Meandering monitoring method and system

Abstract

To predict the occurrence of a meander of a strip in a continuous annealing furnace easily with high accuracy.SOLUTION: A meander monitoring method for monitoring the occurrence of a meander of a strip traveling in a continuous annealing furnace, comprises: an imaging step of imaging a region having the width equal to or greater than the plate width of the strip in the plate width direction of the strip; a light emission step of illuminating the strip with diffusion light such that a highlight part extending in the plate width direction of the stripe as a reflection shape of reflection light of a surface of the strip can be imaged by the imaging step; and a meander monitoring step of monitoring the occurrence of the meander of the strip by using a photographed image captured by the imaging step. The meander monitoring step predicts the occurrence of the meander of the strip on the basis of an output result of a learned model that is learned with the photographed image and the meander presence / absence of the strip being teacher data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a meandering monitoring method and a meandering monitoring system. [Background technology]

[0002] When a strip is threaded through a continuous annealing furnace, it may meander (sometimes called "walk") inside the furnace. If the amount of meandering (the extent of meandering) is large, it may lead to the strip coming into contact with the furnace wall or breaking. For this reason, it is necessary to suppress meandering at the latest before the amount of meandering becomes significant.

[0003] Generally, applying a high strip tension can prevent meandering, but it also causes strip buckling (creases in the strip running direction near the center of the strip width direction, and in severe cases, strip breakage; this is sometimes referred to as heat buckling). For this reason, the strip tension is set to a value that does not cause buckling, and when meandering occurs, an operation to suppress meandering by reducing the strip running speed (strip running speed reduction operation) or by using a steering roll that centers the strip on the roll (steering roll operation) may be performed. However, since the strip running speed reduction operation and steering roll operation are performed when meandering occurs, i.e., after meandering has occurred, the amount of meandering may already be significant by the time the operation is performed, it is not possible to sufficiently prevent the strip from contacting the furnace wall or from breaking.

[0004] Furthermore, it is desirable that the strip running through the continuous annealing furnace is dead flat (precisely flat), but in reality, C-warp, unevenness (described later), etc. may occur.

[0005] Patent Documents 1 and 2 disclose techniques for detecting heat buckles based on image signals obtained by irradiating a strip with a linear laser beam in the width direction and capturing an image of the irradiated portion. Patent Documents 1 and 2 mention C-warp of the strip as a noise component for detecting heat buckles. Patent Document 3 discloses a technique for correcting predicted meandering of a strip in a continuous annealing furnace using data obtained by combining a meandering correction amount based on the amount of meandering of the strip obtained by capturing an image of the strip running near a steering roll in the continuous annealing furnace and a meandering correction amount based on an analysis of the shape of the strip after cold rolling before the continuous annealing process. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Publication No. 63-062825 [Patent Document 2] Japanese Patent Application Publication No. 63-274806 [Patent Document 3] Japanese Patent Application Publication No. 5-017831 Summary of the Invention [Problem to be solved by the invention]

[0007] However, Patent Documents 1 and 2 do not describe the occurrence of meandering or the prevention of meandering, and the techniques disclosed therein naturally cannot predict the occurrence of meandering in a continuous annealing furnace. The technique of Patent Document 3 predicts the occurrence of meandering as a prerequisite for correcting meandering. However, since the shape of the strip after cold rolling is flattened (heat flattened) in the continuous annealing furnace and the degree of flattening is not uniform (because flattening sometimes progresses and sometimes does not), the technique of Patent Document 3 cannot accurately predict the occurrence of meandering. In other words, the conventional techniques listed in the patent documents have a problem in that they cannot accurately predict the occurrence of meandering in a continuous annealing furnace. Note that the techniques of Patent Documents 1 and 2 use linear laser light, making it difficult to detect irregularities (described below) that may occur in the strip. Furthermore, the technique of Patent Document 3 directly detects the amount of meandering of the strip in a continuous annealing furnace, but does not mention irregularities (described below) that may occur in the strip in a continuous annealing furnace. An object of the present invention is to provide a technique for solving the above-mentioned problems, that is, a technique for predicting the occurrence of meandering of a strip in a continuous annealing furnace simply and with higher accuracy. [Means for solving the problem]

[0008] One aspect of the present invention is a meandering monitoring method for monitoring the occurrence of meandering of a strip traveling within a continuous annealing furnace, the method comprising: an imaging step of imaging an area of ​​the strip in the width direction of the strip that is equal to or greater than the width of the strip; a light emitting step of illuminating the strip with diffused light so that the imaging step can image a highlight portion that extends in the width direction of the strip as a reflection shape of light reflected from the surface of the strip; and a meandering monitoring step of monitoring the occurrence of meandering of the strip using the image captured by the imaging step, wherein the meandering monitoring step predicts the occurrence of meandering of the strip based on the output result of a trained model that has been trained using the image and training data on whether or not the strip is meandering.

[0009] Another aspect of the present invention is a meandering monitoring system that monitors the occurrence of meandering of a strip traveling within a continuous annealing furnace, comprising: imaging means that images an area of ​​the strip in the width direction of the strip that is equal to or greater than the width of the strip; light emitting means that illuminates the strip with diffused light so that the imaging means can image a highlight portion that extends in the width direction of the strip as a reflection shape of light reflected from the surface of the strip; and meandering monitoring means that monitors the occurrence of meandering of the strip using the image captured by the imaging means, wherein the meandering monitoring system predicts the occurrence of meandering of the strip based on a determination result of a trained model that has learned using the image captured and the presence or absence of meandering of the strip as training data. [Effects of the Invention]

[0010] According to the present invention, the occurrence of meandering of a strip in a continuous annealing furnace can be predicted simply and with higher accuracy. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a diagram illustrating an example of the configuration of a meandering monitoring system 1. FIG. [Figure 2] 10 is an example of an image. [Figure 3] FIG. 1 is a diagram illustrating a trained model 300. [Figure 4] FIG. 2 is a diagram illustrating an example of the configuration of a model generating device 30. [Figure 5] 10 is a flowchart showing an example of the operation of the meandering monitoring device 40. [Figure 6] 10A and 10B are diagrams illustrating an example of an evaluation result of the meandering monitoring system 1. [Figure 7] 1 is a diagram for clearly explaining the features of the meandering monitoring system 1. FIG. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Fig. 1 is a diagram showing an example of the configuration of a meandering monitoring system 1. Fig. 2 shows an example of an image. Specifically, each of Figs. 2(A) to 2(C) is a portion of an image captured by an imaging device 10 (an image after trimming by a meandering monitoring device 40). Fig. 3 is a diagram illustrating a trained model 300. The meandering monitoring system 1 is a system that monitors the occurrence of meandering of a strip traveling in a heat treatment furnace (a continuous annealing furnace, for example, a vertical continuous annealing furnace) in a line where strips (steel plates) are welded and continuously processed.

[0013] The width of the strip traveling in the continuous annealing furnace is, for example, 800 mm to 1200 mm. The thickness of the strip traveling in the continuous annealing furnace is, for example, 0.50 mm or less (the lower limit is about 0.10 mm). The traveling speed of the strip is, for example, 200 (m / min) to 500 (m / min). Note that the strip may be cold-rolled at a cold rolling reduction ([cold-rolled base sheet thickness - steel sheet thickness] / cold-rolled base sheet thickness) of 80% or more in a process before entering the continuous annealing furnace, and may be washed with an alkaline washing solution or the like. The strip may also be tinplate.

[0014] The meandering monitoring system 1 predicts the occurrence of meandering in the strip. Specifically, the meandering monitoring system 1 predicts the occurrence of meandering of a magnitude equal to or greater than a danger level in the strip. The danger level meandering may be, for example, the amount of meandering that causes the strip to come into contact with the furnace wall. For example, if the meandering magnitude that causes the strip to come into contact with the furnace wall is 200 mm, the danger level meandering may be 50 mm. In other words, the meandering monitoring system 1 predicts an increase in the amount of meandering (increase to 50 mm or greater) at a stage before meandering of the strip occurs (a stage where the amount of meandering is 0 mm) or at a stage where the amount of meandering is small (a stage where the amount of meandering is less than about 50 mm). The meandering monitoring system 1 outputs an alarm when it predicts the occurrence of meandering in the strip (specifically, the occurrence of meandering of a magnitude equal to or greater than a danger level; the same applies hereinafter).

[0015] As shown in Fig. 1, the meandering monitoring system 1 includes an imaging device 10, a light source 20, a meandering monitoring device 40, and a display device 50. For ease of explanation, Fig. 1 also shows a trained model 300 (described later) stored in the meandering monitoring device 40 (trained model storage unit 149).

[0016] The imaging device 10 is an in-furnace camera that images a strip in a continuous annealing furnace. The imaging device 10 images an area of ​​the strip width direction that is equal to or greater than the strip width (for example, if the strip width is 1000 mm, then equal to or greater than 1000 mm). That is, the imaging device 10 is installed at a position / angle that allows it to image an area of ​​the strip width direction that is equal to or greater than the strip width.

[0017] Furthermore, the imaging device 10 may capture an image of an area that is 0.4 times or more the width of the strip in the strip threading direction (traveling direction) (for example, 400 mm or more when the strip width is 1000 mm). In other words, the imaging device 10 may be installed at a position / angle that allows it to capture an image of an area that is equal to or larger than the strip width in the strip width direction and is 0.4 times or more the width of the strip in the strip threading direction.

[0018] The imaging device 10 may image the strip on the roll (the strip wound around the roll), or may image the strip between the rolls (the strip between the upper roll and the lower roll in the case of a vertical continuous annealing furnace). Imaging the strip between the rolls is preferable because it allows for more prominent imaging of irregularities (uneven portions) that may occur in the strip.

[0019] The imaging method by the imaging device 10 may be, for example, to capture video at a predetermined frame rate (for example, 1 / 30 seconds per frame). The imaging device 10 transmits (outputs) the captured images to the meandering monitoring device 40 via a wired or wireless connection. For example, the imaging device 10 transmits the captured images to the meandering monitoring device 40 every frame (1 / 30 seconds) (in real time).

[0020] The imaging device 10 may be a dedicated device for transmitting captured images to the meandering monitoring device 40, or may be a device for transmitting captured images to both the meandering monitoring device 40 and another device (for example, an in-furnace video display device (in-furnace video monitor) not shown). That is, the imaging device 10 may transmit captured images exclusively to the meandering monitoring device 40, or may be a device for transmitting captured images to both the meandering monitoring device 40 and another device. In the latter case, for example, a distributor (not shown) or the like may be used to transmit captured images to both the meandering monitoring device 40 and another device in the same way, or both the meandering monitoring device 40 and another device may be specified as destinations (destinations) of the captured images in the imaging device 10, so that the captured images are transmitted to both the meandering monitoring device 40 and another device in the same way.

[0021] The light source 20 is a diffuse light source (a light source excluding directional laser light, for example, linear laser light) such as an LED or an incandescent lamp. The light source 20 illuminates (irradiates) the strip with diffused light. The light source 20 illuminates the strip with diffused light so that the light reflected from the strip surface can be captured by the imaging device 10, specifically so that a highlight portion extending in the width direction of the strip can be captured by the imaging device 10 as the shape (reflection shape) of the light reflected from the surface of the strip.

[0022] Strips passing through continuous annealing furnaces are known to have wavy shapes (strips exhibiting wavy, uneven shapes) such as C-warp, edge waves, and center roll. The uneven shapes (e.g., symbols B and C in FIG. 2(B)) that constitute the wavy shapes can occur at various locations (locations where protrusions or recesses occur), such as the center in the strip width direction, one end in the strip width direction, or the other end in the strip width direction. The uneven shapes may have, for example, a steep or gentle slope of the slope of the protrusions or recesses, a wide or narrow region where the protrusions or recesses are formed, or one or more recesses or protrusions in the strip width direction. In other words, the uneven shapes of strips have various characteristics, such as the location where they occur, the slope, the region where they are formed, and the number of recesses or protrusions that occur. Regarding the occurrence of meandering, for example, there are cases where meandering is observed when an uneven shape is present at the end of the plate in the plate width direction, and cases where meandering is observed when an uneven shape is present in the center of the plate in the plate width direction. The inventors of the present application have found that it is difficult to attribute this to a specific causal relationship, and have considered that the various characteristics described above interact with each other to determine whether or not meandering occurs. Therefore, the inventors of the present application considered using a linear laser light as described in Patent Documents 1 and 2 to grasp the unevenness of the wavy shape of the strip in the width direction of the plate and detect the occurrence of meandering, but found that there were problems with practical use due to non-detection, false detection, and over-detection occurring.

[0023] Buckling generally presents a wave-like shape in the width direction (the surface moves up and down in the width direction) and may involve plastic deformation, but does not present a wave-like shape in the running direction (the surface moves up and down in the running direction).In contrast, unevenness presents a wave-like shape in both the width direction and the running direction, but does not generally involve plastic deformation.

[0024] The reflection shape that appears in the captured image captured by the imaging device 10 changes depending on the uneven shape of the strip, even if the position / angle of the light source 20 is constant (even if the light source 20 is fixed). In other words, the meandering monitoring device 40 can recognize various characteristics of the uneven shape of the strip (such as the steepness of the above-mentioned concave and convex parts) from the reflection shape in the captured image. The inventors of the present application found a relationship between the occurrence of irregularities on the surface of the strip and the occurrence of meandering of the strip, and focused on the details of the irregular shape of the strip in monitoring (predicting) the occurrence of meandering of the strip.

[0025] The image shown in Fig. 2(A) is an image taken when the surface of the strip is flat (when there are no irregularities). In the image shown in Fig. 2(A), a highlight portion (designated by symbol A in the figure) that spreads in the width direction of the strip is captured as a reflection shape on the strip surface. In other words, when the surface shape of the strip is flat, the light source 20 is installed at a position / angle that allows the imaging device 10 to capture the highlight portion that spreads in the width direction of the strip as a reflection shape on the strip surface.

[0026] The image shown in Figure 2(B) shows an image of a strip with unevenness on its surface, which shows a state in which the strip exhibits a wave-like shape. In the image shown in Figure 2(B), the symbol B indicates the reflection shape caused by the convex portions extending in the strip width direction and the strip running direction, and the symbol C indicates the reflection shape caused by the concave portions extending in the strip width direction and the strip running direction.

[0027] The image shown in Figure 2(C) is an image of a strip with unevenness on its surface. The image shown in Figure 2(B) captures the reflection shapes caused by simple convex and concave portions, whereas the image shown in Figure 2(C) captures the reflection shapes caused by complex convex and concave portions. In the image shown in Figure 2(C), symbol D indicates the reflection shape caused by convex portions extending in the strip width direction and strip running direction, and symbol E indicates the reflection shape caused by concave portions occurring near the tops of the convex portions.

[0028] In addition, as shown in Figures 2(B) and 2(C), multiple irregularities may be observed in relatively close proximity. The shapes of irregularities vary widely in terms of the location where they occur, the degree of inclination, the region where they are formed, the number of occurrences, etc.

[0029] Note that the simple unevenness shown in Figure 2(B) and the complex unevenness shown in Figure 2(C) are sometimes referred to as simple unevenness (simple uneven portion) and complex unevenness (complex uneven portion), respectively. Furthermore, the depressions (complex uneven portion) that appear at the tops of the protrusions, such as those indicated by symbol E in Figure 2(C), appear and disappear continuously, resulting in a motion that can be described as "fluttering (of the strip)." The present inventors have discovered that the presence of complex unevenness as shown in Figure 2(C) is closely related to the occurrence of meandering. Therefore, they have noted that the occurrence of meandering is related not only to the wave shape (unevenness) of the strip in the strip width direction, but also to the size of the area where the wave shape (unevenness) occurs in the strip traveling direction and the state in which the unevenness intrudes, i.e., the occurrence of complex uneven portion. They have noted that detecting the wave shape in the strip traveling direction can improve the accuracy of meandering detection. The above is based on the findings of actual observations that, when complex unevenness (fluttering) occurs, the area where unevenness occurs in the strip traveling direction expands, and the shape of the unevenness changes, such as the appearance or disappearance of complex shapes where recesses occur near the tops of the protrusions.These changes in the shape of unevenness that are specific to fluttering cannot be confirmed unless the unevenness in both the strip width direction and the strip traveling direction is understood. It should be noted that the methods described in Patent Documents 1 to 3 do not evaluate the wavy shape in the entire width direction of the sheet and in the strip running direction in a continuous annealing furnace, i.e., do not evaluate the shape specific to complex uneven portions, and therefore are considered to have low accuracy in detecting meandering.

[0030] The meandering monitoring device 40 monitors (predicts) the occurrence of meandering of a strip traveling in a continuous annealing furnace based on the captured image (specifically, the reflection shape corresponding to the surface shape of the strip) captured by the imaging device 10. The meandering monitoring device 40 is configured, for example, by one server or one personal computer. As shown in FIG. 1 , the meandering monitoring device 40 includes an acquisition unit 141, a cutout unit 142, a meandering monitoring unit 143, a graphing unit 147, an output unit 148, and a trained model storage unit 149. The meandering monitoring unit 143 includes a probability calculation unit 144, an average value calculation unit 145, and a determination unit 146.

[0031] The acquisition unit 141 acquires captured images from the imaging device 10 and outputs (supplies) the acquired captured images to the cropping unit 142. Specifically, the acquisition unit 141 outputs the acquired captured images to the cropping unit 142 every time it acquires a captured image from the imaging device 10. For example, when acquiring captured images in frame units (every 1 / 30 seconds), the acquisition unit 141 outputs the acquired captured images to the cropping unit 142 every 1 / 30 seconds. Note that, although it has been described that the imaging device 10 transmits captured images to the meandering monitoring device 40 via a wired or wireless connection, the acquisition unit 141 acquires captured images in a reception mode (wired or wireless) corresponding to the transmission mode (wired or wireless) of the imaging device 10.

[0032] The cropping unit 142 acquires a captured image from the acquisition unit 141, crops out a still image from the acquired captured image, trims the cropped still image, and outputs the cropped still image (an image such as that shown in FIGS. 2(A) to 2(C)) to the meandering monitoring unit 143. Every time the cropping unit 142 acquires a captured image from the acquisition unit 141 (for example, every 1 / 30 seconds), the cropping unit 142 crops out a still image, trims the cropped still image, and outputs the cropped still image to the meandering monitoring unit 143. Note that the cropping unit 142 may crop out a still image to a trimming size and output the cropped still image to the meandering monitoring unit 143 every time the cropping unit 142 acquires a captured image from the acquisition unit 141.

[0033] The trained model storage unit 149 stores the trained model 300. The trained model storage unit 149 may be a hard disk or a solid state drive (SSD). The trained model 300 is generated by a model generation device 30 (described later) and stored in the trained model storage unit 149 via communication or via a storage medium (CD-ROM, USB memory, etc.). Note that a trained model represented by parameters (trained parameters) optimized through training (learning) is referred to as a trained model. A trained model is generated by training a training model and optimizing the parameters through training.

[0034] The trained model 300 receives an image captured by the imaging device 10 (specifically, an image processed by the clipping unit 142) and outputs a determination result regarding the occurrence of meandering in the strip. Specifically, the trained model 300 is a model that can output, as a determination result, the probability (meandering occurrence probability) that meandering will occur in the strip (specifically, meandering with an amount of meandering equal to or greater than the danger level) each time an image is acquired from the clipping unit 142.

[0035] The trained model 300 is a model expressed using a neural network, for example, as shown in FIG. 3. The trained model 300 may be, for example, a DNN (Deep Neural Network). The trained parameters include, for example, the number of layers of the neural network, the number of neurons in each layer, the connection relationships between neurons, the weights (connection loads) of the connections between each neuron, and the thresholds of each neuron. The trained model 300 shown in FIG. 3 includes an input layer 301, one or more intermediate layers 302 (hidden layers), and an output layer 303. Each of the layers 301, 302, and 303 includes one or more neurons. The number of intermediate layers 302, the number of neurons in each layer, etc. are set by the trained parameters.

[0036] The image processed by the cropping unit 142 is input to the input layer 301. The output layer 303 outputs output values ​​indicating the probability that meandering will occur in the strip (0.00 to 1.00) and the probability that meandering will not occur in the strip (0.00 to 1.00). The sum of the probability that meandering will occur in the strip and the probability that meandering will not occur in the strip is 1. Note that a probability of "0.00" is 0%, and a probability of "1.00" is 100%.

[0037] As described above, the trained model 300 is generated by the model generation device 30 (described later), which will be described later.

[0038] The meandering monitoring unit 143 monitors the occurrence of meandering of the strip based on the captured image captured by the imaging device 10 (specifically, the image after processing by the cropping unit 142) and the trained model 300 stored in the trained model memory unit 149.

[0039] The probability calculation unit 144 of the meandering monitoring unit 143 acquires an image from the clipping unit 142, calculates the probability that meandering will occur in the strip using the trained model 300, and outputs the calculated probability to the average calculation unit 145. In other words, the probability calculation unit 144 inputs the image acquired from the clipping unit 142 to the trained model 300, acquires the probability that meandering will occur in the strip as an output from the trained model 300, and outputs the acquired probability to the average calculation unit 145. The probability calculation unit 144 calculates (acquires) the probability every time it acquires an image from the clipping unit 142 (for example, every 1 / 30 seconds), and outputs it to the average calculation unit 145.

[0040] The average value calculation unit 145 of the meandering monitoring unit 143 acquires the probabilities from the probability calculation unit 144, calculates a moving average (moving average value) of the acquired probabilities, and outputs the calculated moving average value to the determination unit 146 and the graphing unit 147. The average value calculation unit 145 calculates a moving average value of a predetermined number of probabilities (for example, 10 to 12,000) immediately preceding the currently acquired probability, including the currently acquired probability. In other words, the average value calculation unit 145 calculates a moving average value of the probabilities calculated from each of the predetermined number of images (10 images to 12,000 images) immediately preceding the currently acquired image by the probability calculation unit 144. When the probability calculation unit 144 calculates the probabilities every 1 / 30 seconds, the average value calculation unit 145 calculates a moving average value of the probabilities calculated from each of the images (10 images to 12,000 images) in a time range of 1 / 3 seconds (for 10 images) to 400 seconds (for 12,000 images). The average value calculation unit 145 calculates a moving average value every time it acquires a probability from the probability calculation unit 144 (for example, every 1 / 30 seconds), and outputs the calculated moving average value to the determination unit 146 and the graphing unit 147.

[0041] The determination unit 146 of the meandering monitoring unit 143 acquires the moving average value from the average value calculation unit 145, compares the acquired moving average value with a predetermined threshold, and monitors the occurrence of meandering of the strip. Specifically, if the moving average value exceeds the predetermined threshold, the determination unit 146 outputs alarm information warning about meandering to the output unit 148, and if the moving average value is equal to or less than the predetermined threshold, the determination unit 146 does not output alarm information to the output unit 148. Every time the determination unit 146 acquires the moving average value from the average value calculation unit 145 (for example, every 1 / 30 seconds), the determination unit 146 compares the moving average value with the predetermined threshold, and if the moving average value exceeds the predetermined threshold, outputs alarm information to the output unit 148.

[0042] The control parameters for controlling the operation of the meandering monitoring unit 143 (specifically, the range (number of probabilities / number of images / time) within which the average calculation unit 145 calculates the moving average value, and the predetermined threshold value that the determination unit 146 compares with the moving average value) can be set appropriately. For example, the control parameters may be determined depending on the frequency of false alarms (when an alarm is output but no meandering actually occurred) and the acceptable range for false alarms. As an example, 30 probabilities (i.e., 30 images equivalent to one second) may be set as the range within which the average calculation unit 145 calculates the moving average value, and 0.5 may be set as the predetermined threshold value that the determination unit 146 compares with the moving average value.

[0043] Note that, when the average value calculation unit 145 sets 30 probabilities as the range for calculating the moving average value, and the determination unit 146 sets 0.5 as the predetermined threshold for comparison with the moving average value, even if the average value calculation unit 145 continues to acquire probability "0.00" from the probability calculation unit 144 before a certain timing (timing T) and continues to acquire probability "1.00" from the probability calculation unit 144 after timing T, the moving average value calculated by the average value calculation unit 145 will exceed "0.5" when the 16th probability "1.00" is acquired from timing T. In other words, although this is natural given the nature of the moving average value, when the determination unit 146 determines that the moving average value exceeds the predetermined threshold, it does not suddenly exceed the predetermined threshold, but rather approaches the predetermined threshold (or sometimes moves away from it) before exceeding the predetermined threshold.

[0044] Graphing unit 147 acquires the moving average value from average value calculation unit 145, generates graphing display information for graphing and displaying the acquired moving average value (for example, graphing into a line graph or a bar graph), and outputs the graphing display information to output unit 148. Graphing unit 147 outputs the graphing display information to output unit 148 every time it acquires a moving average value from average value calculation unit 145 (for example, every 1 / 30 seconds).

[0045] The output unit 148 acquires graphing display information from the graphing unit 147 and outputs the acquired graphing display information to the display device 50. Every time the output unit 148 acquires graphing display information from the graphing unit 147 (for example, every 1 / 30 seconds), the output unit 148 outputs the graphing display information to the display device 50. Furthermore, when the output unit 148 acquires alarm information from the determination unit 146, the output unit 148 outputs the acquired alarm information to the display device 50.

[0046] The display device 50 is an indicator display monitor that displays an indicator of meandering of the strip. Specifically, the display device 50 acquires graphing display information from the output unit 148 and displays a graph (e.g., a line graph of moving average values, a bar graph of moving average values) based on the acquired graphing display information. Furthermore, when alarm information is acquired from the output unit 148, the display device 50 displays an alarm based on the acquired alarm information (e.g., on the same screen as the graph). Note that when alarm information is acquired, the display device 50 may output an alarm as sound instead of or in addition to displaying the alarm.

[0047] As described above, the display device 50 always displays the graph (regardless of whether the moving average value is 0.00 to 1.00), and outputs an alarm when alarm information is acquired. Note that, upon confirming the alarm, the operator considers measures to address the occurrence of meandering (for example, changing the strip threading speed (slowing down) or changing the strip tension (increasing the tension)), and implements them as necessary.

[0048] FIG. 4 is a diagram showing an example configuration of the model generation device 30. The model generation device 30 generates a trained model 300 to be used in the meandering monitoring device 40. The model generation device 30 is configured, for example, by one server or one personal computer. As shown in FIG. 4, the model generation device 30 includes a model generation unit 133 and a storage unit 139. For convenience of explanation, FIG. 4 also shows a training dataset 250 (described below) and a trained model 300.

[0049] The model generation device 30 trains a learning model using a learning dataset 250 to generate a trained model 300. The learning dataset 250 includes input samples and output samples. The input samples are data input to the input layer (input layer 301 in FIG. 3) when training the learning model. The output samples are data (also referred to as training data or correct answer labels) that serve as correct answers to be compared with output values ​​from the output layer (output layer 303 in FIG. 3) when training the learning model.

[0050] The input samples in the training dataset 250 are images based on captured images taken by the imaging device 10 (still images (e.g., cropped images) obtained from captured images taken by the imaging device 10). Specifically, the input samples are an image based on a captured image before an actual meandering (specifically, a meandering of an amount equal to or greater than a danger level) occurs (hereinafter referred to as an image with meandering), and an image based on a captured image when no meandering occurs (hereinafter referred to as an image without meandering).

[0051] The output samples in the training dataset 250 are information regarding the presence or absence of meandering of the strip for each input sample (presence or absence of meandering). Specifically, for the input sample "image with meandering", the output sample indicates the presence of meandering (information indicating the presence of meandering), and for the input sample "image without meandering", the output sample indicates the absence of meandering (information indicating the absence of meandering). In other words, the pairs of "input sample-output sample" are "image with meandering - presence of meandering" and "image without meandering - absence of meandering".

[0052] In addition, it is believed that the rate (possibility) of complex uneven portions being captured as the reflection shape of the strip in an image with meandering occurring is higher than the rate (possibility) of complex uneven portions being captured as the reflection shape of the strip in an image without meandering occurring.

[0053] (Example of training dataset 250 (input sample, output sample)) In a scene where a meander (specifically, a meander with a meander amount equal to or greater than a danger level) actually occurred (at the time of the meander), 1,000 images (images with a meander occurrence) taken before the meander occurred may be used as input samples, and information indicating the occurrence of a meander (information indicating the occurrence of a meander) may be attached to each output sample. For example, 1,000 images (for example, similar images may be aggregated to extract 1,000 images to increase the variety) may be extracted from 3,600 images (images with a meander occurrence) taken during a two-minute (120-second) period from a point in time (time Ta1) six minutes before a certain point in time (time Ta3) when a meander (e.g., a meander with a meander amount of 50 mm or more) occurred to a point in time (time Ta2) four minutes before time Ta3, and these may be used as input samples, and information indicating the occurrence of a meander may be attached to each output sample.

[0054] 1000 images (images without meandering) taken when no meandering occurs (when no meandering occurs) may be used as input samples, and "no meandering" (information indicating no meandering) may be attached to each output sample. For example, 1000 images may be extracted from 3600 images (images without meandering) taken in the first 2 minutes (2 minutes from time Tb1) of any 6-minute period (from time Tb1 to time Tb2) when no meandering occurs (for example, similar images may be aggregated to extract 1000 images to increase variation) and used as input samples, and "no meandering" may be attached to each output sample.

[0055] Note that (N×1000) images with meandering may be prepared as input samples from N (N is 2 or more) meandering occurrences. When (N×1000) images with meandering occurrence are prepared as input samples (images with meandering occurrence), it is preferable to prepare the same number of images, i.e., (N×1000) images without meandering occurrence, as input samples.

[0056] The storage unit 139 stores the training dataset 250. The storage unit 139 may be a hard disk or a solid state drive (SSD). The training dataset 250 is stored in the storage unit 139 via communication or via a storage medium (CD-ROM, USB memory, etc.). The storage unit 139 also stores a training model and parameters.

[0057] The model generation unit 133 trains the learning model using the learning dataset 250 stored in the storage unit 139, and generates the trained model 300. For example, when the model generation unit 133 receives a model generation instruction operation (when the model generation instruction operation is received via an operation unit not shown, or when a model generation instruction command is received via a communication unit not shown), the model generation unit 133 trains the learning model using the learning dataset 250 stored in the storage unit 139, and generates the trained model 300. In other words, the trained model 300 is generated in the storage unit 139 by the model generation unit 133.

[0058] For example, the model generation unit 133 inputs each input sample to the input layer 301, updates the parameters of the learning model so as to reduce the difference between the output value obtained from the output layer 303 and each output sample (correct label), and generates the learned model 300. As an example, the model generation unit 133 may generate the learned model 300 using backpropagation, as shown in the following (1) to (5). Note that the learning model used by the model generation unit 133 may employ feedback alignment and target propagation in addition to backpropagation.

[0059] (1) The model generation unit 133 inputs input samples (image 1, image 2, image 3, ...) of the learning dataset 250 stored in the storage unit 139 to the input layer 301, and performs calculation processing in the forward propagation direction of the learning model to obtain output values ​​(output value of image 1, output value of image 2, output value of image 3, ...) from the output layer 303. The output values ​​from the output layer 303 are the probability that meandering will occur in the strip and the probability that meandering will not occur in the strip. (2) For each input sample (image 1, image 2, image 3, ...), the model generation unit 133 calculates the error between the output value from the output layer 303 and the output sample, for example, by backpropagation. The output sample indicates whether meandering has occurred (information indicating the presence of meandering) or not (information indicating the absence of meandering). For example, if an image is an image with meandering, and the image is input to the input layer 301 and the output layer 303 outputs a probability of "1.00" that meandering will occur in the strip (and a probability of "0.00" that meandering will not occur in the strip), the error associated with the image is zero. Also, if an image is an image without meandering, and the image is input to the input layer 301 and the output layer 303 outputs a probability of "0.00" that meandering will occur in the strip (and a probability of "1.00" that meandering will not occur in the strip), the error associated with the image is zero. (3) The model generation unit 133 determines whether the calculated error is within a predetermined value. (4) If the calculated error is within a predetermined value, the model generation unit 133 determines that various parameters such as the connection weights between neurons (such as the connection weights between neurons and the thresholds of each neuron) have been optimized, and ends learning (training). In other words, the generation of the trained model 300 by the model generation unit 133 is completed (the trained model in which the various parameters are trained parameters is referred to as the trained model 300). (5) If the calculated errors are not within a predetermined value, the model generation unit 133 updates various parameters based on the calculated errors. Thereafter, the model generation unit 133 inputs the input sample again to the input layer 301 of the learning model whose parameters have been updated, and repeatedly updates various parameters until the errors are within a predetermined value.

[0060] The trained model 300 generated in the storage unit 139 by the model generation unit 133 is stored in the meandering monitoring device 40 (trained model storage unit 149) by communication or via a storage medium.

[0061] FIG. 5 is a flowchart showing an example of the operation of the meandering monitoring device 40. The flowchart in FIG. 5 starts repeatedly (for example, every 1 / 30 seconds). The range in which the average value calculation unit 145 calculates the moving average value is assumed to be a probability of 30. The predetermined threshold value that the determination unit 146 compares with the moving average value is assumed to be 0.5. The learned model storage unit 149 is assumed to store a learned model.

[0062] The acquisition unit 141 acquires a captured image (moving image) captured by the imaging device 10 (step S1). The acquisition unit 141 outputs the captured image to the cropping unit 142. Then, the process proceeds to step S2.

[0063] The cropping unit 142 acquires the captured image from the acquisition unit 141, and crops and trims a still image from the captured image (step S2). The cropping unit 142 outputs the cropped still image to the probability calculation unit 144. Then, the process proceeds to step S3.

[0064] The probability calculation unit 144 acquires the image from the clipping unit 142 and calculates the probability that meandering will occur in the strip (meandering occurrence probability) using the trained model 300 (step S3). The probability calculation unit 144 outputs the calculated probability to the average value calculation unit 145. Then, the process proceeds to step S4.

[0065] The average value calculation unit 145 acquires the probabilities from the probability calculation unit 144 and calculates a moving average (moving average value) of the acquired probabilities (step S4). Specifically, the average value calculation unit 145 calculates the moving average value of the most recently acquired 30 probabilities. The average value calculation unit 145 outputs the calculated moving average value to the determination unit 146 and the graphing unit 147. Then, the process proceeds to step S5.

[0066] Graphing unit 147 acquires the moving average value from average value calculation unit 145 and generates graph display information of the acquired moving average value (step S5). Graphing unit 147 outputs the generated graph display information to output unit 148. Then, the process proceeds to step S6.

[0067] The output unit 148 acquires the graphing display information from the graphing unit 147 and outputs the acquired graphing display information to the display device 50 (step S5). Then, the process proceeds to step S7. The display device 50, which has acquired the graphing display information from the output unit 148, displays a graph based on the acquired graphing display information.

[0068] The determination unit 146 acquires the moving average value from the average value calculation unit 145 and determines whether the acquired moving average value exceeds a predetermined threshold value (0.5) (step S7). If the moving average value exceeds the predetermined threshold value (0.5) (step S7: YES), the process proceeds to step S8. If the moving average value does not exceed the predetermined threshold value (0.5) (step S7: NO), the process ends (returns to step S1).

[0069] The output unit 148 acquires the alarm information from the determination unit 146 and outputs the acquired alarm information to the display device 50 (step S8). Then, this flowchart ends (returns to step S1). Having acquired the alarm information from the output unit 148, the display device 50 outputs (displays, outputs audio) an alarm based on the acquired alarm information.

[0070] Fig. 6 is a diagram illustrating an example of the evaluation results of the meandering monitoring system 1. Specifically, Fig. 6 shows the evaluation results regarding the presence or absence of an alarm output when meandering occurs in actual operation for each imaging condition (each imaging range in the strip running direction of the imaging device 10). The imaging conditions are the following four (imaging condition a to imaging condition d).

[0071] (imaging condition a) The imaging range of the imaging device 10 is set so that the width direction is equal to or greater than the width of the plate and the passing direction is 0.6 times the width of the plate (for example, 600 mm when the plate width is 1000 mm) (imaging condition a).

[0072] (imaging condition b) The imaging range of the imaging device 10 is set so that the width direction is equal to or greater than the width of the plate and the passing direction is 0.4 times the width of the plate (for example, 400 mm when the plate width is 1000 mm) (imaging condition b).

[0073] (imaging condition c) The imaging range of the imaging device 10 is set so that the width direction of the plate is equal to or greater than the plate width and the width in the plate passing direction is 0.2 times the plate width (for example, 200 mm when the plate width is 1000 mm) (imaging condition c). Note that the effective imaging range in the plate passing direction may be set to 0.2 times the plate width by, for example, applying a mask in front of the lens of the imaging device 10.

[0074] (imaging condition d) The imaging range of the imaging device 10 is set so that the width direction of the plate is equal to or greater than the plate width and the width in the plate passing direction is 0.02 times the plate width (for example, 20 mm when the plate width is 1000 mm) (imaging condition d). Note that the effective imaging range in the plate passing direction may be set to 0.02 times the plate width by, for example, applying a mask in front of the lens of the imaging device 10.

[0075] The model generation device 30 generates a trained model 300 under each imaging condition. For example, under imaging condition a, the model generation device 30 generates a trained model 300 (referred to as trained model 300a) using captured images acquired from the imaging device 10 set under imaging condition a, i.e., captured images with an imaging range equal to or greater than the plate width in the plate width direction and 0.6 times the plate width in the plate threading direction (using 1,000 images with meandering and 1,000 images without meandering as shown in the "Specific Example" above). Under imaging condition b, the model generation device 30 generates a trained model 300 (referred to as trained model 300b) using captured images acquired from the imaging device 10 set under imaging condition b, i.e., captured images with an imaging range equal to or greater than the plate width in the plate width direction and 0.4 times the plate width in the plate threading direction (using 1,000 images with meandering and 1,000 images without meandering as shown in the "Specific Example" above). In the case of imaging condition c, the model generation device 30 generates a trained model 300 (referred to as trained model 300c) using captured images acquired from the imaging device 10 set as in imaging condition c, i.e., captured images with an imaging range equal to or greater than the plate width in the plate width direction and 0.2 times the plate width in the plate threading direction (using 1000 images with meandering and 1000 images without meandering as shown in the "Specific Example" above). In the case of imaging condition d, the model generation device 30 generates a trained model 300 (referred to as trained model 300d) using captured images acquired from the imaging device 10 set as in imaging condition d, i.e., captured images with an imaging range equal to or greater than the plate width in the plate width direction and 0.02 times the plate width in the plate threading direction (using 1000 images with meandering and 1000 images without meandering as shown in the "Specific Example" above).

[0076] In the table of Fig. 6, the leftmost column shows the imaging conditions. The second column from the left shows the imaging range of the imaging device 10 (specifically, how many times the strip width in the strip running direction it is; in the strip width direction, it is equal to or greater than the strip width under all imaging conditions). The third column from the left shows the alarm occurrence rate (the alarm display rate on the display device 50) at the time when meandering occurs (the time when the operator visually confirms the occurrence of meandering). The rightmost column shows the alarm occurrence rate three minutes before meandering occurs (three minutes before the operator visually confirms the occurrence of meandering).

[0077] (Evaluation of imaging condition a) The meandering monitoring device 40 checked whether an alarm was issued when meandering occurred and three minutes before the occurrence of meandering based on the output result (probability of meandering occurrence) obtained by inputting images captured by the imaging device 10 set as imaging condition a (images captured in an imaging range equal to or greater than the width of the strip in the strip width direction and 0.6 times the width of the strip in the strip passing direction) into the trained model 300a (by comparing the moving average value of the probability of meandering occurrence with a predetermined threshold). As a result, as shown in Figure 6, an alarm was output 100% of the time when meandering occurred, and an alarm was output 83% of the time three minutes before meandering occurred.

[0078] Common to all imaging conditions (imaging conditions a to d), the average value calculation unit 145 calculated the moving average value of the 30 meandering occurrence probabilities output from the probability calculation unit 144, and the determination unit 146 compared the moving average value output from the average value calculation unit 145 with 0.5 (a predetermined threshold value).

[0079] (Evaluation of imaging condition b) The meandering monitoring device 40 checked whether an alarm was issued when meandering occurred and three minutes before the occurrence of meandering based on the output result (probability of meandering occurrence) obtained by inputting images captured by the imaging device 10 set as imaging condition b (images captured in an imaging range equal to or greater than the width of the plate in the plate width direction and 0.4 times the width of the plate in the plate threading direction) into the trained model 300b (by comparing the moving average value of the probability of meandering occurrence with a predetermined threshold). As a result, as shown in Figure 6, an alarm was output 100% of the time when meandering occurred, and an alarm was output 83% of the time three minutes before meandering occurred.

[0080] (Evaluation of imaging condition c) The meandering monitoring device 40 checked whether an alarm was issued when meandering occurred and three minutes before the occurrence of meandering based on the output result (probability of meandering occurrence) obtained by inputting images captured by the imaging device 10 set as imaging condition c (images captured in an imaging range equal to or greater than the width of the plate in the plate width direction and 0.2 times the width of the plate in the plate threading direction) into the trained model 300c (by comparing the moving average value of the probability of meandering occurrence with a predetermined threshold). As a result, as shown in Figure 6, an alarm was output 60% of the time when meandering occurred, and an alarm was output 20% of the time three minutes before the occurrence of meandering.

[0081] (Evaluation of imaging condition d) In the case of imaging condition d, the imaging range in the strip running direction was narrow, at 0.02 times the strip width, so the reflected light of the annular and semi-annular shapes described below could not be confirmed, and the highlighted areas in the strip width direction only appeared as dotted lines, and a valid learning dataset 250 (teaching data, etc.) could not be obtained (and therefore a valid trained model 300d was not generated), making evaluation impossible. Note that it is thought that similar results would be obtained if laser light were used.

[0082] 6, if the imaging range of the imaging device 10 is equal to or greater than the strip width in the strip width direction and equal to or greater than 0.4 times the strip width in the strip running direction, it can predict, for example, more than 80% of meandering that will occur after 3 minutes. Also, according to FIG. 6, the prediction performance is the same whether the strip running direction is 0.4 times or 0.6 times the strip width.

[0083] Figure 7 is a diagram for clearly explaining the features of the meandering monitoring system 1. Figure 7(A) shows a schematic diagram of unevenness occurring in the strip. In Figure 7(A), D shows a schematic diagram of unevenness occurring in the strip (a convex portion of a simple uneven portion).

[0084] 7(B) and 7(C) show the vertical position (perpendicular to the strip surface) of the strip surface where irregularities have occurred. FIG. 7(B) shows the vertical position of the strip surface along the dashed-dotted line L1-R1 in the width direction shown in FIG. 7(A). FIG. 7(C) shows the vertical position of the strip surface along the diagonal dashed-dotted line L2-R2 in FIG. 7(A). In FIGS. 7(B) and 7(C), d indicates the portion crossing the irregularity D. In other words, FIG. 7(B) is a schematic diagram of a cross section (cross section along dashed-dotted line L1-R1) of the strip including the irregularity D, and FIG. 7(C) is a schematic diagram of a diagonal cross section (cross section along dashed-dotted line L2-R2) of the strip including the irregularity D.

[0085] FIG. 7(D) shows a schematic diagram of a wrinkle (buckling) occurring in a strip. In FIG. 7(D), S indicates a wrinkle (an upward wrinkle) occurring in the strip. The dashed line within S indicates the end of the wrinkle, and the solid line indicates the top. In FIG. 7(D), a cross section of the strip in the width direction including the wrinkle S (cross section taken along the dashed line L1-R1) is shown approximately as in FIG. 7(B). Also, in FIG. 7(D), a diagonal cross section of the strip including the wrinkle S (cross section taken along the dashed line L2-R2) is shown approximately as in FIG. 7(C).

[0086] In other words, the surface of the strip may be uneven or wrinkled, but if the surface of the strip is viewed as a "line," whether in the width direction (dotted line L1-R1) or in an oblique direction (dotted line L2-R2), it is difficult to distinguish whether the surface of the strip is uneven or wrinkled.

[0087] Figures 7(E) and 7(F) show the imaging range of the imaging device 10. Figure 7(E) shows the imaging range P of the imaging device 10 for the strip shown in Figure 7(A) (a strip with irregularities). Figure 7(F) shows the imaging range P of the imaging device 10 for the strip shown in Figure 7(C) (a strip with wrinkles). When the surface of the strip is captured as a "plane," it is possible to distinguish whether the surface of the strip is irregular or wrinkled.

[0088] That is, while it is difficult to recognize unevenness when using laser light or the like, the meandering monitoring system 1 uses a light source 20 (diffuse light source) and an imaging device 10 (camera), making it easy to recognize unevenness. The meandering monitoring system 1 predicts the occurrence of meandering based on the output result (probability of meandering occurrence) of the trained model 300, which has been trained using an image with meandering, which is considered to be relatively likely to have imaged unevenness as a reflection shape of the strip, and an image without meandering, which is considered to be relatively unlikely to have imaged unevenness as a reflection shape of the strip.

[0089] In this embodiment, if the strip surface is uneven, it is possible to capture characteristics such as highlight areas being interrupted halfway across the strip width (reflecting in a direction that cannot be imaged), taking on an annular or semi-annular shape depending on the curve of the uneven surface, or a situation in which the brightness of the reflected light gradually decreases from the peak to the base of the curve. The size of the uneven area can be observed as the distance at which the size and brightness of the annular or semi-annular shape gradually decrease. In other words, if unevenness occurs in the strip (even if complex unevenness occurs in the strip, causing the strip to flutter), it is possible to easily detect that unevenness has occurred in the strip.

[0090] Although this embodiment uses a light source 20, capturing highlights would be difficult if the strip surface were mirror-smooth. However, because the cold rolling process creates microscopic irregularities on the strip surface (unevenness expressed in terms of surface roughness or coarseness, which differ from the irregularities focused on in the present embodiment), highlights can be captured (Figure 2). This embodiment uses a diffused light source (a light source with directional laser light, e.g., excluding linear laser light). However, if a linear laser light source is used instead of a diffused light source, even if irregularities exist on the strip, the high directivity prevents the appearance of optical annular or semi-annular features, and it is difficult to capture changes (decreases) in brightness corresponding to the steepness of the irregularities. Even if the width of the linear laser light irradiated in the strip width direction (the width of the light in the strip traveling direction) is increased, there is a limit to how wide it can be, resulting in the same results as described above.

[0091] It is also conceivable to connect (combine) the "lines" of the laser light to obtain "surface" information in the same imaging range as the imaging device 10 (for example, 0.4 times or more the width of the strip in the strip running direction). However, considering the running speed of the strip (200 m / min or more) and the processing load and requirements for composition (real-time alarm notification), it is not easy to obtain "surface" information from the laser light in the same imaging range as the imaging device 10.

[0092] Furthermore, as described above, the imaging device 10 of the meandering monitoring system 1 may be a device that transmits captured images to the meandering monitoring device 40 or to other devices (for example, an in-furnace video monitor), and a camera that has already been installed for other purposes (for the purpose of transmitting captured images to other devices) can be used as the imaging device 10. In other words, the meandering monitoring system 1 can monitor the occurrence of strip meandering without introducing new equipment such as a laser beam.

[0093] In the present embodiment, an example has been described in which the meandering monitoring system 1 predicts (monitors) the occurrence of meandering on a strip with a meandering amount equal to or greater than a danger level. However, the meandering monitoring system 1 may also predict the occurrence of meandering on a strip with a meandering amount exceeding the danger level. Furthermore, the meandering monitoring system 1 may predict the occurrence of meandering on a strip with a meandering amount equal to or greater than a predetermined standard (or a meandering amount exceeding the predetermined standard). The predetermined standard meandering amount is a meandering amount smaller than the danger level meandering amount (i.e., zero meandering amount (no meandering) < predetermined standard meandering amount < danger level meandering amount). Specifically, a training dataset corresponding to the meandering amount to be predicted (a meandering amount exceeding the danger level, a meandering amount equal to or greater than the predetermined standard, or a meandering amount exceeding the predetermined standard) is prepared, trained data corresponding to the meandering amount to be predicted is generated, and the trained model is used to predict the occurrence of meandering with the target meandering amount.

[0094] The meandering monitoring system 1 according to this embodiment has been described above. According to the meandering monitoring system 1, it is possible to predict the occurrence of meandering of a strip in a continuous annealing furnace simply and with higher accuracy.

[0095] The embodiments of the present invention have been described above, but the embodiments of the present invention include at least the following configurations. (1) A meandering monitoring method (meandering monitoring method using a meandering monitoring system 1) for monitoring the occurrence of meandering of a strip traveling in a continuous annealing furnace, comprising: an imaging step of imaging (using an imaging device 10) an area of ​​the strip in the width direction of the strip that is equal to or greater than the width of the strip; a light emitting step of illuminating the strip with diffused light (diffused light using a light source 20) so that the imaging step can image a highlight portion that extends in the width direction of the strip as a reflection shape of light reflected from the surface of the strip; and a meandering monitoring step of monitoring (using a meandering monitoring device 40) the occurrence of meandering of the strip using the image captured by the imaging step, wherein the meandering monitoring step predicts the occurrence of meandering of the strip based on the output result (probability of meandering occurrence) of a trained model (trained model 300) that has been trained using the captured image and the presence or absence of meandering of the strip, which is training data. (2) A meandering monitoring system (meandering monitoring system 1) that monitors the occurrence of meandering of a strip traveling in a continuous annealing furnace, comprising: an imaging means (imaging device 10) that images an area of ​​the strip in the width direction of the strip that is equal to or greater than the width of the strip; a light emitting means (light source 20) that illuminates the strip with diffused light so that the imaging means can image a highlight portion that extends in the width direction of the strip as a reflection shape of light reflected from the surface of the strip; and a meandering monitoring means (meandering monitoring device 40) that monitors the occurrence of meandering of the strip using the image captured by the imaging means, wherein the meandering monitoring system predicts the occurrence of meandering of the strip based on the judgment results of a trained model (trained model 300) that has learned the image captured and the presence or absence of meandering of the strip as training data.

[0096] In (1) and (2) above, the term "a trained model trained using the captured image and the training data of whether or not the strip meanders" may be rephrased as "a trained model that inputs the captured image and outputs a determination result regarding the occurrence of meandering in the strip," or, since the trained model is a type of algorithm, it may be rephrased as "an algorithm that is generated using the imaging results of the imaging step (the imaging means) including the reflection shape of the reflected light and the presence or absence of meandering in the strip as training data, and determines whether or not meandering in the strip has occurred."

[0097] The above describes the embodiments, but the above embodiments are merely examples and the specific configurations are not limited to the above embodiments, and also include designs within the scope of the invention that do not deviate from the gist of the invention.

[0098] For example, in the above embodiment, an example has been described in which processing is performed for each frame (1 / 30 seconds), but processing may also be performed for each set of frames.

[0099] Furthermore, in the above embodiment, an example has been described in which each meandering monitoring device 40 is configured by one device (one server or one personal computer), but the meandering monitoring device 40 may be configured by two or more devices. Furthermore, in the above embodiment, an example has been described in which each model generating device 30 is configured by one device (one server or one personal computer), but the model generating device 30 may be configured by two or more devices.

[0100] Furthermore, in the above embodiment, an example has been described in which the model generating device 30 and the meandering monitoring device 40 are configured as different devices, but the model generating device 30 and the meandering monitoring device 40 may be configured as the same device. In other words, the meandering monitoring device 40 may also have the functions of the model generating device 30 (or the model generating device 30 may also have the functions of the meandering monitoring device 40).

[0101] In the above embodiment, an example has been described in which the meandering monitoring device 40 and the display device 50 are configured as different devices, but the meandering monitoring device 40 and the display device 50 may be configured as the same device. In other words, the meandering monitoring device 40 may also have the function of the display device 50.

[0102] The programs for implementing the meandering monitoring system 1, the model generating device 30, the meandering monitoring device 40, etc. described above may be recorded on a computer-readable recording medium and loaded into a computer system for execution. The term "computer system" as used herein includes hardware such as an OS and peripheral devices. The term "computer-readable recording medium" also refers to portable media such as flexible disks, optical magnetic disks, ROMs, and CD-ROMs, as well as storage devices such as hard disks built into a computer system. The term "computer-readable recording medium" also includes devices that retain a program for a certain period of time, such as volatile memory (RAM) within a computer system that acts as a server or client when the program is transmitted via a network such as the Internet or a communication line such as a telephone line. The program may also be transmitted from a computer system storing the program in a storage device to another computer system via a transmission medium or by transmission waves within the transmission medium. The term "transmission medium" used to transmit the program refers to a medium capable of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line. The program may also be used to implement some of the functions described above. Furthermore, the above-mentioned functions may be realized in combination with a program already recorded in the computer system, that is, a so-called differential file (differential program). [Explanation of symbols]

[0103] 1. Meandering monitoring system 10. Imaging device 20 light source 30 Model generation device 133 Model Generation Unit 139 Storage section 40 Meandering monitoring device 141 Acquisition Department 142 Cutting part 143 Meandering Monitoring Unit 144 Probability Calculation Unit 145 Average value calculation unit 146 Judgment section 147 Graphing Section 148 Output Section 149 Trained model memory 50 Display device 250 training datasets 300 trained models

Claims

1. A meandering monitoring method for monitoring occurrence of meandering of a strip traveling in a continuous annealing furnace, comprising: an imaging step of imaging an area equal to or greater than the width of the strip in a width direction of the strip; a light emitting step of illuminating the strip with diffused light so that a highlight portion extending in the width direction of the strip can be captured by the capturing step as a reflection shape of light reflected from the surface of the strip; a meandering monitoring step of monitoring occurrence of meandering of the strip using the captured image captured by the imaging step; and The meandering monitoring step includes: The image captured in the imaging step is input to a trained model trained using a training dataset including a plurality of images captured in advance in the continuous annealing furnace where imaging is performed in the imaging step, and a correct answer label indicating whether or not each of the plurality of images represents an actual occurrence of meandering. Based on the output result obtained by inputting the image captured in the imaging step, information indicating the probability of the strip meandering occurring is acquired, and the occurrence of the meandering is predicted. A meandering monitoring method.

2. The imaging step includes: An image of an area of ​​0.4 times or more the width of the strip in the strip running direction is taken.

2. The meandering monitoring method according to claim 1.

3. The trained model is outputting the meandering occurrence probability of the strip; The meandering monitoring step includes: The captured images are sequentially input to the trained model, and a moving average value of the meandering occurrence probability sequentially output from the trained model is sequentially calculated, and the moving average value is compared with a predetermined threshold value to predict the occurrence of meandering of the strip.

3. The meandering monitoring method according to claim 1 or 2.

4. A meandering monitoring system for monitoring the occurrence of meandering of a strip traveling in a continuous annealing furnace, comprising: an imaging means for imaging an area of ​​the strip that is equal to or greater than the width of the strip in the width direction of the strip; a light emitting means for illuminating the strip with diffused light so that the imaging means can capture an image of a highlight portion that spreads in the width direction of the strip as a reflection shape of light reflected from the surface of the strip; a meandering monitoring means for monitoring occurrence of meandering of the strip using the image captured by the imaging means; Equipped with The meandering monitoring means The trained model is trained using a training dataset including a plurality of images captured in advance in the continuous annealing furnace where the imaging means captures images, and a correct answer label indicating whether or not each of the plurality of images represents an actual occurrence of meandering. Based on the determination result obtained by inputting the images captured by the imaging means, the trained model obtains information indicating the probability of the strip meandering occurring, and predicts the occurrence of the meandering. A meandering monitoring system.

Images