JP6849150B2 - Industrial plant monitoring and control system - Google Patents

Description

The present invention relates to a data reproduction device for an industrial plant and an industrial plant monitoring and control system.

Industrial plants (steel plants, power plants, petroleum plants, chemical plants, etc.) that produce materials and resources necessary for industrial activities are known. The plant monitoring and control system of an industrial plant is an input / output device (I / O) to which a large number of field devices (including actuators and sensors) constituting the plant are connected via a control network, and a large number of field devices. It has a configuration in which programmable logic controllers (hereinafter referred to as PLCs) to be controlled are connected to each other.

Further, process data which is an input / output signal of a PLC or an input / output device is collected by a data collection device having a data collection function and a data reproduction function. The data collection device displays the collected process data and is used by the operator to grasp the state of the industrial plant.

As an example of a sensor that outputs process data, Patent Document 1 discloses an HMD (Hot Metal Detector) arranged in a steel plant. This HMD is installed at a position at a predetermined height directly above the table roller downstream of the rolling roll, and the detection direction is set to be a direction desired for the rolling roll in a substantially orthogonal direction and a horizontal direction. The HMD is a laser sensor having a narrow field of view, and outputs an ON signal if it detects a heat mass in the field of view, and outputs an OFF signal if it does not detect it.

Japanese Patent Application Laid-Open No. 2016-87652 International Publication No. 2014/002176

By arranging the sensor as in Patent Document 1, the upward warp of the hot mass (material to be rolled) can be detected. However, the sensor is expensive and its installation location is limited. Further, the sensor only outputs an ON signal or an OFF signal, and the state (shape, position, etc.) of the material to be rolled cannot be grasped in detail.

In order to solve such a demerit, the inventor of the present application has decided to use the moving image data of the object to be photographed taken by a general camera as a sensor as a result of diligent research. By using a camera, there are merits such as cost reduction, a wider shooting range and a higher degree of freedom in installation location than the above-mentioned sensor, and a larger amount of information than the sensor output.

On the other hand, when confirming the state of the object to be photographed by the camera, even if the moving image data is simply visually observed, the judgment is made by visual measurement and the accuracy of confirmation is low. Therefore, a process for improving the accuracy of confirmation is desired.

The present invention has been made to solve the above-mentioned problems, and is an industry capable of assisting an operator who confirms the operating state of an industrial plant by quantitatively analyzing the state of an imaged object in real time using moving image data. It is an object of the present invention to provide an image analysis apparatus for a plant.
Another object of the present invention is to provide an industrial plant monitoring and control system capable of realizing appropriate control according to the state of an imaging target by using the data quantified by the image analysis device for an industrial plant.

In order to achieve the above object, the image analysis apparatus for an industrial plant according to the present embodiment is configured as follows. The image analysis device for an industrial plant includes a moving image data collecting unit, an image processing processing unit, an image quantifying unit, and a numerical output unit.

The video data collection unit collects video data of the equipment constituting the industrial plant and the materials processed by the equipment in real time. Real-time does not necessarily mean the moment when the image is taken, but includes data collection with a delay due to the communication path and data processing, and data collection at regular periodic intervals.

The image processing unit extracts an image from the moving image data at regular intervals, converts a designated color into a first color, and converts a color other than the designated color into a second color to binarize the image. The constant cycle is preferably as short as possible, and is preferably real-time. The image means a one-frame image extracted from moving image data. The designated color means not only a single color but also a designated color range.

The image quantification unit quantifies the binarized image based on the number of pixels converted to the first color. In one embodiment, the image quantifier calculates the proportion of the first color in each strip region of the binarized image divided parallel to the transport direction of the material. In another aspect, the image quantifier calculates the proportion of the first color in each grid region of the binarized image divided into grids.

The numerical output unit outputs the quantified data.

Further, in order to achieve the above object, the industrial plant monitoring and control system according to the present embodiment is configured as follows. The industrial plant monitoring and control system includes the above-mentioned image analysis device for an industrial plant and a programmable logic controller that controls the device.

The equipment includes a pair of rolling rolls for rolling the material to be rolled. The image processing unit binarizes the image of the material to be rolled as viewed from the width direction.

In one embodiment, the image quantifier and the programmable logic controller are configured as follows.

The image quantification unit divides the binarized image into at least a first region and a second region adjacent to the first region in parallel with the transport direction of the material to be rolled, and the image quantification unit describes each region. Calculate the proportion occupied by the first color.

The programmable logic controller provides an alarm signal and an alarm signal when the difference between the increase amount of the ratio occupied by the first color in the second region and the decrease amount of the ratio occupied by the first color in the first region is larger than the threshold value. At least one of the control signals for changing the rotation speed of the pair of rolling rolls is output so as to suppress the warp of the material to be rolled. For example, the control signal is a signal for stopping the pair of rolling rolls, or a signal for making the rotation speed of the lower rolling roll slower than the rotation speed of the upper rolling roll.

In another aspect, the image quantifier and the programmable logic controller are configured as follows.

The image quantification unit arranges the binarized image in a grid pattern to include at least a first region, a second region adjacent to the side of the first region, and a third region adjacent to the first region. It is divided into a fourth region above the second region and adjacent to the side of the third region, and the ratio occupied by the first color for each region is calculated.

In the programmable logic controller, the proportion occupied by the first color increases in the order of the first region and the second region, and the proportion occupied by the first color in the third region decreases. When the proportion occupied by the first collar increases, at least one of an alarm signal and a control signal for changing the rotation speed of the pair of rolling rolls so as to suppress the warp of the material to be rolled is output. For example, the control signal is a signal for stopping the pair of rolling rolls, or a signal for making the rotation speed of the lower rolling roll slower than the rotation speed of the upper rolling roll.

According to the image analysis device for an industrial plant according to the present invention, it is possible to assist an operator who quantitatively analyzes the state of an object to be photographed in real time using moving image data and confirms the operating state of the industrial plant. Further, according to the industrial plant monitoring and control system according to the present invention, appropriate control can be realized by using the data quantified by the image analysis device for an industrial plant.

It is the schematic which shows the structure of the plant monitoring control system of the industrial plant which concerns on Embodiment 1. FIG. It is a block diagram of the image analysis apparatus which concerns on Embodiment 1. FIG. This is a screen display example of the image analysis apparatus according to the first embodiment. It is a block diagram which shows the hardware configuration example of the processing circuit which an image analysis apparatus has. It is a block diagram of the image analysis apparatus which concerns on Embodiment 2. FIG. This is an analysis example in the image analysis apparatus according to the second embodiment. It is a block diagram of the image analysis apparatus which concerns on Embodiment 3. This is an analysis example in the image analysis apparatus according to the third embodiment.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. The elements common to each figure are designated by the same reference numerals, and duplicate description will be omitted.

Embodiment 1.
(System configuration)
FIG. 1 is a schematic view showing a configuration of a plant monitoring control system for an industrial plant according to a first embodiment.

A steel plant is one of the industrial plants that produce the materials and resources necessary for industrial activities. In hot rolling, a high-temperature slab (material to be rolled) heated in a heating furnace is conveyed by a transfer roll and thinly rolled to a desired thickness by a rough rolling mill and a finishing rolling mill, and at the same time processed into a desired width. And finally rolled up with a coiler.

The plant monitoring and control system is configured by connecting an image analysis device 1, a first surveillance camera 2, a second surveillance camera 3, a data collection device 7, HMI8, PLC9, and equipment (not shown) constituting an industrial plant. ing.

The first surveillance camera 2 and the second surveillance camera 3 are arranged so as to include the equipment constituting the industrial plant and the material processed by the equipment in the photographing range. The first surveillance camera 2 is connected to the image data converter 4 via the image signal line 5. The video output of the first surveillance camera 2 is converted into a signal capable of network communication by the image data converter 4, and transmitted to the image analysis device 1 via the moving image network 6. The second surveillance camera 3 is a network camera, and the captured moving image data is transmitted to the image analysis device 1 via the moving image network 6.

The image analysis device 1 is a programmable logic controller (PLC) 9 that controls equipment (including actuators and sensors) constituting an industrial plant via a control network 10, and is used by an operator for constant operation and monitoring of the industrial plant. It is connected to a human-machine interface (HMI) 8 which is a monitoring and control device for monitoring and a data collecting device 7. The image analysis device 1 may be incorporated in the data collection device 7.

The control network 10 has a plurality of nodes having a common memory, and synchronizes data on the common memory by periodic broadcast transmission between the plurality of nodes. As a result, the same memory space is virtually shared between the image analysis device 1, the PLC9, and the HMI8. A storage area (address) for each data is assigned to the common memory. The device connected to each node can send and receive data by writing and reading to the common memory.

(Image analyzer)
The image analysis device 1 includes a moving image data collection unit 21, an image processing processing unit 22, an image quantification unit 23, and a numerical output unit 24.

The moving image data collecting unit 21 collects moving image data of the equipment constituting the industrial plant and the material processed by the equipment in real time. Real-time does not necessarily mean the moment when the image is taken, but includes data collection with a delay due to the communication path and data processing, and data collection at regular periodic intervals. Specifically, the moving image data collecting unit 21 collects moving image data from the first monitoring camera 2 and the second monitoring camera 3 at regular periodic intervals via the moving image network 6. The moving image data collecting unit 21 outputs the moving image data to the image processing unit 22. The moving image data collecting unit 21 stores the collected moving image data in the data storage unit 113b of the storage 113.

The image processing unit 22 extracts an image from the moving image data at regular intervals, converts a designated color into a first color, and converts a color other than the designated color into a second color to binarize the image. The constant cycle is preferably as short as possible, and is preferably real-time. The image means a one-frame image extracted from moving image data. The designated color means not only a single color but also a designated color range.

Specifically, the image processing unit 22 processes an image using the color filter unit 41, the binarization unit 42, and the mapping processing unit 43 shown in FIG. 2, and outputs the processed image to the image quantification unit 23. To do.

The color filter unit 41 extracts designated colors related to devices and materials in the image. As the designated color, for example, the color of the red-hot material, the color indicating the temperature abnormality of the device or the material, and the like are set in advance.

The binarization unit 42 converts the designated color into a first color (for example, white) and the other colors into a second color (for example, black) to binarize the image. According to this, the amount of data can be reduced, the computational load of image processing processing and quantification processing can be reduced, and real-time performance can be ensured.

When the first surveillance camera 2 or the second surveillance camera 3 photographs the object to be photographed from an oblique angle, the mapping processing unit 43 converts the image into an image viewed from the side or the top by performing the mapping conversion. According to this, since the degree of freedom in arranging the cameras is high, it is possible to deal with not only the case where the camera cannot be arranged directly above or beside the shooting target but also the environment where it is difficult to place the sensor near the shooting target. If the camera can be placed directly above or beside the shooting target, the processing by the mapping processing unit 43 does not necessarily have to be executed.

The image quantification unit 23 quantifies the binarized image based on the number of pixels converted to the first color. For example, the ratio of the first color in the image is calculated based on the number of pixels converted into the first color (for example, white) by the image processing unit 22. The image quantification unit 23 outputs the quantified data to the numerical output unit 24.

The numerical output unit 24 outputs the quantified data to the data collection device 7, the HMI 8 and the PLC 9 via the control network 10.

FIG. 3 is a diagram showing a display example displayed on the monitor 117 (FIG. 4) by the image analysis device 1. The image analysis device 1 displays the collected moving image data in real time in the left window 31. In the example of FIG. 3, a pair of rolling rolls 312 (rough rolling mill or finish rolling mill) for rolling the material to be rolled 311 and a transfer roll 313 are included in the photographing range, and the material to be rolled 311 is included in the photographing range. A state of being rolled into a pair of rolling rolls 312 while being conveyed from left to right is displayed. Further, the image analysis device 1 displays a binarized image of the image displayed in the left window 31 in the center window 32. The portion 321 showing the material to be rolled is displayed in white, and the other portion 322 is displayed in black. Further, the image analysis device 1 displays a graph showing the time change of the proportion of white in the binarized image in the right window 33. In the example of FIG. 6, a graph showing the time change of the ratio of white occupying each region divided in the horizontal direction is displayed.

The data collection device 7 collects process data from the PLC 9 and the HMI 8. Process data includes various data regarding the equipment that constitutes an industrial plant and the materials that are processed into the equipment. For example, it includes actuator control values, sensor detection values, material specifications, and the like. Large-scale plants such as steel plants have thousands or tens of thousands of input / output points, and a wide variety of process data exists. These process data are collected in a data collection device 7 having a data collection function and a data reproduction function, and are used for data analysis during testing, adjustment, operation, and failure.

Further, the data collecting device 7 receives the quantified data from the image analysis device 1 and collects and accumulates the data in synchronization with the process data. The data collecting device 7 can also receive necessary data from the image analysis device 1 and realize the same display as in FIG.

The HMI 8 displays the process data received from the PLC 9 in numerical values, characters, lamps, and the like. Further, the HMI 8 includes an operation button for transmitting a button input signal and a numerical value input signal, and outputs a signal for controlling the PLC 9 in response to the pressing of the operation button. Further, the HMI 8 can receive the quantified data from the image analysis device 1 and display the numerical value, or issue an alarm when the numerical value exceeds a predetermined threshold value. ..

The PLC 9 controls an industrial plant by performing calculations based on inputs from sensors of the industrial plant and outputting signals to actuators such as valves and motors. In addition, the industrial plant is controlled by receiving the data output from the image analysis device 1 in the same manner as the input from the sensor, performing calculations, and outputting signals to actuators such as valves and motors. In addition, an alarm is issued when the calculation result exceeds the threshold value.

As described above, according to the image analysis device 1 according to the first embodiment, by quantifying the moving image data collected in real time from the surveillance camera, it is possible to grasp how much the shooting target is within the shooting range. be able to. Therefore, the image analysis device 1 can quantitatively analyze the positions and shapes of the devices and materials in real time, and support the operator in confirming the operating state. In addition, the cost is low because no special sensor is used. For example, it is possible to reduce the sensor installation cost when detecting the warp of a hot strip or a thick plate. In addition, since the shooting range is wider and the degree of freedom of the installation location is higher than that of the sensor, it is possible to grasp the state of the shooting target under various environments.

By the way, in the above-described first embodiment, the number of pixels converted into the first color is counted for the entire image, but the present invention is not limited to this. A part area of the image may be specified, and the number of pixels converted into the first color may be counted for the area. By defining the area of interest in the image, noise can be reduced and detection accuracy can be improved.

Further, by using the image analysis device 1 and the data collection device 7 of the first embodiment described above, it is possible to display the moving image data on the data collection device 7 in real time, and it is stored in the data collection device 7. It is also possible to reproduce the moving image data on the data collecting device 7 from an arbitrary designated time. It is possible to easily grasp the position and size for past events and improve the accuracy of confirming the position and size. It is also possible to stop, fast forward, and fast rewind the video. Note that these points are the same in the following embodiments.

Further, although the image analysis device 1 of the first embodiment described above does not include the monitor 117, the keyboard 118, and the mouse 119 shown in FIG. 4 to be described later, these may be included in the image analysis device 1. This point is the same in the following embodiments.

Further, in the above-described first embodiment, a steel plant is described as an example as an industrial system, but the present invention is not limited to this. Industrial systems also include power plants, oil plants, chemical plants and the like.

(Hardware configuration example)
The hardware configuration of the image analysis device 1 will be described with reference to FIG. FIG. 4 is a block diagram showing a hardware configuration example of the processing circuit included in the image analysis device 1. Each part of the image analysis device 1 shown in FIG. 2 shows a part of the functions of the image analysis device 1, and each function is realized by a processing circuit. For example, the processing circuit includes a CPU 111, a memory 112, a storage 113 such as an HDD or a large-capacity memory, an external device I / F (interface) unit 114, a control network I / F unit 115a, and a moving image network I. The / F unit 115b is connected to the internal bus 116 via the internal bus 116. The data collecting device 7 is also configured in the same manner.

The CPU 111 realizes the functions of each unit of the image analysis device 1 by executing various programs stored in the program storage unit 113a of the storage 113.

The memory 112 is used as a calculation area unit for temporarily storing and expanding data when the CPU 111 executes various programs.

The storage 113 has a program storage unit 113a and a data storage unit 113b. The program storage unit 113a stores an OS (operating system) and various programs. In addition, the data storage unit 113b stores the collected process data and moving image data at each time.

In the example shown in FIG. 4, the program storage unit 113a and the data storage unit 113b are provided in one storage 113, but the program storage unit 113a and the data storage unit 113b are separately arranged in a plurality of storages. You may.

The external device I / F unit 114 is an interface for connecting an external device such as a monitor 117, a keyboard 118, and a mouse 119 to the image analysis device 1.

The control network I / F unit 115a is an interface for connecting the control network 10 and the image analysis device 1. Further, the moving image network I / F unit 115b is an interface for connecting the moving image network 6 and the image analysis device 1.

Embodiment 2.
Next, the second embodiment will be described with reference to FIGS. 5 and 6. In the first embodiment described above, the ratio of the first color to the entire image is calculated. On the other hand, in the second embodiment, the ratio occupied by the first color in each band-shaped region obtained by dividing the image into strips is calculated, and the change in the ratio occupied by the first color in each band-shaped region is compared to obtain a shooting target. It was decided to analyze the state of.

FIG. 5 is a block diagram of the image analysis device 1 according to the second embodiment. Since the configuration shown in FIG. 5 is the same as that of FIG. 2 except that the image quantification unit 23 includes the band-shaped quantification processing unit 50, the description of the common configuration will be omitted or simplified.

The image processing unit 22 binarizes the image of the material viewed from the width direction.

The band-shaped quantification processing unit 50 calculates the ratio of the first color (for example, white) to each band-shaped region obtained by dividing the image binarized by the image processing unit 22 in parallel with the material transport direction. In the example of FIG. 5, the binarized image is divided into four in the horizontal direction. The four-divided regions are referred to as a strip-shaped region A51, a strip-shaped region B52, a strip-shaped region C53, and a strip-shaped region D54 from the bottom. The band-shaped quantification processing unit 50 calculates the ratio of the number of white pixels for each band-shaped region.

By calculating the ratio occupied by the first color (hereinafter, also referred to as the first color ratio) in real time for each band-shaped region obtained by dividing the image into layers and confirming the change in the first color ratio, the position and shape of the shooting target can be confirmed. Can be quantitatively grasped.

For example, the material to be rolled 311 (FIG. 3) may jump on the transfer roll 313 (FIG. 3) of the steel plant. In this case, the object to be photographed (material to be rolled) moves in parallel from the strip-shaped region A51 to the strip-shaped region B52. Therefore, by confirming that the amount of increase in the first color ratio of the band-shaped region B52 and the amount of decrease in the first color ratio of the band-shaped region A51 are equal, it is possible to confirm that the imaging target has moved in parallel.

On the other hand, the shape of the object to be photographed may be deformed. For example, in a hot rolling line or a plate line of a steel plant, rolling may cause the material to be rolled 311 (FIG. 3) to warp. An example of image analysis will be described with reference to FIG. t1 is the shape of the material to be rolled in the previous cycle, and t2 is the shape of the material to be rolled in the current cycle. The strip-shaped quantification processing unit 50 divides the binarized image into at least a strip-shaped region A51 and a strip-shaped region B52 adjacent above the strip-shaped region in parallel with the transport direction of the material to be rolled, and the first band-shaped region is divided into the first. Calculate the color ratio. The boundary between the strip-shaped region A51 and the strip-shaped region B52 is set between the upper surface and the lower surface of the material to be rolled.

The operator confirms the change in the first color ratio in each band-shaped region with the change from t1 to t2. By confirming the magnitude of the difference between the increase in the first color ratio in the strip region B52 and the decrease in the first color ratio in the strip region A51, the warpage of the material to be rolled can be quantitatively grasped. ..

The image analysis device 1 can support the confirmation work by the operator by displaying a graph showing the time change of the first color ratio in each band-shaped region as illustrated in the right window 33 of FIG.

The PLC 9 receives the data (first color ratio in each band-shaped region) output from the numerical output unit 24. From the first color ratio in each band-shaped region, the PLC 9 controls according to the position of the shooting target, the control according to the change movement amount of the shooting target, and the control according to the shape of the shooting target (for example, according to the amount of warpage). Control) can be performed.

The control according to the amount of warpage will be described with reference to FIG. 6 described above. The PLC9 suppresses the alarm signal and the warp of the material to be rolled when the difference between the increase amount of the first color ratio in the strip region B52 and the decrease amount of the first color ratio in the strip region A51 is larger than the threshold value. At least one of the control signals for changing the rotation speed of the pair of rolling rolls 312 is output. For example, the control signal is a signal for stopping the pair of rolling rolls 312, or a signal for making the rotation speed of the lower rolling roll slower than the rotation speed of the upper rolling roll.

Instead, the PLC9 is used for the lower rolling roll when the difference between the increase amount of the first color ratio in the strip region B52 and the decrease amount of the first color ratio in the strip region A51 is larger than the first threshold value. A signal for slowing the rotation speed to be slower than the rotation speed of the upper rolling roll is output, and when the difference is larger than the second threshold value (greater than the first threshold value), a signal for stopping the pair of rolling rolls 312 is output. May be good.

Further, the PLC 9 may output an alarm signal that is more urgent as the difference is larger.

As described above, according to the system according to the present embodiment provided with the strip-shaped quantification processing unit 50, the operator confirms the position and size of the machine and the material with higher accuracy than that of the first embodiment. I can help. In addition, the PLC 9 can realize appropriate control according to the state of the imaging target by using the data quantified by the band-shaped quantification processing unit 50. For example, the control value can be changed so that the device to be photographed can be moved to an appropriate position, or the control value can be changed to prevent the material to be rolled to be photographed from colliding with the sensor or the machine. ..

By the way, the system of the second embodiment described above can be combined with the system of the first embodiment. This point is the same in the following embodiments.

Further, although the strip-shaped quantification processing unit 50 of the second embodiment described above sets the strip-shaped region in the horizontal direction, the strip-shaped region may be set in the vertical direction or the diagonal direction.

Further, although the band-shaped quantification processing unit 50 of the second embodiment described above divides the screen into four, it may be divided into two, three, or five or more.

Embodiment 3.
Next, the third embodiment will be described with reference to FIGS. 7 and 8. In the first embodiment described above, the ratio of the first color to the entire image is calculated. On the other hand, in the third embodiment, the ratio occupied by the first color in each grid-like region obtained by dividing the image into a grid pattern is calculated, and the change in the ratio occupied by the first color in each grid-like region is compared. , It was decided to analyze the state of the subject to be photographed in more detail.

FIG. 7 is a block diagram of the image analysis device 1 according to the third embodiment. Since the configuration shown in FIG. 7 is the same as that of FIG. 2 or 5, except that the image quantification unit 23 includes the grid-like quantification processing unit 60, the description of the common configuration will be omitted or simplified.

The image processing unit 22 binarizes the image of the material viewed from the width direction.

The grid-like quantification processing unit 60 calculates the ratio of the first color (for example, white) to each grid-like region obtained by dividing the image binarized by the image processing unit 22 into a grid pattern. In the example of FIG. 7, the binarized image is divided into 4 in the horizontal direction and 3 in the vertical direction, and is divided into a total of 12 regions. The divided regions are divided into a grid region A61, a grid region B62, a grid region C63, a grid region D64, a grid region E65, a grid region F66, a grid region G67, a grid region H68, and a grid region I69. , Lattice region J70, grid region K71, and grid region L72. The grid-like quantification processing unit 60 calculates the ratio of the number of white pixels for each grid-like region.

The position of the shooting target is determined by calculating the ratio occupied by the first color (hereinafter, also referred to as the first color ratio) in each grid region obtained by dividing the image into a grid pattern in real time and confirming the change in the first color ratio. And the change in shape can be grasped quantitatively.

For example, the material to be rolled 311 (FIG. 3) may jump on the transfer roll 313 (FIG. 3) of the steel plant. In this case, the object to be photographed (material to be rolled) moves in parallel from the grid-like region A61 to the grid-like region B62. Therefore, by confirming that the amount of increase in the first color ratio of the grid-like region A61 and the amount of decrease in the first color ratio of the grid-like region B62 are equal, it is possible to confirm that the imaging target has moved in parallel.

Further, when the object to be photographed extends diagonally from the grid-like region A61 to the grid-like region F66, the first color ratio of the grid-like region A61 is saturated and the first color ratio of the grid-like region F66 increases. .. From the amount of increase / decrease in the first color ratio of the adjacent grid-like region B62 and the amount of increase / decrease in the first color ratio of the grid-like region E65, it can be confirmed whether or not the imaged object is stretched without lateral blurring.

In addition, the shape of the object to be photographed may be deformed. For example, in a hot rolling line or a plate line of a steel plant, rolling may cause the material to be rolled 311 (FIG. 3) to warp. An example of image analysis will be described with reference to FIG. t3 is the shape of the material to be rolled in the previous cycle, and t4 is the shape of the material to be rolled in the current cycle. The grid-like quantification processing unit 60 displays the binarized image in a grid pattern, at least adjacent to the grid-like region F66, the grid-like region J70 adjacent to the grid-like region F66, and adjacent to the grid-like region F66. It is divided into a grid-like region G67 and a grid-like region K71 on the grid-like region J70 and adjacent to the grid-like region G67, and the first color ratio is calculated for each region. The boundary between the grid-like region F66 and the grid-like region G67 is set above the material to be rolled.

The operator confirms the change in the first color ratio in each grid-like region with the change from t3 to t4. The first color ratio in the grid region F66 and the grid region J70 increase in this order, and the first color ratio in the grid region K71 increases as the first color ratio in the grid region G67 decreases. By confirming, the warpage of the material to be rolled can be quantitatively grasped.

The PLC 9 receives the data (first color ratio in each grid region) output from the numerical output unit 24. The PLC 9 controls according to the position of the shooting target from the first color ratio in each grid region, the control according to the change movement amount of the shooting target, and the control according to the shape of the shooting target (for example, according to the amount of warpage). Control) can be performed.

The control according to the amount of warpage will be described with reference to FIG. 8 described above. In PLC9, the first color ratio in the grid region F66 and the grid region J70 increase in this order, and the first color ratio in the grid region K71 increases as the first color ratio in the grid region G67 decreases. When the number increases, at least one of an alarm signal and a control signal for changing the rotation speed of the pair of rolling rolls 312 so as to suppress the warp of the material to be rolled is output. For example, the control signal is a signal for stopping the pair of rolling rolls 312, or a signal for making the rotation speed of the lower rolling roll slower than the rotation speed of the upper rolling roll.

As described above, according to the system according to the present embodiment provided with the grid-like quantification processing unit 60, the operation of confirming the position and size of the machine or material by the operator is more accurate than that of the first embodiment. Can be highly supported. In addition, the PLC 9 can realize appropriate control according to the state of the imaging target by using the data quantified by the band-shaped quantification processing unit 50.

By the way, the system of the third embodiment described above can be combined with the system of the first embodiment and the system of the second embodiment.

Further, although the grid-like quantification processing unit 60 of the third embodiment described above defines the regions in a grid pattern in the horizontal direction and the vertical direction, the grid-like regions may be set in the diagonal direction.

Further, the grid-like quantification processing unit 60 of the third embodiment described above divides the image into 12, but the number of divisions does not matter as long as it is equally divided. In particular, when the object to be photographed is photographed from an oblique angle, the image is processed into an image from the side or the top by the mapping transformation. At this time, the amount of movement or deformation of the object to be photographed may be small. In this case, the reduced movement amount and deformation amount can be detected by increasing the number of grid-like divisions.

Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments, and can be variously modified and implemented without departing from the spirit of the present invention.

1 Image analysis device 2 1st surveillance camera 3 2nd surveillance camera 4 Image data converter 5 Image signal line 6 Video network 7 Data acquisition device 8 HMI
9 PLC
10 Control network 21 Video data collection unit 22 Image processing unit 23 Image quantification unit 24 Numerical output unit 31 Left window 32 Center window 33 Right window 311 Rolled material 312 Pair of rolling rolls 313 Transport roll 41 Color filter unit 42 2 Quantifying unit 43 Mapping processing unit 50 Band-shaped quantification processing unit 60 Grid-shaped quantification processing unit 51-54 Band-shaped area A to band-shaped area D
61-72 Lattice region A to Lattice region L
111 CPU
112 Memory 113, 113a, 113b Storage, program storage, data storage 114 External device I / F 115a, 115b Control network I / F, video network I / F 116 Internal bus 117 Monitor 118 Keyboard 119 Mouse

Claims (2)

A programmable logic controller which controls the devices constituting the industrial plant for the image analysis apparatus, industrial plants, a industrial plant monitoring control system Ru provided with,
The equipment includes a pair of rolling rolls for rolling the material to be rolled.
The image analysis device for an industrial plant is
A moving image data collecting unit that collects moving image data of the device and the material to be rolled processed by the device in real time,
At regular intervals, an image of the material to be rolled viewed from the width direction is extracted from the moving image data, and the designated color is converted to the first color and the non-designated color is converted to the second color to convert the image into binary values. Image processing unit and
The binarized image is divided into at least a first region and a second region adjacent to the first region in parallel with the transport direction of the material to be rolled, and the first color occupies each region. An image quantification unit that quantifies the binarized image by calculating the ratio, and an image quantification unit.
It is provided with a numerical output unit that outputs the quantified data.
In the programmable logic controller, when the difference between the increase amount of the ratio occupied by the first color in the second region and the decrease amount of the ratio occupied by the first color in the first region is larger than the threshold value, the programmable logic controller is used. To output at least one of an alarm signal and a control signal for changing the rotation speed of the pair of rolling rolls so as to suppress the warp of the material to be rolled.
An industrial plant monitoring and control system featuring. A programmable logic controller which controls the devices constituting the industrial plant for the image analysis apparatus, industrial plants, a industrial plant monitoring control system Ru provided with,
The equipment includes a pair of rolling rolls for rolling the material to be rolled.
The image analysis device for an industrial plant is
A moving image data collecting unit that collects moving image data of the device and the material to be rolled processed by the device in real time,
At regular intervals, an image of the material to be rolled viewed from the width direction is extracted from the moving image data, and the designated color is converted to the first color and the non-designated color is converted to the second color to convert the image into binary values. Image processing unit and
The binarized image is arranged in a grid pattern with at least a first region, a second region adjacent to the side of the first region, a third region adjacent to the first region, and the second region. An image quantification unit that quantifies the binarized image by dividing the image into a fourth region adjacent to the third region and calculating the ratio occupied by the first color in each region. When,
It is provided with a numerical output unit that outputs the quantified data.
In the programmable logic controller, the ratio occupied by the first color increases in the order of the first region and the second region, and the ratio occupied by the first color in the third region decreases. When the ratio occupied by the first color in the four regions increases, at least one of an alarm signal and a control signal for changing the rotation speed of the pair of rolling rolls so as to suppress the warp of the material to be rolled is output. To do,
An industrial plant monitoring and control system featuring.

Images