Rapid flame detection method and system in pre-oxidation furnace

Abstract

The present invention relates to the field of carbon fiber production technology, and in particular to a method and system for rapid flame detection in a pre-oxidation furnace, including: collecting images in the pre-oxidation furnace, and screening out suspected flame areas according to feature extraction; setting a first area threshold, if the suspected flame area is less than the first area threshold, flame determination is performed on the suspected flame area by continuously setting images; otherwise, determination is performed only through one image, and including: setting a second area threshold, if the suspected flame area is greater than or equal to the first area threshold, and less than the second area threshold, flame determination is performed according to the average brightness and color in the suspected flame area; if the suspected flame area is greater than the second area threshold, flame determination is performed according to the average brightness and number of red pixels in the suspected flame area. In the present invention, for larger suspected flame areas, determination is performed only through a single image, thereby accelerating the response speed.

Description

Technical Field

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

[0002] The oxidation and carbonization process of PAN-based carbon fibers includes pre-oxidation, low-temperature carbonization, high-temperature carbonization, surface treatment, sizing and drying, etc. Among them, pre-oxidation is an important intermediate process. The linear molecular chain of PAN precursor gradually forms a heat-resistant ladder structure in this process. PAN precursor needs to pass through multiple pre-oxidation furnaces with increasing temperatures in the oxidation furnace cluster. The main reactions of the pre-oxidation process are cyclization, oxidation and dehydrogenation, which are all exothermic reactions, which will cause heat storage and overheating inside the fiber. The temperature in the pre-oxidation furnace is high, and it is easy to catch fire due to excessive local temperature.

[0003] Since the temperature in the pre-oxidation furnace is relatively high, once the furnace catches fire, deflagration will occur, and the flame can spread to the entire oxidation furnace within a few seconds. In order to increase the speed of flame identification in the oxidation furnace, the flame can be identified by visual detection. In the prior art, such as "CN202211033670.4, a fire monitoring method, computer equipment and storage medium in an oxidation furnace", "CN202211047645.1, a flame detection method, computer equipment and storage medium", etc., it was found in the application process that due to the deflagration phenomenon of the flame, the speed from ignition to flame spread is very fast, and its detection speed needs to be improved.

[0004] 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

[0005] The present invention provides a method and system for rapid flame detection in a pre-oxidation furnace, thereby effectively solving the problems in the background technology.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is: a method for rapid flame detection in a pre-oxidation furnace, comprising the following steps:

[0007] Collect images inside the pre-oxidation furnace and filter out suspected flame areas based on feature extraction;

[0008] Setting a first area threshold, if the suspected flame area is smaller than the first area threshold, performing flame determination on the suspected flame area by continuously setting images;

[0009] Otherwise, the judgment is made based on only one image and includes:

[0010] Setting a second area threshold, if the suspected flame area is greater than or equal to the first area threshold and less than the second area threshold, performing flame determination based on average brightness and color in the suspected flame area;

[0011] If the suspected flame area is larger than the second area threshold, flame determination is performed based on the average brightness and the number of red pixels in the suspected flame area.

[0012] Furthermore, the step of performing flame determination on the suspected flame area by continuously setting images includes:

[0013] The flame determination is performed by continuously setting the dynamic changes of the suspected flame area in the image.

[0014] Furthermore, the dynamic changes include:

[0015] A bright yellow area in the suspected flame area is extracted, and the bright yellow area in a plurality of consecutive images is compared. When the area of ​​the bright yellow area becomes larger, it is determined to be a flame, otherwise it is determined to be interference.

[0016] Furthermore, the dynamic changes include:

[0017] First, the area change rate of the suspected area in the two previous and next frames is calculated, and then the variance of several area change rates is calculated, and the variance is compared with a set threshold. When the set threshold is exceeded, the suspected area is determined to be a flame area.

[0018] Furthermore, the dynamic changes include:

[0019] Calculating the Euclidean distance between any two pixels in the suspected flame area, and selecting the longest Euclidean distance in the suspected flame area;

[0020] When the longest Euclidean distance of the suspected flame area gradually increases in the subsequent frames, and the change value of the longest Euclidean distance is nonlinearly related to time, it is determined to be the flame area.

[0021] Furthermore, the flame determination according to the average brightness and color in the suspected flame area includes:

[0022] If the average brightness of the suspected flame area is greater than 150, including bright yellow or bright white areas, and after removing the bright yellow or bright white areas, the proportion of red pixels exceeds 90%, it is determined to be a flame.

[0023] Furthermore, the color judgment conditions in the suspected flame area include:

[0024] Extracting R, G, and B values ​​of pixels in the suspected flame area, and judging the color by the R, G, and B values;

[0025] Red area: satisfies the conditions R>G and R>B, and R−G>50 and R−B>50;

[0026] Bright yellow area: satisfies the conditions R>B and G>B, and R−B>50 and G−B>50;

[0027] Bright white area: meets the conditions R>200, G>200 and B>200.

[0028] Furthermore, the flame determination is performed based on the average brightness and the number of red pixels in the suspected flame area, including:

[0029] If the average brightness of the suspected flame area is greater than 70 and the proportion of red pixels exceeds 95%, it is determined to be a flame.

[0030] The present invention also includes a rapid flame detection system in a pre-oxidation furnace, using the above method, comprising:

[0031] The acquisition unit is used to acquire images in the pre-oxidation furnace and screen out suspected flame areas based on feature extraction;

[0032] a detection unit, configured to set a first area threshold, and if the suspected flame area is smaller than the first area threshold, perform flame determination on the suspected flame area by continuously setting images;

[0033] Otherwise, the judgment is made based on only one image and includes:

[0034] Setting a second area threshold, if the suspected flame area is greater than or equal to the first area threshold and less than the second area threshold, performing flame determination based on average brightness and color in the suspected flame area;

[0035] If the suspected flame area is larger than the second area threshold, flame determination is performed based on the average brightness and the number of red pixels in the suspected flame area.

[0036] 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.

[0037] 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.

[0038] The beneficial effects of the present invention are as follows: in the present invention, when the suspected flame area is small, multiple continuous images are used for detection, which helps to filter out misjudgments caused by noise or non-flame light sources. For larger suspected flame areas, judgment can be made through only a single image, which speeds up the response speed. The flame can be quickly detected in the early stage of flame deflagration in the pre-oxidation furnace, and an alarm can be issued in time and corresponding fire-fighting measures can be taken, thereby effectively preventing the expansion of the fire and damage to the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] 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.

[0040] Figure 1 is a flow chart of the method of the present invention;

[0041] Figure 2 It is a structural schematic diagram of the system of the present invention;

[0042] Figure 3 It is a structural schematic diagram of the computer device of the present invention. DETAILED DESCRIPTION

[0043] 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.

[0044] like Figure 1 As shown: A method for rapid flame detection in a pre-oxidation furnace comprises the following steps:

[0045] Collect images inside the pre-oxidation furnace and filter out suspected flame areas based on feature extraction;

[0046] Setting a first area threshold, if the suspected flame area is smaller than the first area threshold, performing flame determination on the suspected flame area by continuously setting images;

[0047] Otherwise, the judgment is made based on only one image and includes:

[0048] Set a second area threshold, if the suspected flame area is greater than or equal to the first area threshold and less than the second area threshold, perform flame determination based on the average brightness and color in the suspected flame area;

[0049] If the suspected flame area is larger than the second area threshold, flame determination is performed based on the average brightness and the number of red pixels in the suspected flame area.

[0050] When the suspected flame area is small, using multiple consecutive images for detection helps filter out misjudgments caused by noise or non-flame light sources. For larger suspected flame areas, only a single image can be used for judgment, which speeds up the response. The setting of the first and second area thresholds is the key to distinguishing different flame detection strategies. These thresholds can be adjusted based on actual experience and experimental data. Average brightness and color (especially the number of red pixels) are important features for distinguishing flames. These features can help quickly determine the presence of flames. In this way, flames can be quickly detected in the early stages of flame deflagration in the pre-oxidation furnace, and alarms can be issued in time and corresponding fire-fighting measures can be taken, thereby effectively preventing the expansion of fires and damage to equipment.

[0051] According to the previous image of the furnace edge light, the maximum area is within 4W, so for this type of camera alarm caused by external light sources, we generally define the first area threshold as 5W. As the critical value, if the overall area of ​​the suspected area is less than 5W and the average brightness of the area is very small, then three images are judged continuously.

[0052] In this embodiment, flame determination is performed on the suspected flame area by continuously setting images, including:

[0053] The flame determination is performed by continuously setting the dynamic changes of the suspected flame area in the image.

[0054] The dynamic changes include:

[0055] The bright yellow area in the suspected flame area is extracted, and the bright yellow areas in several consecutive images are compared. When the area of ​​the bright yellow area becomes larger, it is judged as a flame, otherwise it is judged as interference.

[0056] An expansion of the bright yellow area is usually a sign of flame development and spread, while stagnation or reduction may be other sources of disturbance.

[0057] Alternatively, dynamic changes include:

[0058] First, the area change rate of the suspected area in the two frames before and after is calculated, and then the variance of several area change rates is calculated. The variance is compared with the set threshold. When it exceeds the set threshold, the suspected area is determined to be a flame area.

[0059] The appearance and expansion of flames usually lead to unstable changes in the area of ​​the image, while interference is generally more stable, so a larger variance may be a flame.

[0060] Alternatively, dynamic changes include:

[0061] The Euclidean distance between any two pixels in the suspected flame area is calculated, and the longest Euclidean distance in the suspected flame area is selected;

[0062] When the longest Euclidean distance of the suspected flame area gradually increases in the photos of subsequent frames, and the change value of the longest Euclidean distance is nonlinearly related to time, it is judged to be a flame area.

[0063] The spread and development of the flame will cause the longest Euclidean distance in the suspected area to gradually increase and show a nonlinear growth trend, which is helpful to distinguish between flames and other interferences.

[0064] The above dynamic changes can be selected for judgment individually or in combination. By analyzing the dynamic changes of the suspected flame area over time, it helps to further improve the accuracy of flame detection. In particular, the analysis of features such as bright yellow area, area change rate and Euclidean distance can provide richer information to judge the presence or absence of flame. This multi-dimensional detection method can effectively meet the needs of flame detection in complex environments and ensure that the system can respond quickly and make correct judgments when a real fire occurs.

[0065] In this embodiment, flame determination is performed based on average brightness and color in the suspected flame area, including:

[0066] If the average brightness of the suspected flame area is greater than 150, including bright yellow or bright white areas, and after removing the bright yellow or bright white areas, the proportion of red pixels exceeds 90%, it is determined to be a flame.

[0067] The flame light in the furnace directly enters the camera. This type of image shows that the fire source can be clearly seen. Generally, the flame core appears bright white, the inner flame appears bright yellow, and the outer flame appears bright red. The flame area is within the camera's shooting area. For this type of image, the average brightness is generally above 150, and the fire source can be clearly seen, that is, the bright yellow and bright white area. Excluding this area, the overall number of red pixels accounts for more than 0.9. For this type of image, we only need to judge one to issue an alarm, indicating that the area is the area of ​​open flame directly captured by the camera.

[0068] The criteria for judging the color in the suspected flame area include:

[0069] Extract the R, G, and B values ​​of the pixels in the suspected flame area, and judge the color by the R, G, and B values;

[0070] Red area: satisfies the conditions R>G and R>B, and R−G>50 and R−B>50;

[0071] Bright yellow area: satisfies the conditions R>B and G>B, and R−B>50 and G−B>50;

[0072] Bright white area: meets the conditions R>200, G>200 and B>200.

[0073] As a preferred embodiment of the above, flame determination is performed based on the average brightness and the number of red pixels in the suspected flame area, including:

[0074] If the average brightness of the suspected flame area is greater than 70 and the proportion of red pixels exceeds 95%, it is determined to be a flame.

[0075] The flame light inside the furnace is reflected into the camera. This type of image generally appears bright red. The flame area is not within the shooting area of ​​this camera, but is inside the furnace where the camera is located, and the area accounts for a large proportion. The average brightness of the image is large, and the red proportion of the image is large.

[0076] For the second area threshold, in this embodiment, a threshold is temporarily set to 100w pixels, that is, 1 / 12 of the image. In the self-developed oxidation furnace, hold the flashlight in your hand and look at the number of pixels at the place closest to the camera, which is the area A we set;

[0077] That is, when the area detected by a camera exceeds A, and the average brightness of this area is B>70, and the number of red pixels in this area is greater than 0.95, this area is the flame area. At this time, only one image needs to be judged to alarm, indicating that the area has turned red in the furnace due to the light of the flame.

[0078] like Figure 2 As shown, this embodiment also includes a rapid flame detection system in a pre-oxidation furnace, using the above method, including:

[0079] The acquisition unit is used to acquire images in the pre-oxidation furnace and screen out suspected flame areas based on feature extraction;

[0080] A detection unit, used to set a first area threshold, and if the suspected flame area is smaller than the first area threshold, perform flame determination on the suspected flame area by continuously setting images;

[0081] Otherwise, the judgment is made based on only one image and includes:

[0082] Set a second area threshold, if the suspected flame area is greater than or equal to the first area threshold and less than the second area threshold, perform flame determination based on the average brightness and color in the suspected flame area;

[0083] If the suspected flame area is larger than the second area threshold, flame determination is performed based on the average brightness and the number of red pixels in the suspected flame area.

[0084] 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.

[0085] 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.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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 method for rapid flame detection in a pre-oxidation furnace, characterized in that: The steps include: Collect images inside the pre-oxidation furnace and filter out suspected flame areas based on feature extraction; Setting a first area threshold, if the suspected flame area is smaller than the first area threshold, performing flame determination on the suspected flame area by continuously setting images; Otherwise, the judgment is made based on only one image and includes: Setting a second area threshold, if the suspected flame area is greater than or equal to the first area threshold and less than the second area threshold, performing flame determination based on average brightness and color in the suspected flame area; If the suspected flame area is larger than the second area threshold, flame determination is performed based on the average brightness and the number of red pixels in the suspected flame area; The first area threshold is 5w pixels, and the second area threshold is 1 / 12 of the image pixels.

2. The method for rapid flame detection in a pre-oxidation furnace according to claim 1, characterized in that: The step of performing flame determination on the suspected flame area by continuously setting images includes: The flame determination is performed by continuously setting the dynamic changes of the suspected flame area in the image.

3. The method for rapid flame detection in a pre-oxidation furnace according to claim 2, characterized in that: The dynamic changes include: A bright yellow area in the suspected flame area is extracted, and the bright yellow area in a plurality of consecutive images is compared. When the area of ​​the bright yellow area becomes larger, it is determined to be a flame, otherwise it is determined to be interference.

4. The method for rapid flame detection in a pre-oxidation furnace according to claim 2, characterized in that: The dynamic changes include: First, the area change rate of the suspected area in the two previous and next frames is calculated, and then the variance of several area change rates is calculated, and the variance is compared with a set threshold. When the set threshold is exceeded, the suspected area is determined to be a flame area.

5. The method for rapid flame detection in a pre-oxidation furnace according to claim 2, characterized in that: The dynamic changes include: Calculating the Euclidean distance between any two pixels in the suspected flame area, and selecting the longest Euclidean distance in the suspected flame area; When the longest Euclidean distance of the suspected flame area gradually increases in the subsequent frames, and the change value of the longest Euclidean distance is nonlinearly related to time, it is determined to be the flame area.

6. The method for rapid flame detection in a pre-oxidation furnace according to any one of claims 1 to 5, characterized in that: The flame determination according to the average brightness and color in the suspected flame area includes: If the average brightness of the suspected flame area is greater than 150, including bright yellow or bright white areas, and after removing the bright yellow or bright white areas, the proportion of red pixels exceeds 90%, it is determined to be a flame.

7. The method for rapid flame detection in a pre-oxidation furnace according to any one of claims 1 to 5, characterized in that: The flame determination is performed based on the average brightness and the number of red pixels in the suspected flame area, including: If the average brightness of the suspected flame area is greater than 70, and the proportion of red pixels exceeds 95%, it is determined to be a flame.

8. A rapid flame detection system in a pre-oxidation furnace, characterized in that: Use of the method according to any one of claims 1 to 7, comprising: The acquisition unit is used to acquire images in the pre-oxidation furnace and screen out suspected flame areas based on feature extraction; a detection unit, configured to set a first area threshold, and if the suspected flame area is smaller than the first area threshold, perform flame determination on the suspected flame area by continuously setting images; Otherwise, the judgment is made based on only one image and includes: Setting a second area threshold, if the suspected flame area is greater than or equal to the first area threshold and less than the second area threshold, performing flame determination based on average brightness and color in the suspected flame area; If the suspected flame area is larger than the second area threshold, flame determination is performed based on the average brightness and the number of red pixels in the suspected flame area.

9. 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 7 is implemented.

10. 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 7 is implemented.

Images