JPH0329111B2 - - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION Field of the Invention The present invention relates to a coke oven mouth situation recognition device that identifies the state and position of a coke oven mouth through image processing.

Conventional technology Coke oven equipment suffers from thermal expansion, aging, etc.
Equipment status changes. Conventionally, in order to understand these phenomena unique to coke ovens and ensure smooth operation of coke oven equipment, it has been necessary to station workers on site to conduct confirmation work.

Problems to be Solved by the Invention However, coke oven equipment is high temperature and has a lot of dust, creating a poor environment for employees, making it difficult to work quickly and making it difficult to automate operations.

SUMMARY OF THE INVENTION Therefore, the present invention aims to provide a coke oven furnace status recognition device that can grasp the equipment status necessary for the operation of coke oven equipment in a non-contact and unmanned manner, and can promote automatic operation of coke oven equipment. purpose.

Means for Solving the Problems The coke oven oven mouth condition recognition device of the present invention comprises two units that are movably supported along the coke oven mouth and each have an upper part of the oven mouth and a bottom part of the oven mouth as imaging regions. An imaging device, two memories that each store one frame image of these imaging devices, and access to these memories to read pixels at arbitrary addresses and recognize the reactor mouth situation through image processing based on the difference in pixel brightness. It is characterized by the fact that it is equipped with an image recognition device.

Embodiments The present invention will be described below with reference to illustrated embodiments.

As shown in FIGS. 1 and 2, two video cameras 1 and 2 are installed vertically near the mouth of a coke oven. The imaging centers of these video cameras 1 and 2 are aligned in the vertical direction, and are capable of capturing images of the upper part of the furnace mouth and the bottom of the furnace mouth, respectively, and are movable along the furnace mouth of the coke oven.

Further, video memories 3 and 4 are connected to the video cameras 1 and 2, respectively, and the video memories 3 and 4 store one frame of image captured by the video cameras 1 and 2 as pixel data.

The video memories 3 and 4 are connected to an image recognition device 5 via an image switch 6. The image switching device 6 switches to either the video memory 3 or 4 according to a command from the image recognition device 5, and outputs the stored contents to the image recognition device 5.

Further, the image recognition device 5 sends a signal to the image switch 6 to switch to either the video memory 3 or 4, and also specifies a pixel address in the frame of the image stored in the video memory 3 or 4 to select an arbitrary one. The pixel data at the address can be read.

In the device configured in this way, video cameras 1 and 2 are mounted on the furnace side of the coke oven working machine, adjusted so that the imaging center of video camera 2 is aligned vertically below the imaging center of video camera 1, and other The equipment can also be located remote from the coke oven.

In addition, as shown in FIG. 1, the images captured by the video cameras 1 and 2 show that the furnace wall 7 is in a dark area due to the temperature difference.
The furnace mouth 8 can be regarded as a bright area.

When performing image processing of the upper part of the furnace mouth, the image recognition device 5 switches the image switching device 6 to the video memory 3 side so that an image of the upper part of the furnace mouth can be obtained, and outputs a freeze signal to the video memory 3. A partial image of the reactor mouth captured by the video camera 1 is stored.

The same image is generated when a pixel address corresponding to a pixel required for processing is outputted from an I/O port (not shown) of the image recognition device 5 to the video memory 3, and the corresponding pixel data is transferred from the video memory 3 to the image recognition device 3.
By sequentially shifting these pixel addresses and outputting them, image data for one screen can be obtained. This pixel data has information on the intensity of light.

The image recognition device 5 performs the above processing to obtain one screen worth of image data and performs processing for detecting the furnace mouth core. First, in order to detect the boundary of the upper end a of the furnace mouth, the image recognition device 5 performs the processing as shown in FIG. The vertical pixel addresses at the center of the screen are output sequentially from the top of the screen downward.

Here, the brightness of the furnace mouth is set in advance in the image recognition device 5, and while inputting the pixel data, it is compared with the set brightness of the furnace mouth, and searches for pixel data having a brightness that is equal to or higher than the brightness of the furnace mouth, and selects the corresponding pixel. When data is detected, it starts accumulating the number of detections and continues to compare the pixel data below.

When the integrated value is greater than or equal to the number of integrated values defined as inside the furnace mouth (set), pixel addresses with pixel data with a brightness greater than or equal to the first detected furnace mouth brightness are assigned to the furnace wall 7 and the top of the furnace mouth 8. The same pixel address is stored as the boundary between the two pixels.

Next, in order to detect the boundary between the left end of the furnace mouth and the right end of the furnace mouth, as shown in Figure 4, the pixel address in the horizontal direction from several lines above the pixel address at the upper end of the furnace mouth is moved from the left end of the screen to the right end. While inputting pixel data, it compares it with the set furnace mouth brightness and searches for pixel data that has a brightness equal to or higher than the furnace mouth brightness. If the corresponding pixel data is not detected even after searching horizontally to the center of the screen, pixel data in the horizontal direction one line below is searched.

While searching in this manner, when the corresponding pixel data is detected, the integration of the number of detections is started, and the comparison of the pixel data on the right side is continued.

Here, when the integrated number is greater than or equal to the set in-mouth integration value, the pixel address having pixel data with a brightness greater than or equal to the first detected furnace mouth brightness is used as the boundary between the furnace wall 7 and the left end of the furnace mouth 8. Store pixel address b.

Next, in order to detect the right end of the furnace mouth, the search continues to the right, and when the input pixel data has a brightness lower than the furnace mouth brightness, it is treated as pixel data of the furnace wall and the number of detections is calculated again. Furthermore, comparison of pixel data in the right direction is continued.

When the cumulative number is greater than or equal to the cumulative number specified for the furnace wall, the pixel addresses with pixel data with a brightness greater than or equal to the last detected furnace mouth brightness are set to the right end of the furnace mouth 8 and the furnace wall 7.
The pixel address c is stored as the boundary between the two pixels. Then, based on the memorized pixel address, the following
Determine and store the number of 8 pixels at the furnace mouth using equation (1).

Number of pixels at the furnace mouth = Pixel address at the right end of the furnace mouth - Pixel address at the left end of the furnace mouth ... (1) The above process is performed until the bottom of the screen, and the number of pixels at the furnace mouth for each horizontal line is stored.

Then, the maximum number of pixels at the furnace mouth is found out of all the number of pixels at the furnace mouth for each horizontal line stored, and the center of the upper part of the furnace mouth is calculated from the left end address of the furnace mouth and the right end address of the furnace mouth using the following formula (2). Obtain pixel address e.

Center pixel address at the top of the furnace mouth = Pixel address at the right end of the furnace mouth - Pixel address at the left end of the furnace mouth / 2... (2) Furthermore, the center deviation f at the top of the furnace mouth from the pixel address d at the center of the screen is calculated by the following equation (3). Find and remember.

Center deviation of the upper part of the furnace mouth = (Pixel address of the center of the screen - Center pixel address of the upper part of the furnace mouth) × Resolution of one pixel mm/pixel ...(3) Next, in order to perform image processing of the lower part of the furnace mouth, an image recognition device is used. Step 5 switches the image switch 6 to the video memory 4 side so that an image of the bottom of the furnace mouth 8 can be obtained. Then, it outputs a freeze signal to the video memory 4 to store image data for one screen of the bottom of the new furnace port 8, outputs the pixel address as described above, and inputs the specified pixel data to the video memory 4. Performs bottom center detection processing. Here, in order to detect the boundary of the lower end of the furnace opening 8, as shown in Fig. 5, the vertical pixel addresses of the center of the screen are sequentially output from the lower end of the screen upwards, the pixel data is input, and the The pixel address b of the boundary between the wall 7 and the lower end of the furnace mouth 8 is found and stored.

Next, in order to detect the boundary between the left end of the furnace port 8 and the right end of the furnace port 8, pixel addresses are sequentially output from the left end to the right end at the top of the screen, as shown in FIG. 6, and pixel data is input. After that, use the same method as above to find the pixel address b at the left end of the furnace mouth and the pixel address c at the right end of the furnace mouth, calculate the number of pixels at the furnace mouth using equation (1), and store it. The above operation is repeated until the number of pixels at the furnace mouth for each line is determined and stored. Then, the maximum number of pixels at the furnace mouth is found from among all the stored numbers of pixels at the furnace mouth, and from the pixel address b at the left end of the furnace mouth and the pixel address c at the right end of the furnace mouth, the center of the furnace mouth bottom is found using equation (2). pixel address h
The center deviation i of the bottom of the furnace mouth is calculated using equation (3).

Cases in which the situation of the furnace mouth 8 and the furnace wall 7 based on the brightness difference identification for each pixel address are used to recognize other furnace conditions will be listed and explained below for each case.

(1) Confirmation of attachment and detachment of furnace lid After the coke oven working machine completes removal of the furnace lid, the boundary with the furnace port 8 or the furnace wall 7 can be detected by the above-mentioned detection method, and the furnace lid is removed (furnace mouth open). After the furnace lid has been attached, the same detection method cannot detect the furnace port 8 or the boundary between the furnace port 8 and the furnace wall 7, so that confirmation of the furnace lid adhesion (furnace port closure) can be done without contact and in a short time.
And it can be done reliably.

(2) Interlock for furnace opening when discharging coke This is an application of the furnace opening detection method in item (1), and is used to check that the working machines moving on both sides of the furnace are stopped at the same furnace number. The communication device (not shown) is used to confirm that both working machines have completed ejecting the furnace lid using the method described in (1), and the furnace opening is open. This is used as an interlock to ensure that both furnace ports are open and coke can be discharged.

(3) Interlock for furnace port closure during coal loading This is an application of the method for detecting furnace port closure described in item (1). After coke discharge is complete, both work machines complete the furnace lid attachment and the furnace port closes. By confirming the status using the communication device, it can also be used as an interlock to ensure that both furnace ports of the chamber furnace are closed and coaling is possible.

(4) Detection of deformation of the furnace mouth As shown in Figure 7, the difference between the center deviation of the upper part of the furnace mouth and the center deviation of the bottom of the furnace mouth, which is determined by the method of detecting the boundary between the furnace mouth 8 and the furnace wall described above, is calculated. When this difference exceeds the allowable value, a warning of abnormal deformation of the furnace mouth is issued, prompting maintenance of the furnace body.

It is also possible to calculate j/k using the lengths of line segments j and k, and to make a determination based on that value.

(5) Detection of furnace core position The distance meter installed on the working machine, such as a light wave distance meter, synchro encoder, or pulse generator, should be operated so that the measuring point is aligned with the vertical line of the center of the video cameras 1 and 2. It is attached to the machine and measures the distance from the measurement point to the starting point of the traveling path as the traveling distance, and this measurement value is sent to the image recognition device 5.
is output to.

Here, the center average deviation m of the furnace mouth 8 obtained by calculating the average of the center deviation of the furnace mouth upper part and the center deviation of the furnace mouth bottom obtained by the above-mentioned method of detecting the boundary between the furnace mouth 8 and the furnace wall 7. The core position can be obtained by adding the traveling distance l obtained from the distance meter of the working machine as illustrated in FIG.

The core position obtained in this way can be used as the target position for the next stop of the working machine in the same reactor, or the core positions of all reactors can be printed and accumulated to check the state of aging of the reactor and necessary for maintenance. You can contribute to the collection of materials.

(6) Detection of furnace core position This is an application of the method for detecting the furnace core position described in item (5) above, and as shown in Figure 9, this method is installed on a working machine that moves on both sides of the furnace. The reactor port situation recognition device detects the core positions n of both reactor ports, and calculates the difference o therebetween.

When the difference o between the two furnace core positions obtained in this manner is greater than the allowable value, a core abnormality alarm is output to prompt maintenance of the furnace body. In addition, by printing and accumulating the positions n of both cores of all furnaces, it is possible to contribute to the collection of materials necessary for the state of aging of the furnace body and its maintenance.

(7) Detection of furnace bottom level This is an application of the method for detecting the opening of the furnace mouth in section (1), and the pixel data of the image of the bottom of the furnace mouth is determined by the brightness in the vertical direction as shown in Figure 10a and b. Performs difference recognition processing.

In this way, the maximum number of pixels is calculated from the number of pixels at the furnace mouth obtained by detecting the boundary between the lower end of the furnace mouth bottom and the furnace wall, and the difference between the reference pixel address and the boundary pixel address at the furnace mouth bottom with the maximum number of pixels is calculated. Multiply by the pixel resolution (mm/pixel) to obtain the hearth bottom deviation value, and use equation (4) to find the hearth bottom level.

Hearth bottom level = Reference value - Hearth bottom deviation value ... (4) From the calculated hearth bottom level, the height P of the bottom of the pusher rod 10 and the height q of the bottom of the ram shoe 11 shown in Figure 10c are calculated. If either of them is lower than the furnace bottom level, discharge of the coke 12 is prohibited to protect the furnace body and to facilitate maintenance of the furnace body.

(8) Quantitative understanding of the cleaning effect This is an application of the method for detecting the boundary between the furnace mouth and the furnace wall described above, and as shown in Figure 11a and b, the images before and after cleaning are The cleaning effect s is quantitatively understood from the reduction rate of the number of pixels with brightness corresponding to carbon by comparing the images.

For carbon pixels, extend the maximum pixel numbers r _x and _ry on the X-axis and Y-axis to the Y-axis and pixel.

(9) Interference monitoring between the pusher rod and the furnace wall This is an application of the method for detecting the boundary between the furnace mouth and the furnace wall described above, and the upper part of the furnace mouth, including the pusher rod 10 that has temporarily stopped in front of the furnace. When imaged, the image shown in FIG. 12 is obtained. and,
Each boundary between the furnace wall 7 and the furnace mouth 8 and between the furnace mouth 8 and the pusher rod 10 is detected, and the number of pixels t of the furnace mouth 8 between the furnace wall 7 and the pusher rod 10 is determined.
When the pressure is less than the allowable value, an alarm is issued to alert the operator that there is a danger of interference between the pusher rod 10 and the furnace wall 8.

Further, when the pusher rod 10 and the furnace wall 7 are interfering with each other, an extrusion prohibition signal is issued to ensure the safety of the furnace body.

(10) Detection of remaining coke at the bottom of the furnace This is an application of the method for detecting the boundary between the furnace mouth 8 and the furnace wall 7 described above.
The image shown in the figure is obtained.

Here, if there is residual coke 12 at the bottom of the furnace mouth, it will appear brighter than the furnace mouth 8 due to the burning flame, and if the number of pixels with the brightness of the residual coke that is set is more than the allowable value, a warning that there is residual coke at the bottom of the furnace will be displayed. can be emitted to alert the operator.

If the residual coke 12 exceeds the allowable value, the bottom level of the furnace will rise substantially, which will directly affect the integrity of the furnace lid 9 installation. Therefore,
If residual coke 12 is detected in the above method, it is removed by re-cleaning.

(11) Detection of misalignment between multiple charging ports A video camera is attached to the charging vehicle 13 so as to take an image of the charging port 14 of the vehicle.

Here, as shown in FIG. 13, l ₁ , l ₂ , −l ₃ ,
l ₄ is detected as the misalignment of the charging port 14 with respect to the charging vehicle 13.

From this value, it is possible to determine whether the operation is possible or not based on the maximum value [absolute value (l ₁ , l ₂ , l ₃ , l ₄ )]≦L, where L is the allowable mechanical dimension of the charging vehicle 13 that can be loaded.

Thereby, it is possible to determine the relative misalignment of the plurality of charging ports with respect to the mechanical core of the charging vehicle, and to achieve automatic operation of the charging vehicle instead of the on-demand operation, or even non-on-the-move operation.

(12) Detection of the average position of multiple charging ports In the previous section (11), the misalignment of the charging port center was detected and it was determined whether or not coal loading work could be performed. It can be used as a reference for the next alignment of the center of the charging port.

By doing so, the charging vehicle 13 can grip the charging port core more flexibly.

Effects of the Invention The embodiment of the coke oven furnace mouth situation recognition device according to the present invention is as described above, and can bring about the following effects.

It is possible to grasp the equipment status necessary for the operation of coke oven equipment in a non-contact and unmanned manner, and promote automatic operation of coke oven equipment.

[Brief explanation of the drawing]

Fig. 1 is an example image of the upper and lower parts of the reactor mouth showing an embodiment of the present invention, Fig. 2 is an apparatus configuration diagram, Figs. 3 and 4 are illustrations of an example of processing for recognizing the upper part of the reactor mouth, and Figs. The figure shows an example of the lower part of the reactor mouth recognition process, Fig. 7 shows the principle of detecting the deformation of the reactor mouth, Fig. 8 shows the principle of detecting the core position, Fig. 9 shows the principle of detecting the center of the reactor body, and Fig. 10 a, b, c is a diagram of the principle of detecting the furnace bottom level, Figures 11a and b are diagrams of the principle of quantitatively determining the cleaning effect, and Figure 12 is a diagram of the principle of detecting the bottom level of the furnace.
FIG. 13 is a diagram showing the principle of monitoring the interference between the rod and the furnace wall, FIG. 13 is a diagram showing the principle of detecting residual coke at the bottom of the furnace, and FIG. 14 is a diagram showing the principle of detecting the width of deviation between the cores of multiple charging ports. 1, 2... Video camera, 3, 4... Video memory, 5... Image recognition device, 6... Image switching device, 7... Furnace wall, 8... Furnace mouth, 9... Furnace lid, 1
0...Pushya Rod, 11...Ram Siyu, 12...Coke, 13...Charging vehicle, 14...
...Charging port, a... Upper end of the furnace mouth, b... Pixel address at the left end of the furnace mouth, c... Pixel address at the right end of the furnace mouth, d
... Pixel address at the center of the screen, e... Center pixel address at the top of the furnace mouth, f... Center deviation at the top of the furnace mouth,
g...Pixel address at the bottom of the furnace mouth, h...Center pixel address at the bottom of the furnace mouth, i...Center deviation at the bottom of the furnace mouth, l: Measurement point, m: Center average deviation at the furnace mouth,
n...Street core, o...Difference in position between both furnace cores, r _x , r _y ...
Maximum pixel, s...Cleaning effect, t...Number of pixels at the furnace mouth between the furnace wall and the pusher rod.

Claims (1)

[Scope of Claims] 1. Two units arranged vertically with their horizontal imaging centers coincident and supported movably along the coke oven mouth, with the upper part of the oven mouth and the bottom part of the oven mouth respectively serving as imaging areas. an imaging device, two memories each connected to these two imaging devices and each storing one frame image of the upper part of the furnace mouth and the bottom of the furnace mouth imaged by the imaging devices; A coke oven furnace mouth situation recognition device characterized by comprising an image recognition device that accesses and reads pixels at arbitrary addresses and grasps the furnace mouth situation based on the luminance difference of the pixels.