Pre-oxidation furnace flame detection method and system based on pixel eigenvalue method

Abstract

The invention relates to the technical field of carbon fiber production detection, in particular to a pre-oxidation furnace flame detection method and system based on a pixel eigenvalue method, and the method comprises the steps: obtaining an RGB image in a pre-oxidation furnace, and screening out a suspected region through the brightness; calculating a pixel ratio to determine three components of red, green and blue in the suspected area, and screening the suspected area according to a set threshold value; further screening the suspected areas through flame combustion characteristics; and judging whether the suspected area is flame or not according to the dynamic characteristics of the flame. According to the method, the proportions of the pixels are calculated respectively, flames usually have high red components, the flames and other light sources can be distinguished preliminarily, and screening is carried out according to the combustion characteristics of the flames. By means of brightness screening, pixel component analysis, flame combustion feature recognition and dynamic feature judgment, flames and other light sources in the pre-oxidation furnace can be effectively distinguished, so that the flame detection accuracy is improved, and the safety in the carbon fiber production process is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon fiber production detection, and in particular to a pre-oxidation furnace flame detection method and system based on a pixel eigenvalue method. Background Art

[0002] Carbon fiber is commonly known as black gold in the market. During the production process of carbon fiber, the PAN-based fiber precursor must first undergo oxidation and carbonization processes before it can become real carbon fiber.

[0003] The process of carbon fiber pre-oxidation is to combine oxygen molecules in the air with PAN-based fibers under high temperature environment, so that the polymer chains begin to cross-link, and the fiber density increases from 1.18g / cc to 1.38g / cc. Temperature control is very important. Usually the temperature range of the pre-oxidation furnace is between 200℃ and 300℃. However, in a high temperature environment, if there are joints on the carbon fiber or the temperature field or wind field in the furnace is uneven, the local temperature of the fiber will be too high, causing fire on the tow, which will cause deflagration in the furnace.

[0004] During the production process, the pre-oxidation furnace is completely dark inside. When there is a flame, a corresponding bright light will be generated. Based on this feature, a visible light camera is selected for flame detection. However, a visible light camera will bring an impact, that is, during the production process, operators use flashlights to inspect the pre-oxidation furnace, so in order to address this phenomenon, it is necessary to distinguish between the flashlight and the flame light source.

[0005] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present invention, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art already known to those skilled in the art. Summary of the invention

[0006] The present invention provides a pre-oxidation furnace flame detection method and system based on a pixel feature value method, thereby effectively solving the problems in the background technology.

[0007] In order to achieve the above object, the technical solution adopted by the present invention is: a pre-oxidation furnace flame detection method based on pixel feature value method, comprising the following steps: Obtain the RGB image inside the pre-oxidation furnace and filter out the suspected areas by brightness; Calculate pixel ratios to determine the red, green, and blue components in the suspected area, and screen the suspected area according to a set threshold; Further screening the suspected area according to the flame combustion characteristics; According to the dynamic characteristics of the flame, it is determined whether the suspected area is a flame.

[0008] Furthermore, the calculating pixel ratio to determine the red, green and blue components in the suspected area includes: Calculate the pixel ratio of each color at each pixel point in the suspected area; Determine the color of each pixel as red, green or blue based on the color ratio of the pixel; The proportions of red, green and blue pixels in the suspected area are calculated to determine the red, green and blue components in the suspected area.

[0009] Furthermore, the calculating the proportion of each color pixel of each pixel point in the suspected area includes: The proportion of red pixels Pr=R / (R+G+B); Green pixel proportion Pg=G / (R+G+B); The proportion of blue pixels Pb=B / (R+G+B); Where R is the red value of the pixel, G is the green value of the pixel, and B is the blue value of the pixel.

[0010] Furthermore, the further screening of the suspected area by flame combustion characteristics comprises the following steps: Set the brightness and color range of the flame core, inner flame and outer flame when the flame is burning; Determine whether the suspected area has three areas from the inside to the outside, and whether the average brightness and average color of each area conform to the brightness and color range of the flame core, inner flame and outer flame; If it does not match, the suspected area is screened out, and if it matches, it is retained.

[0011] Furthermore, judging whether the suspected area is a flame according to the dynamic characteristics of the flame includes: When the area of ​​the suspected area after screening is smaller than the set threshold, several images are judged continuously. If several consecutive images meet the requirements, it is judged as a flame. If the area of ​​the suspected area is larger than the set threshold and the average brightness is larger than the set brightness threshold, it is directly judged as a flame.

[0012] The present invention also includes a pre-oxidation furnace flame detection system based on a pixel feature value method, using the above method, the detection system includes: The acquisition unit is used to obtain the RGB image in the pre-oxidation furnace and filter out the suspected area by brightness; A pixel feature unit, used to calculate pixel proportions to determine the red, green and blue components in the suspected area, and to screen the suspected area according to a set threshold; A combustion characteristic unit, used to further screen the suspected area according to the flame combustion characteristics; The dynamic feature unit is used to determine whether the suspected area is a flame according to the dynamic feature of the flame.

[0013] The present invention also includes a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described above is implemented.

[0014] The present invention also includes a storage medium on which a computer program is stored. When the computer program is executed by a processor, the method described above is implemented.

[0015] The beneficial effects of the present invention are as follows: the present invention utilizes brightness screening, pixel component analysis, flame combustion feature recognition and dynamic feature judgment to effectively distinguish the flame in the pre-oxidation furnace from other light sources, thereby improving the accuracy of flame detection and ensuring safety in the carbon fiber production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 is a flow chart of the method of the present invention; Figure 2 It is a structural schematic diagram of the system of the present invention; Figure 3 It is a schematic diagram of the structure of the computer device of the present invention. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0019] like Figure 1 As shown: A flame detection method for a pre-oxidation furnace based on a pixel feature value method comprises the following steps: Obtain the RGB image inside the pre-oxidation furnace and filter out the suspected areas by brightness; Calculate the pixel ratio to determine the red, green, and blue components in the suspected area, and screen the suspected area according to the set threshold; Further screening of suspected areas is carried out based on flame combustion characteristics; According to the dynamic characteristics of the flame, determine whether the suspected area is a flame.

[0020] Use a visible light camera to capture RGB images inside the pre-oxidation furnace. During the production process, since the interior of the pre-oxidation furnace is dark, the appearance of flames will form obvious bright spots. By acquiring images in real time, the occurrence of flames can be effectively monitored, and the brightness of the acquired RGB images can be analyzed. Since the brightness of the flame area is usually higher than the surrounding background, the suspected flame area can be preliminarily screened out based on the brightness information of the image. This can reduce the burden of subsequent calculations and only further analyze the high-brightness areas.

[0021] In the screened suspected area, the proportion of red R, green G, and blue B pixels are calculated respectively, and the suspected area is further screened according to the preset threshold. Flames usually have a higher red component, while flashlights have a lower red component. This step helps to preliminarily distinguish flames from other light sources, and further screen according to the combustion characteristics of flames. Flames usually have distinct characteristics of flame core (white), inner flame (yellow), and outer flame (red), and the flames are irregular in shape. Combined with the color distribution and morphological characteristics of flames, false alarm sources such as flashlights can be further excluded. Flames have rapidly changing dynamic characteristics, while flashlights and other light sources are relatively stable. By analyzing the dynamic changes of the suspected area in multiple consecutive frames, it can be determined whether it is a flame.

[0022] By utilizing brightness screening, pixel component analysis, flame combustion feature recognition and dynamic feature judgment, it is possible to effectively distinguish the flame in the pre-oxidation furnace from other light sources, thereby improving the accuracy of flame detection and ensuring safety in the carbon fiber production process.

[0023] In this embodiment, the pixel ratio is calculated to determine the red, green and blue components in the suspected area, including: Calculate the percentage of pixels of each color at each pixel point in the suspected area; Determine the color of each pixel as red, green or blue based on the color ratio of the pixel; Calculate the proportion of red, green, and blue pixels in the suspected area to determine the three components of red, green, and blue in the suspected area.

[0024] Calculate the pixel ratio of each color for each pixel in the suspected area, including: The proportion of red pixels Pr=R / (R+G+B); Green pixel proportion Pg=G / (R+G+B); The proportion of blue pixels Pb=B / (R+G+B); Where R is the red value of the pixel, G is the green value of the pixel, and B is the blue value of the pixel.

[0025] Through the optimal pixel ratio calculation method, the color ratio of each pixel in the suspected area can be calculated more accurately, and then the component distribution of red, green and blue colors in the area can be determined. This method can effectively avoid the neutralization of flame characteristics caused by the regional averaging method, thereby improving the accuracy of flame detection. At the same time, through the statistics and analysis of red, green and blue components, flames, edge light and other interfering light sources can be effectively distinguished.

[0026] As a preferred embodiment of the above, further screening the suspected area according to the flame combustion characteristics includes the following steps: Set the brightness and color range of the flame core, inner flame and outer flame when the flame is burning; Determine whether the suspected area has three areas from the inside to the outside, and whether the average brightness and average color of each area conform to the brightness and color range of the flame core, inner flame and outer flame; If it does not match, the suspected area will be screened out, if it matches, it will be retained.

[0027] Set the brightness and color range of the flame core, inner flame and outer flame when the flame is burning: Flame usually consists of three areas, namely the flame core, inner flame and outer flame, each area has different brightness and color characteristics. According to the physical characteristics of flame combustion, the brightness and color range of each area are pre-set, and the brightness and color of these three areas are quantitatively set, such as defining the color range and brightness value of each area through RGB values ​​or brightness models (such as HSV or Lab color space).

[0028] Analyze the suspected flame area to check whether the area has the brightness and color characteristics that gradually change from the inside to the outside. Specifically: Analyze layer by layer from the center to the outside to see if there are three areas with different brightness, and the brightness decreases from the core of the flame to the outer flame.

[0029] Determine whether the average brightness of each area meets the preset brightness range.

[0030] Determine whether the average color of each area meets the preset color range.

[0031] If the brightness and color of the suspected area meet the characteristics of gradual change from the flame core to the outer flame, the suspected area is retained and determined to be a flame area. If the brightness or color of the suspected area does not meet the preset flame characteristics, the area is screened out and considered not to be a flame. By setting the brightness and color characteristics of the flame, the suspected flame area can be further accurately screened. This method can effectively distinguish the difference between flames and other luminous bodies (such as flashlight light sources), improve the accuracy of detection, and avoid false alarms.

[0032] As a preferred embodiment of the above, judging whether the suspected area is a flame according to the dynamic characteristics of the flame includes: When the area of ​​the suspected area after screening is smaller than the set threshold, several images are judged continuously. If several consecutive images meet the requirements, it is judged as a flame. If the area of ​​the suspected area is larger than the set threshold and the average brightness is larger than the set brightness threshold, it is directly judged as a flame.

[0033] The characteristics of flames are usually accompanied by dynamic changes. If the suspected area is small and may not be sufficient to immediately determine it as a flame, further confirmation is required. Set an area threshold Amin. If the area of ​​the suspected flame area after screening is smaller than this threshold, it cannot be determined whether it is a flame based on a single frame image. For suspected areas whose area is smaller than the set threshold, continuously collect several frames of images (for example, 3-5 frames) to observe the dynamic changes of the area. If the suspected area continues to exist in continuous images, and the brightness and color characteristics meet the combustion characteristics of flames, the area can be determined to be a flame. If the area disappears or the characteristics are unstable in several consecutive images, the suspected area is excluded and not judged as a flame.

[0034] If the area of ​​the suspected region is larger than the set area threshold Amin, it can be considered that the region is large enough and has a high probability of being a flame region. In this case, it is only necessary to further determine whether its average brightness exceeds the preset brightness threshold Lmin. If the average brightness of the region is greater than the brightness threshold and meets the flame characteristics, the suspected region can be directly determined to be a flame.

[0035] This method combines the dynamic characteristics of flames with area and brightness information, and can improve real-time response capabilities while ensuring detection accuracy. For small suspected areas, multiple frames of continuous detection are used to effectively reduce the possibility of misjudgment, while for large areas with high brightness, direct judgment is performed to improve detection efficiency.

[0036] like Figure 2 As shown, this embodiment also includes a pre-oxidation furnace flame detection system based on a pixel feature value method. Using the above method, the detection system includes: The acquisition unit is used to obtain the RGB image in the pre-oxidation furnace and filter out the suspected area by brightness; The pixel feature unit is used to calculate the pixel ratio to determine the red, green and blue components in the suspected area, and screen the suspected area according to the set threshold; The combustion characteristic unit is used to further screen the suspected area according to the flame combustion characteristics; The dynamic feature unit is used to determine whether the suspected area is a flame according to the dynamic features of the flame.

[0037] See also Figure 3A computer device 400 provided in an embodiment of the present application includes: a processor 410 and a memory 420, wherein the memory 420 stores a computer program executable by the processor 410, and when the computer program is executed by the processor 410, the above method is executed.

[0038] The embodiment of the present application further provides a storage medium 430 on which a computer program is stored. When the computer program is run by the processor 410, the above method is executed.

[0039] Among them, the storage medium 430 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable red-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, disk or optical disk.

[0040] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. "Multiple" means two or more, unless otherwise clearly and specifically defined.

[0041] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0042] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0043] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0044] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0045] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0046] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0047] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A pre-oxidation furnace flame detection method based on pixel feature value method, characterized in that: The steps include: Obtain RGB images of the pre-oxidation furnace and filter out suspected areas by brightness; Calculate pixel proportions to determine the red, green and blue components in the suspected area, and screen the suspected area according to a set threshold; Further screening the suspected area according to the flame combustion characteristics; According to the dynamic characteristics of the flame, it is determined whether the suspected area is a flame.

2. The pre-oxidation furnace flame detection method based on pixel feature value method according to claim 1 is characterized in that: The calculating pixel ratio to determine the red, green and blue components in the suspected area includes: Calculate the pixel ratio of each color at each pixel point in the suspected area; Determine the color of each pixel as red, green or blue based on the color ratio of the pixel; The proportions of red, green and blue pixels in the suspected area are calculated to determine the red, green and blue components in the suspected area.

3. The pre-oxidation furnace flame detection method based on pixel feature value method according to claim 2 is characterized in that: The calculating the proportion of each color pixel of each pixel point in the suspected area includes: The proportion of red pixels Pr=R / (R+G+B); Green pixel proportion Pg=G / (R+G+B); The proportion of blue pixels Pb=B / (R+G+B); Where R is the red value of the pixel, G is the green value of the pixel, and B is the blue value of the pixel.

4. The pre-oxidation furnace flame detection method based on pixel feature value method according to claim 1 is characterized in that: The further screening of the suspected area by flame combustion characteristics comprises the following steps: Set the brightness and color range of the flame core, inner flame and outer flame when the flame is burning; Determine whether the suspected area has three areas from the inside to the outside, and whether the average brightness and average color of each area conform to the brightness and color range of the flame core, inner flame and outer flame; If it does not match, the suspected area is screened out, and if it matches, it is retained.

5. The pre-oxidation furnace flame detection method based on pixel feature value method according to claim 1 is characterized in that: The step of judging whether the suspected area is a flame according to the dynamic characteristics of the flame includes: When the area of ​​the suspected area after screening is smaller than the set threshold, several images are judged continuously. If several consecutive images meet the requirements, it is judged as a flame. If the area of ​​the suspected area is larger than the set threshold and the average brightness is larger than the set brightness threshold, it is directly judged as a flame.

6. A pre-oxidation furnace flame detection system based on pixel feature value method, characterized in that: Using the method according to any one of claims 1 to 5, the detection system comprises: The acquisition unit is used to obtain the RGB image in the pre-oxidation furnace and filter out the suspected area by brightness; A pixel feature unit, used to calculate pixel proportions to determine the red, green and blue components in the suspected area, and to screen the suspected area according to a set threshold; A combustion characteristic unit, used to further screen the suspected area according to the flame combustion characteristics; The dynamic feature unit is used to determine whether the suspected area is a flame according to the dynamic feature of the flame.

7. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

8. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images