

[0110] A device determination unit is configured to determine a target device for defect removal based on the adaptability and in combination with multiple removal times.

[0111] In an embodiment of the present application, when the billet database further includes standard shapes corresponding to different models of billets, the defect determination module 402 may specifically include the following sub-modules:

[0112] A comparison sub-module is configured to compare the image acquisition information with the image information corresponding to each image in the billet database.

[0113] An image similarity acquisition sub-module is configured to acquire the image similarity between the image acquisition information and the image information corresponding to each image in the billet database, and obtain multiple image similarities.

[0114] A similarity judgment sub-module is configured to determine that the defect type of the image corresponding to the maximum similarity is the defect type of the raw billet, and compare the raw billet with the corresponding standard shape to obtain the defect shape of the raw billet.

[0115] In an embodiment of the present application, the raw material defect removal device may specifically further include the following modules:

[0116] A model prediction module is configured to input the image acquisition information into a defect prediction model, where the defect prediction model is obtained by training a neural network with a training data set composed of billet images corresponding to different defect types, and the defect prediction model is used to extract image features from the image acquisition information.

[0117] Correspondingly, the defect determination module 402 may specifically further include the following sub-modules:

[0118] A model output sub-module is configured to output the defect type and defect shape of the raw billet based on the image features by the defect prediction model.

[0119] In an embodiment of the present application, the raw material defect removal device may specifically further include the following modules:

[0120] A thickness information acquisition module is configured to acquire the thickness information of each position on the raw billet according to the image acquisition information.

[0121] A position information acquisition module is configured to acquire the position information of defect removal according to the thickness information.

[0122] Correspondingly, the control module may specifically include the following sub-modules:

[0123] An execution sub-module, configured to control a target device to perform a defect removal operation at a defect removal position based on the defect removal position information.

[0124] In the embodiment of the present application, the raw material defect removal device may specifically further include the following modules:

[0125] An alarm module, configured to perform a voice alarm prompt when it is determined that there is a defect in the raw material billet according to the comparison result between the image acquisition information and the image information corresponding to each image in the billet database.

[0126] The raw material defect removal device provided in the embodiment of the present application can be applied to the foregoing method embodiment. For details, refer to the description of the foregoing method embodiment, which will not be repeated here.

[0127] Figure 5 It is a schematic structural diagram of a terminal provided in Embodiment 4 of the present application. As Figure 5 shown, the terminal 500 of this embodiment includes: at least one processor 510 ( Figure 5 only one is shown in the figure), a processor, a memory 520, and a computer program 521 stored in the memory 520 and executable on the at least one processor 510. When the processor 510 executes the computer program 521, the steps in the foregoing method embodiment of the raw material defect removal method are implemented.

[0128] The terminal 500 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal may include, but is not limited to, a processor 510 and a memory 520. Those skilled in the art can understand that Figure 5 merely an example of the terminal 500, which does not constitute a limitation on the terminal 500, and may include more or fewer components than shown in the figure, or combine some components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0129] The so-called processor 510 may be a central processing unit (CPU), and this processor 510 may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0130] In some embodiments, the memory 520 may be an internal storage unit of the terminal 500, such as the hard disk or memory of the terminal 500. In other embodiments, the memory 520 may also be an external storage device of the terminal 500, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc., equipped on the terminal 500. Further, the memory 520 may also include both the internal storage unit of the terminal 500 and external storage devices. The memory 520 is used to store an operating system, application programs, a BootLoader, data, and other programs, such as the program code of the computer program, etc. The memory 520 may also be used to temporarily store data that has been output or will be output.

[0131] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0132] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0133] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0134] In the embodiments provided in the present application, it should be understood that the disclosed device / terminal and method can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, 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 displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in electrical, mechanical or other forms.

[0135] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0136] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0137] 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, to implement all or part of the processes in the above-mentioned embodiment methods of the present application, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0138] The implementation of all or part of the processes in the method of the above embodiments in this application can also be completed by a computer program product. When the computer program product runs on a terminal, the terminal can execute the steps in the above method embodiments when executed.

[0139] The above embodiments are only used to illustrate the technical solutions of the present application, rather than limiting them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for removing raw material defects in a steel production line, characterized in that, the steel production line includes at least one defect removal device, and each defect removal device is used to remove the defects existing on the raw steel billet. The raw material defect removal method includes: Obtaining the image acquisition information after the raw steel billet passes through a defect removal device; According to the comparison result between the image acquisition information and the image information corresponding to each image in the steel billet database, determining the defect type and defect shape of the raw steel billet. The steel billet database includes steel billet images corresponding to different defect types; According to the defect type and defect shape of the raw steel billet, determining the target device for defect removal, and the target device is one of the at least one defect removal device; Controlling the target device to perform defect removal operations; The determining the target device for defect removal according to the defect type and defect shape of the raw steel billet includes: According to the defect type of the raw steel billet, screening at least one initial defect removal device corresponding to the defect type from all defect removal devices; According to the volume information corresponding to the defect shape of the raw steel billet and the at least one initial defect removal device corresponding to the defect type, obtaining the removal time required for each of the at least one initial defect removal device to remove the defect of the defect shape; According to the multiple removal times and the at least one initial defect removal device, determining the target device for defect removal; The determining the target device for defect removal according to the multiple removal times and the at least one initial defect removal device includes: Obtaining the adaptability of the at least one initial defect removal device to the defect type, and the adaptability is used to measure the suitability of the initial defect removal device to remove the defects of the raw steel billet of the defect type; Based on the adaptability and in combination with the multiple removal times, determining the target device for defect removal.

2. The raw material defect removal method according to claim 1, characterized in that, the steel billet database further includes the standard shapes corresponding to different models of steel billets. The determining the defect type and defect shape of the raw steel billet according to the comparison result between the image acquisition information and the image information corresponding to each image in the steel billet database includes: Comparing the image acquisition information with the image information corresponding to each image in the steel billet database; Obtaining the image similarity between the image acquisition information and the image information corresponding to each image in the steel billet database, and obtaining multiple image similarities; Determining that the defect type of the image corresponding to the maximum similarity is the defect type of the raw steel billet, and comparing the raw steel billet with the corresponding standard shape to obtain the defect shape of the raw steel billet.

3. The raw material defect removal method according to claim 1, characterized in that, before determining the defect type and defect shape of the raw steel billet according to the comparison result between the image acquisition information and the image information corresponding to each image in the steel billet database, further includes: Input the image acquisition information into a defect prediction model, which is obtained by training a neural network with a training data set composed of bloom images corresponding to different defect types, and the defect prediction model is used to extract image features from the image acquisition information; Correspondingly, the determining of the defect type and defect shape of the raw bloom according to the comparison result between the image acquisition information and the image information corresponding to each image in the bloom database includes: Outputting the defect type and defect shape of the raw bloom by the defect prediction model based on the image features.

4. The raw material defect removal method according to claim 1, wherein, before controlling the target device to perform defect removal processing, it further includes: Obtaining the thickness information of each position on the raw bloom according to the image acquisition information; Obtaining the position information for defect removal according to the thickness information; Correspondingly, the controlling the target device to perform defect removal operations includes: Based on the position information for defect removal, controlling the target device to perform defect removal operations at the positions for defect removal.

5. The raw material defect removal method according to claim 1, wherein, it further includes: When it is determined that the raw bloom has defects according to the comparison result between the image acquisition information and the image information corresponding to each image in the bloom database, a voice alarm prompt is given.

6. A raw material defect removal device for a steel production line, wherein, the raw material defect removal device includes: An image acquisition module, configured to acquire image acquisition information of a raw bloom after passing through a defect removal device; A defect determination module, configured to determine the defect type and defect shape of the raw bloom according to the comparison result between the image acquisition information and the image information corresponding to each image in the bloom database, and the bloom database includes bloom images corresponding to different defect types; A device determination module, configured to determine a target device for defect removal according to the defect type and defect shape of the raw bloom, and the target device is one of at least one defect removal device; A control module, configured to control the target device to perform defect removal operations; The device determination module includes: A screening sub-module, configured to screen at least one initial defect removal device corresponding to the defect type from all defect removal devices according to the defect type of the raw bloom; A removal time determination sub-module, configured to obtain the removal time required for each of the at least one initial defect removal device to remove the defect of the defect shape according to the volume information corresponding to the defect shape of the raw bloom and the at least one initial defect removal device corresponding to the defect type; A target device determination sub-module, configured to determine the target device for defect removal according to the multiple removal times and the at least one initial defect removal device; The target device determination sub-module includes: An adaptability acquisition unit, configured to acquire the adaptability between the at least one initial defect removal device and the defect type, where the adaptability is used to measure the suitability of the initial defect removal device for removing the raw steel billet defects of the defect type; A device determination unit, configured to determine a target device for defect removal based on the adaptability and in combination with the multiple removal times.

7. A terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images