Modeling Methods and Systems for Assessing the Calorific Value of Waste Incineration

Abstract

This invention provides a modeling method and system for assessing the calorific value of waste incineration. The method includes: preprocessing an original image to obtain a primary image; acquiring material combustion characteristic information and material combustion information of the waste to be incinerated based on the primary image; correcting and segmenting the thermal image to obtain multiple segmented image groups, and acquiring corresponding calorific value information based on the segmented image groups; calculating the material calorific value and image calorific value of the waste to be incinerated; comprehensively calculating the comprehensive calorific value of the waste to be incinerated based on the material calorific value and image calorific value; and establishing a training set by combining the original images, thermal images, and comprehensive calorific value of the waste to be incinerated, and inputting it into a convolutional neural network model for training to obtain the target calorific value assessment model. This invention can effectively predict the calorific value of waste incineration and, in conjunction with other equipment in the waste incineration pit, can improve waste incineration efficiency and increase economic benefits.

Description

Technical Field

[0001] This invention belongs to the field of waste incineration technology, and in particular relates to a modeling method and system for evaluating the heat of waste incineration. Background Technology

[0002] Waste incineration technology plays a significant role in reducing, rendering harmless, and recycling waste. However, due to the complex composition and uneven calorific value of waste in my country, and the inability to estimate the calorific value of waste entering the incinerator in advance, the adjustment of the waste feeding rate has a certain lag, which can easily affect the combustion efficiency and stable operation of the incinerator and increase pollutant emissions. Therefore, it is necessary to measure the calorific value and temperature of waste entering the waste pool of the waste incinerator in real time to solve the above problems and achieve clean and efficient energy utilization of waste.

[0003] Before materials enter the incinerator at a waste-to-energy plant, personnel need to monitor the screen in real time. Operators, based on their experience, estimate the calorific value of the waste and adjust the feed rate and airflow to ensure stable combustion within the incinerator. This requires staff to maintain a high level of concentration at all times. Furthermore, manual monitoring cannot accurately estimate the calorific value of the waste, and the control adjustments are delayed, which can easily lead to significant fluctuations in combustion within the incinerator.

[0004] Currently, the methods for calculating the calorific value of municipal solid waste both domestically and internationally generally include instrumental testing (oxygen bomb calorific method), formula estimation (Dulong / Scheurer-Kestner, etc.), and using grey relational analysis to predict the impact of municipal solid waste on calorific value, and using backpropagation (BP) neural networks to establish a calorific value prediction model. However, these methods suffer from drawbacks such as large errors, complex and difficult-to-apply calculation models, and numerous limitations, and cannot achieve real-time measurement of the calorific value of municipal solid waste. At this stage of research, there is a lack of an effective technical method capable of real-time quantitative detection and calculation of the calorific value of municipal solid waste.

[0005] In summary, there is currently no method to directly display the calorific value of waste entering the furnace in real time. Most operators can only estimate the calorific value of waste based on their experience with the accumulation of waste in the waste pit, which has a large error and is inefficient. Summary of the Invention

[0006] In view of the shortcomings of the prior art described above, the purpose of this invention is to provide a modeling method and system for evaluating the calorific value of waste incineration, so as to solve the problem of relying on manual judgment of the calorific value of waste entering the furnace in the prior art.

[0007] To achieve the above and other related objectives, this invention provides a modeling method for evaluating the calorific value of waste incineration, comprising the following steps:

[0008] Acquire raw images of the waste to be incinerated, and preprocess the raw images to obtain primary images;

[0009] Based on the primary image, obtain the material combustion characteristic information and material combustion information of the waste to be incinerated;

[0010] A thermal image of the waste to be incinerated is acquired, the thermal image is corrected and segmented to obtain multiple segmented image groups, and the corresponding thermal feature information is obtained based on the segmented image groups.

[0011] The material calorific value of the waste to be incinerated is calculated based on the material combustion characteristic information and the material combustion information; the image calorific value of the waste to be incinerated is calculated based on the calorific characteristic information.

[0012] The comprehensive calorific value of the waste to be incinerated is calculated based on the material calorific value and the image calorific value.

[0013] The target heat assessment model is obtained by establishing a training set of the original images, thermal images and comprehensive heat assessment values ​​of multiple wastes to be incinerated, and inputting them into a convolutional neural network model for training.

[0014] In one embodiment of the present invention, obtaining the material combustion characteristic information and material combustion information of the waste to be incinerated based on the primary image includes:

[0015] The primary image is processed by a first residual network to obtain material parameters in the primary image, and the corresponding material combustion information is obtained from the material database based on the material parameters.

[0016] A second residual network is used in conjunction with dilated convolution to perform recognition processing on the primary image in order to obtain the pore structure features corresponding to the primary image;

[0017] Collect air parameters in the combustion zone, and calculate the combustion diffusion characteristics of the waste to be incinerated based on the air parameters and the pore structure characteristics;

[0018] The combustion characteristic information of the material is obtained by standardizing the pore structure characteristics and the combustion diffusion characteristics.

[0019] In one embodiment of the present invention, the step of using a second residual network combined with dilated convolution to perform recognition processing on the primary image to obtain the pore structure features corresponding to the primary image includes:

[0020] Based on the pre-set void ratio of the dilated convolution, the second residual network is used to accurately identify the primary image in order to extract the original pores in the primary image whose pore gap is greater than the first preset value.

[0021] The original pores are processed using the Sobel operator and graph theory algorithm to obtain the pore topology corresponding to the original pores;

[0022] The pore topology corresponding to each original pore is converted into a combustion spread path prediction map, and the combustion spread path corresponding to the original pore is determined based on the combustion spread path prediction map.

[0023] In one embodiment of the present invention, the step of collecting air parameters in the combustion zone and calculating the combustion diffusion characteristics of the waste to be incinerated based on the air parameters and the pore structure characteristics includes:

[0024] The first proportion of combustion-supporting gas and the second proportion of combustion-retardant gas are determined based on the collected air parameters, and the combustion coefficient of the current environment is calculated based on the first proportion and the second proportion.

[0025] Obtain the air velocity from the air parameters, and establish a diffusion model of the original pores and oxygen diffusion rate based on the air velocity and the original pore size;

[0026] The combustion diffusion characteristics corresponding to each of the original pores are determined based on the combustion coefficient and the diffusion model.

[0027] In one embodiment of the present invention, the step of standardizing the pore structure features and the combustion diffusion features to obtain the material combustion feature information includes:

[0028] Obtain the original pores corresponding to the combustion spread path, and obtain the material combustion information corresponding to the original pores;

[0029] Calculate the first average value of the combustion spread path and the second average value of the combustion spread characteristics, respectively.

[0030] A first standard deviation is calculated based on the first average value and each of the combustion spread paths, and a second standard deviation is calculated based on the second average value and each of the combustion spread characteristics;

[0031] A first standard value is calculated for each combustion spread path based on the first average value and the first standard deviation, and a second standard value is calculated for each combustion spread feature based on the second average value and the second standard deviation.

[0032] After establishing a mapping relationship between the first standard value and the second standard value and the original pore size, complete combustion characteristic information of the material is obtained.

[0033] In one embodiment of the present invention, the step of acquiring a thermal image of the waste to be incinerated, correcting and segmenting the thermal image to obtain multiple segmented image groups, and obtaining corresponding thermal feature information based on the segmented image groups includes:

[0034] Thermal imaging cameras were set up in multiple directions in the area where the waste to be incinerated was located, and corresponding local thermal images were acquired respectively.

[0035] The overlapping areas of adjacent local thermal images are obtained according to a preset direction, and the first and second overlapping images of two adjacent local thermal images are obtained in the overlapping areas.

[0036] After calculating the average of the first overlapping image and the second overlapping image to obtain a standard overlapping image, the first overlapping image and the second overlapping image in the adjacent local thermal images are replaced by the standard overlapping image to obtain multiple corrected images.

[0037] After combining multiple corrected imaging images, a complete thermal imaging image is obtained, and redundant information in the complete thermal imaging image is removed.

[0038] The complete thermal image after removing the redundant information is segmented according to the segmentation rules to obtain multiple segmented regions;

[0039] Each of the cut regions is color-identified, and regions of different colors are marked to obtain different marking information. Each marking information corresponds to a different amount of heat of combustion.

[0040] The darker the color of the cut area, the higher the combustion heat corresponding to the marking information.

[0041] In one embodiment of the present invention, the step of calculating the material calorific value of the waste to be incinerated based on the material combustion characteristic information and the material combustion information, and calculating the image calorific value of the waste to be incinerated based on the calorific characteristic information, includes:

[0042] Based on the material combustion information, obtain the unit heat value corresponding to each region on each primary image;

[0043] Based on the distribution ratio and density of the waste to be incinerated in the current area, the material calorific value of the waste to be incinerated is calculated according to the unit calorific value and the material combustion characteristic information.

[0044] The combustion heat corresponding to different colored areas within each cutting area is determined based on the labeling information, and the local mass of the waste to be incinerated corresponding to different colored areas within each cutting area is calculated proportionally.

[0045] Based on the combustion heat and local mass corresponding to different color areas within the cutting area, the local heat corresponding to each cutting area is calculated, and the local heat of the cutting areas is summarized to obtain the image heat assessment value of the waste to be incinerated.

[0046] In one embodiment of the present invention, the step of calculating the comprehensive calorific value of the waste to be incinerated based on the material calorific value and the image calorific value includes:

[0047] Retrieve combustion data from previous waste incineration processes, including material data and image data;

[0048] The first weight and the second weight are calculated based on the material data and the image data, respectively.

[0049] The comprehensive heat assessment value is obtained by comprehensively calculating the material heat assessment value and the image heat assessment value based on the first weight and the second weight.

[0050] In one embodiment of the present invention, the method further includes:

[0051] After obtaining the target heat assessment model, historical combustion data is input to verify the target heat assessment model until the output result of the target heat assessment model meets the requirements, and then the verification stops.

[0052] This invention also provides a modeling system for evaluating the calorific value of waste incineration, comprising:

[0053] The first acquisition module is used to acquire original images of the waste to be incinerated and to preprocess the original images to obtain primary images.

[0054] The first calculation module is used to obtain material combustion characteristic information and material combustion information of the waste to be incinerated based on the primary image;

[0055] The second acquisition module is used to acquire thermal images of the waste to be incinerated, correct and segment the thermal images to obtain multiple segmented image groups, and obtain corresponding thermal feature information based on the segmented image groups.

[0056] The second calculation module is used to calculate the material calorific value of the waste to be incinerated based on the material combustion characteristic information and the material combustion information, and to calculate the image calorific value of the waste to be incinerated based on the calorific characteristic information.

[0057] The evaluation module is used to calculate the comprehensive calorific value of the waste to be incinerated based on the material calorific value and the image calorific value.

[0058] The modeling module is used to establish a training set by combining the original images, thermal images and comprehensive heat assessment values ​​of multiple wastes to be incinerated, and input them into a convolutional neural network model for training to obtain the target heat assessment model.

[0059] As described above, the modeling method and system for assessing the calorific value of waste incineration according to the present invention have the following beneficial effects:

[0060] Compared with existing technologies, this invention acquires original images and thermal images of the waste entering the incinerator, and obtains material combustion characteristic information and material combustion information of the waste to be incinerated, as well as the calorific characteristic information of the waste to be incinerated. Subsequently, a material calorific value is calculated based on the material combustion characteristic information and the material combustion information, and an image calorific value of the waste to be incinerated is calculated based on the calorific characteristic information. Finally, a total calorific value of the waste to be incinerated is obtained based on the material calorific value and the image calorific value. Then, a training set is established using the original image of each waste to be incinerated, the thermal image, and the comprehensive calorific value, and input into a convolutional neural network model for training to obtain a target calorific value assessment model. This allows for rapid assessment of the combustion heat during waste incineration, facilitating the adjustment of the working environment within the waste incineration pit, ensuring full utilization of combustion heat while reducing material loss and improving the economic efficiency of waste incineration. Attached Figure Description

[0061] Figure 1 The flowchart shown is a modeling method for the waste incineration calorific value assessment model of the present invention.

[0062] Figure 2 The diagram shown is a structural block diagram of the modeling method for the waste incineration calorific value assessment model of the present invention. Detailed Implementation

[0063] The following specific embodiments illustrate the implementation of the present invention. 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 other different specific embodiments, and various 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, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0064] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. The illustrations only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0065] The modeling method and system for the waste incineration calorific value assessment model of the present invention acquires original images and thermal images of the waste entering the incinerator, and obtains material combustion characteristic information and material combustion information of the waste to be incinerated, as well as calorific value information of the waste to be incinerated. Subsequently, a material calorific value assessment is calculated based on the material combustion characteristic information and the material combustion information, and an image calorific value assessment is calculated based on the calorific value assessment. Finally, a total calorific value assessment is obtained based on the material calorific value assessment and the image calorific value assessment. Then, a training set is established using the original image of each waste to be incinerated, the thermal image, and the comprehensive calorific value assessment, and input into a convolutional neural network model for training to obtain a target calorific value assessment model. This allows for rapid assessment of the combustion calorific value assessment during waste incineration, facilitating the assessment of the working environment conditions within the waste incineration pit, ensuring full utilization of combustion calorific value while reducing material loss and improving the economic efficiency of waste incineration.

[0066] The storage medium of the present invention stores a computer program, which, 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), magnetic disk, USB flash drive, memory card, or optical disk.

[0067] One or more storage media may be used in any combination. The storage medium may be a computer-readable signal medium or a computer-readable storage medium. A 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, erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in connection with an instruction execution system, apparatus, or device.

[0068] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0069] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0070] Computer program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, Smalltalk, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can 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 can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0071] The present invention will now be described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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 apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, these computer program instructions create means for implementing the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams.

[0072] 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 particular manner, thereby producing an article of manufacture that includes instructions for implementing the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0073] Computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, such that the instructions that execute on the computer or other programmable apparatus provide a process for implementing the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0074] The terminal of this invention includes a processor and a memory.

[0075] The memory is used to store computer programs; preferably, the memory includes various media capable of storing program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card or optical disk.

[0076] 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 modeling method of the waste incineration calorific value assessment model described below.

[0077] 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, or discrete hardware components.

[0078] like Figure 1 As shown, in one embodiment, the present invention provides a modeling method for a waste incineration calorific value assessment model, comprising the following steps:

[0079] S101. Acquire the original image of the waste to be incinerated, and preprocess the original image to obtain a primary image.

[0080] In this embodiment, for the waste raw materials that need to be incinerated, the original image is directly acquired, and the original image is denoised to obtain a cleaned primary image, which is convenient for subsequent calculations on the primary image.

[0081] S102. Obtain the material combustion characteristic information and material combustion information of the waste to be incinerated based on the primary image.

[0082] 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:

[0083] The primary image is processed by a first residual network to obtain material parameters in the primary image, and the corresponding material combustion information is obtained from the material database based on the material parameters.

[0084] A second residual network is used in conjunction with dilated convolution to perform recognition processing on the primary image in order to obtain the pore structure features corresponding to the primary image;

[0085] Collect air parameters in the combustion zone, and calculate the combustion diffusion characteristics of the waste to be incinerated based on the air parameters and the pore structure characteristics;

[0086] The combustion characteristic information of the material is obtained by standardizing the pore structure characteristics and the combustion diffusion characteristics.

[0087] 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. Then, based on the material parameters, the corresponding material combustion information, that is, the unit calorific value of each material, is obtained from the material database. Next, a second residual network with perforated convolution is used to perform recognition processing on the primary image to obtain the pore structure features present in the primary image. Simultaneously, air parameters within the combustion area, that is, the air parameters in the waste incineration pit, are collected. Based on the air parameters and pore structure features, the combustion diffusion characteristics corresponding to different pores in the waste to be incinerated are calculated, facilitating subsequent standardization processing based on the pore structure features and combustion diffusion characteristics to obtain material combustion characteristic information.

[0088] The first residual network and the second residual network are both residual networks in the prior art, such as the residual network ResNet-101. They can be the same or different. This solution does not make any special restrictions on this, and will not be elaborated here.

[0089] In some other embodiments, the step of using a second residual network combined with dilated convolution to perform recognition processing on the primary image to obtain the pore structure features corresponding to the primary image includes:

[0090] Based on the pre-set void ratio of the dilated convolution, the second residual network is used to accurately identify the primary image in order to extract the original pores in the primary image whose pore gap is greater than the first preset value.

[0091] The original pores are processed using the Sobel operator and graph theory algorithm to obtain the pore topology corresponding to the original pores;

[0092] The pore topology corresponding to each original pore is converted into a combustion spread path prediction map, and the combustion spread path corresponding to the original pore is determined based on the combustion spread path prediction map.

[0093] In this embodiment, to obtain the pore structure features in the primary image, a second residual network is first used to accurately identify the primary image based on a pre-set void ratio using dilated convolution, extracting the original pores larger than a first preset value. Since the distribution of the 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 algorithm, i.e., the 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 spread path prediction map. Then, based on the combustion spread path prediction map, the combustion spread path of the current region where the original pore is located can be determined.

[0094] It should be noted that the pore topology structure corresponding to each original pore is obtained using a fracture network analysis method based on existing technologies. This solution does not impose any special limitations on this method, and will not be elaborated upon here.

[0095] In some embodiments, collecting air parameters in the combustion zone and calculating the combustion diffusion characteristics of the waste to be incinerated based on the air parameters and the pore structure characteristics includes:

[0096] The first proportion of combustion-supporting gas and the second proportion of combustion-retardant gas are determined based on the collected air parameters, and the combustion coefficient of the current environment is calculated based on the first proportion and the second proportion.

[0097] Obtain the air velocity from the air parameters, and establish a diffusion model of the original pores and oxygen diffusion rate based on the air velocity and the original pore size;

[0098] The combustion diffusion characteristics corresponding to each of the original pores are determined based on the combustion coefficient and the diffusion model.

[0099] In this embodiment, in order to calculate the combustion diffusion characteristics of the waste to be incinerated, the air parameters in the combustion area, that is, the air parameters in the waste incineration pit, are first collected. Based on the air parameters, the first proportion of combustion-supporting gas and the second proportion of combustion-retardant gas are determined, and the combustion coefficient of the current environment is calculated based on the first proportion and the second proportion.

[0100] The combustion coefficient specifically satisfies the following formula: ,in, Indicates the first proportion. Indicates the second proportion. This indicates the combustion coefficient.

[0101] Then, the air velocity in the waste incineration pit is obtained, and a diffusion model of the oxygen diffusion rate in the original pores is established based on the air velocity and the original pores. The oxygen diffusion rate in each original pore is calculated based on the diffusion model. Then, the combustion diffusion characteristics of the waste to be incinerated are calculated based on the combustion coefficient and the oxygen diffusion rate.

[0102] The combustion diffusion characteristic is the combustion diffusion rate of the waste to be incinerated per unit time in the region surrounding the original pores, and its numerical result is the absolute value of the product of the combustion coefficient and the oxygen diffusion rate.

[0103] In further embodiments, the process of standardizing the pore structure features and the combustion diffusion features to obtain the material combustion feature information includes:

[0104] Obtain the original pores corresponding to the combustion spread path, and obtain the material combustion information corresponding to the original pores;

[0105] Calculate the first average value of the combustion spread path and the second average value of the combustion spread characteristics, respectively.

[0106] A first standard deviation is calculated based on the first average value and each of the combustion spread paths, and a second standard deviation is calculated based on the second average value and each of the combustion spread characteristics;

[0107] A first standard value is calculated for each combustion spread path based on the first average value and the first standard deviation, and a second standard value is calculated for each combustion spread feature based on the second average value and the second standard deviation.

[0108] After establishing a mapping relationship between the first standard value and the second standard value and the original pore size, complete combustion characteristic information of the material is obtained.

[0109] In this embodiment, after obtaining the pore structure characteristics and corresponding combustion diffusion characteristics of each original pore, the original pores corresponding to the combustion spread path are first obtained, and the material combustion information corresponding to the original pores is also obtained, that is, the unit combustion heat of the material corresponding to the original pores in the current region. Simultaneously, the first average value of the combustion spread path and the second average value of the corresponding combustion diffusion characteristic for each original pore are calculated. Then, a first standard deviation is calculated based on the first average value and each combustion spread path, and a second standard deviation is calculated based on the second average value and each combustion diffusion characteristic. Next, a first standard value is calculated for each combustion spread path based on the first average value and the first standard deviation, and a second standard value of the combustion diffusion characteristic is calculated based on the second average value and the second standard deviation, thereby completing the standardization process for the combustion spread path and combustion diffusion characteristics. Finally, a mapping relationship is established between the first standard value and the second standard value corresponding to each original pore and the original pore, thus obtaining the material combustion characteristic information corresponding to each original pore.

[0110] It should be noted that the first standard value for each combustion spread path is the ratio of the difference between the path symbol value and the first average value to the first standard deviation, and the path symbol value is the path vector of each combustion spread path, including at least one direction; while the second standard value for each combustion diffusion feature is the ratio of the difference between the feature value of the combustion diffusion feature and the second average value to the second standard value. The above process completes the standardization of combustion spread paths and combustion diffusion features, which facilitates subsequent quantification and improves the accuracy of waste combustion heat prediction results.

[0111] S103. Acquire thermal imaging images of the waste to be incinerated, perform correction processing on the thermal imaging images and segment them to obtain multiple segmented image groups, and obtain corresponding thermal feature information based on the segmented image groups.

[0112] In some embodiments, the process of acquiring thermal images of the waste to be incinerated, correcting and segmenting the thermal images to obtain multiple segmented image groups, and obtaining corresponding thermal feature information based on the segmented image groups includes:

[0113] Thermal imaging cameras were set up in multiple directions in the area where the waste to be incinerated was located, and corresponding local thermal images were acquired respectively.

[0114] The overlapping areas of adjacent local thermal images are obtained according to a preset direction, and the first and second overlapping images of two adjacent local thermal images are obtained in the overlapping areas.

[0115] After calculating the average of the first overlapping image and the second overlapping image to obtain a standard overlapping image, the first overlapping image and the second overlapping image in the adjacent local thermal images are replaced by the standard overlapping image to obtain multiple corrected images.

[0116] After combining multiple corrected imaging images, a complete thermal imaging image is obtained, and redundant information in the complete thermal imaging image is removed.

[0117] The complete thermal image after removing the redundant information is segmented according to the segmentation rules to obtain multiple segmented regions;

[0118] Each of the cut regions is color-identified, and regions of different colors are marked to obtain different marking information. Each marking information corresponds to a different amount of heat of combustion.

[0119] The darker the color of the cut area, the higher the combustion heat corresponding to the marking information.

[0120] In this embodiment, in order to assess the heat of waste combustion using thermal imaging processing, thermal imaging cameras are first set up in multiple directions around the waste incineration area, i.e., the waste incineration pit, to acquire local thermal images from different directions. Then, according to a preset direction, such as clockwise, the overlapping area of ​​two adjacent local thermal images is acquired. Then, a first overlapping image and a second overlapping image are acquired within the overlapping area of ​​the two local thermal images. After obtaining a standard overlapping image based on the average of the first and second overlapping images, the first and second overlapping images in the two adjacent local thermal images are replaced by the standard overlapping image, thereby obtaining multiple corrected images to ensure the accuracy of the final thermal image.

[0121] Afterwards, the multiple corrected images are combined to obtain a complete thermal image. Redundant information, such as text, is removed from the complete thermal image. The image is then segmented according to a division rule to obtain multiple segmented regions. Each segmented region is then color-coded, and different colored regions are labeled to obtain different labeling information. Each labeling information corresponds to a different amount of combustion heat.

[0122] The darker the color of the cut area, the higher the combustion heat corresponding to the marking information.

[0123] Furthermore, during the annotation process, the annotation information is divided into at least three types. For example, taking the first color threshold, the second color threshold, and the third color threshold as increasing sequentially, the area within the cutting region that is between 0 and the first color threshold is labeled as the first annotation information, the area that is between the first color threshold and the second color threshold is labeled as the second annotation information, and the area that is between the second color threshold and the third color threshold is labeled as the third annotation information. This completes the annotation of each cutting region within the corrected imaging image, making it convenient to obtain the corresponding combustion heat assessment results based on the annotation information.

[0124] It should be noted that when setting up a thermal imaging camera to acquire local thermal images, only two adjacent local thermal images have overlapping areas, and there is no overlap between two local thermal images that are separated by at least one local thermal image.

[0125] S104. Calculate the material calorific value of the waste to be incinerated based on the material combustion characteristic information and the material combustion information, and calculate the image calorific value of the waste to be incinerated based on the calorific characteristic information.

[0126] In some embodiments, calculating the material calorific value of the waste to be incinerated based on the material combustion characteristic information and the material combustion information, and calculating the image calorific value of the waste to be incinerated based on the calorific characteristic information, includes:

[0127] Based on the material combustion information, obtain the unit heat value corresponding to each region on each primary image;

[0128] Based on the distribution ratio and density of the waste to be incinerated in the current area, the material calorific value of the waste to be incinerated is calculated according to the unit calorific value and the material combustion characteristic information.

[0129] The combustion heat corresponding to different colored areas within each cutting area is determined based on the labeling information, and the local mass of the waste to be incinerated corresponding to different colored areas within each cutting area is calculated proportionally.

[0130] Based on the combustion heat and local mass corresponding to different color areas within the cutting area, the local heat corresponding to each cutting area is calculated, and the local heat of the cutting areas is summarized to obtain the image heat assessment value of the waste to be incinerated.

[0131] In this embodiment, after determining the material combustion information, the unit heat value corresponding to each region on the primary image is obtained based on the material combustion information, which is the heat combustion value per unit weight. Then, the combustion diffusion of the material in the current region is calculated based on the pore structure characteristics and combustion diffusion characteristics in the material combustion feature information, and the regional weight of the waste in the current region is determined based on the distribution ratio and density of the waste to be incinerated in the current region. Then, the sum of X and Y is used to obtain the material heat assessment value in the current region, based on the product X of the unit heat value and the regional weight, 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.

[0132] Regarding the heat corresponding to the thermal imaging image, the combustion heat corresponding to different colored areas within each cut area is first determined based on the annotation information. At the same time, the local mass of the waste to be incinerated corresponding to different colored areas within each cut area is calculated proportionally. Then, based on the combustion heat and local mass corresponding to the colors in the annotation information, the heat in each cut area is locally summarized and calculated to obtain the local heat. Finally, the local heat of each cut area is summarized together to obtain the thermal imaging image heat assessment value of the waste to be incinerated.

[0133] By employing both image recognition and thermal imaging processing to independently calculate the calorific value, more accurate calorific value assessments of waste incineration can be obtained after subsequent model building.

[0134] S105. Calculate the comprehensive calorific value of the waste to be incinerated based on the material calorific value and the image calorific value.

[0135] In some embodiments, calculating the comprehensive calorific value of the waste to be incinerated based on the material calorific value and the image calorific value includes:

[0136] Retrieve combustion data from previous waste incineration processes, including material data and image data;

[0137] The first weight and the second weight are calculated based on the material data and the image data, respectively.

[0138] The comprehensive heat assessment value is obtained by comprehensively calculating the material heat assessment value and the image heat assessment value based on the first weight and the second weight.

[0139] In this embodiment, to further improve the accuracy of the modeling results, combustion data of previously incinerated waste is called, including material data and image data. The material data is the identified heat data obtained directly from the waste identification of previously incinerated waste, while the image data is the imaging heat data estimated by thermal imaging of previously incinerated waste. By calculating the ratio of the identified heat data and imaging heat data to the actual heat of previously incinerated waste, the first weight and the second weight can be obtained. Subsequently, the comprehensive heat assessment value corresponding to the current waste to be incinerated can be obtained by comprehensively calculating the material heat assessment value and the image heat assessment value based on the first weight and the second weight.

[0140] The comprehensive calorie assessment value The calculation process satisfies the following formula: ,in, Indicates the first weight. Indicates the second weight. This indicates the material's heat assessment value. This indicates the image's thermal assessment value.

[0141] S106. A training set is established by combining the original images, thermal images, and comprehensive heat assessment values ​​of multiple wastes to be incinerated, and then input into a convolutional neural network model for training to obtain the target heat assessment model.

[0142] In some embodiments, the method further includes:

[0143] After obtaining the target heat assessment model, historical combustion data is input to verify the target heat assessment model. If the verification fails, the target heat assessment model is retrained until the output result of the target heat assessment model meets the requirements, and then the verification stops.

[0144] By validating the target heat model in real time, the accuracy of the final target heat model output can be guaranteed, and the model can be adjusted in a timely manner to meet the usage requirements of different environments.

[0145] It should be noted that the protection scope of the modeling method for the waste incineration heat assessment model described in this invention is not limited to the execution order of the steps listed in this embodiment. Any solution implemented by adding, subtracting, or replacing steps in the prior art based on the principles of this invention is included within the protection scope of this invention.

[0146] This invention also discloses a modeling system for evaluating the calorific value of waste incineration, with reference to... Figure 2 ,include:

[0147] The first acquisition module 201 is used to acquire the original image of the waste to be incinerated and to preprocess the original image to obtain a primary image;

[0148] The first calculation module 202 is used to obtain material combustion characteristic information and material combustion information of the waste to be incinerated based on the primary image;

[0149] The second acquisition module 203 is used to acquire thermal imaging images of the waste to be incinerated, perform correction processing on the thermal imaging images and segment them to obtain multiple segmented image groups, and obtain corresponding thermal feature information based on the segmented image groups.

[0150] The second calculation module 204 is used to calculate the material calorific value of the waste to be incinerated based on the material combustion characteristic information and the material combustion information, and to calculate the image calorific value of the waste to be incinerated based on the calorific characteristic information.

[0151] The evaluation module 205 is used to calculate the comprehensive calorific value of the waste to be incinerated based on the material calorific value and the image calorific value.

[0152] The modeling module 206 is used to establish a training set by combining the original images, thermal images and comprehensive heat assessment values ​​of multiple wastes to be incinerated, and input them into a convolutional neural network model for training to obtain a target heat assessment model.

[0153] It should be noted that the structure and principle of the modeling system for the waste incineration calorific value assessment model correspond one-to-one with the steps in the modeling method of the waste incineration calorific value assessment model described above, so they will not be repeated here.

[0154] It should be noted that the division of the various modules in the above system is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software through processing element calls; they can be fully implemented in hardware; or some modules can be implemented by processing element calls to software, while others are implemented in hardware. For example, module x can be a separate processing element, or it can be integrated into a chip within the system. Alternatively, it can be stored as program code in the system's memory, and its function can be called and executed by a processing element. The implementation of other modules is similar. Moreover, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element mentioned here can be an integrated circuit with signal processing capabilities. During implementation, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0155] For example, these modules can 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). As another example, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together as a System-On-a-Chip (SOC).

[0156] 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. However, 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 modifications and substitutions of the prior art made according to the principle of the present invention are included within the protection scope of the present invention.

[0157] In summary, the modeling method and system for the waste incineration calorific value assessment model of the present invention acquires original images and thermal images of the waste entering the incinerator, and obtains material combustion characteristic information and material combustion information of the waste to be incinerated, as well as calorific value information of the waste to be incinerated. Subsequently, a material calorific value assessment is calculated based on the material combustion characteristic information and the material combustion information, and an image calorific value assessment is calculated based on the calorific value assessment. Finally, a total calorific value assessment is obtained based on the material calorific value assessment and the image calorific value assessment. Then, a training set is established using the original image of each waste to be incinerated, the thermal image, and the comprehensive calorific value assessment, and input into a convolutional neural network model for training to obtain the target calorific value assessment model. This allows for rapid assessment of the combustion calorific value during waste incineration, facilitating the assessment of the working environment conditions within the waste incineration pit, ensuring full utilization of combustion calorific value while reducing material loss and improving the economic efficiency of waste incineration. Therefore, the present invention effectively overcomes the various shortcomings of the prior art and has high industrial application value.

[0158] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can 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 those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A modeling method for evaluating the calorific value of waste incineration, characterized in that, Includes the following steps: Acquire raw images of the waste to be incinerated, and preprocess the raw images to obtain primary images; Based on the primary image, obtain the material combustion characteristic information and material combustion information of the waste to be incinerated; Thermal images of the waste to be incinerated are acquired, corrected, and segmented to obtain multiple segmented image groups. Corresponding thermal feature information is obtained from each segmented image group. The material calorific value of the waste to be incinerated is calculated based on the material combustion feature information and the material combustion data. The image calorific value of the waste to be incinerated is calculated based on the thermal feature information. A comprehensive calorific value of the waste to be incinerated is calculated by combining the material calorific value and the image calorific value. A training set is established using the original images, thermal images, and comprehensive calorific values ​​of the multiple wastes to be incinerated, and then input into a convolutional neural network model for training to obtain the target calorific value model. 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: The primary image is processed by a first residual network to obtain material parameters in the primary image, and the corresponding material combustion information is obtained from the material database based on the material parameters. A second residual network is used in conjunction with dilated convolution to perform recognition processing on the primary image in order to obtain the pore structure features corresponding to the primary image; Collect air parameters in the combustion zone, and calculate the combustion diffusion characteristics of the waste to be incinerated based on the air parameters and the pore structure characteristics; The combustion characteristic information of the material is obtained by standardizing the pore structure characteristics and the combustion diffusion characteristics.

2. The modeling method for the waste incineration calorific value assessment model according to claim 1, characterized in that, The step of using a second residual network combined with 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 pre-set void ratio of the dilated convolution, the second residual network is used to accurately identify the primary image in order to extract the original pores in the primary image whose pore gap is greater than the first preset value. The original pores are processed using the Sobel operator and graph theory algorithm to obtain the pore topology corresponding to the original pores; The pore topology corresponding to each original pore is converted into a combustion spread path prediction map, and the combustion spread path corresponding to the original pore is determined based on the combustion spread path prediction map.

3. The modeling method for the waste incineration calorific value assessment model according to claim 2, characterized in that, The air parameters of the combustion zone are collected, and the combustion diffusion characteristics of the waste to be incinerated are calculated based on the air parameters and the pore structure characteristics, including: The first proportion of combustion-supporting gas and the second proportion of combustion-retardant gas are determined based on the collected air parameters, and the combustion coefficient of the current environment is calculated based on the first proportion and the second proportion. Obtain the air velocity from the air parameters, and establish a diffusion model of the original pores and oxygen diffusion rate based on the air velocity and the original pore size; The combustion diffusion characteristics corresponding to each of the original pores are determined based on the combustion coefficient and the diffusion model.

4. The modeling method for the waste incineration calorific value assessment model according to claim 3, characterized in that, The material combustion characteristic information is obtained by standardizing the pore structure characteristics and the combustion diffusion characteristics, including: Obtain the original pores corresponding to the combustion spread path, and obtain the material combustion information corresponding to the original pores; Calculate the first average value of the combustion spread path and the second average value of the combustion spread characteristics, respectively. A first standard deviation is calculated based on the first average value and each of the combustion spread paths, and a second standard deviation is calculated based on the second average value and each of the combustion spread characteristics; A first standard value is calculated for each combustion spread path based on the first average value and the first standard deviation, and a second standard value is calculated for each combustion spread feature based on the second average value and the second standard deviation. After establishing a mapping relationship between the first standard value and the second standard value and the original pore size, complete combustion characteristic information of the material is obtained.

5. The modeling method for the waste incineration calorific value assessment model according to claim 1, characterized in that, The process involves acquiring thermal images of the waste to be incinerated, correcting and segmenting the thermal images to obtain multiple segmented image groups, and acquiring corresponding thermal feature information based on the segmented image groups, including: Thermal imaging cameras were set up in multiple directions in the area where the waste to be incinerated was located, and corresponding local thermal images were acquired respectively. The overlapping areas of adjacent local thermal images are obtained according to a preset direction, and the first and second overlapping images of two adjacent local thermal images are obtained in the overlapping areas. After calculating the average of the first overlapping image and the second overlapping image to obtain a standard overlapping image, the first overlapping image and the second overlapping image in the adjacent local thermal images are replaced by the standard overlapping image to obtain multiple corrected images. After combining multiple corrected imaging images, a complete thermal imaging image is obtained, and redundant information in the complete thermal imaging image is removed. The complete thermal image after removing the redundant information is segmented according to the segmentation rules to obtain multiple segmented regions; Each of the cut regions is color-identified, and regions of different colors are marked to obtain different marking information. Each marking information corresponds to a different amount of heat of combustion. The darker the color of the cut area, the higher the combustion heat corresponding to the marking information.

6. The modeling method for the waste incineration calorific value assessment model according to claim 5, characterized in that, The step of calculating the material calorific value of the waste to be incinerated based on the material combustion characteristic information and the material combustion information, and calculating the image calorific value of the waste to be incinerated based on the calorific characteristic information, includes: Based on the material combustion information, obtain the unit heat value corresponding to each region on each primary image; Based on the distribution ratio and density of the waste to be incinerated in the current area, the material calorific value of the waste to be incinerated is calculated according to the unit calorific value and the material combustion characteristic information. The combustion heat corresponding to different colored areas within each cutting area is determined based on the labeling information, and the local mass of the waste to be incinerated corresponding to different colored areas within each cutting area is calculated proportionally. Based on the combustion heat and local mass corresponding to different color areas within the cutting area, the local heat corresponding to each cutting area is calculated, and the local heat of the cutting areas is summarized to obtain the image heat assessment value of the waste to be incinerated.

7. The modeling method for the waste incineration calorific value assessment model according to claim 5, characterized in that, The step of calculating the comprehensive calorific value of the waste to be incinerated based on the material calorific value and the image calorific value includes: Retrieve combustion data from previous waste incineration processes, including material data and image data; The first weight and the second weight are calculated based on the material data and the image data, respectively. The comprehensive heat assessment value is obtained by comprehensively calculating the material heat assessment value and the image heat assessment value based on the first weight and the second weight.

8. The modeling method for the waste incineration calorific value assessment model according to claim 6, characterized in that, The method further includes: After obtaining the target heat assessment model, historical combustion data is input to verify the target heat assessment model. If the verification fails, the target heat assessment model is retrained until the output result of the target heat assessment model meets the requirements, and then the verification stops.

9. A modeling system for evaluating the calorific value of waste incineration, characterized in that, include: The first acquisition module is used to acquire original images of the waste to be incinerated and to preprocess the original images to obtain primary images. The first calculation module is used 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 is used to acquire thermal images of the waste to be incinerated, correct and segment the thermal images to obtain multiple segmented image groups, and obtain corresponding thermal feature information based on the segmented image groups. The second calculation module is used to calculate the material calorific value of the waste to be incinerated based on the material combustion characteristic information and the material combustion information, and to calculate the image calorific value of the waste to be incinerated based on the calorific characteristic information. The evaluation module is used to calculate the comprehensive calorific value of the waste to be incinerated based on the material calorific value and the image calorific value. The modeling module is used to establish a training set by combining the original images, thermal images and comprehensive heat assessment values ​​of multiple wastes to be incinerated, and input them into a convolutional neural network model for training to obtain the target heat assessment model; 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: The primary image is processed by a first residual network to obtain material parameters in the primary image, and the corresponding material combustion information is obtained from the material database based on the material parameters. A second residual network is used in conjunction with dilated convolution to perform recognition processing on the primary image in order to obtain the pore structure features corresponding to the primary image; Collect air parameters in the combustion zone, and calculate the combustion diffusion characteristics of the waste to be incinerated based on the air parameters and the pore structure characteristics; The combustion characteristic information of the material is obtained by standardizing the pore structure characteristics and the combustion diffusion characteristics.

Images