JP7673695B2 - Method for determining whether a steel plate can be threaded through a straightening machine, straightening method, manufacturing method, and method for generating a model for determining whether a steel plate can be threaded through a straightening machine - Google Patents

Description

The present invention relates to a method for determining whether a steel plate can be passed through a straightening machine, a straightening method, a manufacturing method, and a method for generating a model for determining whether a steel plate can be passed through a straightening machine.

In the manufacturing process of steel plates, if uneven cooling occurs in the steel plate when cooling the steel plate after hot rolling, it can cause deterioration of the flatness of the steel plate product, generation of camber due to residual stress, and variation in mechanical properties, so it is preferable to perform cooling as uniformly as possible. Therefore, the flatness of the steel plate may be corrected before cooling the steel plate after hot rolling. For example, when accelerating cooling of the steel plate after hot rolling in the manufacturing process of thick steel plate, the flatness of the steel plate may be corrected by a straightening machine such as a roller leveler before accelerated cooling in order to suppress the occurrence of uneven cooling. In addition, when manufacturing a relatively thick material such as a line pipe material in the manufacturing process of hot rolled steel plate, if the steel plate (sheet bar) after rough rolling has a warp, the passing of the plate in the finish rolling becomes unstable, so the flatness of the steel plate after rough rolling may be corrected before finish rolling. However, the steel plate after hot rolling often has a warp at the tip due to the temperature difference in the thickness direction. If there is a large warp at the tip of the steel plate, a problem may occur in which the steel plate does not bite into the straightening machine. Furthermore, if the leading edge of a steel sheet has an uneven planar shape such as a fishtail or tang shape, the steel sheet may collide with the straightening rolls when passing through the straightening machine, causing bending at the leading edge of the steel sheet and resulting in sheet passing defects. When such defects occur in the steel sheet's engagement with the straightening machine or in sheet passing defects, the efficiency of the subsequent cooling process and finish rolling process is hindered, resulting in significant opportunity loss.

In contrast, in the past, if the warp at the tip of a steel plate was judged to be large by visual inspection before it was passed through the straightener, the steel plate was stopped from passing through the straightener, and the steel plate was once reversed to the hot rolling mill, where the warp was straightened by the hot rolling mill, and then passed through the straightener again. In some cases, a knockdown roll arranged at the entry side of the straightener was used to give bending deformation to the tip of the steel plate before passing through the straightener. However, if an additional process is added before passing the steel plate through the straightener, the temperature of the steel plate will decrease during that time, and the cooling start temperature for accelerated cooling cannot be ensured, which will cause poor material quality of the steel plate product. Therefore, Patent Document 1 discloses a method of arranging a steel plate guide at the entry side of the straightener. It is said that this allows the steel plate to be stably inserted into the straightener even if the tip of the steel plate is warped. Patent Document 2 discloses an apparatus that has two guides divided along the conveying direction of the steel plate at the entry side of the straightener, and the position of the downstream guide is synchronized with the elevation of the straightening roll of the straightener. This is said to enable the steel plate to be stably engaged in the straightening machine even when the warp or thickness of the leading end of the steel plate varies. Patent Document 3 also discloses a method in which the roll thrust of the straightening machine is maintained in a state smaller than the desired roll thrust when the leading end of the steel plate is engaged in the straightening machine, and then the roll thrust is increased to the desired roll thrust. This is said to reduce the resistance acting on the steel plate when it is engaged in the straightening machine, and to prevent the steel plate from getting stuck.

Patent No. 5007697 Patent No. 5531772 JP 2003-117606 A

However, the method described in Patent Document 1 is for enabling the steel plate to be bitten into the straightener even when warpage occurs at the tip of the steel plate, and if the warpage at the tip of the steel plate becomes excessive, the occurrence of sheet threading failure cannot be suppressed. In addition, although Patent Document 1 describes the preferable conditions for the installation angle of the steel plate guide, it is difficult to completely prevent sheet threading failure at the tip of the steel plate. The method described in Patent Document 2 is similar, and although the preferable range of the installation angle of the guide to prevent sheet threading failure is described, the amount of warpage of the steel plate that can be threaded is not disclosed. In addition, it is not possible to determine in advance whether the steel plate can be threaded through the straightener when there is warpage at the tip of the steel plate. On the other hand, Patent Document 3 describes that the roll push amount of the straightener that allows the tip of the steel plate to be bitten is set from experiments and operation record data using the equipment specifications of the straightener and the dimensions of the steel plate as parameters. However, since the initial roll push amount is set regardless of the amount of warpage at the tip of the steel plate, it is difficult to completely prevent sheet threading failure at the tip of the steel plate. In addition, the amount of warping of steel plates that can be threaded is not disclosed, and if there is warping at the tip of the steel plate, it is not possible to determine in advance whether the steel plate can be threaded through the straightening machine.

The present invention has been made to solve the above problems, and its object is to provide a method for determining whether a steel plate can be passed through a straightening machine, which is capable of determining whether the steel plate can be passed through the straightening machine depending on the warped shape at the tip of the steel plate. Another object of the present invention is to provide a method for straightening a steel plate, which is capable of suppressing the occurrence of failures in passing the steel plate through the straightening machine. Still another object of the present invention is to provide a method for manufacturing a steel plate, which is capable of manufacturing a steel plate having excellent uniformity of material properties. Another object of the present invention is to provide a method for generating a model for determining whether a steel plate can be passed through a straightening machine, which is capable of generating a model for determining whether the steel plate can be passed through a straightening machine depending on the warped shape at the tip of the steel plate.

The method for determining whether a steel plate can be passed through a straightening machine according to the first aspect of the present invention is a method for determining whether a steel plate can be passed through a straightening machine in a steel plate manufacturing facility including a straightening machine having at least one pair of rolls, a conveying device for loading the steel plate into the straightening machine, and a warp shape measuring device for measuring the warp shape of the tip of the steel plate, and includes a warp shape measuring step for measuring the warp height and warp curvature of the tip of the steel plate using the warp shape measuring device before the steel plate is loaded into the straightening machine, and a passability determining step for determining whether the steel plate can be passed through the straightening machine based on the warp height and warp curvature of the tip of the steel plate measured in the warp shape measuring step.

The step of determining whether the steel plate can be passed through the straightening machine may include a step of determining whether the steel plate can be passed through the straightening machine based on one or more operational parameters selected from the warp height and warp curvature of the tip of the steel plate measured in the warp shape measurement step, as well as the thickness, width, length, and weight of the steel plate, and the speed at which the steel plate is fed into the straightening machine by the conveying device.

The steel plate manufacturing equipment may include a planar shape measuring device that measures the planar shape of the tip of the steel plate, and the step of determining whether the steel plate can be threaded may further include a step of determining whether the steel plate can be threaded through the straightening machine using the planar shape of the tip of the steel plate measured using the planar shape measuring device before the steel plate is loaded into the straightening machine.

The method for determining whether a steel plate can be passed through a straightening machine according to a second aspect of the present invention is a method for determining whether a steel plate can be passed through a straightening machine in a manufacturing facility including a straightening machine having at least one pair of rolls, a conveying device for loading the steel plate into the straightening machine, and a warp shape measuring device for measuring the warp shape of the tip of the steel plate, and includes a step of determining whether the steel plate can be passed through the straightening machine using a passing possibility determination model learned by machine learning, which includes as input data the warp height and warp curvature of the tip of the steel plate measured by the warp shape measuring device before being loaded into the straightening machine, and which uses as output data information on whether the steel plate can be passed through the straightening machine.

The method for straightening a steel plate according to the present invention includes a step of using the method for determining whether a steel plate can be threaded through a straightening machine according to the present invention to determine whether the steel plate can be threaded through the straightening machine before the steel plate is loaded into the straightening machine, and if it is determined that the steel plate cannot be threaded, resetting the operating conditions of the manufacturing equipment for the steel plate.

The method for manufacturing a steel plate according to the present invention includes a step of manufacturing a steel plate using the method for straightening a steel plate according to the present invention.

The method for generating a judgment model for determining whether a steel plate can be passed through a straightening machine according to the present invention is a method for generating a judgment model for determining whether a steel plate can be passed through a straightening machine in a steel plate manufacturing facility including a straightening machine having at least one pair of rolls, a conveying device for loading the steel plate into the straightening machine, and a warp shape measuring device for measuring the warp shape of the tip of the steel plate, and includes the steps of acquiring a plurality of learning data including the warp height and warp curvature of the tip of the steel plate measured by the warp shape measuring device before being loaded into the straightening machine as input actual data, and output actual data including information on whether the steel plate can be passed through the straightening machine corresponding to the input actual data, and generating the judgment model for whether the steel plate can be passed through the straightening machine by machine learning using the acquired plurality of learning data.

According to the method for determining whether a steel plate can be passed through a straightening machine of the present invention, it is possible to determine whether the steel plate can be passed through the straightening machine depending on the warped shape at the tip of the steel plate. Furthermore, according to the method for straightening a steel plate of the present invention, it is possible to suppress the occurrence of failures in passing a steel plate through a straightening machine. Furthermore, according to the method for manufacturing a steel plate of the present invention, it is possible to manufacture a steel plate with excellent uniformity of material properties. Furthermore, according to the method for generating a model for determining whether a steel plate can be passed through a straightening machine of the present invention, it is possible to generate a model for determining whether the steel plate can be passed through a straightening machine depending on the warped shape at the tip of the steel plate.

FIG. 1 is a schematic diagram showing the configuration of a steel sheet manufacturing facility according to an embodiment of the present invention. FIG. 2 is a schematic diagram showing an example of the configuration of the warpage shape measuring device shown in FIG. FIG. 3 is a diagram for explaining the function of the warpage shape analysis unit shown in FIG. FIG. 4 is a schematic diagram showing another example of the configuration of the warp shape measuring device shown in FIG. FIG. 5 is a diagram for explaining the function of the planar shape analysis unit. FIG. 6 is a diagram for explaining a sheet threading defect at the leading end of a steel sheet. FIG. 7 is a diagram showing an example of the results of investigating the conditions under which failure to pass a steel plate through a straightening machine occurs. FIG. 8 is a diagram showing an example of the results of investigating the influence of the charging speed of the steel plate by the conveying device and the plate length of the steel plate on the failure of the steel plate to pass through the straightener. FIG. 9 is a diagram for explaining a method for generating a model for determining whether or not a strip can be threaded using machine learning. FIG. 10 is a schematic diagram showing the configuration of a neural network. FIG. 11 is a diagram showing the erroneous determination rates in the embodiment and the conventional example. FIG. 12 is a diagram showing the rate of occurrence of material defects in the examples and the comparative examples.

Below, with reference to the drawings, we will explain in detail one embodiment of the present invention, a method for determining whether a steel plate can be passed through a straightening machine, a straightening method, a manufacturing method, and a method for generating a model for determining whether a steel plate can be passed through a straightening machine.

[Steel plate manufacturing equipment]
First, the configuration of a steel sheet manufacturing facility to which the present invention is applied will be described with reference to Figs.

1 is a schematic diagram showing the configuration of a steel plate manufacturing equipment according to one embodiment of the present invention. As shown in FIG. 1, the steel plate manufacturing equipment according to one embodiment of the present invention includes a straightener 1 having at least one pair of rolls arranged in the vertical direction, a conveying device 2 for feeding the steel plate S into the straightener 1, and a warp shape measuring device 3 for measuring the warp shape of the tip of the steel plate S. The steel plate manufacturing equipment of this embodiment also includes a planar shape measuring device 4 for measuring the planar shape of the tip of the steel plate S. However, the planar shape measuring device 4 may not be required. The steel plate manufacturing equipment of this embodiment also includes a control computer 5 for setting and controlling the operating conditions of the steel plate manufacturing equipment. The steel plate manufacturing equipment of this embodiment is arranged as a part of a hot rolling line, and the steel plate S that has been reverse-rolled by one or two rolling mills arranged upstream of the steel plate manufacturing equipment is transported to the steel plate manufacturing equipment. A cooling device for cooling the steel plate S may be arranged downstream of the steel plate manufacturing equipment. By using cooling equipment to accelerate cooling of steel plate S that has been hot rolled by a rolling mill, thick steel plate with excellent material properties can be produced.

The steel plate S to be straightened in the straightener 1 has, for example, a thickness of 6 to 30 mm, a width of 2000 to 4500 mm, a length of 10 to 50 m, and a weight of 8 to 25 tons. The temperature of the steel plate S to be loaded into the straightener 1 is not limited, but in the case of a straightener arranged in a hot rolling line, it is about 650 to 950 ° C. The straightener 1 has at least one pair of rolls arranged in the vertical direction (thickness direction of the steel plate S) and has the function of straightening the shape of the steel plate S. The straightener 1 is, for example, a roller leveler. The roller leveler flattens the shape of the steel plate S by repeatedly bending and unbending deformation to the steel plate S using multiple straightening rolls arranged in a staggered pattern in the vertical direction. For example, 4 to 6 straightening rolls are arranged on the upper side and 4 to 6 on the lower side. In a typical roller leveler, the upper straightening roll is held by an upper frame, and the lower straightening roll is held by a lower frame. Then, by fixing the position of the lower frame and tilting the upper frame, bending deformations of different curvatures are sequentially given to the steel sheet S in the conveying direction of the steel sheet S. In this case, in the example shown in FIG. 1, the pushing amount of the most upstream straightening roll 6_1 and the most downstream straightening roll 6_i (i = 4 to 6) among the upper straightening rolls performing the tilting reduction are set in advance according to the material and dimensions of the steel sheet S. However, the pushing method of the straightening rolls may be a method in which the pushing amount of each straightening roll can be arbitrarily set instead of a tilting pushing method. In addition, the straightening machine 1 may be equipped with a pair of rolls arranged opposite each other in the vertical direction. This is similar to a so-called rolling mill, in which the steel sheet S is pressed by a pair of rolls arranged opposite each other in the vertical direction to straighten the shape of the steel sheet S. In this embodiment, a steel sheet guide 7 is arranged on the entrance side of the straightening machine 1. This is because the steel sheet guide 7 can reduce sheet passing defects when the leading end of the steel sheet S is loaded into the straightening machine 1.

The conveying device 2 conveys the steel sheet S from the upstream side of the straightening machine 1 and operates to load the leading end of the steel sheet S into the straightening machine 1. The conveying device 2 may be a conveying table of a steel sheet manufacturing facility. In that case, the conveying table may be divided into multiple zones and controlled individually, but in this embodiment, the conveying table of the zone upstream of the straightening machine 1 and closest to the straightening machine 1 is referred to as the conveying device 2. The speed at which the steel sheet S is fed into the straightening machine 1 by the conveying device 2 is set by the control computer 5. The control computer 5 sets the pressing amount of the straightening roll of the straightening machine 1 and the rotation speed of the straightening roll. The speed at which the steel sheet S is fed by the conveying device 2 is often set to about 0.5 to 0.8 VL with respect to the rotation speed VL of the straightening roll. This is because the charging speed of the steel sheet S by the conveying device 2 is set to be smaller than the rotation speed VL of the straightening roll to reduce the impact force when the steel sheet S is bitten into the straightening machine 1 and suppress damage to the equipment.

The warpage shape measuring device 3 measures the warpage shape of the tip of the steel sheet S. The tip of the steel sheet S refers to the part on the tip side of the steel sheet S in the conveying direction. The tip of the steel sheet S refers to, for example, a range of 1 to 3 m from the tip of the steel sheet S. When the tip of the steel sheet S is loaded into the straightening machine 1, slippage or the like often occurs between the steel sheet S and the straightening roll, resulting in poor sheet passing. The warpage shape measuring device 3 may be any measuring device that can quantitatively determine the amount of warpage at the tip of the steel sheet S. For example, the warpage shape measuring device 3 may use an image processing method that extracts the contour shape of the steel sheet S from an image of the tip of the steel sheet S and determines the amount of warpage at the tip of the steel sheet S by image processing. The warpage shape measuring device 3 may also use a distance measurement method in which a distance meter is installed at a position a predetermined distance above or below the steel sheet S and determines the amount of warpage at the tip of the steel sheet S from information on the height distribution in the longitudinal direction of the steel sheet S.

As shown in FIG. 2, the warpage shape measuring device 3 using the image processing method includes an imaging unit (area camera) 3a that captures an image of the tip of the steel sheet S, and a warpage shape analysis unit 3b that identifies the warpage shape of the steel sheet S from the image data captured by the imaging unit 3a. The area camera used as the imaging unit 3a may be a color or black-and-white type. Any imaging element such as a CCD or CMOS may be used as the imaging element. The imaging unit 3a may be an infrared area camera that selectively converts a specific wavelength signal among the wavelengths of light into an image. The imaging unit 3a can be appropriately selected from those with an effective pixel count of 640×480 pixels to those with an effective pixel count of about 4872×3248 pixels, depending on the resolution required to identify the warpage shape of the tip of the steel sheet S by image processing, the distance between the imaging unit 3a and the tip of the steel sheet S, etc. In this embodiment, the imaging range (field of view) V1 of the steel plate S by the imaging unit 3a is set so that the leading edge of the steel plate S (within a range of 1 to 3 m from the leading edge) fits into one image. The imaging unit 3a is preferably positioned slightly above the conveying device 2 from the lateral side of the conveying direction of the steel plate S, facing diagonally downward to capture the leading edge of the steel plate S. However, the leading edge of the steel plate S may also be captured in a generally horizontal direction from approximately the same height as the conveying device 2 toward the side of the steel plate S. This is because it is easier to distinguish the contour of one end face of the steel plate S.

The warpage shape analysis unit 3b identifies the warpage shape of the steel sheet S from the image data of the tip of the steel sheet S captured by the imaging unit 3a. FIG. 3 is a diagram for explaining the function of the warpage shape analysis unit 3b. The warpage shape analysis unit 3b detects the contour of the width direction end of the steel sheet S by image processing within the range of the image data of the tip of the steel sheet S (edge detection). Then, the warpage shape analysis unit 3b calculates the warpage height and warpage curvature of the tip of the steel sheet S as the warpage shape from the contour of the width direction end of the steel sheet S. Specifically, as shown in FIG. 3, the warpage shape analysis unit 3b calculates the difference between the height H of the steel sheet S at the reference position and the height of the tip as the warpage height, using a position at a distance L preset from the tip of the steel sheet S as the reference position. In addition, the warpage shape analysis unit 3b calculates an approximation circle TL that approximates the coordinates on the approximation curve connecting the reference position and the tip of the steel sheet S by an approximation method such as the least squares method, and calculates the reciprocal of its radius as the warpage curvature. The height and curvature on the image data may be converted to the actual height and curvature according to the imaging magnification of the image data. The warp height and the warp curvature may be calculated so that the direction can be distinguished by assuming that the warp of the steel sheet S is an upward warp and a downward warp as a positive value and a negative value, respectively. On the other hand, when the warp shape of the tip of the steel sheet S is specified using the distance measurement method, as shown in FIG. 4, the warp shape analysis unit 3b acquires height information of the tip of the steel sheet S from the reference position using a distance meter 3c arranged at a reference position a predetermined distance from above the steel sheet S, and specifies the warp shape of the steel sheet S from the height information of the tip of the steel sheet S. As a method for acquiring the height information of the distance meter 3c, a method based on a publicly known technology such as laser light or microwaves can be used. In addition, the warp shape analysis unit 3b acquires information on the conveying speed of the steel sheet S using a speed meter 3d. As a result, the distance from the tip of the steel sheet S is associated with the height information of the tip of the steel sheet S, and the warp height and warp curvature of the tip of the steel sheet S can be calculated as the warp shape in the same manner as described above.

The planar shape measuring device 4 measures the planar shape of the tip of the steel plate S before the steel plate S is loaded into the straightening machine 1. As the planar shape measuring device 4, a measuring device capable of quantitatively identifying the planar shape of the tip of the steel plate S is used. For example, the planar shape measuring device 4 may use an image processing method in which the contour shape of the steel plate S is extracted based on an image of the tip of the steel plate S captured from the top, and the planar shape of the tip of the steel plate S is identified by image processing. The planar shape measuring device 4 includes an imaging unit (area camera) 4a (see FIG. 1) that images the top surface of the tip of the steel plate S from above in the conveying direction of the steel plate S, and a planar shape analysis unit 4b (see FIG. 5) that identifies the planar shape of the steel plate S from the image data acquired by the imaging unit 4a. The area camera used as the imaging unit 4a may be the same as that used in the warp shape measuring device 3. The planar shape analysis unit 4b identifies the planar shape of the steel plate S from the image data of the top surface of the tip of the steel plate S captured by the imaging unit 4a. FIG. 5 is a diagram for explaining the function of the planar shape analysis unit 4b. As shown in FIG. 5, the planar shape analysis unit 4b detects the contour of the steel sheet S by image processing within the range V2 of image data of the top surface of the tip of the steel sheet S. Then, the planar shape analysis unit 4b acquires the longitudinal distance (tip crop length) between the most protruding position and the most recessed position in the width direction of the steel sheet S as a measurement value of the planar shape. In this case, the tip crop length may be defined as positive when the most protruding position in the width direction of the steel sheet S is on the end side of the steel sheet S in the width direction, and negative when it is on the center side of the width direction.

[Improper threading of the tip of the steel plate]
Next, threading defects at the leading end of a steel sheet will be described with reference to Figs.

The passage (biting) of the steel sheet S into the straightening machine 1 refers to the process in which the leading end of the steel sheet S reaches the straightening machine 1 and passes through the positions of all the straightening rolls. In other words, it includes not only the case in which the leading end of the steel sheet S collides with the steel sheet guide 7 or the housing of the straightening machine 1 before passing between the straightening rolls arranged in the vertical direction and the steel sheet S does not pass through the straightening rolls, but also the case in which the leading end of the steel sheet S passes between some of the straightening rolls, but slip occurs between the steel sheet S and the straightening rolls, and the steel sheet S stops without being transported. Figures 6(a) to (c) are schematic diagrams showing the process in which the steel sheet S is loaded into the straightening machine 1 equipped with the steel sheet guide 7. As shown in Figure 6(a), if the leading end of the steel sheet S has a large upward camber when it is loaded into the straightening machine 1, the leading end of the steel sheet S comes into contact with the steel sheet guide 7. At this time, since the steel sheet S is given an inertial force (kinetic energy) by the conveying device 2, if the inertial force of the steel sheet S is greater than the reaction force that the steel sheet S receives from the steel sheet guide 7, the leading end of the steel sheet S is guided by the steel sheet guide 7 and guided between the upper and lower straightening rolls as shown in FIG. 6(b). Then, as shown in FIG. 6(c), when the leading end of the steel sheet S passes between the upper and lower straightening rolls, if the energy of the driving force that rotates the straightening rolls is sufficient for the bending work given to the steel sheet S, the steel sheet S advances in the conveying direction in the straightening machine 1, and the leading end of the steel sheet S passes through the positions of all the straightening rolls. On the other hand, if the inertial force of the steel sheet S is smaller than the reaction force that the steel sheet S receives from the steel sheet guide 7 or if the energy of the driving force that rotates the straightening rolls is insufficient, the progress of the steel sheet S stops in the straightening machine 1, resulting in a sheet passing failure.

The inventors have studied the conditions under which such a failure to pass the steel sheet S through the straightener 1 occurs, and have come to the following findings. First, it was found that a steel sheet with a large warp height at the tip and a large thickness is more likely to pass through the straightener 1 with a failure. This is thought to be because, when the tip of the steel sheet S collides with the steel sheet guide 7 and the thickness is large, a large amount of kinetic energy is consumed due to the inertial force of the steel sheet S when the tip of the steel sheet S is bent and passed through the straightening roll when the tip of the steel sheet S collides with the steel sheet guide 7. Figure 7 shows an example of the results of investigating the conditions under which a failure to pass the steel sheet S through the straightener 1 occurs. Figure 7 shows the conditions under which a failure to pass the steel sheet S occurs, obtained under operating conditions where the thickness of the steel sheet S is 25 to 30 mm, the length is 30 to 32 m, and the loading speed (biting speed) of the steel sheet S into the straightener 1 by the conveying device 2 is 50 m/min. From Fig. 7, it can be seen that even if the warpage height at the tip of the steel sheet S is the same, when the warpage curvature at the tip of the steel sheet S is small, no sheet passing failure occurs, and when the warpage curvature is large, sheet passing failure occurs. On the other hand, Fig. 8 shows an example in which the influence of the charging speed of the steel sheet S by the conveying device 2 and the plate length of the steel sheet S on the sheet passing failure of the steel sheet S into the straightener 1 was examined for steel sheets S having the same warpage height and warpage curvature. In this case, the plate thickness of the steel sheet S is 25 to 30 mm, and the tip warpage height is 100 to 120 mm. From Fig. 8, it can be seen that the sheet passing property of the steel sheet S into the straightener 1 is improved as the charging speed of the steel sheet S into the straightener 1 by the conveying device 2 and the plate length of the steel sheet S are larger. This is considered to be because the inertial force (kinetic energy) when the steel sheet S is charged into the straightener 1 is increased, thereby suppressing the biting failure of the steel sheet S into the straightener 1. Furthermore, the inventors have found that the planar shape of the tip of the steel sheet S also affects the occurrence of failure in threading the steel sheet S through the straightener 1. As shown in FIG. 5, when the tip of the steel sheet S has an uneven shape, the part (tip crop part) that locally protrudes forward when biting is likely to bend. The longer the length (tip crop length) of this tip crop part is and the narrower the width is, the more likely the steel sheet S is to bend and the more likely the failure in threading the steel sheet S is to occur. For example, when the tip crop length and the occurrence of failure in threading were investigated for a steel sheet having a thickness of 30 mm and a tip warp height of 100 mm, the steel sheet S with a tip crop length of 50 mm was able to be threaded, but the steel sheet S with a tip crop length of 200 mm had a failure in threading. Note that the temperature of the steel sheet S when the steel sheet S is charged into the straightener 1 and the yield stress of the steel sheet S at that temperature may affect the biting ability of the straightener 1. This is because there is a correlation between the temperature and yield stress of the steel plate S and the resistance force when the tip of the steel plate S passes through the steel plate guide 7.

[Table for determining whether or not strip can be threaded]
Next, a description will be given of a plate threading feasibility determination table used in the method of determining whether a steel plate can be threaded through a straightening machine according to this embodiment.

In the method of this embodiment for determining whether a steel sheet can be passed through a straightening machine, a table for determining whether a steel sheet S can be passed through a straightening machine 1 is generated in advance based on past operational performance data, etc., in order to determine whether a steel sheet S can be passed through a straightening machine 1 based on the warp height and warp curvature of the tip of the steel sheet S. Specifically, using past operational performance, data on whether the steel sheet S could be inserted into the steel sheet manufacturing equipment is collected for each category of performance data on the warp height and warp curvature of the tip of the steel sheet S, and a table for determining whether a steel sheet can be passed through is generated. The warp height of the tip of the steel sheet can be divided into 4 to 10 categories. For example, the warp height can be divided into categories every 20 to 50 mm. On the other hand, the warp curvature of the tip of the steel sheet can be divided into 4 to 10 categories. For example, the warp curvature can be divided into categories every 0.0001 to 0.0002/mm. For the past data on whether or not a steel plate can be threaded through the steel plate manufacturing equipment corresponding to each category, the probability of whether or not the steel plate can be threaded may be calculated, and the information on whether or not the steel plate can be threaded (information for determining whether or not the steel plate can be threaded) may be determined based on a preset probability threshold value. However, it is preferable to determine that if there is a history of even one occurrence of a threading failure on the straightener 1 among steel plates belonging to the same category, the steel plate is judged as "not threadable (biting failure)," and if no threading failure occurs for any steel plate, the steel plate is judged as "threadable (good biting)." This is because if a threading failure occurs in the steel plate manufacturing equipment, it can cause damage to the steel plate manufacturing equipment or a long-term stoppage of operations, which has a large impact on operations, and therefore it is preferable to reduce the risk of threading failure as much as possible.

It is preferable to collect data on the performance of the steel plate S in the steel plate manufacturing equipment, not only in terms of the warp height and warp curvature of the tip of the steel plate S, but also in terms of other parameters. For example, in addition to the warp height and warp curvature of the tip of the steel plate S, it is preferable to classify the steel plate S using one or more operation parameters selected from the plate thickness, plate width, plate length, weight, and the loading speed of the steel plate S into the straightening machine 1 by the conveying device 2. This is because these operation parameters affect the mass or conveying speed of the steel plate S when the steel plate S is loaded into the straightening machine 1, and the biteability of the steel plate S into the straightening machine 1 changes due to the inertial force (kinetic energy) of the steel plate S. On the other hand, if the steel plate manufacturing equipment is equipped with a planar shape measuring device 4 that measures the planar shape of the tip of the steel plate S, the planar shape of the tip of the steel plate S before the steel plate S is loaded into the straightening machine 1, measured by the planar shape measuring device 4, may be added to the above classification. This is because the planar shape of the tip of the steel plate S affects the biteability of the steel plate S into the straightening machine.

Table 1 shows a table of whether or not a steel plate S can be threaded through a steel plate manufacturing facility, which is generated by collecting data on whether or not a steel plate S can be threaded through the steel plate manufacturing facility, based on past operational results. The table is divided into categories based on the warp height at the tip of the steel plate, the curvature at the tip, the crop length (tip crop length) which is the planar shape of the tip, the plate length of the steel plate, and the loading speed (transport speed) of the steel plate S into the straightener 1 by the transport device 2. The "o" indicating whether or not a steel plate can be threaded indicates "biting possible (good biting)," and the "x" indicates "not possible to thread (poor threading)." A category in which a threading failure has occurred even once is labeled with judgment information indicating that the steel plate is poorly threaded. The data on whether or not a steel plate can be threaded is marked with "x" if a threading failure has occurred even once within the same category. The table of whether or not a steel plate can be threaded does not need to be generated only from past operational results data. For example, a table of whether or not a steel plate can be threaded may be generated using a numerical analysis method such as the finite element method for the operational conditions corresponding to each category.

[Method for determining whether a steel plate can be threaded through a straightening machine]
Next, a method for determining whether or not a steel plate can be passed through a straightening machine according to this embodiment will be described.

The threading possibility determination table is stored in a storage device or the like inside the control computer 5. During operation, as shown in FIG. 1, a warp shape measurement step is performed in which the warp height and warp curvature of the tip of the steel sheet S are measured using the warp shape measurement device 3 before the steel sheet S is loaded into the straightener 1. As described above, the warp shape measurement step can be performed by, for example, the warp shape measurement device 3 equipped with the imaging unit 3a and the warp shape analysis unit 3b. The warp height and warp curvature of the tip of the steel sheet S identified in the warp shape measurement step are sent from the warp shape measurement device 3 to the control computer 5. Based on the measured values of the warp height and warp curvature of the tip of the steel sheet S acquired from the warp shape measurement device 3, the control computer 5 determines whether the steel sheet S can be threaded in the steel sheet manufacturing facility by referring to information on whether the steel sheet can be threaded in the corresponding section of the threading possibility determination table (threading possibility determination step).

When one or more operational parameters selected from the thickness, width, length, and weight of the steel plate S, and the speed at which the steel plate S is fed into the straightener 1 by the conveying device 2 are included as categories in the threading feasibility determination table, these operational parameters are information generated inside the control computer 5 as the operating conditions of the steel plate manufacturing equipment, so that the operational parameters for the steel plate S can be acquired. On the other hand, when a planar shape measuring device 4 is provided for measuring the planar shape of the leading end of the steel plate S, and the planar shape of the leading end of the steel plate S is included as a category in the threading feasibility determination table, data on the planar shape of the leading end of the steel plate S identified by the planar shape measuring device 4 is sent to the control computer 5. This makes it possible to refer to the threading feasibility determination table inside the control computer 5 and determine whether the steel plate S can be threaded in the steel plate manufacturing equipment.

Using the above-mentioned method for determining whether the steel sheet S can be passed through the steel sheet manufacturing equipment before the steel sheet S is loaded into the straightening machine 1, it is determined whether the steel sheet S can be passed through the steel sheet manufacturing equipment, and if it is determined that the steel sheet S can be passed through (no passing defects), the steel sheet S can be straightened by the straightening machine 1 under the operating conditions previously set by the control computer 5 for the steel sheet manufacturing equipment. On the other hand, before the steel sheet S is loaded into the straightening machine 1, it is determined whether the steel sheet S can be passed through the steel sheet manufacturing equipment, and if it is determined that the steel sheet S cannot be passed through (there is a passing defect), the operating conditions of the steel sheet manufacturing equipment are reset (resetting step). For example, the operating conditions of the conveying device 2 are reset so as to increase the loading speed of the steel sheet S into the straightening machine 1, which is previously set by the control computer 5. In addition, as described in Patent Document 3, it may be reset so as to reduce the amount of pressing of the straightening roll when the tip of the steel sheet S is loaded into the straightening machine 1. This method of straightening steel plates is preferably applied to a hot leveler (hot straightener) that is arranged between a rolling mill and a cooling device (accelerated cooling device) in a thick plate production line. Since the steel plate S is straightened to a flat shape in the steel plate production equipment, the occurrence of uneven cooling of the steel plate S in the cooling device can be suppressed. In addition, when the steel plate S is loaded into the straightener 1, the temperature drop of the steel plate S caused by an increase in the processing time of the steel plate S due to poor plate threading can be suppressed, and an appropriate cooling start temperature can be secured in the cooling equipment, so that the desired material properties can be secured.

[Model for determining whether strip can be threaded]
Next, a model for determining whether or not a strip can be threaded according to one embodiment of the present invention will be described with reference to Figs.

Instead of the above-mentioned threading possibility judgment table, a threading possibility judgment model generated by machine learning may be used to judge whether the steel sheet S can be threaded. Specifically, the threading possibility judgment model learned by machine learning may be used to judge whether the steel sheet S can be threaded through the straightening machine 1, in which the input data includes the warp height and warp curvature of the tip of the steel sheet S measured by the warp shape measuring device 3 before the steel sheet S is loaded into the straightening machine 1, and the output data is information on whether the steel sheet S can be threaded through the straightening machine 1. In addition, it is preferable that the input data includes one or more operation parameters selected from the thickness, width, length, and weight of the steel sheet S, and the loading speed of the steel sheet S into the straightening machine 1 by the conveying device 2. Furthermore, it is preferable to judge whether the steel sheet S can be threaded through the straightening machine 1 using the planar shape of the tip of the steel sheet S measured by the planar shape measuring device 4 before the steel sheet S is loaded into the straightening machine 1 as input data. This is because these input data are correlated with the threading ability of the steel sheet S in the straightening machine 1, as described above.

The strip threading feasibility determination model can be generated by machine learning using past operational performance data. Figure 9 is a diagram for explaining a method for generating a strip threading feasibility determination model using machine learning. As shown in Figure 9, the strip threading feasibility determination model generation unit 11 of this embodiment includes a database unit 11a and a machine learning unit 11b.

The database unit 11a accumulates the actual data of the warp height and warp curvature of the tip of the steel sheet S measured by the warp shape measuring device 3, and the actual data of the information on whether the steel sheet S can be threaded in the steel sheet manufacturing equipment. The database unit 11a may accumulate the actual data of the operation parameters such as the thickness and width of the steel sheet S, and the actual data of the planar shape (tip crop length) of the tip of the steel sheet S measured by the planar shape measuring device 4, as necessary. In this case, it is preferable to appropriately acquire information stored in the control computer 5 for controlling the operation of the steel sheet manufacturing equipment as the input actual data of the threading judgment model. In addition, a data acquisition unit 12 may be provided to collect the input actual data, and the actual data may be temporarily stored in the data acquisition unit 12, and a data set in which multiple types of actual data are associated may be generated and then accumulated in the database unit 11a. 500 or more data sets are accumulated in the database unit 11a. Preferably, 2000 or more, more preferably 10,000 or more. The data accumulated in the database unit 11a may be screened as necessary. This is because there may be measurement errors in the measurement of the warp height and warp curvature using the warp shape measuring device 3, and the accuracy of the judgment model for judging whether or not the plate can be threaded is improved by accumulating highly reliable data. On the other hand, the number of data sets accumulated in the database unit 11a may be limited to a certain number, and the data sets accumulated in the database unit 11a may be updated as appropriate within the upper limit.

The machine learning unit 11b uses the data set accumulated in the database unit 11a to generate a threading possibility judgment model M that predicts the threading possibility information of the steel sheet by machine learning using multiple learning data. The learning data is the actual data of the warp height and warp curvature of the tip of the steel sheet S as input actual data, and the actual data of the threading possibility information of the steel sheet S as output actual data. The machine learning model for generating the threading possibility judgment model M may be any machine learning model as long as it can obtain sufficient judgment accuracy of the threading possibility information of the steel sheet S for practical use. For example, a commonly used neural network (including deep learning and convolutional neural network, etc.), decision tree learning, random forest, support vector regression, etc. may be used. An ensemble model combining multiple models may also be used. A classification model such as the k-nearest neighbor method or logistic regression may also be used. For example, the threading possibility judgment model M can be generated by machine learning using a general neural network as shown in FIG. 10. In addition, the symbols L1, L2, and L3 in FIG. 10 respectively indicate the input layer, intermediate layer, and output layer. In particular, when deep learning is used, it is possible to freely select other operational parameters that are correlated with the threading suitability information of the steel sheet S as inputs without having to consider the problem of multicollinearity, thereby improving the estimation accuracy of the threading suitability judgment of the steel sheet S. For example, a neural network with two intermediate layers, each with three nodes, and using a sigmoid function as the activation function can be used. It is preferable to use a softmax function in the output layer to output the threading suitability information of the steel sheet S as a binary classification result.

The machine learning unit 11b may improve the estimation accuracy of the threading possibility information of the steel sheet S by dividing the data set accumulated in the database unit 11a into training data and test data and performing learning. For example, the machine learning unit 11b may use the training data to learn the weight coefficients of the neural network, and generate the threading possibility judgment model M while appropriately changing the structure of the neural network (the number of intermediate layers and the number of nodes) so that the accuracy rate of the threading possibility information of the steel sheet S in the test data is high. The error propagation method can be used to update the weight coefficients. The threading possibility judgment model M may be updated to a new model by re-learning, for example, every six months or every year. This is because the more data stored in the database unit 11a, the more accurate the prediction of the threading possibility information of the steel sheet S can be. By updating the threading possibility judgment model M based on the latest data, a threading possibility judgment model M that reflects changes in the manufacturing conditions of the steel sheet S to be charged into the steel sheet manufacturing equipment can be generated.

As an embodiment of the present invention, an example will be described in which the steel plate manufacturing equipment shown in FIG. 1 is arranged as a roller leveler downstream of a reverse rolling mill arranged in a thick plate rolling line. In this embodiment, a warp shape measuring device 3 and a planar shape measuring device 4 are arranged upstream of the roller leveler. These devices take images of the tip of the steel plate using a CCD camera, and calculate the warp height, warp curvature, and planar shape (tip crop length) of the tip of the steel plate using an image processing method. In addition, the plate thickness, plate length, steel plate temperature when being charged into the straightener 1, and charging speed of the steel plate S were obtained as operational data of the steel plate manufacturing equipment. Then, a plate threading feasibility judgment table was generated using operational performance data for about half a year. The classification of the plate threading possibility judgment table is divided into 10 categories for each of the seven parameters of the warp height at the front end of the steel plate S, the warp curvature, the front end crop length, the plate thickness, the plate length, the steel plate temperature, and the charging speed, and the category in which the plate threading defect occurred in the past operation is marked with "x", and the category in which the plate threading defect did not occur is marked with "o". The plate threading possibility judgment table is stored in the storage unit of the control computer 5, and the control computer 5 is provided with a plate threading possibility judgment unit inside. On the other hand, a plate threading possibility judgment model M was generated by machine learning using the neural network shown in FIG. 10, using two intermediate layers and a softmax function in the output layer. As in the classification of the plate threading possibility judgment table, seven parameters of the warp height at the front end of the steel plate, the warp curvature, the front end crop length, the plate thickness, the plate length, the steel plate temperature, and the charging speed were used for the input record data when generating the plate threading possibility judgment model M. In addition, the output data is classified as "threading failure (x)" for categories in which threading failures occurred in past operations, and "no threading failure (o)" for categories in which threading failures did not occur. The generated threading feasibility judgment model M is also stored in the memory unit of the control computer 5, and the control computer 5 is equipped with a threading feasibility judgment unit inside.

After that, during operation, before the steel sheet S was loaded into the straightening machine 1, it was determined whether the steel sheet S could be threaded in the steel sheet manufacturing equipment. However, regardless of the result of the determination as to whether the steel sheet S could be threaded, the operating conditions of the steel sheet manufacturing equipment were not reset, and the steel sheet S was straightened by the straightening machine 1 with the initial settings. In Example 1, the rate of cases in which the steel sheet S was judged to be threadable (no threading defects) using a previously generated threading determination table, but in which a threading defect actually occurred in the straightening machine 1, was determined as the erroneous determination rate. In Example 2, the erroneous determination rate was also evaluated for the results of the threading determination using the threading determination model M. On the other hand, as a conventional example, the rate of cases in which an operator in charge of the operation of the steel sheet manufacturing equipment visually confirmed the warping state of the steel sheet tip, and the operator judged that the steel sheet S could be threaded, but in fact a threading defect occurred, was evaluated. Figure 11 shows the results of evaluating the erroneous determination rate for 20,000 steel sheets with a thickness of 20 to 40 mm. As shown in FIG. 11, it can be seen that the misjudgment rate in Example 1 is lower than that in the conventional example. It was also found that the misjudgment rate is further reduced in Example 2.

Next, the threading feasibility determination model M created in Example 2 was used online to determine whether the steel sheet S could be threaded in a threading feasibility determination step before the steel sheet S was loaded into the straightening machine 1. If the determination was "no threading defects (◯)," straightening was performed by the straightening machine 1 under the operating conditions preset by the control computer 5. On the other hand, if the determination was "threading defects (×)," the operation was performed by increasing the loading speed of the steel sheet S into the straightening machine 1 from the initial setting value among the operating conditions of the straightening machine 1. As a result, as shown in FIG. 12, when the operating conditions of the steel sheet manufacturing equipment were reset (Example), the occurrence rate of material defects (defects in which the mechanical properties of the steel sheet are outside the target range) was lower than when they were not reset (Comparative Example).

The above describes an embodiment of the invention made by the inventors, but the present invention is not limited to the descriptions and drawings that form part of the disclosure of the present invention according to this embodiment. In other words, other embodiments, examples, and operational techniques made by those skilled in the art based on this embodiment are all included in the scope of the present invention.

1 Straightener 2 Conveyor 3 Warpage shape measuring device 3a, 4a Imaging unit (area camera)
3b Warp shape analysis unit 3c Distance meter 3d Speed meter 4 Plane shape measurement device 4b Plane shape analysis unit 5 Control computer 11 Strip threading suitability determination model generation unit 11a Database unit 11b Machine learning unit 12 Data acquisition unit M Strip threading suitability determination model S Steel strip

Claims (6)

A method for determining whether a steel plate can be passed through a straightener in a steel plate manufacturing facility including a straightener having at least one pair of rolls, a conveying device for feeding a steel plate into the straightener, and a warpage shape measuring device for measuring a warpage shape of a leading end of the steel plate, comprising:
a warpage shape measuring step of measuring a warpage height and a warpage curvature of a tip end portion of the steel plate using the warpage shape measuring device before the steel plate is loaded into a straightening machine;
a plate threading possibility determination step of determining whether the steel plate can be threaded through the straightener based on the warp height and the warp curvature of the tip portion of the steel plate measured in the warp shape measurement step;
Including ,
The method for determining whether a steel plate can be passed through a straightening machine includes a step of determining whether the steel plate can be passed through the straightening machine based on operational parameters that affect the mass or transport speed of the steel plate when the steel plate is loaded into the straightening machine, selected from the warp height and warp curvature of the tip of the steel plate measured in the warp shape measurement step, as well as the thickness, width, length, and weight of the steel plate, and the loading speed of the steel plate into the straightening machine by the transport device . The steel plate manufacturing facility includes a planar shape measuring device that measures a planar shape of a tip end of the steel plate,
2. The method for determining whether a steel plate can be passed through a straightening machine as described in claim 1, wherein the step of determining whether the steel plate can be passed through the straightening machine further includes a step of determining whether the steel plate can be passed through the straightening machine using the planar shape of the leading end of the steel plate measured using the planar shape measuring device before the steel plate is loaded into the straightening machine. A method for determining whether a steel plate can be passed through the straightener in a manufacturing facility including a straightener having at least one pair of rolls, a conveying device for feeding a steel plate into the straightener, and a warpage shape measuring device for measuring a warpage shape of a leading end of the steel plate, comprising:
a step of judging whether the steel plate can be threaded through the straightening machine by using a threading possibility judgment model learned by machine learning, the model including, as input data, a warpage height and a warpage curvature of a front end portion of the steel plate measured by the warpage shape measuring device before the steel plate is loaded into the straightening machine, and output data, information on whether the steel plate can be threaded through the straightening machine;
The input data includes, in addition to the warp height and warp curvature at the tip of the steel plate, one or more operational parameters that affect the mass or transport speed of the steel plate when the steel plate is loaded into the straightening machine, selected from the plate thickness, plate width, plate length, and weight of the steel plate, and the loading speed of the steel plate into the straightening machine by the transport device . 4. A method for straightening a steel plate, comprising: using the method for determining whether a steel plate can be passed through a straightening machine according to claim 1 or 3 , determining whether the steel plate can be passed through the straightening machine before the steel plate is loaded into the straightening machine; and, if it is determined that the steel plate cannot be passed through, resetting operating conditions of the steel plate manufacturing equipment. A method for manufacturing a steel plate, comprising the step of manufacturing a steel plate using the method for straightening a steel plate according to claim 4 . A method for generating a judgment model for determining whether a steel plate can be passed through a straightener in a steel plate manufacturing facility including a straightener having at least one pair of rolls, a conveying device for loading a steel plate into the straightener, and a warpage shape measuring device for measuring a warpage shape of a leading end of the steel plate, the method comprising:
a step of acquiring a plurality of learning data, the learning data including, as input record data, a warpage height and a warpage curvature of a front end portion of a steel plate measured by the warpage shape measuring device before the steel plate is loaded into the straightening machine, and output record data including information on whether the steel plate can be threaded through the straightening machine corresponding to the input record data, and generating the threading possibility judgment model by machine learning using the acquired plurality of learning data;
The input actual data includes, in addition to the warp height and warp curvature at the tip of the steel plate, one or more operational parameters that affect the mass or transport speed of the steel plate when the steel plate is loaded into the straightening machine, selected from the thickness, width, length, and weight of the steel plate, and the loading speed of the steel plate into the straightening machine by the transport device.

Images