Method, system and equipment for identifying flame morphology in heating furnace and medium

Abstract

The invention provides a flame morphology identification method, system and device in a heating furnace and a medium, and belongs to the technical field of image identification. The method comprises the following steps: acquiring multiple frames of images in a heating furnace in an actual combustion process; wherein the multiple frames of images are obtained by decompressing video information in the heating furnace in the actual combustion process; for each frame of image, identifying the frame of image by using different image identification algorithms to obtain the flame morphology of each frame of image under each image identification algorithm, and determining the flame morphology under each image identification algorithm based on the flame morphology of each frame of image under each image identification algorithm; and based on the characteristic parameters of the flame morphology under each image recognition algorithm, flame morphology correction is carried out, and the corrected flame morphology is obtained. According to the invention, the flame morphology in the heating furnace can be effectively identified.

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition, and in particular to a method for recognizing flame shape in a heating furnace, a system for recognizing flame shape in a heating furnace, an electronic device and a readable storage medium. Background Art

[0002] At present, the Emergency Management Department's "Catalogue of Outdated Dangerous Chemicals Production Safety Technology Equipment (First Batch)" and the Refining Division's "Guidance on the Installation of Interlocking Protection Systems for Tubular Heating Furnaces in Refining Units" have clearly pointed out the safety requirements for heating furnace flame identification. Monitoring the combustion state of the heating furnace flame and evaluating its combustion efficiency are the general trend of clean, safe and efficient production.

[0003] At present, the combustion state of the heating furnace flame is mainly monitored by the following methods: (1) flame detector detects the combustion state; (2) combustion state monitoring system. However, method (1) cannot accurately monitor the combustion state of the heating furnace flame when the hardware is damaged or the detection optical path is blocked, and method (2) is not suitable for the complex environment in the actual application scenario of the heating furnace, resulting in the inability to quantify and evaluate the combustion state of the heating furnace flame.

[0004] In general, the existing flame combustion state monitoring technology cannot effectively identify the flame morphology of the heating furnace. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a method, system, device and medium for identifying the flame morphology in a heating furnace, so as to solve the problem that the existing flame combustion state monitoring technology cannot effectively identify the flame morphology of the heating furnace.

[0006] In order to achieve the above object, an embodiment of the present invention provides a method for identifying flame morphology in a heating furnace, comprising:

[0007] Acquire multiple frames of images during the actual combustion process in the heating furnace; wherein the multiple frames of images are obtained by decompressing video information during the actual combustion process in the heating furnace;

[0008] For each frame of image, different image recognition algorithms are used to respectively recognize the frame of image, and the flame morphology of each frame of image under each image recognition algorithm is obtained, and the flame morphology under each image recognition algorithm is determined based on the flame morphology of each frame of image under each image recognition algorithm;

[0009] Based on the characteristic parameters of the flame morphology under each image recognition algorithm, the flame morphology is corrected to obtain the corrected flame morphology.

[0010] Optionally, the duration of the video information of the actual combustion process in the heating furnace is 1-5s.

[0011] Optionally, for each frame of image, using different image recognition algorithms to respectively recognize the frame of image, and obtaining the flame morphology of each frame of image under each image recognition algorithm, includes:

[0012] Extract the gray value and brightness information of each pixel on each frame of the image;

[0013] The maximum inter-class variance method is used to calculate the gray value of each pixel on each frame of the image to obtain the gray threshold of each frame of the image;

[0014] The pixels on each frame of the image that are greater than the corresponding grayscale threshold are determined as the flame morphology under the maximum inter-class variance method;

[0015] Determine the brightness change of each pixel on each frame of the image relative to adjacent pixels based on the extracted brightness information;

[0016] The pixels whose brightness change is greater than zero are activated to obtain the flame morphology in each frame of the image under the Boolean variable.

[0017] Optionally, extracting the grayscale value and brightness information of each pixel on each frame of the image includes:

[0018] Using formulas (1) and (2), the pixel value of each pixel point on each frame of the image is calculated to obtain the grayscale value and brightness information of each pixel point on each frame of the image; wherein the pixel value includes: red channel value, green channel value and blue channel value;

[0019] Gray=0.299*R+0.587*G+0.114*B(1);

[0020] Light=0.2126*R+0.7152*G+0.0722*B(2);

[0021] Among them, Gray represents the grayscale value of each pixel in each frame image; Light represents the brightness information of each pixel in each frame image; R represents the red channel value of each pixel in each frame image; G represents the green channel value of each pixel in each frame image; B represents the blue channel value of each pixel in each frame image.

[0022] Optionally, the determining the flame morphology under each image recognition algorithm based on the flame morphology of each frame image under each image recognition algorithm comprises:

[0023] The flame morphology in each frame of the image under the maximum inter-class variance method is superimposed, and the probability of each pixel point appearing in the flame morphology under the maximum inter-class variance method formed after superposition is determined;

[0024] The flame morphology under the maximum inter-class variance method is determined by pixel points whose occurrence probability is greater than a preset probability threshold;

[0025] The flame morphology in each frame image under the Boolean variable is superimposed, and the probability of each pixel point appearing in the flame morphology under the Boolean variable formed after superposition is determined;

[0026] The pixel points whose occurrence probability is greater than a preset probability threshold are used to determine the flame morphology under the Boolean variable.

[0027] Optionally, the determining the probability of each pixel point appearing in the flame morphology under the maximum inter-class variance method after superposition includes:

[0028] For each pixel:

[0029] If the current pixel point is within the flame shape formed by the maximum between-class variance method after superposition, the current pixel point is set as the first mark;

[0030] If the current pixel point is not within the flame morphology formed by the maximum inter-class variance method after superposition, the current pixel point is set as the second mark;

[0031] The number of times the current pixel is the first mark in the multi-frame image is calculated, and the ratio of the number of times to the number of frames of the multi-frame image is used as the probability of the current pixel appearing in the flame morphology under the maximum between-class variance method after superposition.

[0032] Optionally, determining the probability of each pixel point appearing in the flame morphology under the Boolean variable formed after superposition includes:

[0033] For each pixel:

[0034] If the current pixel point is within the flame shape under the Boolean variable formed after superposition, the current pixel point is set as the third identifier;

[0035] If the current pixel point is not within the flame shape under the Boolean variable formed after superposition, the current pixel point is set as the fourth mark;

[0036] The number of times the current pixel is the first mark in the multi-frame image is calculated, and the ratio of the number of times to the number of frames of the multi-frame image is used as the probability of the current pixel appearing in the flame morphology under the Boolean variable formed after superposition.

[0037] Optionally, the flame morphology correction is performed based on the characteristic parameters of the flame morphology under each image recognition algorithm to obtain the corrected flame morphology, including:

[0038] Based on the characteristic parameters of flame morphology under the maximum inter-class variance method and the characteristic parameters of flame morphology under Boolean variables, the flame morphology error value is determined;

[0039] If the flame shape error value is less than a preset error threshold, the flame shape under the Boolean variable is used as the corrected flame shape.

[0040] Optionally, the characteristic parameters of the flame morphology include: flame height, flame width, flame area, flame pulsation frequency and flame inclination;

[0041] The flame shape error value is determined based on the characteristic parameters of the flame shape under the maximum inter-class variance method and the characteristic parameters of the flame shape under the Boolean variable, including:

[0042] Calculate the differences between the flame height, flame width, flame area, flame pulsation frequency and flame inclination under the maximum inter-class variance method and the flame height, flame width, flame area, flame pulsation frequency and flame inclination under the Boolean variable respectively, and obtain the flame height error value, flame width error value, flame area error value, flame pulsation frequency error value and flame inclination error value;

[0043] Using formula (3), the flame height error value, flame width error value, flame area error value, flame pulsation frequency error value and flame inclination error value are calculated to obtain the flame shape error value;

[0044] X=0.2*H+0.2*W+0.1*S+0.1*f+0.4*θ (3);

[0045] Among them, X represents the flame shape error value; H represents the flame height error value; W represents the flame width error value; S represents the flame area error value; f represents the flame pulsation frequency error value; θ represents the flame inclination error value.

[0046] Optionally, the method further comprises:

[0047] The modified flame appearance is sent to a user terminal display device, so that the user terminal display device displays the modified flame appearance.

[0048] In a second aspect of an embodiment of the present invention, a flame morphology recognition system in a heating furnace is provided, comprising:

[0049] An image acquisition module, used to acquire multiple frames of images during the actual combustion process in the heating furnace; wherein the multiple frames of images are obtained by decompressing video information during the actual combustion process in the heating furnace;

[0050] The flame recognition module is used to recognize each frame of image by using different image recognition algorithms to obtain the flame morphology of each frame of image under each image recognition algorithm, and determine the flame morphology under each image recognition algorithm based on the flame morphology of each frame of image under each image recognition algorithm;

[0051] The flame correction module is used to correct the flame shape based on the characteristic parameters of the flame shape under each image recognition algorithm to obtain the corrected flame shape.

[0052] In a third aspect of the embodiments of the present invention, there is provided an electronic device, comprising: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the machine-readable instructions are executed by the processor, the above-mentioned method for identifying flame morphology in a heating furnace is executed.

[0053] In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided, storing computer instructions, which, when executed on a computer, enable the computer to execute the above-mentioned method for identifying flame morphology in a heating furnace.

[0054] In an embodiment of the present invention, multiple frames of images are obtained during the actual combustion process in a heating furnace; wherein the multiple frames of images are obtained by decompressing the video information during the actual combustion process in the heating furnace; for each frame of image, different image recognition algorithms are used to respectively recognize the frame of image, and the flame morphology of each frame of image under each image recognition algorithm is obtained, and the flame morphology under each image recognition algorithm is determined based on the flame morphology of each frame of image under each image recognition algorithm; based on the characteristic parameters of the flame morphology under each image recognition algorithm, the flame morphology is corrected to obtain the corrected flame morphology. The present invention corrects the flame morphology through the flame morphology under different image recognition algorithms to obtain the corrected flame morphology, thereby avoiding the problem of recognition errors caused by the complex environment in the actual application scenario of the heating furnace, thereby realizing the effective recognition of the flame morphology in the heating furnace.

[0055] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0057] Figure 1 It is a schematic diagram of the flow of a method for identifying flame morphology in a heating furnace provided by an embodiment of the present invention;

[0058] Figure 2 It is a structural schematic diagram of a flame morphology recognition system in a heating furnace provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0059] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0061] In the description of the embodiments of the present invention, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present invention, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0062] Embodiment 1

[0063] Please refer to Figure 1 , Figure 1 1 is a flow chart of a method for identifying flame morphology in a heating furnace provided by an embodiment of the present invention, the method comprising the following steps:

[0064] S100, acquiring multiple frames of images during the actual combustion process in the heating furnace; wherein the multiple frames of images are obtained by decompressing video information during the actual combustion process in the heating furnace;

[0065] Among them, the petrochemical heating furnace is a kind of equipment specially used for heating product materials and workpieces. Unlike drying equipment, the main purpose of the heating furnace is not to heat general materials, but to heat metal products at high temperatures without or with little oxidation so that they can be further processed.

[0066] It should be noted that a plurality of furnace nozzles are provided in the heating furnace, and the fuel sprayed from the furnace nozzles burns to form flames, that is, the video information of the actual combustion process in the heating furnace includes the video information of the plurality of furnace nozzles in the actual combustion process.

[0067] It is understandable that the number of multi-frame images of the actual combustion process in the heating furnace is determined by the frame rate and duration of the video information of the actual combustion process in the heating furnace, and the frame rate and duration of the video information of the actual combustion process in the heating furnace are determined by the camera, and the embodiment of the present invention does not specifically limit this. For example: the video frame rate of the camera is 50fps, and the total shooting time is 10s, then the number of multi-frame images of the actual combustion process in the heating furnace is 50fps*10s=500.

[0068] The video information of the actual combustion process in the heating furnace is obtained by shooting with a camera.

[0069] In one embodiment, the duration of the video information of the actual combustion process in the heating furnace is limited to 1-5 seconds. Since the video information is limited to a short time, not many frames of images will be obtained after decompression, thereby avoiding the failure to identify a certain abnormal image frame due to image superposition, so that the flame morphology in the image can be accurately identified.

[0070] S200, for each frame of image, using different image recognition algorithms to respectively recognize the frame of image, obtain the flame morphology of each frame of image under each image recognition algorithm, and determine the flame morphology under each image recognition algorithm based on the flame morphology of each frame of image under each image recognition algorithm;

[0071] Image recognition algorithm refers to the algorithm for identifying specific targets in an image, including but not limited to: maximum inter-class variance method, Boolean variables, YOLO, etc.

[0072] In this step, different image recognition algorithms are used to recognize multiple frames of images respectively, and the flame morphology in each frame of image under each image recognition algorithm is obtained, and then the flame morphology of multiple frames of images is superimposed to finally obtain the flame morphology under each image recognition algorithm. How to implement image recognition and image superposition will be described in detail later and will not be described here.

[0073] S300, performing flame shape correction based on characteristic parameters of the flame shape under each image recognition algorithm to obtain a corrected flame shape.

[0074] In order to avoid errors in the image recognition algorithm itself, or errors in the image recognition algorithm caused by the complex combustion environment in the heating furnace, the differences between the characteristic parameters of the flame morphology under different image recognition algorithms are compared. If the differences between different image recognition algorithms are very large, it means that there is an error in one of the algorithms. At this time, the flame morphology needs to be corrected.

[0075] In this embodiment, multiple frames of images are obtained during the actual combustion process in the heating furnace; wherein the multiple frames of images are obtained by decompressing the video information of the actual combustion process in the heating furnace; for each frame of image, different image recognition algorithms are used to respectively recognize the frame of image, and the flame morphology of each frame of image under each image recognition algorithm is obtained, and the flame morphology under each image recognition algorithm is determined based on the flame morphology of each frame of image under each image recognition algorithm; based on the characteristic parameters of the flame morphology under each image recognition algorithm, the flame morphology is corrected to obtain the corrected flame morphology. The present invention corrects the flame morphology through the flame morphology under different image recognition algorithms to obtain the corrected flame morphology, thereby avoiding the problem of recognition errors caused by the complex environment in the actual application scenario of the heating furnace, thereby realizing the effective recognition of the flame morphology in the heating furnace.

[0076] Optionally, the above step S200 may specifically include:

[0077] S210, extracting the gray value and brightness information of each pixel on each frame of the image;

[0078] In one embodiment, the grayscale value and brightness information of each pixel in each frame of the image may be extracted by the following steps:

[0079] Using formulas (1) and (2), the pixel value of each pixel point on each frame of the image is calculated to obtain the grayscale value and brightness information of each pixel point on each frame of the image; wherein the pixel value includes: red channel value, green channel value and blue channel value;

[0080] Gray=0.299*R+0.587*G+0.114*B (1);

[0081] Light=0.2126*R+0.7152*G+0.0722*B (2);

[0082] Among them, Gray represents the grayscale value of each pixel in each frame image; Light represents the brightness information of each pixel in each frame image; R represents the red channel value of each pixel in each frame image; G represents the green channel value of each pixel in each frame image; B represents the blue channel value of each pixel in each frame image.

[0083] S211, using the maximum inter-class variance method, calculating the gray value of each pixel on each frame of the image to obtain a gray threshold value of each frame of the image;

[0084] The maximum inter-class variance method is a method for automatically finding thresholds that is suitable for bimodal situations, also known as the Otsu method. It divides the image into two parts, background and target, according to the grayscale characteristics of the image. The larger the inter-class variance between the background and the target, the greater the difference between the two parts of the image. The smaller the inter-class variance between the background and the target, the smaller the difference between the two parts of the image.

[0085] For ease of understanding, the maximum between-class variance method is explained below:

[0086] p1m1+p2m2=mG (1);

[0087] p1+p2=1 (2);

[0088] σ 2 =p1(m1-mG) 2 +p2(m2-mG) 2 (3);

[0089] Substituting formula (3) into formula (1) to simplify, we get σ 2 =p1p2(m1-m2) 2 (4);

[0090] Where m1 represents the average grayscale value of the background pixels in the image; m2 represents the average grayscale value of the foreground pixels in the image; mG represents the mean grayscale value of all pixels in the image; p1 represents the probability that a pixel in the image is classified as a background pixel, and p2 represents the probability that a pixel in the image is classified as a foreground pixel; σ 2 represents the between-class variance.

[0091] σ 2 This is the grayscale threshold of the image we want to obtain.

[0092] S212, determining the pixel points on each frame of the image that are greater than the corresponding grayscale threshold as the flame morphology under the maximum inter-class variance method;

[0093] Specifically, the grayscale value of each pixel on each frame is compared with the grayscale threshold of each frame, and the pixels with grayscale values ​​greater than the grayscale threshold are determined as flame pixels. Then all flame pixels constitute the flame morphology in each frame under the maximum inter-class variance method.

[0094] S213, determining a brightness change amount of each pixel point on each frame of the image relative to adjacent pixels points according to the extracted brightness information;

[0095] According to the nature of combustion, the outer ring of the flame has the highest brightness, so Boolean variables are used to identify the flame morphology of each frame image.

[0096] Specifically, after the brightness information of each pixel on each frame of the image is read, each pixel is then compared and analyzed with the brightness data of four other adjacent pixels, so as to determine the brightness change of each pixel.

[0097] S214, activating the pixel points whose brightness change is greater than zero, and obtaining the flame morphology in each frame of the image under the Boolean variable.

[0098] Specifically, the pixels whose brightness change is greater than zero are activated to obtain the outer ring of the flame in each frame of the image. Then, the outer ring of the flame in the image is drawn by reading the pixels of the image array using a function, thereby obtaining the flame morphology in each frame of the image under the Boolean variable.

[0099] Optionally, the above step S200 may further include the following steps:

[0100] S215, superimposing the flame morphology in each frame image under the maximum inter-class variance method, and determining the probability of each pixel point appearing in the flame morphology under the maximum inter-class variance method formed after superposition;

[0101] In one embodiment, the probability of each pixel appearing in the flame morphology under the maximum inter-class variance method after superposition can be obtained as follows:

[0102] For each pixel:

[0103] Step 1: If the current pixel point is within the flame morphology formed by the maximum inter-class variance method after superposition, the current pixel point is set as the first mark;

[0104] Step 2: If the current pixel point is not within the flame morphology formed by the maximum inter-class variance method after superposition, the current pixel point is set as the second mark;

[0105] Step 3: Calculate the number of times the current pixel is the first identifier in multiple frames, and use the ratio of this number to the number of frames in the multiple frames as the probability of the current pixel appearing in the flame morphology under the maximum between-class variance method after superposition.

[0106] For ease of understanding, the following example is given:

[0107] Each pixel point on each frame of the flame morphology identified by the maximum inter-class variance method is binarized, that is, the pixel point representing the flame morphology is set to 1 (first identification), and the pixel point representing the non-flame morphology is set to 0 (second identification). Then, the number of times each pixel point appears as 1 in multiple frames of images is calculated, and the ratio of the number of occurrences to the number of frames of the multiple frames is used as the probability of each pixel point appearing in the flame morphology under the maximum inter-class variance method after superposition. Finally, the pixel point whose probability of appearance is greater than the preset probability threshold is used as the flame morphology under the maximum inter-class variance method.

[0108] S216, determining the flame morphology under the maximum inter-class variance method for pixel points whose occurrence probability is greater than a preset probability threshold;

[0109] It is understandable that when high-precision identification of flame morphology is required, the preset probability threshold is set to be smaller, and when high-precision identification of flame morphology is not required, the preset probability threshold is set to be larger. Therefore, the embodiment of the present invention does not make specific limitations on this, and it can be reasonably set according to actual needs.

[0110] S217, superimposing the flame morphology in each frame image under the Boolean variable, and determining the probability of each pixel point appearing in the flame morphology under the Boolean variable formed after superposition;

[0111] In one embodiment, the probability of each pixel point appearing in the flame profile under the Boolean variable formed after superposition can be obtained as follows:

[0112] For each pixel:

[0113] Step 1: If the current pixel point is within the flame shape under the Boolean variable formed after superposition, the current pixel point is set as the third identifier;

[0114] Step 2: If the current pixel point is not within the flame shape under the Boolean variable formed after superposition, the current pixel point is set as the fourth mark;

[0115] Step 3: Calculate the number of times the current pixel is the third identifier in the multi-frame image, and use the ratio of this number to the number of frames in the multi-frame image as the probability of the current pixel appearing in the flame morphology under the Boolean variable formed after superposition.

[0116] For ease of understanding, the following example is given:

[0117] Each pixel point on each frame image of the flame morphology identified by the Boolean variable is binarized, that is, the pixel point representing the flame morphology is set to 1 (the third identifier), and the pixel point representing the non-flame morphology is set to 0 (the fourth identifier), and then the number of times each pixel point appears as 1 in the multiple-frame image is calculated, and the ratio of the number of occurrences to the number of frames of the multiple-frame image is used as the probability of each pixel point appearing in the flame morphology under the Boolean variable formed after superposition, and finally the pixel point whose probability of appearance is greater than the preset probability threshold is used as the flame morphology under the Boolean variable.

[0118] S218, determining the flame morphology under the Boolean variable for the pixel points whose occurrence probability is greater than the preset probability threshold.

[0119] Optionally, the above step S300 may specifically include:

[0120] S310, determining a flame shape error value based on the characteristic parameters of the flame shape under the maximum inter-class variance method and the characteristic parameters of the flame shape under the Boolean variable;

[0121] The flame morphology characteristic parameters are parameters used to describe the flame morphology characteristics, including but not limited to: flame height, flame width, flame area, flame pulsation frequency and flame inclination. The embodiment of the present invention does not specifically limit this.

[0122] Flame height refers to the vertical distance between the lowest and highest points of the flame shape.

[0123] The flame width refers to the lateral distance between the leftmost and rightmost sides of the flame shape.

[0124] The flame area refers to the size of the flame shape, which can be calculated in the following way: flame area = 5 / 6*flame width squared.

[0125] Flame pulsation frequency refers to the phenomenon of periodic changes in flame length. Flame pulsation frequency is the reciprocal of the number of times the maximum / minimum height of the same flame occurs within one second.

[0126] Flame inclination refers to the angle at which the line connecting the highest point and the lowest point of the flame deviates from the center line.

[0127] In one embodiment, the implementation of step S310 includes the following steps:

[0128] S311, respectively calculating the difference between the flame height, flame width, flame area, flame pulsation frequency and flame inclination under the maximum inter-class variance method and the flame height, flame width, flame area, flame pulsation frequency and flame inclination under the Boolean variable, and obtaining the flame height error value, flame width error value, flame area error value, flame pulsation frequency error value and flame inclination error value;

[0129] Specifically, the flame height error value = |flame height under the maximum inter-class variance method - flame height under the Boolean variable|; the flame width error value = |flame width under the maximum inter-class variance method - flame width under the Boolean variable|; the flame area error value = |flame area under the maximum inter-class variance method - flame area under the Boolean variable|; the flame pulsation frequency error value = |flame pulsation frequency under the maximum inter-class variance method - flame pulsation frequency under the Boolean variable|; the flame inclination error value = |flame inclination under the maximum inter-class variance method - flame inclination under the Boolean variable|.

[0130] S312, using formula (3), calculating the flame height error value, the flame width error value, the flame area error value, the flame pulsation frequency error value and the flame inclination error value to obtain the flame shape error value;

[0131] X=0.2*H+0.2*W+0.1*S+0.1*f+0.4*θ (3);

[0132] Among them, X represents the flame shape error value; H represents the flame height error value; W represents the flame width error value; S represents the flame area error value; f represents the flame pulsation frequency error value; θ represents the flame inclination error value.

[0133] Since flame inclination is the most representative feature of flame morphology, the weight of flame morphology error value is set to be relatively large (0.4). Secondly, flame width and flame height are also the features that can obviously represent flame morphology, so the flame height error value and flame width error value are set to be normal (0.2). Flame area and flame pulsation frequency cannot actually represent the characteristics of flame morphology well, so the weights of flame pulsation frequency error value and flame area error value are set to be minimum (0.1).

[0134] It is understandable that when other characteristic parameters of flame morphology are selected, the parameters and corresponding weight values ​​in formula (3) need to be replaced. For example, if the characteristic parameters of flame morphology are flame width, flame height and flame area, then formula (3) is replaced by: X = 0.4*H + 0.4*W + 0.2*S. Other cases are similar and will not be described here.

[0135] S320, if the flame shape error value is less than the preset error threshold, the flame shape under the Boolean variable is used as the corrected flame shape;

[0136] The preset error threshold is used to characterize the difference between flame morphologies under different image recognition algorithms.

[0137] Specifically, when the flame morphology error value is less than the preset error threshold, it means that the flame morphology under the maximum inter-class variance method and the flame morphology under the Boolean variable are both correctly identified, so the difference between the two is small, and then the flame morphology under the Boolean variable is used as the corrected flame morphology.

[0138] In one embodiment, when the flame morphology error value is greater than a preset error threshold, it means that one of the flame morphology under the maximum inter-class variance method and the flame morphology under the Boolean variable is misidentified, resulting in a large difference between the two. At this time, the image needs to be re-identified until the flame morphology error value is less than the preset error threshold, and the flame morphology under the Boolean variable is used as the corrected flame morphology.

[0139] It is understandable that the size of the preset error threshold determines the correction accuracy of the flame morphology, that is, when the preset error threshold is small, the allowable error range between the flame morphologies under different image recognition algorithms is small, and when the preset error threshold is large, the allowable error range between the flame morphologies under different image recognition algorithms is large. The embodiment of the present invention does not make specific limitations on this and can be set according to actual needs.

[0140] In this embodiment, the flame morphology is corrected by using the characteristic parameters of the flame morphology under the maximum inter-class variance and the characteristic parameters of the flame morphology under the Boolean variable to obtain a corrected flame morphology, thereby avoiding the problem of recognition errors caused by the complex environment in the actual application scenario of the heating furnace, thereby achieving effective recognition of the flame morphology in the heating furnace.

[0141] Optionally, the above step S300 may further include:

[0142] S400, sending the corrected flame appearance to a user terminal display device, so that the user terminal display device displays the corrected flame appearance.

[0143] User terminal displays include but are not limited to: PC, TV, tablet and mobile phone.

[0144] In this embodiment, by sending the corrected flame morphology to the user terminal display device, the user can see the flame morphology in the heating furnace, and can judge the operating status of the heating furnace according to the flame morphology.

[0145] Embodiment 2

[0146] Please refer to Figure 2 , Figure 2 : is a structural schematic diagram of a flame shape recognition system in a heating furnace provided by an embodiment of the present invention. The flame shape recognition system 200 in a heating furnace includes:

[0147] The image acquisition module 210 is used to acquire multiple frames of images during the actual combustion process in the heating furnace; wherein the multiple frames of images are obtained by decompressing the video information of the actual combustion process in the heating furnace;

[0148] The flame recognition module 220 is used to recognize each frame of image by using different image recognition algorithms to obtain the flame morphology of each frame of image under each image recognition algorithm, and determine the flame morphology under each image recognition algorithm based on the flame morphology of each frame of image under each image recognition algorithm;

[0149] The flame correction module 230 is used to correct the flame shape based on the characteristic parameters of the flame shape under each image recognition algorithm to obtain a corrected flame shape.

[0150] It should be understood that the device corresponds to the above-mentioned embodiment of the method for identifying flame morphology in a heating furnace, and can execute the various steps involved in the above-mentioned method embodiment. The specific functions of the device can be found in the description above. To avoid repetition, the detailed description is appropriately omitted here. The device includes at least one software function module that can be stored in a memory in the form of software or firmware or solidified in the operating system (OS) of the device.

[0151] Embodiment 3

[0152] An electronic device comprises: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the machine-readable instructions are executed by the processor to implement the above-mentioned method for identifying flame morphology in a heating furnace.

[0153] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0154] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0155] Embodiment 4

[0156] An embodiment of the present invention also provides a computer-readable storage medium, which stores instructions. When the instructions are executed by a processor, the program is suitable for executing the following method steps: obtaining multiple frames of images during the actual combustion process in the heating furnace; wherein the multiple frames of images are obtained by decompressing the video information of the actual combustion process in the heating furnace; for each frame of image, using different image recognition algorithms to respectively identify the frame of image, and obtain the flame morphology of each frame of image under each image recognition algorithm, and determine the flame morphology under each image recognition algorithm based on the flame morphology of each frame of image under each image recognition algorithm; based on the characteristic parameters of the flame morphology under each image recognition algorithm, the flame morphology is corrected to obtain the corrected flame morphology.

[0157] In one embodiment, the flame morphology recognition method in the heating furnace further includes: extracting the grayscale value and brightness information of each pixel point on each frame of the image; using the maximum inter-class variance method to calculate the grayscale value of each pixel point on each frame of the image to obtain the grayscale threshold of each frame of the image; determining the pixel points on each frame of the image that are greater than the corresponding grayscale threshold as the flame morphology under the maximum inter-class variance method; determining the brightness change of each pixel point on each frame of the image relative to the adjacent pixel points based on the extracted brightness information; activating the pixel points whose brightness change is greater than zero to obtain the flame morphology in each frame of the image under the Boolean variable.

[0158] In one embodiment, the flame morphology recognition method in the heating furnace further includes: using formulas (1) and (2) to calculate the pixel value of each pixel point on each frame image respectively, and obtain the gray value and brightness information of each pixel point on each frame image; wherein the pixel value includes: red channel value, green channel value and blue channel value; Gray = 0.299*R + 0.587*G + 0.114*B (1); Light = 0.2126*R + 0.7152*G + 0.0722*B (2); wherein Gray represents the gray value of each pixel point on each frame image; Light represents the brightness information of each pixel point on each frame image; R represents the red channel value of each pixel point on each frame image; G represents the green channel value of each pixel point on each frame image; B represents the blue channel value of each pixel point on each frame image.

[0159] In one embodiment, the flame morphology recognition method in the heating furnace further includes: superimposing the flame morphology in each frame of the image under the maximum inter-class variance method, and determining the probability of each pixel point appearing in the flame morphology under the maximum inter-class variance method after superposition; determining the flame morphology under the maximum inter-class variance method for pixels whose probability of appearance is greater than a preset probability threshold; superimposing the flame morphology in each frame of the image under a Boolean variable, and determining the probability of each pixel point appearing in the flame morphology under the Boolean variable after superposition; determining the flame morphology under the Boolean variable for pixels whose probability of appearance is greater than a preset probability threshold.

[0160] In one embodiment, the flame morphology recognition method in the heating furnace further includes: if the current pixel point is within the flame morphology under the maximum inter-class variance method formed after superposition, setting the current pixel point to the first identifier; if the current pixel point is not within the flame morphology under the maximum inter-class variance method formed after superposition, setting the current pixel point to the second identifier; calculating the number of times the current pixel point is the first identifier in multiple frames of images, and using the ratio of the number of times to the number of frames of the multiple frames as the probability of the current pixel point appearing in the flame morphology under the maximum inter-class variance method formed after superposition.

[0161] In one embodiment, the flame morphology recognition method in the heating furnace further includes: if the current pixel point is within the flame morphology under the Boolean variable formed after superposition, setting the current pixel point as the third identifier; if the current pixel point is not within the flame morphology under the Boolean variable formed after superposition, setting the current pixel point as the fourth identifier; calculating the number of times the current pixel point is the third identifier in multiple frames of images, and using the ratio of the number of times to the number of frames of the multiple frames as the probability of the current pixel point appearing in the flame morphology under the Boolean variable formed after superposition.

[0162] In one embodiment, the above-mentioned method for identifying flame morphology in a heating furnace also includes: determining a flame morphology error value based on characteristic parameters of the flame morphology under the maximum inter-class variance method and characteristic parameters of the flame morphology under a Boolean variable; if the flame morphology error value is less than a preset error threshold, using the flame morphology under the Boolean variable as a corrected flame morphology.

[0163] In one embodiment, the flame morphology recognition method in the heating furnace further includes: respectively calculating the difference between the flame height, flame width, flame area, flame pulsation frequency and flame inclination under the maximum inter-class variance method and the flame height, flame width, flame area, flame pulsation frequency and flame inclination under the Boolean variable, and obtaining the flame height error value, flame width error value, flame area error value, flame pulsation frequency error value and flame inclination error value; using formula (3), calculating the flame height error value, flame width error value, flame area error value, flame pulsation frequency error value and flame inclination error value, and obtaining the flame morphology error value X=0.2*H+0.2*W+0.1*S+0.1*f+0.4*θ(3); wherein X represents the flame morphology error value; H represents the flame height error value; W represents the flame width error value; S represents the flame area error value; f represents the flame pulsation frequency error value; θ represents the flame inclination error value.

[0164] In one embodiment, the above-mentioned method for identifying flame morphology in a heating furnace further includes: sending the corrected flame morphology to a user terminal display device, so that the user terminal display device displays the corrected flame morphology.

[0165] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0166] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0167] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0168] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0169] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0170] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0171] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0172] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for identifying flame morphology in a heating furnace, characterized in that: include: Acquire multiple frames of images during the actual combustion process in the heating furnace; wherein the multiple frames of images are obtained by decompressing video information during the actual combustion process in the heating furnace; For each frame of image, different image recognition algorithms are used to respectively recognize the frame of image, and the flame morphology of each frame of image under each image recognition algorithm is obtained, and the flame morphology under each image recognition algorithm is determined based on the flame morphology of each frame of image under each image recognition algorithm; Based on the characteristic parameters of the flame morphology under each image recognition algorithm, the flame morphology is corrected to obtain the corrected flame morphology.

2. The method for identifying flame morphology in a heating furnace according to claim 1, characterized in that: The duration of the video information of the actual combustion process in the heating furnace is 1-5s.

3. The method for identifying flame morphology in a heating furnace according to claim 1, characterized in that: For each frame of image, different image recognition algorithms are used to respectively recognize the frame of image, and the flame morphology of each frame of image under each image recognition algorithm is obtained, including: Extract the gray value and brightness information of each pixel on each frame of the image; The maximum inter-class variance method is used to calculate the gray value of each pixel on each frame of the image to obtain the gray threshold of each frame of the image; The pixels on each frame of the image that are greater than the corresponding grayscale threshold are determined as the flame morphology under the maximum inter-class variance method; Determine the brightness change of each pixel on each frame of the image relative to adjacent pixels based on the extracted brightness information; The pixels whose brightness change is greater than zero are activated to obtain the flame morphology in each frame of the image under the Boolean variable.

4. The method for recognizing flame morphology in a heating furnace according to claim 3, characterized in that: The step of extracting the grayscale value and brightness information of each pixel on each frame of the image includes: Using formulas (1) and (2), the pixel value of each pixel point on each frame of the image is calculated to obtain the grayscale value and brightness information of each pixel point on each frame of the image; wherein the pixel value includes: red channel value, green channel value and blue channel value; Gray=0.299*R+0.587*G+0.114*B(1); Light=0.2126*R+0.7152*G+0.0722*B(2); Among them, Gray represents the grayscale value of each pixel in each frame image; Light represents the brightness information of each pixel in each frame image; R represents the red channel value of each pixel in each frame image; G represents the green channel value of each pixel in each frame image; B represents the blue channel value of each pixel in each frame image.

5. The method for recognizing flame morphology in a heating furnace according to claim 3, characterized in that: The method of determining the flame morphology under each image recognition algorithm based on the flame morphology of each frame image under each image recognition algorithm comprises: The flame morphology in each frame of the image under the maximum inter-class variance method is superimposed, and the probability of each pixel point appearing in the flame morphology under the maximum inter-class variance method formed after superposition is determined; The flame morphology under the maximum inter-class variance method is determined by pixel points whose occurrence probability is greater than a preset probability threshold; The flame morphology in each frame image under the Boolean variable is superimposed, and the probability of each pixel point appearing in the flame morphology under the Boolean variable formed after superposition is determined; The pixel points whose occurrence probability is greater than a preset probability threshold are used to determine the flame morphology under the Boolean variable.

6. The method for recognizing flame morphology in a heating furnace according to claim 5, characterized in that: The method of determining the probability of each pixel point appearing in the flame morphology under the maximum inter-class variance method after superposition includes: For each pixel: If the current pixel point is within the flame shape formed by the maximum between-class variance method after superposition, the current pixel point is set as the first mark; If the current pixel point is not within the flame morphology formed by the maximum inter-class variance method after superposition, the current pixel point is set as the second mark; The number of times the current pixel is the first mark in the multi-frame image is calculated, and the ratio of the number of times to the number of frames of the multi-frame image is used as the probability of the current pixel appearing in the flame morphology under the maximum between-class variance method after superposition.

7. The method for recognizing flame morphology in a heating furnace according to claim 5, characterized in that: The method of determining the probability of each pixel point appearing in the flame morphology under the Boolean variable formed after superposition includes: For each pixel: If the current pixel point is within the flame shape under the Boolean variable formed after superposition, the current pixel point is set as the third identifier; If the current pixel point is not within the flame shape under the Boolean variable formed after superposition, the current pixel point is set as the fourth mark; The number of times the current pixel is the first mark in the multi-frame image is calculated, and the ratio of the number of times to the number of frames of the multi-frame image is used as the probability of the current pixel appearing in the flame morphology under the Boolean variable formed after superposition.

8. The method for recognizing flame morphology in a heating furnace according to claim 5, characterized in that: The flame shape correction is performed based on the characteristic parameters of the flame shape under each image recognition algorithm to obtain the corrected flame shape, including: Based on the characteristic parameters of flame morphology under the maximum inter-class variance method and the characteristic parameters of flame morphology under Boolean variables, the flame morphology error value is determined; If the flame shape error value is less than a preset error threshold, the flame shape under the Boolean variable is used as the corrected flame shape.

9. The method for recognizing flame morphology in a heating furnace according to claim 8, characterized in that: The characteristic parameters of the flame morphology include: flame height, flame width, flame area, flame pulsation frequency and flame inclination; The flame shape error value is determined based on the characteristic parameters of the flame shape under the maximum inter-class variance method and the characteristic parameters of the flame shape under the Boolean variable, including: Calculate the differences between the flame height, flame width, flame area, flame pulsation frequency and flame inclination under the maximum inter-class variance method and the flame height, flame width, flame area, flame pulsation frequency and flame inclination under the Boolean variable respectively, and obtain the flame height error value, flame width error value, flame area error value, flame pulsation frequency error value and flame inclination error value; Using formula (3), the flame height error value, flame width error value, flame area error value, flame pulsation frequency error value and flame inclination error value are calculated to obtain the flame shape error value; X=0.2*H+0.2*W+0.1*S+0.1*f+0.4*θ (3); Among them, X represents the flame shape error value; H represents the flame height error value; W represents the flame width error value; S represents the flame area error value; f represents the flame pulsation frequency error value; θ represents the flame inclination error value.

10. The method for recognizing flame morphology in a heating furnace according to claim 1, characterized in that: The method further comprises: The modified flame appearance is sent to a user terminal display device, so that the user terminal display device displays the modified flame appearance.

11. A flame morphology recognition system in a heating furnace, characterized in that: include: An image acquisition module, used to acquire multiple frames of images during the actual combustion process in the heating furnace; wherein the multiple frames of images are obtained by decompressing video information during the actual combustion process in the heating furnace; The flame recognition module is used to recognize each frame of image by using different image recognition algorithms to obtain the flame morphology of each frame of image under each image recognition algorithm, and determine the flame morphology under each image recognition algorithm based on the flame morphology of each frame of image under each image recognition algorithm; The flame correction module is used to correct the flame shape based on the characteristic parameters of the flame shape under each image recognition algorithm to obtain the corrected flame shape.

12. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the machine-readable instructions are executed by the processor, the method for identifying flame morphology in a heating furnace according to any one of claims 1 to 10 is executed.

13. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instructions are executed on a computer, the computer executes the method for recognizing flame morphology in a heating furnace according to any one of claims 1 to 10.

Images