Steel material determination device, trained model generation method, steel material determination method, and steel material manufacturing method

Abstract

To provide a steel material determination device capable of generating and using a learned model that appropriately excludes disturbance to precisely determine characteristics of the steel material by performing image processing in advance on a spark image to be used when generating a learned model to be used when determining characteristics of the steel material and when determining the steel material by actually using the learned model, a method for generating the learned model, a method for determining the steel material, and a method for manufacturing the steel material.SOLUTION: A steel material determination device includes: an image processing unit 22 for extracting only a spark image from image data including a spark generated when grinding a steel material S acquired by an imaging device C; and a determination unit 25 for determining the steel material indicated by the spark image by applying the spark image after image processing by the image processing unit 22 as inference data to a learned model prepared in advance.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] Embodiments of the present invention relate to a steel material determination device, a method for generating a steel type trained model, a steel material determination method, and a method for manufacturing steel material. [Background technology]

[0002] For example, when manufacturing and shipping pipe-shaped steel materials, in order to prevent steel materials of different properties (foreign materials) from being mixed in and shipped, a so-called spark test is conducted in which an operator checks for the presence of foreign materials by observing sparks that are generated when a grinder is brought into contact with the end of the steel material.

[0003] The spark test involves visually checking for sparks that are generated when the edge of a steel material is ground, because it is empirically known that the shape and quantity of flying sparks, such as the number of spark explosions and the number of streamlines, change depending on the chemical composition of the steel material.

[0004] However, the spark test is a sensory test that depends on the skill of the operator, and the skills must be passed on to continue performing the spark test. In addition, some customers of these steel products may require that the spark test be performed on all steel products they deliver.

[0005] As a method for automatically performing a spark test, for example, the technology described in Patent Document 1 below is disclosed. Patent Document 1 discloses a device that estimates the composition of steel material from image data using a trained model for estimating the composition of steel material. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Publication No. 2020-009435 Summary of the Invention [Problem to be solved by the invention]

[0007] However, in the device for estimating the composition of steel materials described in Patent Document 1, the image data on which the estimation is based is the data generated by the camera itself, and no image processing is performed. Therefore, there is a possibility of disturbances such as differences in the brightness of the lighting at the shooting location, background equipment being reflected in the image, or background equipment reflecting light from lighting or sparks, which may be mistakenly recognized as part of the sparks.

[0008] If such uncertain data due to disturbances is used, it is inappropriate to use it for estimating the composition of steel material, and it is thought that the accuracy of the judgment will be reduced. Furthermore, even if a trained model is constructed using such data, the accuracy of the trained model itself is low, so the accuracy of the judgment will also inevitably be low.

[0009] The present invention has been made with a focus on the points mentioned above, and aims to provide a steel material determination device, a method for generating a trained model, a steel material determination method, and a method for manufacturing steel material that can accurately determine the characteristics of steel material by performing image processing in advance on spark images that are used when generating a trained model to be used when determining the characteristics of steel material or when actually using the trained model to determine steel material, thereby generating and utilizing a trained model that appropriately eliminates disturbances. [Means for solving the problem]

[0010] The steel material determination device according to the embodiment of the present invention is configured to obtain image data including sparks generated when grinding a steel material, the image data being obtained by an imaging device. For the color determined for each pixel, a threshold value based on a gradation that is set in advance for each color is used to perform image processing to separate the sparks from other components in the image data, The system is equipped with a determination unit that uses the spark image after image processing as inference data and applies it to a pre-prepared trained model to determine the steel material indicated by the spark image.

[0012] The steel material determination device in an embodiment of the present invention further includes a learning unit that uses the spark image after image processing as input data and the characteristics of the steel material as training data to generate a trained model through machine learning to determine the steel material indicated by the spark image.

[0013] The method for generating a trained model according to an embodiment of the present invention includes the steps of acquiring image data including sparks generated when grinding steel material, which is acquired by an imaging device, and performing processing on the image data. Execute image processing to separate sparks from other components in the image data using a threshold value based on gradation that is set in advance for each color, for a color determined for each pixel of the image data; The method includes the steps of acquiring a spark image after image processing, and using the spark image after image processing as input data and the characteristics of the steel material as training data, to generate a trained model through machine learning that determines the steel material indicated by the spark image.

[0014] The step of performing image processing in the method for generating a trained model in an embodiment of the present invention involves extracting only sparks from image data through image processing to create a spark image after image processing.

[0015] The steel material determination method according to the embodiment of the present invention includes the steps of acquiring image data including sparks generated when grinding a steel material, which image data is acquired by an imaging device, and Execute image processing to separate sparks from other components in the image data using a threshold value based on gradation that is set in advance for each color, for a color determined for each pixel of the image data; The method includes the steps of acquiring a spark image after image processing, and determining the steel material indicated by the spark image using a trained model generated by machine learning, with the spark image after image processing as input data and the characteristics of the steel material as training data.

[0016] In the step of performing image processing in the steel material determination method according to the embodiment of the present invention, only sparks are extracted from the image data by image processing to produce a spark image after image processing.

[0017] A method for manufacturing a steel material according to an embodiment of the present invention includes the steps of: acquiring image data including sparks generated when grinding a steel material, the image data being acquired by an imaging device; Execute image processing to separate sparks from other components in the image data using a threshold value based on gradation that is set in advance for each color, for a color determined for each pixel of the image data;The steel material determination method includes the steps of acquiring a spark image after image processing, and determining the steel material indicated by the spark image using a trained model generated by machine learning, with the spark image after image processing as input data and the characteristics of the steel material as training data. [Effects of the Invention]

[0018] With the steel material determination device, trained model generation method, steel material determination method, and steel material manufacturing method according to the embodiments of the present invention, by performing image processing in advance on the spark images used when generating the trained model used to determine the characteristics of steel material or when actually using the trained model to determine steel material, it is possible to generate and use a trained model that appropriately eliminates external disturbances, thereby enabling the characteristics of steel material to be determined with high accuracy. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is an explanatory diagram showing an entire apparatus for discriminating steel materials from the characteristics of the steel materials, including a steel material determination device according to an embodiment of the present invention; [Figure 2] 2 is a block diagram showing the internal configuration of a control device provided in the steel material determination device according to the embodiment of the present invention. FIG. [Figure 3] 1 is a spark image used in an embodiment of the present invention, showing the spark image before image processing in the image processing unit. [Figure 4] 10 is a spark image used in an embodiment of the present invention, showing the spark image after image processing in an image processing unit. [Figure 5] 1 is a flowchart showing the flow of machine learning to generate a trained model used by a steel material determination device to determine steel material in an embodiment of the present invention. [Figure 6] 3 is a flowchart showing an inference flow for determining a steel material by the steel material determination device according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0020] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. Fig. 1 is an explanatory diagram showing an entire device for discriminating a steel material S from the characteristics of the steel material S, including a steel material determination device 1 according to an embodiment of the present invention.

[0021] The steel material S is identified based on a spark image obtained by photographing the shape of sparks F generated when the end of the steel material S is ground with a grinder G using an imaging device C. As mentioned above, the shape of the sparks changes depending on the component composition; for example, the number of spark explosions and the number of streamlines increases as the carbon content increases. Therefore, it is possible to identify the steel material S by looking at the shape of the sparks.

[0022] In addition, the location where the steel material S is ground by the grinder G, i.e., the location where the spark image is captured by the imaging device C, may be, for example, in the middle of the production line, or may be a location specifically set up for identifying the steel material S.

[0023] The imaging device C is, for example, a camera that captures spark images. The imaging device C used in the embodiment of the present invention is configured to be able to capture monochrome images or color images. Therefore, what is sent to the control device 2 of the steel product determination device 1, which will be described later, is image data of monochrome or color images of sparks. It is possible to arbitrarily select whether to use monochrome or color images. Furthermore, although not shown, auxiliary equipment, such as a strobe, may be combined to capture spark images more clearly. 。

[0024] In Figure 1, the imaging device C is located below the grinder G, in a position that allows it to photograph the sparks F from below, but it may be located in any position as long as it can acquire a spark image sufficient to be used to determine the steel material S.

[0025] Data of the spark images captured by the imaging device C is transmitted to a steel material determination device 1 connected to the imaging device C. The steel material determination device 1 controls the imaging device C, and is a device that uses the spark image data acquired by the imaging device C to generate a trained model for identifying the steel material S, and then uses the generated trained model to identify the steel material S.

[0026] Fig. 2 is a block diagram showing the internal configuration of the control device 2 provided in the steel material determination device 1 according to the embodiment of the present invention. Note that the control device 2 shown in Fig. 2 only shows functions related to the generation of a trained model used when determining the steel material S, which will be described below, and the determination of the steel material S, and various other functions are not shown.

[0027] Therefore, the control device 2 may have various configurations not shown in FIG. 2, such as a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), and input / output interfaces connected via a bus.

[0028] That is, the input / output interface may be connected to, for example, an input unit for inputting various parameters required when generating a trained model used to discriminate steel material S, a display unit that shows the operator the steel type of the discriminated steel material S as a result of the judgment, or a communication control unit that controls communication with other devices.

[0029] The control device 2 includes an information acquisition unit 21, an image processing unit 22, a learning unit 23, a memory unit 24, a determination unit 25, and a determination result notification unit 26. The information acquisition unit 21 acquires, from an imaging device C, data on spark images generated when the steel material S is ground.

[0030] The spark image data may be acquired directly from the imaging device C, or may be temporarily stored in a database or the like (not shown in FIG. 2) and then acquired at a preset timing.

[0031] The image processing unit 22 performs image processing on the spark image data acquired via the information acquisition unit 21. The reason for performing image processing on the spark image data here is to remove any disturbances that may be contained in the data that are unnecessary for identifying the steel material S. If the spark image contains disturbances, this will reduce the accuracy of the trained model that was generated using the spark image data as input data, and will also reduce the accuracy of steel material identification when an identification process is actually performed using the trained model. For this reason, it is necessary to perform image processing on the spark image data to remove the disturbances.

[0032] Specifically, the image processing unit 22 can perform processing using a variety of methods, but in this embodiment of the present invention, for example, the following processing is performed. First, binarization processing is performed based on the acquired spark image data. Binarization processing is an image processing method that converts the target image into only two colors, white and black, for each pixel, using a certain threshold as a reference. By performing this processing, it is possible to separate the target spark from the rest of the background and eliminate background disturbances.

[0033] In the image data, a color is determined for each pixel. If the spark image data is grayscale, each pixel contains only one type of information, that is, luminosity, and is therefore represented, for example, in 256 gradations from white to black. On the other hand, as described above, if the imaging device C acquires a color image, each pixel can be represented in 256 gradations for each of the RGB colors.

[0034] Therefore, in image processing when the acquired image is a color image, for example, upper and lower thresholds are set in advance for each RGB of each pixel, and pixels that fall within the thresholds are marked white, and pixels that fall outside the thresholds are marked black.

[0035] For example, when we look at the color of sparks, they are mainly expressed in colors such as red (R:255, G:0, B:0), orange (R:255, G:60-170, B:0), and yellow (R:255, G:255, B:0). On the other hand, reflected light, which may be reflected in something other than sparks, is often white (R:255, G:255, B:255).

[0036] Therefore, for example, the upper threshold for "B" among RGB is changed to set the threshold so that white or near-white colors are not extracted. By setting it in this way, it is possible to eliminate disturbances other than sparks, such as background equipment that may be reflected in the spark image data, making it easier to extract only sparks from the obtained spark image data.

[0037] FIG. 3 shows a spark image BF before image processing in the image processing unit 22, and FIG. 4 shows a spark image AF after image processing, with respect to a spark image used in the embodiment of the present invention.

[0038] In addition to the spark F, the spark image BF shown in Fig. 3 also shows the background equipment B at the bottom of the image. By performing the image processing described above on the spark image BF in the image processing unit 22, the spark image AF shown in Fig. 4 is acquired.

[0039] As shown in spark image AF in Fig. 4, the lower region of spark image BF, where background equipment B was shown, is shown in black, and background equipment B is not shown in spark image AF. Therefore, only the image of the sparks is extracted.

[0040] As described above, there is an image processing method in which only sparks are extracted by performing binarization processing in the image processing unit 22, but as described above, methods that can be adopted as image processing methods are not limited to this method.

[0041] For example, when using a threshold value to distinguish between sparks and non-sparks, it is possible to process the extracted spark image as it is, and change the non-spark parts to a color that can be distinguished from sparks, such as black. That is, particularly when the image acquired by the imaging device C is a color image, it is possible to leave the color as it is, without performing processing such as binarization, in which the spark parts are displayed in white, and to perform color conversion processing only on the disturbance parts other than sparks. In this case, the color of the sparks is also trained into the trained model as data indicating the characteristics of the steel material S, so it is possible to generate a trained model with higher accuracy.

[0042] By performing such processing, it is possible to extract only the spark portion with the same degree of certainty as when performing binarization processing, and the load on the image processing unit 22 when performing image processing is reduced, allowing for faster processing.

[0043] The learning unit 23 generates, by machine learning, a trained model to be used when discriminating the steel material S. That is, in generating the trained model, the learning unit 23 uses, as input data, data of the spark image acquired by the information acquisition unit 21 and after image processing by the image processing unit 22.

[0044] On the other hand, the training data is data that indicates the characteristics of the steel material S to be discriminated. Examples of the data that indicates the characteristics of the steel material S that serve as training data include the steel type (standard) and components of the steel material S. Furthermore, examples of the components that indicate the characteristics of the steel material S include the carbon content and alloy elements.

[0045] The teacher data may be acquired from a storage unit 24 of the steel material determination device 1, which will be described later, or may be acquired from a database or the like to which the steel material determination device 1 is separately connected.

[0046] The learning unit 23 uses the spark image data after image processing as input data and the data indicating the characteristics of the steel material S as training data to generate a trained model by machine learning. A machine learning algorithm is used to generate the trained model. Examples of machine learning algorithms that can be used include neural networks, decision tree learning, random forests, and support vector regression.

[0047] The trained model generated (constructed) by the training unit 23 is stored in the storage unit 24, for example, and is used when the determination unit 25, which will be described next, performs a discrimination process for the steel material S.

[0048] Here, the storage unit 24 is configured, for example, by a semiconductor or a magnetic disk, and stores the above-described generated trained model, a program for controlling the steel material determination device 1, and the like.

[0049] As shown in Figure 3, the control device 2 in this embodiment of the present invention is described assuming that it has a memory unit 24 installed inside it, but the memory unit 24 does not have to be installed inside the control device 2, and for example, an external database connected to the steel product judgment device 1 may perform its function, and the configuration can be freely selected.

[0050] The determination unit 25 uses the trained model to identify the steel material S. That is, the determination unit 25 performs inference using the trained model stored in the storage unit 24, with the spark image data acquired from the imaging device C as inference data. Note that the spark image used as inference data is the spark image data after image processing by the image processing unit 22.

[0051] Then, when inference is executed in the determination unit 25, a determination is made for each steel material S regarding characteristics such as the steel type (standard) and components of the steel material S. The determination result is transmitted to the determination result notification unit 26. The determination result notification unit 26 notifies the operator of the result determined by the determination unit 25 via, for example, a display unit or the like.

[0052] [Operation] Next, a flow of generating a trained model in the control device 2 and a flow of determining the steel material S using the generated trained model will be described with reference to FIGS. 5 and 6.

[0053] First, the flow of generating a trained model is shown in Fig. 5. Fig. 5 is a flowchart showing the flow of machine learning for generating a trained model used by the steel material determination device 1 when determining the steel material S in the embodiment of the present invention.

[0054] The information acquisition unit 21 of the control device 2 acquires data of a spark image that is generated when the grinder G comes into contact with the end of the steel material S, which is photographed by the imaging device C (ST1). The acquired spark image data includes not only the spark image but also data about disturbances such as background equipment.

[0055] Such spark image data is transmitted from the information acquisition unit 21 to the image processing unit 22, where image processing is performed (ST2). The image processing unit 22 performs image processing such as binarization as described above, removes disturbances, and generates an image containing only the image of the sparks. The spark image after image processing is used as input data in the learning unit 23 when a trained model is generated.

[0056] Furthermore, the information acquiring unit 21 acquires data indicating the characteristics of the steel material S, which serves as training data (ST3). As described above, the training data may be acquired, for example, from a database (not shown) connected to the control device 2.

[0057] The control device 2 now has the data necessary to generate a trained model. The learning unit 23 then performs machine learning using the spark image after image processing as input data and data indicating the characteristics of the steel material S as training data (ST4). The model obtained as a result of the machine learning is then stored in the storage unit 24 as a trained model (ST5).

[0058] This completes the learning stage in the control device 2. Next, the flow of the inference process (determination process) for the steel material S using the generated trained model will be described. Fig. 6 is a flowchart showing the flow of inference for determining a steel material by the steel material determination device 1 in the embodiment of the present invention.

[0059] The control device 2 first acquires, via the information acquisition unit 21, data that will be the basis of inference data used to determine the steel material S (ST11). This data is the spark image data acquired by the imaging device C itself, and has not been subjected to any image processing.

[0060] Next, the information acquisition unit 21 sends the acquired spark image data to the image processing unit 22. The image processing unit 22 executes image processing on the spark image data (ST12). The spark image after the image processing in the image processing unit 22 is used as inference data.

[0061] The determination unit 25 uses the data of the spark image after image processing as inference data and performs a determination process on the steel material S that is the subject of the spark image using the trained model acquired by accessing the storage unit 24 (ST13, ST14). The determination result is transmitted from the determination unit 25 to the determination result notification unit 26, and is notified to, for example, an operator (ST15).

[0062] As explained above, in both the process of generating a trained model and the process of determining steel materials using the trained model, the spark image data acquired by the imaging device C is not used as is, but is image processed to remove information that could be a disturbance, leaving only the spark image data. By using such image-processed spark images as input data in machine learning or as inference data in inference processing, it is possible to generate and use a trained model from which disturbances have been appropriately removed, thereby enabling the characteristics of steel materials to be determined with high accuracy.

[0063] The embodiments of the present invention described above are merely examples of the present invention. Various modifications and improvements can be made to these embodiments, and such modifications and improvements are also included in the present invention. These embodiments and their modifications are intended to be included within the scope and spirit of the inventions, as well as within the scope of the claims and their equivalents. [Explanation of symbols]

[0064] 1 Steel material determination device 2 Control device 21 Information Acquisition Department 22 Image processing section 23 Learning Department 24 Memory section 25 Judgment section 26 Judgment result notification unit C. Imaging device G Grinder S steel material

Claims

1. an image processing unit that performs image processing for separating the sparks from other components in the image data, using a threshold value based on gradation that is set in advance for each color, on a color determined for each pixel of image data including sparks generated when grinding steel material, acquired by an imaging device, and extracts a spark image after image processing; a determination unit that determines the steel material indicated by the spark image by using the spark image after image processing by the image processing unit as inference data and applying it to a trained model prepared in advance; A steel material determination device equipped with:

2. a learning unit that uses the spark image after image processing as input data and the characteristics of the steel material as training data to generate a trained model for determining the steel material indicated by the spark image by machine learning; The steel material determination device according to claim 1, further comprising:

3. The steel product determination device according to claim 2, characterized in that the learning unit performs machine learning using at least one machine learning algorithm selected from the group consisting of neural network, decision tree learning, random forest, and support vector regression.

4. acquiring image data including sparks generated when grinding the steel material, the image data being acquired by an imaging device; a step of executing image processing on the image data to separate the sparks from other components in the image data using a threshold value based on gradation that is set in advance for each color determined for each pixel of the image data, and acquiring a spark image after image processing; a step of generating a trained model by machine learning that determines the steel material indicated by the spark image using the spark image after image processing as input data and the characteristics of the steel material as training data; A method for generating a trained model, comprising:

5. The step of performing image processing includes: The method for generating a trained model according to claim 4, characterized in that only sparks are extracted from the image data by image processing to obtain the spark image after image processing.

6. The method for generating a trained model according to claim 4 or claim 5, characterized in that the machine learning uses at least one machine learning algorithm from among neural networks, decision tree learning, random forests, and support vector regression.

7. acquiring image data including sparks generated when grinding the steel material, the image data being acquired by an imaging device; a step of executing image processing on the image data to separate the sparks from other components in the image data using a threshold value based on gradation that is set in advance for each color determined for each pixel of the image data, and acquiring a spark image after image processing; a step of determining the steel material indicated by the spark image using a trained model generated by machine learning, with the spark image after image processing as input data and the characteristics of the steel material as training data; A steel material determination method comprising:

8. The step of performing image processing includes:

8. The steel material determination method according to claim 7, wherein only sparks are extracted from the image data by image processing, and the spark image after image processing is used.

9. A method for manufacturing a steel product, comprising the steel product determination method according to claim 7 or 8.

Images