Method, device and equipment for detecting burnout degree of waste incinerator and storage medium

Abstract

The present application relates to the field of garbage disposal, and discloses a method, device and equipment for detecting the burnout degree of a garbage incinerator and a storage medium, which are used to improve the accuracy of burnout degree detection of the garbage incinerator. The method comprises the following steps: obtaining a flame image of a burnout section in the garbage incinerator; inputting the flame image into a preset flame state recognition model to recognize the flame state and obtaining a recognition result; if the recognition result is normal, inputting the flame image into a preset burnout degree detection model to detect the burnout degree and obtaining a target burnout degree; and if the recognition result is abnormal, obtaining the temperature of the burnout section of the garbage incinerator and generating the target burnout degree according to the temperature of the burnout section.

Description

Technical Field

[0001] This invention relates to the field of waste treatment, and in particular to a method, apparatus, equipment and storage medium for detecting the combustibility of a waste incinerator. Background Technology

[0002] In municipal solid waste incineration, the amount of combustible material produced by the final stage of the combustion grate is a crucial indicator of whether the incinerator is operating normally. The degree of combustion is an important parameter reflecting the remaining state of the incinerator ash, i.e., the waste after incineration, and is a key parameter reflecting the incinerator's combustion efficiency.

[0003] Currently, there are two main methods for detecting the degree of combustibility: one is to observe the amount of waste remaining in the combustible section with the naked eye and judge based on human experience. This method requires a lot of manpower, is inefficient, and is easily affected by human experience and observation angle. The other method is to periodically test and calculate the loss on ignition rate to estimate the proportion of unburned material, thereby judging the degree of combustibility. However, this method cannot reflect the state of waste incineration in real time and has a high implementation cost. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and storage medium for detecting the burnout degree of a waste incinerator, which improves the accuracy of burnout degree detection in waste incinerators.

[0005] The first aspect of this invention provides a method for detecting the burnout degree of a waste incinerator. The method includes: acquiring a flame image of the burnout section inside the waste incinerator; inputting the flame image into a preset flame state recognition model to perform flame state recognition and obtain a recognition result; if the recognition result is normal, inputting the flame image into a preset burnout degree detection model to perform burnout degree detection and obtain a target burnout degree; if the recognition result is abnormal, acquiring the burnout section temperature of the waste incinerator and generating a target burnout degree based on the burnout section temperature.

[0006] Optionally, in a first implementation of the first aspect of the present invention, the step of inputting the flame image into a preset smoldering degree detection model to perform smoldering degree detection and obtain a target smoldering degree if the identification result is normal includes: if the identification result is normal, performing clustering segmentation on the flame image using an image clustering algorithm to obtain a smoldering fireline height value; and inputting the smoldering fireline height value and the flame image into a preset smoldering degree detection model to perform smoldering degree detection and obtain a target smoldering degree.

[0007] Optionally, in a second implementation of the first aspect of the present invention, if the recognition result is normal, the flame image is clustered and segmented using an image clustering algorithm to obtain the burnout fireline height value, including: if the recognition result is normal, the flame image is converted into a binary image using an image clustering algorithm; the binary image is filtered and morphologically processed to obtain the burnout fireline height value.

[0008] Optionally, in a third implementation of the first aspect of the present invention, the step of inputting the burnout line height value and the flame image into a preset burnout degree detection model for burnout degree detection to obtain a target burnout degree includes: segmenting the flame image into regions to obtain multiple region images; calculating the burnout degree level of each of the multiple region images based on the burnout line height value to obtain the burnout degree level of each region image; and inputting the burnout degree level of each region image into the preset burnout degree detection model for burnout degree detection to obtain the target burnout degree.

[0009] Optionally, in a fourth implementation of the first aspect of the present invention, if the identification result is abnormal, the temperature of the combustion section of the waste incinerator is obtained, and a target combustion degree is generated based on the temperature of the combustion section, including: if the identification result is abnormal, the temperature of the combustion section of the waste incinerator is obtained; and the target combustion degree corresponding to the waste incinerator is calculated based on the temperature of the combustion section and a preset mapping relationship between the temperature of the combustion section and the combustion degree.

[0010] Optionally, in a fifth implementation of the first aspect of the present invention, the method for detecting the burnout degree of the waste incinerator further includes: acquiring a sample flame image of the burnout section inside the waste incinerator; extracting image features from the sample flame image to obtain feature parameters corresponding to the sample flame image, wherein the feature parameters include: high-temperature area ratio, average image grayscale, and effective average grayscale; and training a preset neural network model based on the sample flame image and the feature parameters to obtain a flame state recognition model.

[0011] Optionally, in a sixth implementation of the first aspect of the present invention, the method for detecting the burnout degree of the waste incinerator further includes: acquiring the flame outline of the flame image; extracting the center line of the flame image based on the flame outline; dividing the flame image into a left image and a right image based on the center line; and calculating the burnout degree levels of the left image and the right image respectively to obtain the left burnout degree level and the right burnout degree level.

[0012] A second aspect of the present invention provides a burnout degree detection device for a waste incinerator. The burnout degree detection device includes: an acquisition module for acquiring a flame image of the burnout section inside the waste incinerator; an identification module for inputting the flame image into a preset flame state identification model to perform flame state identification and obtain an identification result; a detection module for inputting the flame image into a preset burnout degree detection model to perform burnout degree detection if the identification result is normal, and obtaining a target burnout degree; and a generation module for acquiring the burnout section temperature of the waste incinerator and generating a target burnout degree based on the burnout section temperature if the identification result is abnormal.

[0013] Optionally, in the first implementation of the second aspect of the present invention, the detection module further includes: a clustering unit, used to perform clustering and segmentation on the flame image using an image clustering algorithm to obtain the burnout line height value if the identification result is normal; and an output unit, used to input the burnout line height value and the flame image into a preset burnout degree detection model to perform burnout degree detection and obtain the target burnout degree.

[0014] Optionally, in a second implementation of the second aspect of the present invention, the clustering unit is specifically used for: if the identification result is normal, converting the flame image into a binary image using an image clustering algorithm; and performing filtering and morphological processing on the binary image to obtain the burnout fire line height value.

[0015] Optionally, in a third implementation of the second aspect of the present invention, the output unit is specifically used for: performing region segmentation on the flame image to obtain multiple region images; calculating the smoldering degree level of the multiple region images according to the smoldering fire line height value to obtain the smoldering degree level of each region image; and inputting the smoldering degree level of each region image into a preset smoldering degree detection model for smoldering degree detection to obtain the target smoldering degree.

[0016] Optionally, in the fourth implementation of the second aspect of the present invention, the generation module is specifically used to: if the identification result is abnormal, obtain the combustion section temperature of the waste incinerator; and calculate the target combustion degree corresponding to the waste incinerator based on the combustion section temperature and the preset mapping relationship between the combustion section temperature and the combustion degree.

[0017] Optionally, in a fifth implementation of the second aspect of the present invention, the burnout detection device for the waste incinerator further includes: a training module, used to acquire sample flame images of the burnout section inside the waste incinerator; extract image features from the sample flame images to obtain feature parameters corresponding to the sample flame images, wherein the feature parameters include: high-temperature area ratio, average image grayscale, and effective average grayscale; and train a preset neural network model based on the sample flame images and the feature parameters to obtain a flame state recognition model.

[0018] Optionally, in a sixth implementation of the second aspect of the present invention, the burnout detection device for the waste incinerator further includes: a division module, used to acquire the flame outline of the flame image; extract the center line of the flame image based on the flame outline; divide the flame image into a left image and a right image based on the center line; and calculate the burnout level of the left image and the right image respectively to obtain the left burnout level and the right burnout level.

[0019] A third aspect of the present invention provides a burnout detection device for a waste incinerator, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor invokes the instructions in the memory to cause the burnout detection device for the waste incinerator to perform the above-described burnout detection method for the waste incinerator.

[0020] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the above-described method for detecting the combustibility of a waste incinerator.

[0021] The technical solution provided by this invention, which combines digital image processing technology with incinerator environmental monitoring data to determine the degree of combustion in the combustion section of a waste incinerator, can effectively meet the requirements for automatic monitoring of the combustion status in the combustion section. It also exhibits high reliability and stability. When no abnormalities are observed, the degree of combustion can be determined based on image recognition. When the flame image is unclear or even nonexistent due to dust or equipment malfunction, the degree of combustion can be further assessed by combining the incinerator environmental monitoring data. This improves the accuracy of combustion degree detection in waste incinerators. Furthermore, quantitative judgment and analysis of the combustion degree facilitates adjustments to incineration control strategies, regulates incineration operating parameters, and improves the operating efficiency of the waste incinerator. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of an embodiment of the combustibility detection method for a waste incinerator according to the present invention;

[0023] Figure 2This is a schematic diagram of another embodiment of the combustibility detection method for a waste incinerator according to the present invention;

[0024] Figure 3 This is a schematic diagram of one embodiment of the combustibility detection device for a waste incinerator in this invention.

[0025] Figure 4 This is a schematic diagram of another embodiment of the combustibility detection device for a waste incinerator in this invention.

[0026] Figure 5 This is a schematic diagram of one embodiment of the combustibility detection device for a waste incinerator in this invention. Detailed Implementation

[0027] This invention provides a method, apparatus, device, and storage medium for detecting the burnup degree of a waste incinerator, aimed at improving the accuracy of burnup degree detection in waste incinerators. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] For ease of understanding, the specific process of the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 1 One embodiment of the combustibility detection method for waste incinerators in this invention includes:

[0029] 101. Obtain flame images of the combustion zone inside the waste incinerator;

[0030] It is understood that the executing entity of this invention can be a combustibility detection device for a waste incinerator, or it can be a terminal or a server; no specific limitation is made here. This embodiment of the invention will be described using a server as an example.

[0031] Specifically, the server acquires images through a pre-set image acquisition terminal. The server obtains flame images of the combustion section inside the waste incinerator, and then identifies these flame images to facilitate subsequent detection of the degree of combustion.

[0032] 102. Input the flame image into the preset flame state recognition model to perform flame state recognition and obtain the recognition result;

[0033] Specifically, flame images of the combustion zone inside the waste incinerator are acquired and input into an automatic combustion degree discrimination model to obtain the combustion degree level. The automatic combustion degree discrimination model is obtained through the following steps: the flame image is clustered and segmented using an image clustering algorithm to obtain the combustion line height value. Image clustering algorithms include K-means algorithm, fuzzy c-means algorithm, EM algorithm, etc., with fuzzy c-means algorithm being preferred. Flame image recognition using the above automatic discrimination model can improve the accuracy of flame image recognition.

[0034] 103. If the recognition result is normal, the flame image is input into the preset burnout detection model to detect the burnout and obtain the target burnout.

[0035] Specifically, flame images of the combustion zone within the waste incinerator are acquired, and image features are extracted to obtain characteristic parameters such as high-temperature area ratio, average image grayscale, and effective average grayscale. The values ​​of these characteristic parameters differ between normal flame images and those exhibiting phenomena such as dust emission. Based on this difference, flame images are categorized into normal and abnormal types. A neural network model is then trained to obtain a flame state identification model. When a flame image at a given moment is identified as normal, digital image processing methods are used to determine the combustion degree level at that moment.

[0036] 104. If the identification result is abnormal, obtain the combustion section temperature of the waste incinerator and generate the target combustion degree based on the combustion section temperature.

[0037] Specifically, when a flame image at a certain moment is identified as abnormal, a method combining digital image processing and incinerator environmental monitoring data is used to determine the degree of combustion and obtain the furnace negative pressure data of the combustion section of the incinerator at the corresponding moment of the flame image. When the furnace negative pressure changes drastically, it indicates that dust has occurred during that period, which will lead to unclear flame images. In this case, a method combining digital image processing and incinerator environmental monitoring data should be used to determine the degree of combustion, which can reflect the status of waste incineration in real time and has a low implementation cost.

[0038] In this embodiment of the invention, the method for determining the degree of combustion in the combustion section of a waste incinerator by combining digital image processing technology with environmental monitoring data of the incinerator can effectively meet the requirements of automatic monitoring of the combustion status of the combustion section, and has high reliability and stability. When there are no abnormalities, the degree of combustion can be determined by image recognition. When the flame image is unclear or even nonexistent due to dust or equipment failure, the degree of combustion can be further determined by combining environmental monitoring data of the incinerator, which improves the accuracy of combustion degree detection in the waste incinerator. Furthermore, quantitative judgment and analysis of the degree of combustion is beneficial for adjusting the incineration control strategy, regulating the incineration operating parameters, and improving the operating efficiency of the waste incinerator.

[0039] Please see Figure 2 Another embodiment of the combustibility detection method for waste incinerators in this invention includes:

[0040] 201. Obtain flame images of the combustion zone inside the waste incinerator;

[0041] Specifically, in this embodiment, the specific implementation of step 201 is similar to that of step 101 described above, and will not be repeated here.

[0042] 202. Input the flame image into the preset flame state recognition model to perform flame state recognition and obtain the recognition result;

[0043] Optionally, a sample flame image of the combustion section inside the waste incinerator is acquired; image features are extracted from the sample flame image to obtain the corresponding feature parameters, including: high-temperature area ratio, average image gray level, and effective average gray level; a pre-set neural network model is trained based on the sample flame image and the feature parameters to obtain a flame state recognition model.

[0044] The server acquires the furnace negative pressure data of the burnout section of the incinerator at the corresponding flame image moment. When the furnace negative pressure changes drastically, it indicates dust emission during that period, leading to unclear flame images. In this case, a combination of digital image processing and incinerator environmental monitoring data should be used to determine the degree of combustion. Optionally, the server can also acquire the grate sliding speed data of the burnout section of the incinerator at the corresponding flame image moment. When the grate in the burnout section slides forward, slag is pushed out of the grate, generating a large amount of dust, which can also cause unclear flame images. In this case, a combination of digital image processing and incinerator environmental monitoring data should be used to determine the degree of combustion, improving the robustness of flame image recognition.

[0045] 203. If the recognition result is normal, the flame image is clustered and segmented using an image clustering algorithm to obtain the height value of the burnt-out fire line;

[0046] Specifically, if the recognition result is normal, the flame image is converted into a binary image using an image clustering algorithm; the binary image is then filtered and morphologically processed to obtain the height value of the burnt-out fire line.

[0047] The process involves converting the original R, G, and B three-channel color image into a single-channel grayscale image. First, the grayscale values ​​of the R, G, and B channels are calculated. Then, a gamma correction algorithm is used to correct the RGB values, resulting in the grayscale image. The calculation formula is as follows:

[0048]

[0049] The grayscale image is converted into a binary image, and then filtered and morphologically processed. Filtering algorithms include median filtering, Gaussian filtering, and mean filtering. Morphological processing includes dilation, erosion, opening, and closing operations. Image clustering algorithms are used to obtain the flame outline, thus yielding the burnt-out fire lines. The binary matrix of each burnt-out fire line is denoted as F(y). i ), where y i This refers to the fire line height value corresponding to each pixel. The flame outline is obtained through filtering and image clustering algorithms, which facilitates the clarity and accuracy of subsequent flame recognition.

[0050] 204. Input the burnout line height value and flame image into the preset burnout detection model to detect the burnout and obtain the target burnout.

[0051] Specifically, the flame image is segmented into multiple regions; the burn intensity level of each region image is calculated based on the burnout line height value; the burn intensity level of each region image is then input into a preset burn intensity detection model for burn intensity detection to obtain the target burn intensity.

[0052] This involves partitioning the image horizontally into n regions, denoted as Q. j And there are Where a j b j For the corresponding region Q j The upper and lower limits of the interval, j = 1, 2, 3…n. Each region Q j There are n burnout levels corresponding to different burnout levels, denoted as L for each burnout level. j The flame image is input into the automatic burnout determination model. If the binary matrix of the burnout fire line contains the most... The burn level corresponding to this burn line is L. j ,make C l Let C be a 1×j matrix, where l is the l-th input image. Calculate C.l The coordinates corresponding to the maximum value in the middle are denoted as level. l then level l This represents the burn level corresponding to the l-th input image.

[0053] Optionally, obtain the flame outline of the flame image; extract the center line of the flame image based on the flame outline; divide the flame image into a left image and a right image based on the center line; calculate the burn-out level of the left image and the right image respectively to obtain the burn-out level of the left image and the burn-out level of the right image.

[0054] It should be noted that, in practice, incomplete combustion may occur on the left and right sides of the furnace. Therefore, the image can be divided into left and right sides based on the center line of the flame outline, and the burnout level can be calculated separately. When the flame image is unclear or even nonexistent due to dust or equipment malfunction, it is necessary to use incinerator environmental monitoring data for auxiliary judgment of burnout level. This incinerator environmental monitoring data includes: furnace negative pressure in the burnout section, running speed of the sliding grate in the burnout section, temperature on the left and right sides above the grate in the burnout section, and the action signal of the slag discharger. The server then extracts the center line of the flame image based on the flame outline; the flame image is divided into left and right images based on the center line; and the burnout level of the left and right images is calculated separately to obtain the left burnout level and right burnout level. By combining incinerator environmental monitoring data for auxiliary judgment of burnout level, the accuracy of burnout level detection in waste incinerators can be improved.

[0055] 205. If the identification result is abnormal, obtain the combustion section temperature of the waste incinerator and generate the target combustion degree based on the combustion section temperature.

[0056] Specifically, if the identification result is abnormal, the temperature of the combustion section of the waste incinerator is obtained; based on the temperature of the combustion section and the preset mapping relationship between the temperature of the combustion section and the degree of combustion, the target degree of combustion of the waste incinerator is calculated.

[0057] If the identification result is abnormal, the temperature of the combustion zone of the waste incinerator is obtained. Based on the combustion zone temperature and the preset mapping relationship between combustion zone temperature and combustion degree, the target combustion degree corresponding to the waste incinerator is calculated. Specifically, the incinerator environmental monitoring data at the corresponding flame image moment is obtained. The combustion degree level at the corresponding flame image moment is then determined. For the obtained combustion degree level... l Find the level l The functional relationship between the temperature on the left and right sides above the grate in the combustion section at the corresponding moment forms a one-to-one mapping relationship. When the combustion level cannot be determined from the image, the combustion level at that moment can be deduced from this mapping relationship.

[0058] In this embodiment of the invention, the method for determining the degree of combustion in the combustion section of a waste incinerator by combining digital image processing technology with environmental monitoring data of the incinerator can effectively meet the requirements of automatic monitoring of the combustion status of the combustion section, and has high reliability and stability. When there are no abnormalities, the degree of combustion can be determined by image recognition. When the flame image is unclear or even nonexistent due to dust or equipment failure, the degree of combustion can be further determined by combining environmental monitoring data of the incinerator, which improves the accuracy of combustion degree detection in the waste incinerator. Furthermore, quantitative judgment and analysis of the degree of combustion is beneficial for adjusting the incineration control strategy, regulating the incineration operating parameters, and improving the operating efficiency of the waste incinerator.

[0059] The above describes the burnout detection method for a waste incinerator in an embodiment of the present invention. The following describes the burnout detection device for a waste incinerator in an embodiment of the present invention. Please refer to [link to relevant documentation]. Figure 3 One embodiment of the combustibility detection device for a waste incinerator in this invention includes:

[0060] The acquisition module 301 is used to acquire flame images of the combustion section inside the waste incinerator;

[0061] The recognition module 302 is used to input the flame image into a preset flame state recognition model to perform flame state recognition and obtain the recognition result;

[0062] The detection module 303 is used to input the flame image into a preset burnout detection model to detect burnout if the recognition result is normal, so as to obtain the target burnout.

[0063] The generation module 304 is used to obtain the combustion section temperature of the waste incinerator if the identification result is abnormal, and generate a target combustion degree based on the combustion section temperature.

[0064] In this embodiment of the invention, the method for determining the degree of combustion in the combustion section of a waste incinerator by combining digital image processing technology with environmental monitoring data of the incinerator can effectively meet the requirements of automatic monitoring of the combustion status of the combustion section, and has high reliability and stability. When there are no abnormalities, the degree of combustion can be determined by image recognition. When the flame image is unclear or even nonexistent due to dust or equipment failure, the degree of combustion can be further determined by combining environmental monitoring data of the incinerator, which improves the accuracy of combustion degree detection in the waste incinerator. Furthermore, quantitative judgment and analysis of the degree of combustion is beneficial for adjusting the incineration control strategy, regulating the incineration operating parameters, and improving the operating efficiency of the waste incinerator.

[0065] Please see Figure 4 Another embodiment of the combustibility detection device for a waste incinerator in this invention includes:

[0066] The acquisition module 301 is used to acquire flame images of the combustion section inside the waste incinerator;

[0067] The recognition module 302 is used to input the flame image into a preset flame state recognition model to perform flame state recognition and obtain the recognition result;

[0068] The detection module 303 is used to input the flame image into a preset burnout detection model to detect burnout if the recognition result is normal, so as to obtain the target burnout.

[0069] The generation module 304 is used to obtain the combustion section temperature of the waste incinerator if the identification result is abnormal, and generate a target combustion degree based on the combustion section temperature.

[0070] Optionally, the detection module 303 further includes:

[0071] A clustering unit is used to perform clustering and segmentation on the flame image using an image clustering algorithm if the identification result is normal, to obtain the burnout fire line height value.

[0072] The output unit is used to input the burnout line height value and the flame image into a preset burnout detection model to perform burnout detection and obtain the target burnout level.

[0073] Optionally, the clustering unit is specifically used to: if the recognition result is normal, convert the flame image into a binary image using an image clustering algorithm; and perform filtering and morphological processing on the binary image to obtain the burnout fire line height value.

[0074] Optionally, the output unit is specifically used for: performing region segmentation on the flame image to obtain multiple region images; calculating the smoldering degree level of the multiple region images according to the smoldering fire line height value to obtain the smoldering degree level of each region image; inputting the smoldering degree level of each region image into a preset smoldering degree detection model for smoldering degree detection to obtain the target smoldering degree.

[0075] Optionally, the generation module 304 is specifically used to: if the identification result is abnormal, obtain the combustion section temperature of the waste incinerator; and calculate the target combustion degree corresponding to the waste incinerator based on the combustion section temperature and the preset mapping relationship between the combustion section temperature and the combustion degree.

[0076] Optionally, the combustibility detection device for the waste incinerator further includes:

[0077] Training module 305 is used to acquire sample flame images of the combustion section inside the waste incinerator; extract image features from the sample flame images to obtain feature parameters corresponding to the sample flame images, wherein the feature parameters include: high temperature area ratio, average image gray level, and effective average gray level; and train a preset neural network model based on the sample flame images and the feature parameters to obtain a flame state recognition model.

[0078] Optionally, the combustibility detection device for the waste incinerator further includes:

[0079] The segmentation module 306 is used to obtain the flame outline of the flame image; extract the center line of the flame image based on the flame outline; divide the flame image into a left image and a right image based on the center line; and calculate the burn-out level of the left image and the right image respectively to obtain the left burn-out level and the right burn-out level.

[0080] In this embodiment of the invention, the method for determining the degree of combustion in the combustion section of a waste incinerator by combining digital image processing technology with environmental monitoring data of the incinerator can effectively meet the requirements of automatic monitoring of the combustion status of the combustion section, and has high reliability and stability. When there are no abnormalities, the degree of combustion can be determined by image recognition. When the flame image is unclear or even nonexistent due to dust or equipment failure, the degree of combustion can be further determined by combining environmental monitoring data of the incinerator, which improves the accuracy of combustion degree detection in the waste incinerator. Furthermore, quantitative judgment and analysis of the degree of combustion is beneficial for adjusting the incineration control strategy, regulating the incineration operating parameters, and improving the operating efficiency of the waste incinerator.

[0081] above Figure 3 and Figure 4 The burnup detection device for the waste incinerator in this embodiment of the invention is described in detail from the perspective of modular functional entities. The burnup detection device for the waste incinerator in this embodiment of the invention is described in detail from the perspective of hardware processing.

[0082] Figure 5This is a schematic diagram of the structure of a combustibility detection device for a waste incinerator according to an embodiment of the present invention. The combustibility detection device 500 can vary significantly due to different configurations or performance characteristics. It may include one or more central processing units (CPUs) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) storing application programs 533 or data 532. The memory 520 and storage media 530 can be temporary or persistent storage. The program stored in the storage media 530 may include one or more modules (not shown in the diagram), each module including a series of instruction operations on the combustibility detection device 500. Furthermore, the processor 510 may be configured to communicate with the storage media 530 and execute the series of instruction operations in the storage media 530 on the combustibility detection device 500.

[0083] The combustibility detection device 500 for a waste incinerator may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input / output interfaces 560, and / or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will understand that... Figure 5 The structure of the burnout detection device for the waste incinerator shown does not constitute a limitation on the burnout detection device for the waste incinerator. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0084] The present invention also provides a burnout detection device for a waste incinerator. The burnout detection device includes a memory and a processor. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor performs the steps of the burnout detection method for the waste incinerator described in the above embodiments.

[0085] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when the instructions are executed on a computer, cause the computer to perform the steps of the combustibility detection method for the waste incinerator.

[0086] Furthermore, the computer-readable storage medium may primarily include a stored program area and a stored data area, wherein the stored program area may store the operating system, an application program required for at least one function, etc.; and the stored data area may store data created based on the use of blockchain nodes, etc.

[0087] The blockchain referred to in this invention is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0088] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0089] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0090] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting the combustibility of a waste incinerator, characterized in that, The method for detecting the combustibility of the waste incinerator includes: Acquire flame images of the combustion zone inside the waste incinerator; The flame image is input into a preset flame state recognition model to perform flame state recognition and obtain the recognition result; If the identification result is normal, the flame image is input into a preset burnout detection model for burnout detection to obtain the target burnout level. Specifically, this includes: if the identification result is normal, converting the flame image into a binary image using an image clustering algorithm; filtering and morphological processing of the binary image to obtain the burnout fireline height value; segmenting the flame image into multiple region images; calculating the burnout level of each of the multiple region images based on the burnout fireline height value to obtain the burnout level of each region image; and inputting the burnout level of each region image into a preset burnout detection model for burnout detection to obtain the target burnout level. If the identification result is abnormal, the temperature of the combustion section of the waste incinerator is obtained, and a target combustion degree is generated based on the temperature of the combustion section. The method for detecting the burnout degree of the waste incinerator further includes: acquiring the flame outline of the flame image; extracting the center line of the flame image based on the flame outline; dividing the flame image into a left image and a right image based on the center line; and calculating the burnout degree level of the left image and the right image respectively to obtain the left burnout degree level and the right burnout degree level.

2. The method for detecting the combustibility of a waste incinerator according to claim 1, characterized in that, If the identification result is abnormal, the temperature of the combustion zone of the waste incinerator is obtained, and a target combustion degree is generated based on the temperature of the combustion zone, including: If the identification result is abnormal, the temperature of the combustion section of the waste incinerator is obtained; The target burnout degree corresponding to the waste incinerator is calculated based on the burnout section temperature and the preset mapping relationship between burnout section temperature and burnout degree.

3. The method for detecting the combustibility of a waste incinerator according to claim 1, characterized in that, The method for detecting the combustibility of the waste incinerator also includes: Obtain sample flame images of the combustion zone inside the waste incinerator; Image features are extracted from the sample flame image to obtain the feature parameters corresponding to the sample flame image, wherein the feature parameters include: high temperature area ratio, average image gray level, and effective average gray level. A flame state recognition model is obtained by training a preset neural network model based on the sample flame images and the feature parameters.

4. A burnout detection device for a waste incinerator, characterized in that, For performing the burnout detection method for a waste incinerator as described in any one of claims 1-3, the burnout detection device for the waste incinerator comprises: The acquisition module is used to acquire flame images of the combustion zone inside the waste incinerator; The recognition module is used to input the flame image into a preset flame state recognition model to perform flame state recognition and obtain the recognition result; The detection module is used to input the flame image into a preset burnout detection model to detect burnout if the recognition result is normal, and obtain the target burnout. The generation module is used to obtain the combustion section temperature of the waste incinerator if the identification result is abnormal, and generate a target combustion degree based on the combustion section temperature.

5. A device for detecting the combustibility of a waste incinerator, characterized in that, The combustibility detection device for the waste incinerator includes: a memory and at least one processor, wherein the memory stores instructions; The at least one processor invokes the instructions in the memory to cause the burnout detection device of the waste incinerator to perform the burnout detection method of the waste incinerator as described in any one of claims 1-3.

6. A computer-readable storage medium storing instructions thereon, characterized in that, When the instruction is executed by the processor, it implements the combustibility detection method for a waste incinerator as described in any one of claims 1-3.

Images