KR20240076461A - Apparatus for monitoring dust generation - Google Patents

Abstract

The present invention is to provide a dust generation monitoring device that can determine the dust and its extent locally generated around an electric furnace by applying an image processing technique using CCTV for monitoring equipment installed and operated in most factories. A dust generation monitoring device according to an embodiment of the present invention includes an image acquisition unit for acquiring an image of a preset area, a signal for histogram equalization and binarization of the image acquired by the image acquisition unit and a preset representative image, respectively. It may include a processing unit and a determination unit that determines whether dust is generated by comparing the image signal processed by the signal processing unit and the representative image.

Description

Dust generation monitoring device {APPARATUS FOR MONITORING DUST GENERATION}

The present invention relates to a dust generation monitoring device.

Generally, an electric furnace is a furnace that produces steel by melting metal with heat generated using electricity. Electric furnaces can be classified into resistance furnaces, arc furnaces, induction furnaces, electron beam furnaces, etc. depending on the heating method. Double arc furnaces are widely used for industrial purposes, that is, steelmaking. The arc furnace heats and melts scrap metal inside the furnace using the heat of the arc discharge generated from the electrode to which high voltage is applied.

Arc furnaces generate combustion gases when charging, melting, or tapping scrap iron. This combustion gas contains dust and gas. Combustion gases emitted from electric furnaces contain various harmful substances and, if discharged as is, cause serious environmental pollution. Therefore, dust collection equipment is installed in the electric furnace, and the combustion gas is discharged as purified air after dust is removed using the dust collection equipment.

Electric furnace dust collection equipment uses different dust collection methods depending on the work situation. For example, when charging scrap metal into an electric furnace, dust is collected by collecting it from the top of the electric furnace, and when the scrap metal is melted by applying electricity after charging, direct dust collection is performed by sucking the scrap metal directly from the electric furnace.

However, when direct dust collection is performed for electric furnace melting work, there are cases where leakage occurs between the electric furnace lid (lid). At this time, the leaked combustion gas is visually checked by a person and collected through the hood at the top of the electric furnace by increasing the bag filter operation amount and increasing the speed of the dust collection fan. Therefore, there is currently an inconvenience in that workers must continuously monitor and respond to leaks, and if workers miss, there is a risk that combustion gases may leak outside without being collected, so it is necessary to control the dust collection equipment at maximum output to remove dust. There are many cases.

Republic of Korea Patent Publication No. 10-2010-0115519

According to one embodiment of the present invention, a dust generation monitoring device is provided that can determine the dust and its extent locally generated around an electric furnace by applying an image processing technique using CCTV for monitoring equipment installed and operated in most plants. provided.

In order to solve the problem of the present invention described above, a dust generation monitoring device according to an embodiment of the present invention includes an image acquisition unit that acquires an image of a preset area, an image acquired by the image acquisition unit and a preset It may include a signal processing unit that performs histogram equalization and binarization of the representative images, and a determination unit that determines whether dust is generated by comparing the representative image with the image signal processed by the signal processing unit.

According to one embodiment of the present invention, it can be installed without a large additional cost compared to the existing direct dust measurement method and has excellent effects in terms of maintenance.

1 is a schematic configuration diagram of a dust generation monitoring device according to an embodiment of the present invention.
Figure 2 is a flow chart showing the schematic operation of a dust generation monitoring device according to an embodiment of the present invention.
Figure 3a is a dust-free image acquired from the image acquisition unit of the dust generation monitoring device according to an embodiment of the present invention, and Figure 3b is an image acquired from the image acquisition section of the dust generation monitoring device according to an embodiment of the present invention. This is a video of dust generation.
Figure 4 is a diagram showing image signal processing of equipment interference and equipment non-interference images of the signal processing unit of the dust generation monitoring device according to an embodiment of the present invention.
Figure 5 is a diagram showing image signal processing of dust generation and fine dust generation images of the signal processing unit of the dust generation monitoring device according to an embodiment of the present invention.
Figure 6 is a diagram illustrating an exemplary computing environment in which a dust generation monitoring device according to an embodiment of the present invention may be implemented.

Hereinafter, with reference to the attached drawings, preferred embodiments will be described in detail so that those skilled in the art can easily practice the present invention.

1 is a schematic configuration diagram of a dust generation monitoring device according to an embodiment of the present invention.

Referring to Figure 1, the dust generation monitoring device 100 according to an embodiment of the present invention may include an image acquisition unit 110, a signal processing unit 120, and a determination unit 130.

The image acquisition unit 110 is configured with a camera, etc., and can acquire images of a preset area. For example, the image acquisition unit 110 is supported on pillars, walls, etc. in a factory, a steel work environment where an electric furnace, etc. are located, and acquires an image of an area that includes the electric furnace or other components that may generate dust. can do.

The signal processing unit 120 may signal process the image acquired by the image acquisition unit 110. For example, the histogram of the image acquired by the image acquisition unit 110 may be equalized and binarization processing may be performed. Additionally, the signal processing unit 120 may set a representative image from an image previously acquired by the image acquisition unit 110, equalize the histogram of the set representative image, and perform binarization processing.

The determination unit 130 may determine whether dust is generated by comparing the image acquired by the current image acquisition unit 110, whose signal has been processed by the signal processing unit 120, with a preset representative image. In addition, the degree of dust generation can be determined.

Figure 2 is a flow chart showing the schematic operation of a dust generation monitoring device according to an embodiment of the present invention.

Referring to FIG. 2 along with FIG. 1 , the image acquired by the image acquisition unit 110 may be input to the signal processing unit 120 (S1).

For example, the signal processing unit 120 may divide the input image into preset division areas.

In order to determine whether dust is generated in an input CCTV image, the input image can be divided into preset division areas and processed as a single image in order to reduce signal processing noise in determining dust generation. For example, the input image may be processed in quadrant image units.

Figure 3a is a dust-free image acquired from the image acquisition unit of the dust generation monitoring device according to an embodiment of the present invention, and Figure 3b is an image acquired from the image acquisition section of the dust generation monitoring device according to an embodiment of the present invention. This is a video of dust generation.

Referring to FIGS. 3A and 3B along with FIG. 1 , the signal processor 120 may, for example, divide the input image into quadrants. The signal processor 120 may set the same division area in the previously acquired image of FIG. 3A and the currently acquired image of FIG. 3B. In the first process, the signal processor 120 performs a pre-processing process to detect the borderline of the image. To this end, the borderline can be detected by applying, for example, a Sobel mask of 3x3 size to the entire image. . At this time, the difference value per pixel based on the quadrant between the detected boundary image and the boundary image of the previously prepared image without dust (representative image) is calculated and added. The quadrant where the summed value is maximum corresponds to the quadrant where dust was generated.

Meanwhile, in the actual factory environment, unexpected situations are often encountered, a typical example being when a crane or other mobile equipment passes through the CCTV shooting area. In other words, shooting interference due to other equipment may occur from time to time, and as a first process, the image generalization process can be performed using the histogram equalization method after LAB color coordinate conversion for the input image. Additionally, the same generalization process is performed on representative images prepared in advance. After performing binarization on the current input image on which the generalization process was performed and the representative image, the difference value (δ) can be obtained for these two images.

More specifically, the number of critical pixels of the input image for the representative image and the difference image between the representative images can be calculated as shown in Equation 1 below.

(Formula 1)

Here, δ may mean the number of difference image pixels, avg may mean the average, σ may mean the standard deviation, and max may mean the maximum.

As a result of Equation 1 described above, if it is less than the critical pixel number, it can be recognized as data captured by the crane without blocking the photographing area, and if it is greater than the critical pixel number, it can be recognized as data photographed by the crane blocking the photographing area. .

Figure 4 is a diagram showing image signal processing of equipment interference and equipment non-interference images of the signal processing unit of the dust generation monitoring device according to an embodiment of the present invention.

Referring to FIG. 4 along with FIGS. 1 and 2, the signal processor 120 can equalize and binarize the histogram of the acquired image, and determines the number of critical pixels of the input image for the representative image and the difference image between the representative images. By calculating, it is possible to check whether there is interference in the image (S2). Calculating the number of critical pixels for determining dust generation described above can also be applied in the same way.

For example, the above-mentioned Equation 1 can calculate the data recognition result for the corresponding image as follows.

Next, the signal processor 120 may calculate the number of pixels of the difference image between the input image and the representative image in the area where dust was generated (S3).

The signal processing unit 120 can equalize and binarize the histogram of the image currently acquired by the image acquisition unit 110, and can equalize and binarize the histogram of a preset representative image, where dust is generated and not generated. The colors can be spread evenly by adjusting the color and equalizing the color histogram so that the factory equipment is similar.

Meanwhile, the determination unit 130 may determine whether dust is generated by comparing the current image processed by the signal processing unit 120 with a representative image that has been set and processed in advance (S4). The determination unit 130 compares the image of each divided area divided by the signal processing unit 120 in the current image with the representative image of each divided area divided by the signal processing unit 120 in the representative image to determine whether dust is generated. can be judged.

Figure 5 is a diagram showing image signal processing of dust generation and fine dust generation images of the signal processing unit of the dust generation monitoring device according to an embodiment of the present invention.

Referring to FIG. 5, each of the currently acquired image and the representative image without dust may be histogram equalized and binarized by the signal processor 120.

The determination unit 130 selects an image of each of the divided areas divided by the signal processing unit 120 among the images processed by the signal processing unit 120 and a representative image of each of the divided areas divided by the signal processing unit 120 from the representative image. You can determine whether dust is generated by comparing .

That is, the determination unit 130 performs dust generation judgment and generation rate determination on the entire acquired image, and histogram equalization and binarization are applied to the image input by the signal processing unit 120, and the same processed representative image is processed. Find the difference between the image and the image.

In the case of dust generation, a difference image appears in the image depending on the difference from the representative image of the actual dust generation, and the area of the remaining image shows the extent of dust generation. A process of selecting a dust-generating quadrant area according to the installation location of the image acquisition unit 110 is performed, and the determination unit 130 may proceed by using a boundary line detection method in the process of selecting a dust-generating quadrant area. The above-described boundary detection method is a method of selecting a quadrant area by comparing the object boundary information that becomes blurred when dust is generated compared to the object boundary information when no dust is generated. Through the process of selecting the dust generation quadrant area described above, it is possible to determine the level of dust generation according to the influence of various factory interior lighting environments and camera automatic shooting settings.

The determination unit 130 uses information on the shape of factory objects when no dust is generated to calculate the number of pixels for the dust generation area excluding the changing factory equipment area to calculate the degree of dust generation in the interference environment between the dust generation area and surrounding objects. can do.

The dust generation index indicating the degree of dust generation may be expressed as Equation 2 below.

(Formula 2)

Here, the number of difference image pixels refers to the number of image pixels that differ according to comparison between the image of the selected segment and the representative image of the segment, and the maximum pixel number of the input image refers to the number of image pixels in the image of the selected segment. it means.

Afterwards, the color histogram for the binarized grayscale image can be used to determine the darkness of the input image using the number of pixels of color 0 and color 255, and analyze the color histogram for the area to determine whether it is a dark environment. If the degree of reflection of factory equipment in the equipment area is low, it is recognized as a dark shooting environment, and in the dust generation area, if the degree of light scattered by dust is small, it is recognized as a dark shooting environment, and the lighting of the area where the image acquisition unit 110 is installed is adjusted. (S4).

Figure 6 is a diagram illustrating an exemplary computing environment in which a dust generation monitoring device according to an embodiment of the present invention may be implemented.

6, an example system 1000 is shown that includes a computing device 1100 configured to implement one or more embodiments described above. For example, computing device 1100 may include a personal computer, server computer, handheld or laptop device, mobile device (mobile phone, PDA, media player, etc.), multiprocessor system, consumer electronics, minicomputer, mainframe computer, Distributed computing environments including any of the above-described systems or devices, etc. are included, but are not limited thereto.

Computing device 1100 may include at least one processing unit 1110 and memory 1120. Here, the processing unit 1110 may include, for example, a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor, an application specific integrated circuit (ASIC), or a field programmable gate array (Field Programmable Gate Arrays). FPGA), etc., and may have multiple cores. Memory 1120 may be volatile memory (eg, RAM, etc.), non-volatile memory (eg, ROM, flash memory, etc.), or a combination thereof.

Additionally, computing device 1100 may include additional storage 1130. Storage 1130 includes, but is not limited to, magnetic storage, optical storage, etc. The storage 1130 may store computer-readable instructions for implementing one or more embodiments disclosed in this specification, and other computer-readable instructions for implementing an operating system, application program, etc. may also be stored. Computer-readable instructions stored in storage 1130 may be loaded into memory 1120 for execution by processing unit 1110.

Computing device 1100 may also include input device(s) 1140 and output device(s) 1150. Here, the input device(s) 1140 may include, for example, a keyboard, mouse, pen, voice input device, touch input device, infrared camera, video input device, or any other input device, etc. Additionally, output device(s) 1150 may include, for example, one or more displays, speakers, printers, or any other output devices. Additionally, the computing device 1100 may use an input device or output device provided in another computing device as the input device(s) 1140 or the output device(s) 1150.

Additionally, computing device 1100 may include communication connection(s) 1160 that enable communication with another device (e.g., computing device 1300) via network 1200. Here, communication connection(s) 1160 may include a modem, network interface card (NIC), integrated network interface, radio frequency transmitter/receiver, infrared port, USB connection, or other device for connecting computing device 1100 to another computing device. May contain interfaces. Additionally, communication connection(s) 1160 may include a wired connection or a wireless connection.

Each component of the computing device 1100 described above may be connected by various interconnections such as buses (e.g., peripheral component interconnect (PCI), USB, firmware (IEEE 1394), optical bus structure, etc.) and may be interconnected by a network.

Terms such as “image acquisition unit,” “signal processing unit,” “judgment unit,” etc. used in this specification generally refer to computer-related entities that are hardware, a combination of hardware and software, software, or running software. For example, components such as "image acquisition unit", "signal processing unit", "judgment unit", etc. are processes running on a processor, processors, objects, executables, threads of execution, programs, and/or computers. For example, but is not limited to this, both the application running on the controller and the controller may be components, and one or more components may exist within a process and/or thread of execution. It can be localized on one computer, or distributed between two or more computers.

As described above, according to the present invention, it can be installed without a large additional cost compared to the existing direct dust measurement method and can also be superior in terms of maintenance. In addition, it can show a significantly improved dust generation determination effect (95.12%) compared to the results of the existing simple boundary detection method (77.47%).

The present invention described above is not limited by the above-described embodiments and the accompanying drawings, but is limited by the scope of the patent claims described below, and the configuration of the present invention can be varied within the scope without departing from the technical spirit of the present invention. Those skilled in the art can easily see that changes and modifications can be made.

100: Dust generation monitoring device
110: Image acquisition unit
120: signal processing unit
130: Judgment unit

Claims (6)

An image acquisition unit that acquires an image of a preset area;
a signal processing unit that performs histogram equalization and binarization on the image acquired by the image acquisition unit and a preset representative image, respectively; and
A determination unit that determines whether dust is generated by comparing the image signal processed by the signal processing unit and the representative image.
A dust generation monitoring device comprising a.
According to paragraph 1,
The signal processing unit is a dust generation monitoring device that divides the image acquired by the image acquisition unit into a plurality of preset division areas.
According to paragraph 2,
The signal processing unit is a dust generation monitoring device that sets a representative image of each of the divided areas in advance.
According to paragraph 3,
The judgment department
A dust generation monitoring device that compares the image of each divided area with the representative image to determine dust generation in the corresponding divided area.
According to paragraph 4,
The determination unit selects an image of a divided area in which the clarity of the area of a preset object is less than or equal to a preset standard among the images of each divided area, and determines dust generation in the divided area by comparing it with a representative image of the divided area. Dust generation monitoring device.
According to clause 5,
The determination unit determines the image of the selected segmented area.

A dust generation monitoring device that determines the level of dust generated.
(Here, the number of difference image pixels refers to the number of image pixels that differ according to comparison between the image of the selected segment area and the representative image of the segment area, and the maximum pixel number of the input image is the number of image pixels in the image of the selected segment area. means.)

Images