Modeling method and system for waste incineration heat evaluation model

Abstract

The invention provides a modeling method and system for a waste incineration heat evaluation model. The method comprises the steps that an original image is preprocessed to obtain a primary image; material combustion characteristic information and material combustion information of the to-be-incinerated waste are obtained according to the primary image; correcting and segmenting the thermal image to obtain a plurality of segmented image groups, and acquiring corresponding heat feature information according to the segmented image groups; calculating a material heat evaluation value and an image heat evaluation value of the to-be-incinerated garbage; comprehensively calculating a comprehensive heat evaluation value of the to-be-incinerated garbage according to the material heat evaluation value and the image heat evaluation value; and establishing a training set for the original images, the thermal images and the comprehensive heat evaluation values of the to-be-incinerated garbage, and inputting the training set into a convolutional neural network model for training to obtain a target heat evaluation model. The waste incineration heat can be effectively estimated, the waste incineration efficiency can be improved in cooperation with work of other devices in the waste incineration pool, and economic benefits are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of waste incineration, and in particular relates to a modeling method and system for a waste incineration heat assessment model. Background Art

[0002] Waste incineration technology plays a significant role in reducing, harmlessly treating, and repurposing waste. However, due to the complex composition and uneven calorific value of my country's waste, and the inability to estimate the calorific value of incoming waste in advance, the adjustment of the waste feed rate has a certain lag, which can easily affect the incinerator's combustion efficiency and stable operation, and increase pollutant emissions. Therefore, real-time measurement of the calorific value and temperature of incoming waste into the incinerator's waste pool is necessary to address these issues and achieve clean and efficient waste energy utilization. Before materials enter the incinerator at a waste-to-energy plant, operators must monitor the monitoring screens in real time. Operators estimate the calorific value of the waste based on experience and adjust the feed rate and air volume to achieve stable combustion within the incinerator. This requires constant, focused attention from operators. Furthermore, manual monitoring methods cannot accurately estimate the calorific value of the waste, and control adjustments are subject to lags, which can easily lead to large fluctuations in combustion within the incinerator. Currently, methods for calculating the calorific value of garbage, both domestically and internationally, include instrumental testing (oxygen bomb calorimetry), formula estimation methods (such as Dulong and Scheuerer-Kestner), the use of grey correlation to predict the impact of the calorific value of domestic garbage, and the development of garbage calorific value prediction models using BP (backpropagation) neural networks. However, these methods suffer from large errors, complex and difficult-to-apply calculation models, and numerous restrictions, making them incapable of real-time measurement of garbage calorific value. Current research lacks an effective technical approach for real-time quantitative measurement and calculation of garbage calorific value. In summary, there is currently no method that can directly display the combustion heat of garbage entering the furnace in real time. Most operators can only roughly estimate the calorific value of garbage based on their experience in garbage pool accumulation, which has large errors and low efficiency. Summary of the Invention

[0003] In view of the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a modeling method and system for a waste incineration heat assessment model to solve the problem of relying on manual judgment of the combustion heat of waste entering the waste pool in the prior art.

[0004] To achieve the above and other related purposes, the present invention provides a method for modeling a waste incineration heat assessment model, comprising the following steps: Collecting original images of the garbage to be incinerated, and preprocessing the original images to obtain primary images; Acquiring material combustion characteristic information and material combustion information of the garbage to be incinerated based on the primary image; Collecting a thermal image of the garbage to be incinerated, performing correction processing on the thermal image and segmenting the image to obtain a plurality of segmented image groups, and obtaining corresponding thermal characteristic information according to the segmented image groups; Calculating a material heat evaluation value of the garbage to be incinerated based on the material combustion characteristic information and the material combustion information, and calculating an image heat evaluation value of the garbage to be incinerated based on the heat characteristic information; Calculating a comprehensive heat evaluation value of the garbage to be incinerated based on the material heat evaluation value and the image heat evaluation value; A training set is established by using the original images, thermal images and comprehensive heat evaluation values ​​of the multiple garbage to be incinerated and inputting them into a convolutional neural network model for training to obtain a target heat evaluation model.

[0005] In one embodiment of the present invention, the step of obtaining the material combustion characteristic information and material combustion information of the waste to be incinerated based on the primary image includes: Using a first residual network to perform recognition processing on the primary image to obtain material parameters in the primary image, and obtaining corresponding material combustion information from a material database according to the material parameters; Using a second residual network in combination with a dilated convolution to perform recognition processing on the primary image to obtain pore structure features corresponding to the primary image; collecting air parameters of the combustion area, and calculating the combustion and diffusion characteristics of the garbage to be incinerated based on the air parameters and the pore structure characteristics; The material combustion characteristic information is obtained after standardization processing is performed on the pore structure characteristics and the combustion diffusion characteristics.

[0006] In one embodiment of the present invention, the use of the second residual network in combination with the dilated convolution to perform recognition processing on the primary image to obtain the pore structure features corresponding to the primary image includes: Based on the preset dilation rate of the dilated convolution, the second residual network is used to accurately identify the primary image to extract original pores in the primary image whose pore gaps are greater than a first preset value; Processing the original pores according to the Sobel operator and graph theory algorithm to obtain a pore topology structure corresponding to the original pores; The pore topology corresponding to each original pore is converted into a combustion propagation path prediction map, and the combustion propagation path corresponding to the original pore is determined according to the combustion propagation path prediction map.

[0007] In one embodiment of the present invention, collecting air parameters of the combustion area and calculating the combustion diffusion characteristics of the garbage to be incinerated based on the air parameters and the pore structure characteristics include: Determining a first ratio of combustion-supporting gas and a second ratio of flame-retardant gas in the air according to the collected air parameters, and calculating a combustion coefficient of the current environment according to the first ratio and the second ratio; Acquiring the air flow rate from the air parameters, and establishing a diffusion model of the original pores and oxygen diffusion rate according to the air flow rate and the original pores; The combustion diffusion characteristics corresponding to each of the original pores are determined according to the combustion coefficient and the diffusion model.

[0008] In one embodiment of the present invention, the step of obtaining the material combustion characteristic information after normalizing the pore structure characteristics and the combustion diffusion characteristics includes: Obtaining the original pores corresponding to the combustion propagation path, and obtaining the material combustion information corresponding to the original pores; respectively calculating a first average value of the combustion propagation path and a second average value of the combustion diffusion characteristic; calculating a first standard deviation based on the first average value and each of the combustion propagation paths, and calculating a second standard deviation based on the second average value and each of the combustion propagation characteristics; Calculating a first standard value for each of the combustion propagation paths based on the first average value and the first standard deviation, and calculating a second standard value corresponding to each of the combustion propagation characteristics based on the second average value and the second standard deviation; After establishing a mapping relationship between the first standard value, the second standard value and the original pore size, complete combustion characteristic information of the material is obtained.

[0009] In one embodiment of the present invention, the step of collecting a thermal image of the garbage to be incinerated, correcting and segmenting the thermal image to obtain a plurality of segmented image groups, and obtaining corresponding thermal characteristic information based on the segmented image groups includes: Thermal imaging cameras are respectively set up in multiple directions of the area where the garbage to be incinerated is located and corresponding local thermal imaging images are respectively obtained; Acquire overlapping areas of adjacent local thermal images respectively according to a preset direction, and acquire a first overlapping image and a second overlapping image of two adjacent local thermal images in the overlapping area respectively; After calculating the average value of the first overlapping imaging image and the second overlapping imaging image to obtain a standard overlapping imaging image, the first overlapping imaging image and the second overlapping imaging image in adjacent local thermal imaging images are replaced by the standard overlapping imaging image to obtain a plurality of corrected imaging images; Combining the plurality of corrected images to obtain a complete thermal image, and removing redundant information from the complete thermal image; performing a cutting process on the complete thermal imaging image after removing the redundant information according to a division rule to obtain a plurality of cutting areas; Performing color recognition on each of the cutting areas, and marking areas of different colors to obtain different marking information, each of the marking information corresponding to a different combustion heat; The darker the color of the cutting area, the higher the combustion heat corresponding to the marking information.

[0010] In one embodiment of the present invention, the step of calculating the material heat evaluation value of the waste to be incinerated based on the material combustion characteristic information and the material combustion information, and calculating the image heat evaluation value of the waste to be incinerated based on the heat characteristic information, includes: Acquire a unit calorific value corresponding to each area on each of the primary images according to the material combustion information; Calculating a material calorific value of the waste to be incinerated based on the distribution ratio and density of the waste to be incinerated in the current area and the unit calorific value and the material combustion characteristic information; Determine the combustion heat corresponding to the different color areas in each of the cutting areas according to the marking information, and calculate the local mass of the garbage to be incinerated corresponding to the different color areas in each of the cutting areas according to the proportion; The local heat corresponding to each cutting area is calculated according to the combustion heat and local mass corresponding to the different color areas in the cutting area, and the local heat of the cutting area is summarized and calculated to obtain the image heat evaluation value of the garbage to be incinerated.

[0011] In one embodiment of the present invention, the comprehensive heat evaluation value of the garbage to be incinerated is calculated based on the material heat evaluation value and the image heat evaluation value, including: Retrieving combustion data of previous garbage incinerations, the combustion data including material data and image data; Calculate a first weight and a second weight according to the material data and the image data respectively; The material heat evaluation value and the image heat evaluation value are comprehensively calculated according to the first weight and the second weight to obtain the comprehensive heat evaluation value.

[0012] In one embodiment of the present invention, the method further includes: After the target calorific value evaluation model is obtained, historical combustion data is input to verify the target calorific value evaluation model, and the verification is stopped after the output result of the target calorific value evaluation model meets the requirements.

[0013] The present invention also provides a modeling system for a waste incineration heat assessment model, comprising: A first acquisition module is used to acquire an original image of the garbage to be incinerated and pre-process the original image to obtain a primary image; a first calculation module, configured to obtain material combustion characteristic information and material combustion information of the waste to be incinerated based on the primary image; a second acquisition module, configured to acquire a thermal image of the waste to be incinerated, perform correction processing on the thermal image, and segment the image to obtain a plurality of segmented image groups, and obtain corresponding thermal characteristic information based on the segmented image groups; a second calculation module, configured to calculate a material heat evaluation value of the garbage to be incinerated based on the material combustion characteristic information and the material combustion information, and to calculate an image heat evaluation value of the garbage to be incinerated based on the heat characteristic information; An evaluation module, configured to calculate a comprehensive heat evaluation value of the garbage to be incinerated based on the material heat evaluation value and the image heat evaluation value; The modeling module is used to establish a training set by inputting the original images, thermal images and comprehensive heat evaluation values ​​of the plurality of the waste to be incinerated into a convolutional neural network model for training to obtain a target heat evaluation model.

[0014] As described above, the modeling method and system of the waste incineration heat assessment model of the present invention have the following beneficial effects: Compared with the prior art, the present invention collects the original image and thermal imaging image of the garbage entering the furnace, and obtains the material combustion characteristic information and material combustion information of the garbage to be incinerated, as well as the heat characteristic information of the garbage to be incinerated, and subsequently calculates the material heat evaluation value according to the material combustion characteristic information and the material combustion information, calculates the image heat evaluation value of the garbage to be incinerated according to the heat characteristic information, and obtains the total heat evaluation value of the garbage to be incinerated according to the material heat evaluation value and the image heat evaluation value, and then establishes a training set for each original image of the garbage to be incinerated, the thermal imaging image and the comprehensive heat evaluation value and inputs them into the convolutional neural network model for training to obtain the target heat evaluation model, so that when the garbage entering the furnace is incinerated, the target heat evaluation model is used to quickly evaluate the combustion heat, which is convenient for conditioning the working environment in the garbage incineration pool, ensuring full utilization of the combustion heat while reducing material loss and improving the economic benefits of garbage incineration. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Shown is a flow chart of the modeling method of the waste incineration heat assessment model of the present invention.

[0016] Figure 2 Shown is a structural block diagram of the modeling method of the waste incineration heat evaluation model of the present invention. DETAILED DESCRIPTION

[0017] The following describes the embodiments of the present invention through specific embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other unless they conflict.

[0018] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. The illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0019] The modeling method and system of the waste incineration heat assessment model of the present invention collect the original image and thermal imaging image of the waste entering the furnace, and respectively obtain the material combustion characteristic information and material combustion information of the waste to be incinerated, as well as the heat characteristic information of the waste to be incinerated, and subsequently calculate the material heat assessment value according to the material combustion characteristic information and the material combustion information, calculate the image heat assessment value of the waste to be incinerated according to the heat characteristic information, and obtain the total heat assessment value of the waste to be incinerated according to the material heat assessment value and the image heat assessment value, so as to subsequently establish a training set for each original image of the waste to be incinerated, the thermal imaging image and the comprehensive heat assessment value and input them into the convolutional neural network model for training to obtain the target heat assessment model, so that when the waste entering the furnace is subsequently incinerated, the target heat assessment model is used to quickly assess the combustion heat, which is convenient for conditioning the working environment in the waste incineration pool, ensuring full utilization of the combustion heat while reducing material loss and improving the economic benefits of waste incineration.

[0020] The storage medium of the present invention stores a computer program that, when executed by a processor, implements the following method. The storage medium includes various media capable of storing program code, such as read-only memory (ROM), random access memory (RAM), a magnetic disk, a USB flash drive, a memory card, or an optical disk.

[0021] Any combination of one or more storage media may be used. The storage medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, RAM, ROM, an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in connection with an instruction execution system, apparatus, or device.

[0022] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0023] Program code embodied on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0024] Computer program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and the like, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0025] The present invention will be described below with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It should be understood that each block of the flowcharts and / or block diagrams, as well as combinations of blocks in the flowcharts and / or block diagrams, 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, or other programmable data processing device to produce a machine such that, when executed by the processor of the computer or other programmable data processing device, these computer program instructions generate a device that implements the functions / actions specified in one or more blocks in the flowcharts and / or block diagrams.

[0026] These computer program instructions may also be stored in a computer-readable medium, which causes a computer, other programmable data processing apparatus, or other device to operate in a specific manner, so that the instructions stored in the computer-readable medium produce an article of manufacture that includes instructions for implementing the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0027] Computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, such that the instructions executed on the computer or other programmable apparatus provide a process for implementing the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0028] The terminal of the present invention includes a processor and a memory.

[0029] The memory is used to store computer programs; preferably, the memory includes: ROM, RAM, magnetic disk, USB flash drive, memory card or optical disk and other media that can store program codes.

[0030] The processor is connected to the memory and is used to execute the computer program stored in the memory, so that the terminal executes the following modeling method of the waste incineration heat evaluation model.

[0031] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0032] like Figure 1 As shown, in one embodiment, the present invention provides a modeling method for a waste incineration heat assessment model, comprising the following steps: S101 , collecting original images of garbage to be incinerated, and preprocessing the original images to obtain primary images.

[0033] In this embodiment, for the garbage raw materials that need to be incinerated, the original image is directly obtained, and the original image is subjected to denoising processing to obtain a cleaned primary image, which facilitates subsequent calculations on the primary image.

[0034] S102: Obtain material combustion characteristic information and material combustion information of the garbage to be incinerated according to the primary image.

[0035] In some embodiments, obtaining the material combustion characteristic information and material combustion information of the waste to be incinerated based on the primary image includes: Using a first residual network to perform recognition processing on the primary image to obtain material parameters in the primary image, and obtaining corresponding material combustion information from a material database according to the material parameters; Using a second residual network in combination with a dilated convolution to perform recognition processing on the primary image to obtain pore structure features corresponding to the primary image; collecting air parameters of the combustion area, and calculating the combustion and diffusion characteristics of the garbage to be incinerated based on the air parameters and the pore structure characteristics; The material combustion characteristic information is obtained after standardization processing is performed on the pore structure characteristics and the combustion diffusion characteristics.

[0036] In this embodiment, after obtaining a primary image of the waste to be incinerated, a first residual network is first used to perform image recognition on the primary image to obtain the material parameters corresponding to the waste to be incinerated in the primary image. Based on these material parameters, corresponding material combustion information, namely the unit combustion heat corresponding to each material, is then retrieved from the material database. A second residual network then uses a set of atrous convolutions to identify and process the primary image, thereby obtaining the pore structure characteristics present in the primary image. Simultaneously, air parameters within the combustion area, specifically those within the waste incineration tank, are collected. Based on these air parameters and pore structure characteristics, the combustion diffusion characteristics corresponding to different pores in the waste to be incinerated are calculated. This facilitates subsequent standardization based on the pore structure characteristics and combustion diffusion characteristics to obtain material combustion characteristic information.

[0037] Among them, the first residual network and the second residual network are both residual networks in the prior art, such as the residual network ResNet-101. The two can be the same or different. This solution does not specifically limit this and will not be repeated here.

[0038] In some further embodiments, the use of a second residual network in combination with a dilated convolution to perform recognition processing on the primary image to obtain pore structure features corresponding to the primary image includes: Based on the preset dilation rate of the dilated convolution, the second residual network is used to accurately identify the primary image to extract original pores in the primary image whose pore gaps are greater than a first preset value; Processing the original pores according to the Sobel operator and graph theory algorithm to obtain a pore topology structure corresponding to the original pores; The pore topology corresponding to each original pore is converted into a combustion propagation path prediction map, and the combustion propagation path corresponding to the original pore is determined according to the combustion propagation path prediction map.

[0039] In this embodiment, to capture the pore structure characteristics of the primary image, a second residual network is first used to accurately identify the primary image based on a preset void ratio using dilated convolution. Original pores greater than a first preset value are extracted. Because the distribution of original pores in the primary image is relatively random, to further improve accuracy, the original pores are processed using the Sobel operator and graph theory algorithms, namely, a fracture network analysis method, to obtain the pore topology corresponding to each original pore. After obtaining the pore topology corresponding to each original pore, the pore topology is converted into a combustion propagation path prediction map. Based on this combustion propagation path prediction map, the combustion propagation path in the region where the original pore is located can be determined.

[0040] It should be noted that the pore topology corresponding to each original pore is obtained by using a fracture network analysis method summarized in the prior art. This solution does not specifically limit this and will not be described in detail here.

[0041] In some embodiments, collecting air parameters of the combustion area and calculating the combustion diffusion characteristics of the waste to be incinerated based on the air parameters and the pore structure characteristics include: Determining a first ratio of combustion-supporting gas and a second ratio of flame-retardant gas in the air according to the collected air parameters, and calculating a combustion coefficient of the current environment according to the first ratio and the second ratio; Acquiring the air flow rate from the air parameters, and establishing a diffusion model of the original pores and oxygen diffusion rate according to the air flow rate and the original pores; The combustion diffusion characteristics corresponding to each of the original pores are determined according to the combustion coefficient and the diffusion model.

[0042] In this embodiment, in order to calculate the combustion diffusion characteristics of the garbage to be incinerated, the air parameters in the combustion area, that is, the air parameters in the garbage incineration pool, are first collected, and the first proportion of the combustion-supporting gas and the second proportion of the flame-retardant gas therein are determined based on the air parameters, and the combustion coefficient of the current environment is calculated based on the first proportion and the second proportion.

[0043] The combustion coefficient specifically satisfies the following formula: ,in, represents the first ratio, represents the second ratio, Indicates the combustion coefficient.

[0044] Then, the air flow rate in the waste incineration pool is obtained, and a diffusion model of the oxygen diffusion rate in the original pores is established based on the air flow rate and the original pores. The oxygen diffusion rate in each original pore is calculated based on the diffusion model, and then the combustion diffusion characteristics of the waste to be incinerated are calculated based on the combustion coefficient and the oxygen diffusion rate.

[0045] The combustion diffusion characteristic is the combustion diffusion speed of the garbage to be incinerated per unit time in the area around the original pores, and the numerical result is the absolute value of the product of the combustion coefficient and the oxygen diffusion rate.

[0046] In some further embodiments, the obtaining of the material combustion characteristic information after normalizing the pore structure characteristics and the combustion diffusion characteristics includes: Obtaining the original pores corresponding to the combustion propagation path, and obtaining the material combustion information corresponding to the original pores; respectively calculating a first average value of the combustion propagation path and a second average value of the combustion diffusion characteristic; calculating a first standard deviation based on the first average value and each of the combustion propagation paths, and calculating a second standard deviation based on the second average value and each of the combustion propagation characteristics; Calculating a first standard value for each of the combustion propagation paths based on the first average value and the first standard deviation, and calculating a second standard value corresponding to each of the combustion propagation characteristics based on the second average value and the second standard deviation; After establishing a mapping relationship between the first standard value, the second standard value and the original pore size, complete combustion characteristic information of the material is obtained.

[0047] In this embodiment, after obtaining the pore structure characteristics and corresponding combustion diffusion characteristics of each original pore, the original pore corresponding to the combustion diffusion path is first obtained, along with the material combustion information corresponding to the original pore, namely, the unit combustion heat of the material corresponding to the original pore in the current region. Simultaneously, a first average value of the combustion diffusion path and a second average value of the corresponding combustion diffusion characteristic are calculated for each original pore. A first standard deviation is then calculated based on the first average value and each combustion diffusion path, while a second standard deviation is calculated based on the second average value and each combustion diffusion characteristic. A first standard value for each combustion diffusion path is then calculated based on the first average value and the first standard deviation, while a second standard value for the combustion diffusion characteristic is calculated based on the second average value and the second standard deviation, thereby completing the standardization of the combustion diffusion paths and combustion diffusion characteristics. A mapping relationship is then established between the first standard value and the second standard value corresponding to each original pore and the original pore, thereby obtaining the material combustion characteristic information corresponding to each original pore.

[0048] It should be noted that the first standard value of each combustion propagation path is the difference between the path symbol value and the first average value, and the ratio to the first standard deviation, and the path symbol value is the path vector of each combustion propagation path, including at least one direction; and the second standard value of each combustion diffusion feature is the difference between the characteristic value of the combustion diffusion feature and the second average value, and the ratio to the second standard value. The above process completes the standardization of the combustion propagation path and the combustion diffusion feature, facilitates subsequent quantification, and improves the accuracy of the garbage combustion heat estimation results.

[0049] S103 , collecting a thermal image of the garbage to be incinerated, performing correction processing on the thermal image and segmenting the image to obtain a plurality of segmented image groups, and obtaining corresponding thermal characteristic information according to the segmented image groups.

[0050] In some embodiments, the collecting of the thermal image of the waste to be incinerated, correcting and segmenting the thermal image to obtain a plurality of segmented image groups, and obtaining corresponding thermal characteristic information according to the segmented image groups include: Thermal imaging cameras are respectively set up in multiple directions of the area where the garbage to be incinerated is located and corresponding local thermal imaging images are respectively obtained; Acquire overlapping areas of adjacent local thermal images respectively according to a preset direction, and acquire a first overlapping image and a second overlapping image of two adjacent local thermal images in the overlapping area respectively; After calculating the average value of the first overlapping imaging image and the second overlapping imaging image to obtain a standard overlapping imaging image, the first overlapping imaging image and the second overlapping imaging image in adjacent local thermal imaging images are replaced by the standard overlapping imaging image to obtain a plurality of corrected imaging images; Combining the plurality of corrected images to obtain a complete thermal image, and removing redundant information from the complete thermal image; performing a cutting process on the complete thermal imaging image after removing the redundant information according to a division rule to obtain a plurality of cutting areas; Performing color recognition on each of the cutting areas, and marking areas of different colors to obtain different marking information, each of the marking information corresponding to a different combustion heat; The darker the color of the cutting area, the higher the combustion heat corresponding to the marking information.

[0051] In this embodiment, in order to evaluate the heat of garbage combustion by using thermal imaging processing, thermal imaging cameras are first set up in multiple directions around the garbage incineration area, that is, the garbage incineration pool, to obtain local thermal imaging images in different directions respectively. Then, the overlapping areas of two adjacent local thermal imaging images are obtained in a preset direction, such as a clockwise direction. Then, the first overlapping imaging image and the second overlapping imaging image of the two local thermal imaging images in the overlapping area are obtained respectively. After obtaining a standard overlapping imaging image based on the average value of the first overlapping imaging image and the second overlapping imaging image, the standard overlapping imaging image is used to replace the first overlapping imaging image and the second overlapping imaging image in the two adjacent local thermal imaging images, thereby obtaining multiple corrected imaging images, thereby ensuring the accuracy of the final thermal imaging.

[0052] The corrected images are then combined to form a complete thermal image. Excessive information, such as text, is removed from the complete thermal image. The image is then segmented according to a segmentation rule to form multiple segmented regions. Each segmented region is then color-recognized, and regions of different colors are labeled to obtain different labeled information, each corresponding to a different combustion calorie. The darker the color of the cutting area, the higher the combustion heat corresponding to the marking information.

[0053] And when marking, the marking information is divided into at least three types. For example, taking the first color threshold, the second color threshold, and the third color threshold that increase in sequence as an example, the area between 0 and the first color threshold in the cutting area is marked as the first marking information, the area between the first color threshold and the second color threshold is marked as the second marking information, and the area between the second color threshold and the third color threshold is marked as the third marking information, thereby completing the marking of each cutting area in the corrected imaging image, making it convenient to subsequently obtain the corresponding combustion calorie assessment result based on the marking information.

[0054] It should be noted that, for the local thermal imaging images acquired by the thermal imaging camera, only two adjacent local thermal imaging images have overlapping areas, and there is no overlap between two local thermal imaging images separated by at least one local thermal imaging image.

[0055] S104: Calculate a material heat evaluation value of the garbage to be incinerated based on the material combustion characteristic information and the material combustion information, and calculate an image heat evaluation value of the garbage to be incinerated based on the heat characteristic information.

[0056] In some embodiments, calculating the material heat evaluation value of the waste to be incinerated based on the material combustion characteristic information and the material combustion information, and calculating the image heat evaluation value of the waste to be incinerated based on the heat characteristic information, includes: Acquire a unit calorific value corresponding to each area on each of the primary images according to the material combustion information; Calculating a material calorific value of the waste to be incinerated based on the distribution ratio and density of the waste to be incinerated in the current area and the unit calorific value and the material combustion characteristic information; Determine the combustion heat corresponding to the different color areas in each of the cutting areas according to the marking information, and calculate the local mass of the garbage to be incinerated corresponding to the different color areas in each of the cutting areas according to the proportion; The local heat corresponding to each cutting area is calculated according to the combustion heat and local mass corresponding to the different color areas in the cutting area, and the local heat of the cutting area is summarized and calculated to obtain the image heat evaluation value of the garbage to be incinerated.

[0057] In this embodiment, after determining the material combustion information, the unit calorific value (i.e., the calorific value per unit weight) corresponding to each region on the primary image is obtained based on the material combustion information. The combustion diffusion of the material within the current region is then calculated based on the pore structure characteristics and the combustion diffusion characteristics in the material combustion characteristic information. The regional weight of the waste within the current region is determined based on the distribution ratio and density of the waste to be incinerated in the current region. The material calorific value for the current region is then determined by summing the product (X) of the unit calorific value and the regional weight, and the product (Y) of the first standard value corresponding to the pore structure characteristics and the second standard value corresponding to the combustion diffusion characteristics.

[0058] As for the heat corresponding to the thermal imaging image, the combustion heat corresponding to the different color areas in each cutting area is first determined according to the annotation information, and the local mass of the garbage to be incinerated corresponding to the different color areas in each cutting area is calculated according to the proportion. Then, according to the combustion heat and local mass corresponding to the color of the annotation information, the heat in each cutting area is locally summarized and calculated to obtain the local heat. The local heat of each cutting area is then summarized together to obtain the image heat evaluation value of the garbage to be incinerated based on thermal imaging.

[0059] By using image recognition and thermal imaging processing to independently calculate the heat assessment results, it is convenient to obtain more accurate heat assessment results of waste incineration after the subsequent model is established.

[0060] S105 , comprehensively calculating a comprehensive heat evaluation value of the garbage to be incinerated based on the material heat evaluation value and the image heat evaluation value.

[0061] In some embodiments, the comprehensive heat evaluation value of the waste to be incinerated is calculated based on the material heat evaluation value and the image heat evaluation value, including: Retrieving combustion data of previous garbage incinerations, the combustion data including material data and image data; Calculate a first weight and a second weight according to the material data and the image data respectively; The material heat evaluation value and the image heat evaluation value are comprehensively calculated according to the first weight and the second weight to obtain the comprehensive heat evaluation value.

[0062] In this embodiment, in order to further improve the accuracy of the modeling results, the combustion data of previously incinerated garbage is called, including material data and image data. The material data is the identification heat data obtained after garbage identification is performed directly based on the previously incinerated garbage, and the image data is the imaging heat data estimated based on thermal imaging of the previously incinerated garbage. By calculating the ratio of the identification heat data and the imaging heat data to the actual heat of the previously incinerated garbage, the first weight and the second weight can be obtained. Subsequently, the material heat evaluation value and the image heat evaluation value are comprehensively calculated based on the first weight and the second weight to obtain the comprehensive heat evaluation value corresponding to the current garbage to be incinerated.

[0063] The comprehensive calorie assessment value The calculation process satisfies the following formula: ,in, represents the first weight, represents the second weight, Indicates the material heat assessment value, Indicates the thermal evaluation value of the image.

[0064] S106. Establish a training set by using the original images, thermal images and comprehensive heat evaluation values ​​of the plurality of the garbage to be incinerated and input them into a convolutional neural network model for training to obtain a target heat evaluation model.

[0065] In some embodiments, the method further comprises: After obtaining the target calorie assessment model, historical combustion data is input to verify the target calorie assessment model. If the verification fails, the target calorie assessment model is retrained until the output result of the target calorie assessment model meets the requirements and the verification is stopped.

[0066] By verifying the target thermal model in real time, the accuracy of the final target thermal model output can be guaranteed, and the model can be adjusted in time to meet the usage requirements of different environments.

[0067] It should be noted that the protection scope of the modeling method of the waste incineration heat assessment model described in the present invention is not limited to the execution order of the steps listed in this embodiment. All solutions implemented by adding, reducing, or replacing steps in the prior art based on the principles of the present invention are included in the protection scope of the present invention.

[0068] The present invention also discloses a modeling system for a waste incineration heat evaluation model, referring to Figure 2 ,include: The first acquisition module 201 is used to acquire the original image of the garbage to be incinerated and pre-process the original image to obtain a primary image; A first calculation module 202 is configured to obtain material combustion characteristic information and material combustion information of the waste to be incinerated based on the primary image; The second acquisition module 203 is used to acquire a thermal image of the waste to be incinerated, perform correction processing on the thermal image, and segment the image to obtain a plurality of segmented image groups, and obtain corresponding thermal characteristic information based on the segmented image groups; A second calculation module 204 is configured to calculate a material heat evaluation value of the waste to be incinerated based on the material combustion characteristic information and the material combustion information, and calculate an image heat evaluation value of the waste to be incinerated based on the heat characteristic information; An evaluation module 205 is configured to calculate a comprehensive heat evaluation value of the waste to be incinerated based on the material heat evaluation value and the image heat evaluation value; The modeling module 206 is used to establish a training set by using the original images, thermal images and comprehensive heat evaluation values ​​of the plurality of the waste to be incinerated and input them into a convolutional neural network model for training to obtain a target heat evaluation model.

[0069] It should be noted that the structure and principle of the modeling system of the waste incineration heat assessment model correspond one-to-one to the steps in the modeling method of the above-mentioned waste incineration heat assessment model, so they will not be repeated here.

[0070] It should be understood that the division of the modules in the above system is merely a division of logical functions. In actual implementation, they may be fully or partially integrated into a single physical entity or physically separated. Furthermore, these modules may be implemented entirely in software called by a processing element, or entirely in hardware. Alternatively, some modules may be implemented in software called by a processing element, while others may be implemented in hardware. For example, module x may be a separate processing element, or integrated into a chip in the above system. Furthermore, it may be stored in the form of program code in the memory of the above system, called by a processing element in the system to perform the functions of module x. The implementation of other modules is similar. Furthermore, these modules may be fully or partially integrated or implemented independently. The processing element described herein may be an integrated circuit with signal processing capabilities. During implementation, the steps of the above method or the modules above may be performed by hardware integrated logic circuits in the processor element or by software instructions.

[0071] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs). For another example, when a module is implemented by scheduling program code on a processing element, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor capable of calling program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0072] It should be noted that the modeling system of the waste incineration heat assessment model of the present invention can implement the modeling method of the waste incineration heat assessment model of the present invention, but the implementation device of the modeling method of the waste incineration heat assessment model of the present invention includes but is not limited to the structure of the modeling system of the waste incineration heat assessment model listed in this embodiment. All structural deformations and replacements of the prior art made according to the principles of the present invention are included in the protection scope of the present invention.

[0073] In summary, the modeling method and system of the waste incineration heat assessment model of the present invention collect the original image and thermal image of the waste entering the furnace, and respectively obtain the material combustion characteristic information and material combustion information of the waste to be incinerated, as well as the heat characteristic information of the waste to be incinerated, and subsequently calculate the material heat assessment value according to the material combustion characteristic information and the material combustion information, calculate the image heat assessment value of the waste to be incinerated according to the heat characteristic information, and obtain the total heat assessment value of the waste to be incinerated according to the material heat assessment value and the image heat assessment value, so that the original image of each waste to be incinerated, the thermal image and the comprehensive heat assessment value are used to establish a training set and input it into the convolutional neural network model for training to obtain the target heat assessment model, so that when the waste entering the furnace is incinerated, the target heat assessment model is used to quickly assess the combustion heat, which is convenient for conditioning the working environment in the waste incineration pool, ensuring full utilization of the combustion heat while reducing material loss and improving the economic benefits of waste incineration; therefore, the present invention effectively overcomes the various shortcomings of the prior art and has high industrial utilization value.

[0074] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the present invention. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by one of ordinary skill in the art without departing from the spirit and technical principles disclosed herein are intended to be covered by the claims of the present invention.

Claims

1. A modeling method for a waste incineration heat assessment model, characterized in that: The following steps are involved: Collecting original images of the garbage to be incinerated, and preprocessing the original images to obtain primary images; Acquiring material combustion characteristic information and material combustion information of the garbage to be incinerated based on the primary image; Collect thermal images of the garbage to be incinerated, perform correction processing on the thermal images, and segment them to obtain multiple segmented image groups, and obtain corresponding thermal characteristic information based on the segmented image groups; calculate the material thermal evaluation value of the garbage to be incinerated based on the material combustion characteristic information and the material combustion information, and calculate the image thermal evaluation value of the garbage to be incinerated based on the thermal characteristic information; calculate the comprehensive thermal evaluation value of the garbage to be incinerated based on the material thermal evaluation value and the image thermal evaluation value; establish a training set based on the original images, thermal images, and comprehensive thermal evaluation values ​​of the multiple garbage to be incinerated, and input them into a convolutional neural network model for training to obtain a target thermal evaluation model.

2. The modeling method of the waste incineration heat assessment model according to claim 1 is characterized in that: The obtaining of the material combustion characteristic information and material combustion information of the garbage to be incinerated according to the primary image includes: Using a first residual network to perform recognition processing on the primary image to obtain material parameters in the primary image, and obtaining corresponding material combustion information from a material database according to the material parameters; Using a second residual network in combination with a dilated convolution to perform recognition processing on the primary image to obtain pore structure features corresponding to the primary image; collecting air parameters of the combustion area, and calculating the combustion and diffusion characteristics of the garbage to be incinerated based on the air parameters and the pore structure characteristics; The material combustion characteristic information is obtained after standardization processing is performed on the pore structure characteristics and the combustion diffusion characteristics.

3. The modeling method of the waste incineration heat assessment model according to claim 2 is characterized in that: The use of the second residual network in combination with the dilated convolution to perform recognition processing on the primary image to obtain pore structure features corresponding to the primary image includes: Based on the preset dilation rate of the dilated convolution, the second residual network is used to accurately identify the primary image to extract original pores in the primary image whose pore gaps are greater than a first preset value; Processing the original pores according to the Sobel operator and graph theory algorithm to obtain a pore topology structure corresponding to the original pores; The pore topology corresponding to each original pore is converted into a combustion propagation path prediction map, and the combustion propagation path corresponding to the original pore is determined according to the combustion propagation path prediction map.

4. The modeling method of the waste incineration heat assessment model according to claim 3 is characterized in that: The collecting of air parameters in the combustion area and calculating the combustion diffusion characteristics of the garbage to be incinerated based on the air parameters and the pore structure characteristics include: Determining a first ratio of combustion-supporting gas and a second ratio of flame-retardant gas in the air according to the collected air parameters, and calculating a combustion coefficient of the current environment according to the first ratio and the second ratio; Acquiring the air flow rate from the air parameters, and establishing a diffusion model of the original pores and oxygen diffusion rate according to the air flow rate and the original pores; The combustion diffusion characteristics corresponding to each of the original pores are determined according to the combustion coefficient and the diffusion model.

5. The modeling method of the waste incineration heat assessment model according to claim 4 is characterized in that: The material combustion characteristic information is obtained after the pore structure characteristics and the combustion diffusion characteristics are normalized, including: Obtaining the original pores corresponding to the combustion propagation path, and obtaining the material combustion information corresponding to the original pores; respectively calculating a first average value of the combustion propagation path and a second average value of the combustion diffusion characteristic; calculating a first standard deviation based on the first average value and each of the combustion propagation paths, and calculating a second standard deviation based on the second average value and each of the combustion propagation characteristics; Calculating a first standard value for each of the combustion propagation paths based on the first average value and the first standard deviation, and calculating a second standard value corresponding to each of the combustion propagation characteristics based on the second average value and the second standard deviation; After establishing a mapping relationship between the first standard value, the second standard value and the original pore size, complete combustion characteristic information of the material is obtained.

6. The modeling method of the waste incineration heat assessment model according to claim 1 is characterized in that: The collecting of the thermal image of the garbage to be incinerated, correcting and segmenting the thermal image to obtain a plurality of segmented image groups, and obtaining corresponding thermal characteristic information according to the segmented image groups include: Thermal imaging cameras are respectively set up in multiple directions of the area where the garbage to be incinerated is located and corresponding local thermal imaging images are respectively obtained; Acquire overlapping areas of adjacent local thermal images respectively according to a preset direction, and acquire a first overlapping image and a second overlapping image of two adjacent local thermal images in the overlapping area respectively; After calculating the average value of the first overlapping imaging image and the second overlapping imaging image to obtain a standard overlapping imaging image, the first overlapping imaging image and the second overlapping imaging image in adjacent local thermal imaging images are replaced by the standard overlapping imaging image to obtain a plurality of corrected imaging images; Combining the plurality of corrected images to obtain a complete thermal image, and removing redundant information from the complete thermal image; performing a cutting process on the complete thermal image after removing the redundant information according to a division rule to obtain a plurality of cutting areas; Performing color recognition on each of the cutting areas, and marking areas of different colors to obtain different marking information, each of the marking information corresponding to a different combustion heat; The darker the color of the cutting area, the higher the combustion heat corresponding to the marking information.

7. The modeling method of the waste incineration heat assessment model according to claim 6 is characterized in that: The step of calculating the material heat evaluation value of the garbage to be incinerated based on the material combustion characteristic information and the material combustion information, and calculating the image heat evaluation value of the garbage to be incinerated based on the heat characteristic information, includes: Acquire a unit calorific value corresponding to each area on each of the primary images according to the material combustion information; Calculating a material calorific value of the waste to be incinerated based on the distribution ratio and density of the waste to be incinerated in the current area and the unit calorific value and the material combustion characteristic information; Determine the combustion heat corresponding to the different color areas in each of the cutting areas according to the marking information, and calculate the local mass of the garbage to be incinerated corresponding to the different color areas in each of the cutting areas according to the proportion; The local heat corresponding to each cutting area is calculated according to the combustion heat and local mass corresponding to the different color areas in the cutting area, and the local heat of the cutting area is summarized and calculated to obtain the image heat evaluation value of the garbage to be incinerated.

8. The modeling method of the waste incineration heat assessment model according to claim 6 is characterized in that: The comprehensive heat evaluation value of the garbage to be incinerated is calculated based on the material heat evaluation value and the image heat evaluation value, including: Retrieving combustion data of previous garbage incinerations, the combustion data including material data and image data; Calculate a first weight and a second weight according to the material data and the image data respectively; The material heat evaluation value and the image heat evaluation value are comprehensively calculated according to the first weight and the second weight to obtain the comprehensive heat evaluation value.

9. The modeling method of the waste incineration heat assessment model according to claim 7, characterized in that: The method further comprises: After obtaining the target calorie assessment model, historical combustion data is input to verify the target calorie assessment model. If the verification fails, the target calorie assessment model is retrained until the output result of the target calorie assessment model meets the requirements and the verification is stopped.

10. A modeling system for a waste incineration heat assessment model, characterized in that: include: A first acquisition module is used to acquire an original image of the garbage to be incinerated and pre-process the original image to obtain a primary image; a first calculation module, configured to obtain material combustion characteristic information and material combustion information of the waste to be incinerated based on the primary image; a second acquisition module, configured to acquire a thermal image of the waste to be incinerated, perform correction processing on the thermal image, and segment the image to obtain a plurality of segmented image groups, and obtain corresponding thermal characteristic information based on the segmented image groups; a second calculation module, configured to calculate a material heat evaluation value of the garbage to be incinerated based on the material combustion characteristic information and the material combustion information, and to calculate an image heat evaluation value of the garbage to be incinerated based on the heat characteristic information; An evaluation module, configured to calculate a comprehensive heat evaluation value of the garbage to be incinerated based on the material heat evaluation value and the image heat evaluation value; The modeling module is used to establish a training set by inputting the original images, thermal images and comprehensive heat evaluation values ​​of the plurality of the waste to be incinerated into a convolutional neural network model for training to obtain a target heat evaluation model.

Images