JP5760462B2 - Tail-end crop detection device - Google Patents

Description

The present invention relates to a tail end crop detection equipment which detects the tail end crop of the material to be rolled during rolling in the hot rolling line.

  In hot rolling, meandering of the material to be rolled often becomes a problem during rolling in a finishing mill. When the tail end of the material to be rolled meanders, the material to be rolled comes into contact with the side guide installed on the entrance side of the rolling stand, and the material to be rolled is folded and rolled, so-called narrowing may occur. is there. If the work roll is damaged due to the narrowing, the wrinkle is transferred to another subsequent rolled material and becomes a surface defect. Therefore, it is necessary to replace the work roll, which induces a reduction in the line operation rate. . As described above, meandering in a finishing mill is a major factor in deteriorating productivity and surface quality.

As a technique for preventing such meandering, for example, there is meandering correction control of Patent Document 1. This technique uses a plurality of optical means such as cameras installed in the hot rolling line to produce a tip and tail crop of the material to be rolled in a finish rolling mill (an end of the material to be rolled). The shape portion) is detected, and the leveling amount of the rolling stand (left and right reduction amount difference) is controlled to correct the meandering of the material to be rolled based on the difference in elongation in the longitudinal direction at both ends in the width direction.
Further, as a crop shape recognition device, for example, there is a technique described in Patent Document 2. This technology is based on plate width information and movement information from a plate width meter and speed detector installed in a hot rolling line for a material whose center position is adjusted by equipment such as side guides. It recognizes the crop shape at the end.

JP-A-60-199513 Japanese Patent Publication No. 63-60841

  By the way, in the technique described in Patent Document 1, it is necessary to install a plurality of crop shape detection cameras in the hot rolling line, but the cameras are installed in the hot rolling line having a poor photographing environment. In order to do this, it is necessary to take various measures such as heat resistance and steam resistance, which increases costs. Further, although maintenance of the camera may be necessary due to contamination of vapor or foreign matter on the light receiving surface, the maintenance work needs to be carried out in the hot rolling line, so workability is poor. In addition, since it is necessary to ensure safety in such maintenance work, the hot rolling line must be stopped during the maintenance work, and the line operation rate decreases. Maintenance work can also be performed when the hot rolling line is stopped for a long time such as periodic repairs, but in this case, the camera cannot be used until the maintenance is completed, so meandering correction control is not activated during that time End up.

In the technique described in Patent Document 2, in the case of a hot rolling facility in which a sheet width meter is not installed, it is necessary to newly install a sheet width meter. Moreover, since it is necessary to install a plate | board width meter in a hot rolling line, similarly to the technique of the patent document 1 mentioned above, also in this case, there exists a subject by cost and a maintenance surface. Furthermore, when the image of the material to be rolled is offset from the center position, it is not possible to distinguish whether the material to be rolled is offset from the center position or whether the material is offset from the center position due to foreign matter mixed in the light receiving surface. There is also a problem that proper crop shape recognition is not possible.
Accordingly, the present invention is a preferred arrangement in cost-and maintenance plane and an object to provide a proper tail end crop detection equipment capable of detecting the tail end cropping.

In order to solve the above-mentioned problems, a tail end cropping device according to the present invention detects a tail end crop of a material to be rolled at several hundred to several hundreds of degrees Celsius passing between finish rolling stands of a hot rolling line. It is an end crop detection device, disposed outside the hot rolling line and at a position along the hot rolling line, and a surface image of the rolled material passing through a predetermined imaging position on the hot rolling line. An image capturing means for continuously capturing images of the material to be rolled, which is disposed outside the hot rolling line and at a position along the hot rolling line, and passes a predetermined imaging position on the hot rolling line. An image pickup means for continuously picking up a surface image, and it is not necessary to install a camera for picking up the material to be rolled outside a hot rolling line having a good installation environment and to take heat and steam resistance measures for the camera. , vs. the camera to the imaging position Together is arranged at a predetermined distance and offset in the line operation can also be carried out maintenance work position Te, the NIR corresponding camera set shutter speed corresponding to the rate of passage of the rolled material between said finish rolling stand An imaging means that continuously captures a surface image of the material to be rolled at several hundred to several hundreds of degrees Celsius passing through a predetermined imaging position on the hot rolling line with near-infrared brightness; and A tail end for detecting a crop at the tail end of the material to be rolled based on a surface image of the material to be rolled at several hundred to several hundreds of degrees Celsius of near-infrared brightness imaged by an imaging unit configured with an infrared camera. And crop detection means.

  As described above, since the image pickup means is arranged outside the hot rolling line, it is not necessary to take measures such as heat resistance and steam resistance for the image pickup means unlike the case where the image pickup means is arranged inside the hot rolling line. Edge crops can be detected. Furthermore, since the imaging means can be maintained outside the hot rolling line, maintenance work can be performed even during line operation. Therefore, it is not necessary to stop the line for a long time for maintenance work, and the line operation rate can be secured.

Further, in the above, the tail end crop detection unit detects a tail end image obtained by imaging a tail end of the material to be rolled from a continuous surface image of the material to be rolled imaged by the imaging unit. And edge portion extraction means for extracting an edge portion in the tail edge image detected by the tail edge detection means, and based on the edge portion extracted by the edge portion extraction means, the tail of the material to be rolled It is characterized by detecting end crops.
Thus, the shape of the tail end of the material to be rolled can be appropriately detected by analyzing the luminance information of the continuous surface image obtained by continuously imaging the material to be rolled.

Further, in the above, the tail end detection means is configured such that a distribution of white pixels in a binarized continuous image obtained by binarizing a continuous surface image of the material to be rolled imaged by the imaging means is the tail end image. An area having a distribution satisfying the above condition is detected as the tail image.
Thereby, the tail end image can be detected with high accuracy from the continuous surface image of the material to be rolled.

Further, in the above, the imaging means is arranged so that an arrangement position in the rolling direction of the hot rolling line is a position offset by a predetermined distance with respect to an imaging position of the material to be rolled. The end crop detection means includes correction means for correcting the edge image corresponding to the edge portion extracted by the edge portion extraction means based on the relationship between the arrangement position of the imaging means and the imaging position of the material to be rolled. It is characterized by.
Thereby, the edge image of the tail end of the material to be rolled viewed from an oblique direction with respect to the rolling direction is converted into an edge image viewed from a direction orthogonal to the rolling direction, and the presence or absence of the tail end crop is determined. Can do. Therefore, when one end side in the width direction of the material to be rolled seems to extend due to the relationship between the position of the imaging means and the imaged position of the material to be rolled, even though no tail end cropping has actually occurred. Even so, it is possible to prevent erroneous determination that the tail crop has occurred.

Furthermore, in the above, it is further characterized by further comprising display means for monitoring and displaying the tail edge crop detected by the tail edge crop detection means.
As a result, the operator can easily recognize the shape of the tail end crop .

According to the present invention, from outside the hot rolling line, the material to be rolled conveyed through the hot rolling line is imaged, and the tail edge crop of the material to be rolled is detected by analyzing the obtained surface image. Without taking various measures such as heat resistance and steam resistance, it is possible to provide a tail end crop detection device that is inexpensive and can be maintained even during line operation. Moreover, since disturbances such as temperature and water vapor can be eliminated, the tail end crop can be detected with high accuracy .

It is a figure which shows the structure of a hot rolling installation provided with the tail end crop detection apparatus in this embodiment. 4 is a flowchart showing a tail end crop detection processing procedure executed by the image processing apparatus 12. It is a figure explaining the tail end detection principle. It is a figure explaining the edge detection principle. It is a figure which shows the viewpoint before and behind angle-of-view adjustment. It is a figure explaining a view angle adjustment principle. It is a figure for demonstrating the operation | movement of this embodiment. It is a figure for demonstrating the effect of this embodiment.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
(Constitution)
FIG. 1 is a diagram illustrating a configuration of a hot rolling facility including a tail end crop detection device according to the present embodiment.
In the figure, reference numeral 1 denotes a hot rolling facility. The hot rolling equipment 1 includes a heating furnace 2, a sizing press 3, a rough rolling mill 4 including a plurality of rough rolling stands (R1 to R3), and a plurality of finishing rolling stands (F1 to F7) from the upstream side of the hot rolling line. A finishing rolling mill 5 and a winding facility 6 are provided. Reference numeral 7 denotes a material to be rolled.
The hot rolling facility 1 includes a tail end crop detection device 10 that detects a tail end crop of the material 7 to be rolled that is transported through the hot rolling line. The tail end crop detection device 10 includes a camera 11, an image processing device 12, and a monitor 13.

  The camera 11 is installed outside the hot rolling line and at a position along the hot rolling line, and an imaging position between the outside of the hot rolling line and the finishing rolling stand (here, the third stand F3 and the fourth stand). A surface image of the material 7 to be rolled passing through (between F4) is continuously taken and acquired as a continuous image of the material 7 to be rolled. Here, the camera 11 shall be arrange | positioned so that the arrangement | positioning position in the rolling direction of a hot rolling line may become a position offset predetermined distance with respect to the imaging position of the material 7 to be rolled. The camera 11 is, for example, a near-infrared camera, and is set to a shutter speed (for example, 1/1000 s) corresponding to the passing speed of the material to be rolled 7 between the finish rolling stands.

  The continuous image acquired by the camera 11 is input to the image processing device 12. The image processing device 12 is configured by a computer such as a microcomputer or a personal computer having a CPU, a memory, and the like (not shown), and executes tail edge crop detection processing described later. By this tail end crop detection processing, image processing is performed on the continuous image of the material 7 to be rolled, and the tail end crop of the material 7 is detected. The shape of the tail end crop detected by the image processing device 12 is displayed on the monitor 13 so that the operator can recognize it.

Next, tail end crop detection processing executed by the image processing apparatus 12 will be described.
FIG. 2 is a flowchart showing a tail end crop detection processing procedure.
First, in step S1, the image processing apparatus 12 acquires a continuous image of the material 7 to be rolled acquired by the camera 11, and proceeds to step S2.
In step S2, the image processing apparatus 12 performs tail end detection processing based on the continuous image acquired in step S1. First, a target range for tail end detection processing is set for the acquired continuous images, and luminance information for each pixel in the set tail end detection target range is obtained. Then, binarization processing is performed on the tail end detection target range using a preset white pixel determination threshold value X. For example, when the continuous image (original image) shown in FIG. 3A is acquired, the binarization processing is performed on the tail end detection target range α to obtain the binary image shown in FIG.

  Next, the number of white pixels is measured for each column (width direction) in the binarized image. Then, for example, as shown in FIG. 3C, a measurement result is obtained with the rolling direction as the horizontal axis and the number of white pixels as the vertical axis. In the tail end detection target range α, the number of white pixels at the right end, which is the number of white pixels at the most downstream side in the rolling direction (right end in FIG. 3), the presence / absence of a column with the number of white pixels “0”, and the total number of white pixels are calculated. Ask for each.

Next, in step S3, the image processing apparatus 12 determines whether or not the image of the tail end detection target range α is a tail end image obtained by capturing the tail end based on the result of the tail end detection process in step S2. To do. Specifically, the following three items are confirmed, and when all the conditions are satisfied, the image is determined as the tail end image.
[1] The number of white pixels at the right end is equal to or greater than a constant (Y% of the number of pixels in the width direction).
[2] There is a row with 0 white pixels.
[3] The total number of white pixels is equal to or greater than a constant Z.

If it is determined that it is not the tail end, the process proceeds to step S1, and if it is determined that it is the tail end, the process proceeds to step S4.
In step S4, the image processing apparatus 12 performs edge detection processing based on the continuous image acquired in step S1. First, a target range of edge detection processing is set for the acquired continuous image, and luminance information for each pixel in the set edge detection target range is obtained. For example, when the continuous image (original image) shown in FIG. 4A is acquired, the luminance information for each pixel in the edge detection target range β is as shown in FIG. Here, in order to simplify the description, the pixels are shown very rough. The edge detection target range β is the same as the tail end detection target range α described above.

  Next, a horizontal luminance difference for each pixel is calculated in the edge detection target range β. The horizontal luminance difference is calculated by subtracting the total luminance value of several pixels (Kpx) upstream in the rolling direction from the total luminance value of several pixels (Kpx) downstream in the rolling direction. That is, when the horizontal luminance difference is calculated based on the luminance information shown in FIG. 4B with K = 1, the result shown in FIG. 4C is obtained. When the maximum value of the horizontal luminance difference is selected for each row (rolling direction), the edge portion in the edge detection target range β can be drawn as shown by the shaded area in FIG.

Next, in step S <b> 5, the image processing device 12 performs a view angle matching process on the edge image. The angle-of-view adjustment processing is an image obtained by capturing an original image captured from a direction oblique to the rolling direction (a position indicated by a solid line in FIG. 5) from a direction orthogonal to the rolling direction (a position indicated by a broken line in FIG. 5). It is processing to convert to.
FIG. 6 is a diagram showing the view angle matching principle. As shown in FIG. 6, first, an intersection P of edge extension lines at both ends in the rolling direction (x direction) of the original image is obtained. Next, a straight line L1 passing through the intersection point P and perpendicular to the image is calculated. Next, a straight line L2 passing through the intersection point P and the point (stretching point) Q in the most upstream direction in the rolling direction of the original image in the width direction is calculated. Finally, for each line of the original image, the image between the straight line L1 and the straight line L2 is stretched. In addition, at the time of the view angle matching process, a correction amount (stretching amount) of each line for the view angle matching process is determined in advance from a sample image obtained by imaging a sample plate such as a square, and the above correction amount is used to Assume that the edge image angle-of-view adjustment processing is performed.

Next, in step S6, the image processing apparatus 12 displays the angle-of-view matching processing result in step S5 on the monitor 13, and proceeds to step S7. In step S7, the image processing apparatus 12 stores the angle-of-view matching process result in step S5 in the memory, and ends the tail edge crop detection process.
In this way, the camera 11 installed outside the hot rolling line continuously images the rolled material 7 passing through a predetermined imaging position of the hot rolling line, and this is taken when the rolled material 7 passes the tail end. The tail edge image is detected and displayed on the monitor 13 and stored in the memory in the image processing device 12. At this time, the tail edge image is corrected (angle of view matching process) according to the positional relationship between the arrangement position of the camera 11 and the imaging position of the material 7 to be rolled. Thus, the operator can appropriately recognize the tail end crop shape from the corrected tail end edge image displayed on the monitor 13.

  In FIG. 1, a camera 11 corresponds to an imaging unit, an image processing device 12 corresponds to a tail end crop detection unit, and a monitor 13 corresponds to a display unit. In FIG. 2, step S2 corresponds to the tail end detection means, step S4 corresponds to the edge portion extraction means, and step S5 corresponds to the correction means.

(Operation)
Next, the operation of this embodiment will be described.
In the hot rolling facility 1, the material 7 to be rolled that has been heated to several hundred to several hundreds of degrees Celsius by the heating furnace 2 is pressed to a predetermined width by the sizing press 3, and then the rough rolling mill 4 and the finish rolling mill 5. Rolled into thin strips. At this time, the camera 11 installed outside the hot rolling line continuously images the material 7 to be rolled that passes between the third stand F3 and the fourth stand F4 of the finishing mill 5.

  The surface image of the material 7 to be rolled picked up by the camera 11 is input to the image processing device 12 at a fixed period, and the tail end detection processing is performed by the image processing device 12. When the center portion of the material 7 to be rolled passes between the third stand F3 and the fourth stand F4 of the finish rolling mill 5, the tail end detection target range in the surface image of the material 7 to be rolled captured by the camera 11 Even if α is binarized (step S2 in FIG. 2), there is no column in which the number of white pixels is “0”. Therefore, the image processing apparatus 12 determines that the image captured at this time is not a tail end image (No in step S3).

  Thereafter, the tail end of the material 7 to be rolled passes between the third stand F3 and the fourth stand F4 of the finishing mill 5, and the camera 11 displays the image 1 (original image) shown in the upper part of FIG. Is obtained. In FIG. 7, the vertical direction in the figure is the width direction of the material 7 to be rolled (upper side is the drive side, the lower side is the working side), and the left-right direction in the figure is the longitudinal direction of the material 7 to be rolled (the right side is the downstream side). The left side is the upstream side).

  At this time, the image processing device 12 performs a binarization process on the original image 1 and determines whether or not the image 1 acquired based on the binarized image is a tail end image of the material 7 to be rolled. Determine (steps S2 and S3). Since image 1 is a tail-end image, in the binarized image, [1] the number of white pixels at the right end is equal to or greater than a constant (Y% of the number of pixels in the width direction), and [2] a column with zero white pixels Yes, [3] The total number of white pixels is equal to or greater than a constant Z. Therefore, the image processing apparatus 12 determines that the image 1 is a tail end image (Yes in step S3).

  Thus, in this embodiment, the to-be-rolled material 7 is continuously imaged by the camera 11 from the outside of the hot rolling line, and the luminance information of the obtained continuous image is analyzed, thereby obtaining a predetermined value on the hot rolling line. The tail end of the material 7 to be rolled passing through the imaging position (here, between the third stand F3 and the fourth stand F4 of the finishing mill 5) is detected. At that time, the continuous image is binarized using a predetermined white pixel determination threshold value X, and the distribution of white pixels in the binarized image satisfies the conditions of the tail end image (the above conditions [1] to [3]). When it is determined that it is the tail end.

FIG. 8 shows the result of measuring the tail end detection rate when the binarization processing is performed as in the present embodiment and when the binarization processing is not performed during the tail end detection processing. In the method that does not perform binarization processing, the tail end detection rate was 94%, whereas in the method that performs binarization processing, the tail end detection rate was 100%.
When imaging the material 7 to be rolled that passes between the finish rolling stands (between F3 and F4) of the hot rolling line as in the present embodiment, the image has a relatively small luminance fluctuation due to the temperature and water vapor in the line. It will be a thing. For this reason, if the tail end is detected without performing the binarization process, an oversight occurs. By performing the tail end detection process using the binarization process, it is possible to accurately detect the tail end from the continuous images.

  If the image processing device 12 determines that the image 1 is a tail end image, the image processing device 12 extracts an edge portion of the image 1 (step S4). The edge image obtained at this time is as shown in the lower part of FIG. Next, the image processing apparatus 12 performs a view angle matching process on the edge image (step S5). Thereby, the image imaged from diagonally with respect to the rolling direction is converted into the image imaged from the direction orthogonal to the rolling direction. The edge image after the angle adjustment is as shown in the lower part of FIG.

  The edge shape shown in the lower part of FIG. 7B is the planar shape of the tail end of the material 7 to be rolled. Therefore, the image processing apparatus 12 displays the planar shape on the monitor 13 (step S6) and stores it in the memory (step S7). As shown in the lower part of FIG. 7B, the planar shape of the tail end of the material 7 to be rolled is a rectangular shape, and no elongation occurs on either the drive side or the work side of the material 7 to be rolled. . Therefore, in this case, the operator recognizes that no tail end cropping has occurred from the planar shape of the tail end displayed on the monitor 13.

By the way, in this embodiment, the arrangement position of the camera 11 in the rolling direction is offset by a predetermined distance with respect to the imaging position of the material 7 to be rolled, and the camera 11 removes the material 7 to be rolled from an oblique direction with respect to the rolling direction. In order to capture an image, the planar shape of the material 7 to be rolled is distorted obliquely according to the imaging angle. That is, as shown in FIG. 7B, even if the actual planar shape is rectangular, as shown in FIG. 7A, the original image is on one side in the width direction (here, the working side). Becomes a shape extending in the longitudinal direction. Therefore, if the original image is used as it is as a planar image of the material 7 to be rolled, the tail end crop shape cannot be accurately recognized, and it is erroneously determined that the tail end crop has occurred.
On the other hand, in the present embodiment, by performing an angle-of-view adjustment process on the original image, an image viewed from an oblique direction with respect to the rolling direction is converted into an image viewed from a direction orthogonal to the rolling direction. To do. Therefore, the tail end crop shape can be accurately recognized.

  Thereafter, the subsequent material 7 to be rolled is conveyed on the hot rolling line, and its tail end passes between the third stand F3 and the fourth stand F4 of the finish rolling mill 5, and is shown in FIG. Assume that image 2 (original image) shown in the upper part of FIG. Then, the image processing apparatus 12 determines that the image 2 is the tail end image of the material 7 to be rolled as a result of performing the binarization process on the original image 2 (Yes in step S3). Therefore, the image processing apparatus 12 extracts an edge portion of the image 2 (step S4), and further performs an angle-of-view adjustment process on the edge image (step S5). The edge image of the original image is as shown in the lower part of FIG. 7C, and the edge image after the angle adjustment is as shown in the lower part of FIG. Therefore, the image processing device 12 displays the planar shape of the tail end of the material 7 to be rolled shown in the lower part of FIG. 7D on the monitor 13 (step S6) and stores it in the memory (step S7).

  The operator confirms the planar shape of the tail end displayed on the monitor 13 and determines the presence or absence of the tail end cropping. At this time, in the image 2, as shown in the lower part of FIG. 7D, the planar shape of the tail end is not rectangular, and the work side extends in the longitudinal direction. It can be judged. At this time, the tail end crop shape can be accurately recognized.

  By the way, when recognizing the tail end crop shape of the material to be rolled conveyed through the hot rolling line, it is common to use a camera or the like installed in the hot rolling line. Since the installation environment is poor due to problems such as heat and steam, it is necessary to take various measures such as heat resistance and steam resistance to install the camera in the line. For this reason, a higher cost is required. In addition, since it is necessary to perform camera maintenance in the line, maintenance work cannot be performed while the line is in operation. That is, since the maintenance work is accompanied by a long stop of the line, productivity is lowered.

  On the other hand, in this embodiment, the tail end crop of the to-be-rolled material 7 is detected by imaging the to-be-rolled material 7 conveyed by the camera 11 installed outside the hot-rolling line. be able to. As described above, since the camera 11 for imaging the material 7 to be rolled is installed outside the hot rolling line with good installation environment, it is not necessary to take measures such as heat resistance and steam resistance for the camera, and the cost is reduced accordingly. be able to. Further, since the maintenance work of the camera 11 can be performed outside the hot rolling line, the maintenance can be performed even during the line operation. Thus, it can be set as a suitable structure in terms of cost and maintenance.

(effect)
As described above, in the above embodiment, the imaging means for imaging the material to be rolled conveyed on the hot rolling line is installed outside the hot rolling line, and the tail end crop of the material to be rolled is detected. However, it is not necessary to take various measures such as heat resistance and steam resistance, and the cost increase can be suppressed, and the imaging means can be maintained even during operation of the hot rolling line. Moreover, since disturbances to the imaging means such as temperature and water vapor can be eliminated, the tail end crop can be detected with high accuracy.

  Further, in the tail end crop detection processing, after detecting the tail end image obtained by imaging the tail end of the material to be rolled from the continuous surface image of the material to be rolled taken by the imaging means, the edge in the detected tail end image is detected. Edge detection processing for detecting a part is performed. At this time, since the tail end image is detected based on the distribution of the white pixels in the binarized continuous image obtained by binarizing the continuous surface image of the rolled material imaged by the imaging unit, the hot rolling line is The tail end of the material to be rolled can be detected with high accuracy. In addition, since the edge detection process is performed on the tail end image, the tail end crop shape can be accurately depicted.

  In addition, an angle-of-view adjustment process for correcting the edge image obtained by the edge detection process based on the relationship between the arrangement position of the imaging means and the imaging position of the material to be rolled is performed, and the result is obtained by changing the planar shape of the material to be rolled. The edge image is shown. Therefore, converting the edge image obtained by viewing the tail end of the material to be rolled from the oblique direction with respect to the rolling direction into the edge image viewed from the direction orthogonal to the rolling direction, and determining the presence or absence of the tail end crop. Can do. Therefore, when one end side in the width direction of the material to be rolled seems to extend due to the relationship between the position of the imaging means and the imaged position of the material to be rolled, even though no tail end cropping has actually occurred. Even so, it is possible to prevent erroneous determination that the tail crop has occurred.

Further, since the detected tail end crop is displayed on the monitor, the operator can easily recognize the shape of the tail end crop.
As described above, it is possible to provide a tail end crop detection device that is inexpensive and can be maintained even during line operation without taking various measures such as heat resistance and steam resistance. Moreover, since disturbances such as temperature and water vapor can be eliminated, the tail end crop can be detected with high accuracy.

(Application examples)
In addition, in the said embodiment, after identifying the crop shape of a tail end, the case where it displayed on the monitor 13 was demonstrated, but meandering prevention control of the to-be-rolled material 7 can also be performed based on the recognized crop shape. . Specifically, a wedge ratio is obtained from the recognized crop shape, and based on the wedge ratio, a finish rolling stand (here, the fourth stand F4 to the seventh stand F7) downstream from the imaging position to prevent meandering. ) And the roll opening difference between the driving side and the driving side may be controlled. As a result, the difference in roll opening between the work side and the drive side of the finish rolling stand can be corrected so that the planar shape of the tail end of the material to be rolled is symmetric in the width direction. Generation of a wraparound moment force can be prevented, and meandering can be prevented.

  Moreover, although the said embodiment demonstrated the case where the imaging position of the to-be-rolled material 7 was only between finishing rolling stands F3-F4, you may provide two or more said imaging positions. In this case, after imaging between the finishing rolling stands F3-F4 with one camera 11, the camera 11 can be moved, for example, imaging between the finishing rolling stands F6-F7. Thereby, since the to-be-rolled material 7 can be imaged in a several imaging position, without providing several cameras 11, it can be set as an inexpensive installation.

  DESCRIPTION OF SYMBOLS 1 ... Hot rolling equipment, 2 ... Heating furnace, 3 ... Sizing press, 4 ... Rough rolling mill, 5 ... Finish rolling mill, 6 ... Winding equipment, 7 ... Rolled material, 10 ... Tail end crop detection apparatus, 11 ... Camera (imaging means), 12 ... Image processing device (tail end crop detection means), 13 ... Monitor (display means)

Claims (5)

A tail end crop detection device for detecting a tail end crop of a material to be rolled at several hundred to several hundreds of degrees Celsius passing between finish rolling stands of a hot rolling line,
An imaging unit that is arranged outside the hot rolling line and at a position along the hot rolling line and continuously captures a surface image of the material to be rolled that passes a predetermined imaging position on the hot rolling line; there are, it is not necessary to the installed a camera for imaging a material to be rolled out good hot rolling line of the installation environment take measures for heat and steam-resistant to the camera, given the camera to the imaging position It is arranged at a position where the distance can be offset and maintenance work can be performed even during line operation, and it is composed of a near-infrared camera that is set to a shutter speed according to the passing speed of the material to be rolled between the finishing rolling stands Imaging means for continuously imaging the surface image of the material to be rolled at several hundred to several hundreds of degrees Celsius passing through a predetermined imaging position on the hot rolling line with near infrared luminance;
Based on a surface image of the material to be rolled at several hundred to several hundreds of degrees Celsius picked up by the imaging means configured with the near infrared camera, a crop at the tail end of the material to be rolled is detected. And a tail end crop detection means. The tail end crop detection means includes:
From a continuous surface image of the material to be rolled imaged by the imaging means, a tail edge detecting means for detecting a tail edge image of the tail edge of the material to be rolled,
Edge portion extraction means for extracting an edge portion in the tail edge image detected by the tail edge detection means,
2. The tail end crop detection apparatus according to claim 1, wherein the tail end crop of the material to be rolled is detected based on the edge portion extracted by the edge portion extracting means.   The tail end detection means has a white pixel distribution in a binarized continuous image obtained by binarizing a continuous surface image of the rolled material imaged by the imaging means, satisfying the condition of the tail end image. The tail end crop detection apparatus according to claim 2, wherein a distributed region is detected as the tail end image. The imaging means is arranged such that the arrangement position in the rolling direction of the hot rolling line is a position offset by a predetermined distance with respect to the imaging position of the material to be rolled,
The tail end crop detection means includes:
The image processing apparatus includes a correction unit that corrects an edge image corresponding to the edge portion extracted by the edge portion extraction unit based on a relationship between an arrangement position of the imaging unit and an imaging position of the material to be rolled. The tail end crop detection device according to claim 2 or 3.   The tail end crop detection device according to claim 1, further comprising display means for displaying the tail end crop detected by the tail end crop detection means on a monitor.

Images