Combustion optimization control system and method based on flame intensity detection

Abstract

The invention discloses a combustion optimization control system and method based on flame intensity detection. Relates to the technical field of combustion parameter optimization. The method comprises the following steps: acquiring flame intensity signals of a plurality of wavebands of combustion flame; determining the combustion efficiency of the comburent based on the flame intensity signal; the combustion efficiency is sent to a coupling index calculation model, so that the coupling index calculation model outputs a coupling index of the combustion efficiency and NOx emission; and the coupling index is sent to a preset combustion parameter solving model, so that the combustion parameter solving model solves combustion parameters with combustion efficiency maximization and pollutant emission minimization as objective functions, and material combustion is controlled according to the solved combustion parameters. The combustion efficiency of comburent is improved.

Description

Technical Field

[0001] This application relates to the technical field of combustion parameter optimization, and particularly to a combustion optimization control system and method based on flame intensity detection. Background Art

[0002] In the field of combustion control of pulverized coal furnaces, the operation mode mainly relies on the manual adjustment by operators based on their long-term accumulated experience. However, the pulverized coal furnace system has the characteristics of numerous equipment and complex structure. Its combustion process involves the interaction of multiple parameters, presenting a complex non-linear relationship. Moreover, due to factors such as large variations in the in-furnace medium, variable load operation, and complex operating parameters, it is difficult for operators to make appropriate decisions in real time relying on experience.

[0003] Therefore, in the patent with the publication number CN117433036A and the name "A Combustion Optimization Control System and Method for Pulverized Coal Furnaces Based on Flame Intensity Detection", a combustion optimization control system and method for pulverized coal furnaces are proposed. This method optimizes combustion parameters, but the optimization effect is limited. Moreover, in the actual operation process, it may also face challenges of various complex working conditions. Therefore, the combustion efficiency of combustibles needs to be improved. Summary of the Invention

[0004] The purpose of this application is to provide a combustion optimization control system and method based on flame intensity detection to solve the problem of low combustion efficiency described in the background art.

[0005] To achieve the above purpose, this application provides the following solutions:

[0006] In the first aspect, this application provides a combustion optimization control system based on flame intensity detection, including an acquisition module for acquiring flame intensity signals of multiple bands of a combustion flame;

[0007] A determination module for determining the combustion efficiency of a combustible based on the flame intensity signal;

[0008] A first sending module for sending the combustion efficiency to a coupling index calculation model so that the coupling index calculation model outputs the coupling index of the combustion efficiency and NO x emission;

[0009] A second sending module for sending the coupling index to a predetermined combustion parameter solving model so that the combustion parameter solving model takes maximizing combustion efficiency and minimizing pollutant emissions as objective functions, solves combustion parameters, and controls the combustion of materials according to the solved combustion parameters.

[0010] Optionally, the acquisition module includes:

[0011] The first receiving sub-module is used to receive the visible light intensity signal of the flame sent by the visible light camera;

[0012] The second receiving sub-module is used to receive the infrared thermal radiation intensity signal of the flame sent by the infrared detector;

[0013] The third receiving sub-module is used to receive the ultraviolet thermal radiation intensity signal of the flame sent by the ultraviolet detector.

[0014] Optionally, the determining module includes:

[0015] The construction sub-module is used to construct an original three-dimensional flame intensity model based on the flame intensity signals of the multiple bands;

[0016] The transformation sub-module is used to perform wavelet packet transformation on the original three-dimensional flame intensity model to obtain a new three-dimensional flame intensity model containing different frequencies;

[0017] The first sending sub-module is used to send the new three-dimensional flame intensity model to the convolutional neural network so that the convolutional neural network outputs the time-varying feature vector of the new three-dimensional flame intensity model;

[0018] The second sending sub-module is used to send the time-varying feature vector to the pre-trained combustion state classifier so that the combustion state classifier outputs the combustion efficiency of the combustible material.

[0019] In a second aspect, the present application provides a combustion optimization control method based on flame intensity detection, including:

[0020] Obtain the flame intensity signals of multiple bands of the combustion flame;

[0021] Determine the combustion efficiency of the combustible based on the flame intensity signal;

[0022] Send the combustion efficiency to the coupling index calculation model so that the coupling index calculation model outputs the coupling index of the combustion efficiency and NO x emission;

[0023] Send the coupling index to a predetermined combustion parameter solving model so that the combustion parameter solving model takes maximizing the combustion efficiency and minimizing the pollutant emission as the objective function, solves the combustion parameters, and controls the material combustion according to the solved combustion parameters.

[0024] Optionally, the obtaining the flame intensity signals of multiple bands of the combustion flame includes:

[0025] Receive the visible light intensity signal of the flame sent by the visible light camera;

[0026] Receive the infrared thermal radiation intensity signal of the flame sent by the infrared detector;

[0027] Receive the flame's ultraviolet thermal radiation intensity signal sent by the ultraviolet detector.

[0028] Optionally, determining the combustion efficiency of the combustion material based on the flame intensity signal includes:

[0029] constructing an original three-dimensional flame intensity model based on the flame intensity signals of the multiple bands;

[0030] Performing wavelet packet transformation on the original three-dimensional flame intensity model to obtain a new three-dimensional flame intensity model containing different frequencies;

[0031] Sending the new three-dimensional flame intensity model to a convolutional neural network so that the convolutional neural network outputs a time-varying feature vector of the new three-dimensional flame intensity model;

[0032] The time-varying feature vector is sent to a pre-trained combustion state classifier, so that the combustion state classifier outputs the combustion efficiency of the combustion material.

[0033] Optionally, the time-varying characteristic vector includes: flame front position, flame brightness gradient distribution and characteristic radiation wavelength.

[0034] Optionally, the predetermined combustion parameter solving model is a multi-objective genetic model, and the coupling index is sent to the predetermined combustion parameter solving model so that the combustion parameter solving model takes maximizing combustion efficiency and minimizing pollutant emissions as objective functions, and solving the combustion parameters is achieved by the following method:

[0035] The coupling index is sent to the multi-objective genetic model, so that the multi-objective genetic model solves the combustion parameters with maximizing combustion efficiency and minimizing pollutant emissions as objective functions.

[0036] Optionally, after sending the coupling index to a predetermined combustion parameter solving model so that the combustion parameter solving model solves the combustion parameters with maximizing combustion efficiency and minimizing pollutant emissions as objective functions, the method further includes:

[0037] The optimized solution set is sent to a non-dominated sorting and crowding distance calculation model, so that the non-dominated sorting and crowding distance calculation model outputs a frontier solution set of the optimized solution set.

[0038] Optionally, after sending the optimized solution set to the non-dominated sorting and crowding distance calculation model so that the non-dominated sorting and crowding distance calculation model outputs a frontier solution set of the optimized solution set, the method further includes:

[0039] Generate control instructions according to the obtained leading-edge solution set, where the control instructions carry the combustion parameters to control the combustion of the combustion material through the combustion parameters.

[0040] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the steps of the method described in any one of the above second aspects.

[0041] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in any one of the above second aspects are implemented.

[0042] In a fifth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the method described in any one of the above second aspects are implemented.

[0043] According to the specific embodiments provided by the present application, the following technical effects are disclosed in the present application:

[0044] The combustion optimization control system based on flame intensity detection provided by the embodiments of the present application obtains flame intensity signals of multiple bands of a combustion flame; determines the combustion efficiency of a combustible based on the flame intensity signals; sends the combustion efficiency to a coupling index calculation model so that the coupling index calculation model outputs a coupling index between the combustion efficiency and NO x emissions; sends the coupling index to a predetermined combustion parameter solution model so that the combustion parameter solution model takes maximizing combustion efficiency and minimizing pollutant emissions as objective functions, solves combustion parameters, and controls the combustion of materials according to the solved combustion parameters. The present application optimizes both the combustion efficiency and pollutant emissions parameters, improving the combustion efficiency of the material. Description of the Drawings

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0046] Figure 1 It is an application environment diagram of a combustion optimization control method based on flame intensity detection in an embodiment of the present application;

[0047] Figure 2 It is a flowchart of a combustion optimization control method based on flame intensity detection provided by an embodiment of the present application;

[0048] Figure 3 Schematic flow chart of a combustion efficiency determination method provided by an embodiment of the present application;

[0049] Figure 4 Schematic flow chart of a combustion optimization control method based on flame intensity detection provided by another embodiment of the present application;

[0050] Figure 5 Schematic structural diagram of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0051] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0052] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0053] The combustion optimization control system and method based on flame intensity detection provided by the embodiments of the present application can be applied to an application environment as shown in Figure 1 The application environment includes a multi-spectral sensor array, a diffraction grating spectroscope group, and a server. Among them, the diffraction grating spectroscope group is used to separate the combustion flame mixed light and separate the mixed light into visible light, near-infrared light, and ultraviolet light.

[0054] Among them, the multi-spectral sensor array is used to receive the separated visible light, near-infrared light, and ultraviolet light, convert the optical signals of the visible light, near-infrared light, and ultraviolet light into respective intensity signals, and send the converted intensity signals to the server.

[0055] The server communicates with the multi-spectral sensor array through the network to receive the intensity signals sent by the multi-spectral sensor array. The data storage system can store the data that the server needs to process. The data storage system can be set separately, integrated on the server, placed in the cloud or on other servers. The terminal can send the intensity signals to be processed to the server. After receiving the intensity signals to be processed, the server can first store the intensity signals and then obtain them from the storage location when processing is required, or the processing task can be executed while storing.

[0056] In addition, the server can also feedback the obtained processing results to the terminal configured with a display.

[0057] Among them, the terminal can be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc.

[0058] The server can be implemented by an independent server or a server cluster composed of multiple servers, and can also be a cloud server.

[0059] In an exemplary embodiment, refer to Figure 2 As shown, a combustion optimization control method based on flame intensity detection is provided. This method is executed by a computer device, and specifically can be executed alone by a computer device such as a server, or jointly executed by a terminal and a server. In the embodiments of the present application, taking this method applied to Figure 1 the server in as an example for illustration, it includes the following steps 201 to step 204:

[0060] Step 201, obtain the flame intensity signals of multiple bands of the combustion flame.

[0061] The combustion flame is mixed light. The mixed light is decomposed into visible light, near-infrared light, and ultraviolet light by a diffraction grating spectroscope group. Then, the corresponding spectrometers are respectively used to obtain the flame intensity signals of the light in the corresponding bands and send them to the server. The server receives and stores the flame intensity signals for timely acquisition when needed.

[0062] Among them, the flame intensity signal is used to reflect the vigorous degree of flame combustion. The stronger the intensity, the more vigorous the combustion.

[0063] Step 202, determine the combustion efficiency of the combustible based on the flame intensity signal.

[0064] Step 203, send the combustion efficiency to the coupling index calculation model so that the coupling index calculation model outputs the coupling index of the combustion efficiency and NO x emission.

[0065] Step 204, send the coupling index to a predetermined combustion parameter solving model so that the combustion parameter solving model takes maximizing the combustion efficiency and minimizing the pollutant emission as the objective function, solves the combustion parameters, and controls the material combustion according to the solved combustion parameters.

[0066] The combustion optimization control method based on flame intensity detection provided by the embodiments of the present application obtains the flame intensity signals of multiple bands of the combustion flame; determines the combustion efficiency of the combustible based on the flame intensity signals; sends the combustion efficiency to the coupling index calculation model so that the coupling index calculation model outputs the coupling index of the combustion efficiency and NO x emissions; sends the coupling index to a predetermined combustion parameter solving model so that the combustion parameter solving model takes maximizing the combustion efficiency and minimizing the pollutant emissions as the objective function, solves the combustion parameters, and controls the material combustion according to the solved combustion parameters. The present application optimizes both the combustion efficiency and the pollutant emissions parameters, and improves the combustion efficiency of the material.

[0067] Optionally, in another exemplary embodiment of the present application, the multiple bands include three bands, namely the visible light band, the infrared light band, and the ultraviolet light band, and the above step 201 is replaced by the following steps 301 to 303:

[0068] Step 301, receive the visible light intensity signal of the flame sent by the visible light camera.

[0069] Step 302, receive the infrared thermal radiation intensity signal of the flame sent by the infrared detector.

[0070] Step 303, receive the ultraviolet thermal radiation intensity signal of the flame sent by the ultraviolet detector.

[0071] Among them, the infrared detector can be an InGaAs infrared detector, and the ultraviolet detector can be a SiC ultraviolet detector. Further, the visible light camera, the infrared detector, and the ultraviolet detector are collectively referred to as a multi-spectral sensor array. The multi-spectral sensor array continuously collects the visible light intensity signal of the flame, which can be a texture image of visible light, the infrared thermal radiation intensity signal, and the ultraviolet radiation intensity signal, at a predetermined sampling frequency, for example, 1000 Hz sampling frequency, during the combustion cycle.

[0072] When obtaining the intensity signal of the flame, each sensor included in the multi-spectral sensor array is synchronously triggered to ensure the temporal unity of the intensity signals of different bands obtained. In addition, when the multi-spectral sensor array obtains the intensity signal of the flame, it is close to the high-temperature area of the flame, but direct contact needs to be avoided.

[0073] Optionally, referring to Figure 3 , in another exemplary embodiment of the present application, the above step 202 is replaced by the following steps 401 to 404:

[0074] Step 401, based on the flame intensity signals of the multiple bands, construct an original three-dimensional flame intensity model by machine learning modeling.

[0075] Step 402: Perform wavelet packet transform on the original three-dimensional flame intensity model to obtain a new three-dimensional flame intensity model containing different frequencies.

[0076] Among them, wavelet packet transform can perform multi-resolution analysis on signals. It decomposes the signal into sub-signals of different frequencies, thereby providing detailed information about the signal at different times and frequencies. After decomposing the original three-dimensional flame intensity model into multiple layers, for example, decomposing it into 5 layers, it means decomposing the signal into multiple levels of details and approximation components to analyze the dynamic characteristics of the flame at different scales. This multi-resolution analysis helps to capture the complex characteristics during the flame combustion process.

[0077] The number of frequency types included in the new three-dimensional flame intensity model is determined by the wavelet packet transform. For example, when the wavelet packet transform decomposes the original signal into 5 layers, the new three-dimensional flame intensity model contains intensity signals of 32 frequencies. By increasing the number of sub-bands, refined analysis of the flame pulsation frequency is achieved.

[0078] Step 403: Send the new three-dimensional flame intensity model to a convolutional neural network so that the convolutional neural network outputs the time-varying feature vector of the new three-dimensional flame intensity model.

[0079] Optionally, the time-varying feature vector includes: flame front position, flame brightness gradient distribution, and characteristic radiation wavelength.

[0080] Furthermore, the flame front position is obtained after the convolutional neural network detects and locates the visible light edge. The flame brightness gradient distribution is obtained by calculating the infrared band using the Sobel operator in the convolutional neural network. The characteristic radiation wavelength is obtained by detecting the characteristic absorption peak at the flame front position in the ultraviolet band spectrum. The time-varying feature vector provides important input information for subsequent combustion efficiency evaluation and optimization control.

[0081] Step 404: Send the time-varying feature vector to a pre-trained combustion state classifier so that the combustion state classifier outputs the combustion state (complete combustion, oxygen-rich combustion, or oxygen-deficient combustion) of the combustion material.

[0082] Optionally, in another exemplary embodiment of the present application, the coupling index in step 203 is the coupling index of combustion efficiency and NO x emission, and the calculation model of this coupling index is the following formula (1):

[0083]

[0084] Among them, is the emission limit of 50 ppm; η is the combustion efficiency; NO Xis the actual nitrogen oxide emission concentration.

[0085] Optionally, in another exemplary embodiment of the present application, the predetermined combustion parameter solving model is a multi-objective genetic model, and step 204 is implemented through the following step 501:

[0086] Step 501: Send the coupling index to the multi-objective genetic model (NSGA-II) so that the multi-objective genetic model takes maximizing combustion efficiency and minimizing pollutant emissions as the objective functions, solves the combustion parameters, and outputs them.

[0087] Among them, the pollutants mainly refer to nitrogen oxides.

[0088] Optionally, referring to Figure 4 , in another exemplary embodiment of the present application, after the step 204, the method further includes the following step 601:

[0089] Step 601: Send the optimization solution set to the non-dominated sorting and crowding distance calculation model so that the non-dominated sorting and crowding distance calculation model outputs the frontier solution set of the optimization solution set.

[0090] Optionally, in another exemplary embodiment of the present application, after the step 601, the method further includes the following step 701:

[0091] Step 701: Generate a control instruction according to the frontier solution set, and the control instruction carries the combustion parameters to control the combustion of the combustion material through the combustion parameters.

[0092] In addition, dynamic reconstruction of the burner is performed through a distributed actuator. The dynamic reconstruction of the distributed actuator is driven by an adaptive control unit through the CAN bus, and the Kalman filter is embedded as an algorithm module. While realizing real-time correction, the Kalman filter is used to perform real-time prediction and correction on the control effect of the combustion of the combustion material to ensure the stability and accuracy of the combustion system. The combustion state equation of the combustion material is:

[0093]

[0094] Among them, is the estimated value of the combustion state vector at the current moment (k), that is, after fusing the current sensor feedback value z k , the optimal estimation of the key physical parameters of the combustion system (including fuel supply, oxidant ratio, combustion chamber pressure, flame pulsation frequency, etc.);; is the predicted value of the combustion state vector at the current moment (k), that is, the prior prediction of the physical parameters at the current moment based only on the state estimate at the previous moment (k - 1) and the system model. H is the observation matrix, which is used to map the state vector to the sensor measurement space; K k is the Kalman gain, z k is the sensor feedback value;

[0095] Furthermore, the method further includes a self - learning mechanism. The process of the self - learning mechanism is as follows: by online real - time updating the weight parameters of the combustion state classifier, the combustion efficiency will also be updated in real - time. Furthermore, the optimization solution set, the frontier solution set, and the control instructions will all be updated accordingly. In addition, each iteration cycle contains at least 3 complete combustion process data samples to ensure the generalization ability of the model.

[0096] The self - learning mechanism includes online parameter transfer learning, specifically including: when it is detected that the combustion condition changes suddenly, for example, when the fuel type is switched from natural gas to hydrogen, through a domain adaptation algorithm, such as the maximum mean discrepancy (MMD) minimization method, the weight parameters of the pre - trained combustion state classifier are transferred to the new condition. The transfer learning process adopts a freeze - fine - tuning strategy: freeze the first 5 - layer feature extraction layers of the bottom layer of the CNN and only fine - tune the parameters of the last 3 - layer classifier of the top layer to ensure that the convergence speed of the model under the new condition is increased by more than 30%.

[0097] In the self - learning mechanism, when the fuel type is switched from natural gas to hydrogen, the domain adaptation algorithm acts on the weight parameters of the pre - trained model. In the way of minimizing the maximum mean discrepancy (MMD), the weight parameters of the pre - trained model are transferred to the new condition. By freezing the first 5 - layer feature extraction layers of the bottom layer of the CNN and only fine - tuning the parameters of the last 3 - layer classifier of the top layer, it is ensured that the convergence speed of the model under the new condition is increased by more than 30%, enabling the model to quickly adapt to the new combustion condition.

[0098] Another embodiment of the present application provides a combustion optimization control system based on flame intensity detection, including an acquisition module for acquiring flame intensity signals of multiple bands of the combustion flame;

[0099] a determination module for determining the combustion efficiency of the combustible based on the flame intensity signal;

[0100] a first sending module for sending the combustion efficiency to a coupling index calculation model so that the coupling index calculation model outputs the coupling index between the combustion efficiency and NO x emission;

[0101] The second sending module is used to send the coupling index to a predetermined combustion parameter solving model, so that the combustion parameter solving model solves the combustion parameters with maximizing combustion efficiency and minimizing pollutant emissions as objective functions, so as to control material combustion according to the solved combustion parameters.

[0102] Optionally, the acquisition module includes:

[0103] The first receiving submodule is used to receive the visible light intensity signal of the flame sent by the visible light camera;

[0104] The second receiving submodule is used to receive the infrared thermal radiation intensity signal of the flame sent by the infrared detector;

[0105] The third receiving submodule is used to receive the ultraviolet thermal radiation intensity signal of the flame sent by the ultraviolet detector.

[0106] Optionally, the determining module includes:

[0107] A construction submodule, configured to construct an original three-dimensional flame intensity model based on the flame intensity signals of the plurality of wavebands;

[0108] a transformation submodule, configured to perform wavelet packet transformation on the original three-dimensional flame intensity model to obtain a new three-dimensional flame intensity model containing different frequencies;

[0109] a first sending submodule, configured to send the new three-dimensional flame intensity model to a convolutional neural network, so that the convolutional neural network outputs a time-varying feature vector of the new three-dimensional flame intensity model;

[0110] The second sending submodule is configured to send the time-varying feature vector to a pre-trained combustion state classifier, so that the combustion state classifier outputs the combustion efficiency of the combustion material.

[0111] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be referred to as Figure 5As shown in the figure. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store relevant data for combustion optimization control based on flame intensity detection. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a combustion optimization control method based on flame intensity detection can be implemented.

[0112] Those skilled in the art can understand that Figure 5 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0113] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the steps in the above method embodiments are implemented.

[0114] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0115] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0116] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0117] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, in each of the embodiments provided in the present application, any reference to a memory, a database, or other media can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAM), magnetoresistive random access memories (MRAM), ferroelectric random access memories (FRAM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memory (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0118] In each of the embodiments provided in the present application, the databases involved can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. In each of the embodiments provided in the present application, the processors involved can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logics, data processing logics based on quantum computing, etc., without limitation.

[0119] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0120] Specific examples are used in this article to elaborate on the principles and implementation manners of the present application. The descriptions of the above embodiments are only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A combustion optimization control system based on flame intensity detection, characterized in that, Comprising: An acquisition module, configured to acquire flame intensity signals of multiple bands of a combustion flame; A determination module, configured to determine the combustion efficiency of a combustible based on the flame intensity signals; The first sending module is configured to send the combustion efficiency to a coupling index calculation model, so that the coupling index calculation model outputs a coupling index between the combustion efficiency and NO x emissions; A second sending module, configured to send the coupling index to a predetermined combustion parameter solving model, so that the combustion parameter solving model uses maximizing combustion efficiency and minimizing pollutant emissions as objective functions to solve combustion parameters, and controls the combustion of materials according to the solved combustion parameters.

2. The combustion optimization control system based on flame intensity detection according to claim 1, characterized in that The acquisition module includes: A first receiving sub-module, configured to receive the visible light intensity signal of the flame sent by a visible light camera; A second receiving sub-module, configured to receive the infrared thermal radiation intensity signal of the flame sent by an infrared detector; A third receiving sub-module, configured to receive the ultraviolet thermal radiation intensity signal of the flame sent by an ultraviolet detector.

3. The combustion optimization control system based on flame intensity detection according to claim 1, characterized in that, The determination module includes: A construction sub-module, configured to construct an original three-dimensional flame intensity model based on the flame intensity signals of the multiple bands; A transformation sub-module, configured to perform wavelet packet transformation on the original three-dimensional flame intensity model to obtain a new three-dimensional flame intensity model containing different frequencies; A first sending sub-module, configured to send the new three-dimensional flame intensity model to a convolutional neural network, so that the convolutional neural network outputs a time-varying feature vector of the new three-dimensional flame intensity model; A second sending sub-module, configured to send the time-varying feature vector to a pre-trained combustion state classifier, so that the combustion state classifier outputs the combustion efficiency of the combustible material.

4. A combustion optimization control method based on flame intensity detection, characterized in that, Comprising: Acquiring flame intensity signals of multiple bands of a combustion flame; Determining the combustion efficiency of a combustible based on the flame intensity signals; Send the combustion efficiency to the coupling index calculation model so that the coupling index calculation model outputs the coupling index of the combustion efficiency and NO x emissions; Sending the coupling index to a predetermined combustion parameter solving model, so that the combustion parameter solving model uses maximizing combustion efficiency and minimizing pollutant emissions as objective functions to solve combustion parameters, and controls the combustion of materials according to the solved combustion parameters.

5. The combustion optimization control method based on flame intensity detection according to claim 4, wherein The acquiring flame intensity signals of multiple bands of a combustion flame includes: Receiving the visible light intensity signal of the flame sent by a visible light camera; Receiving the infrared thermal radiation intensity signal of the flame sent by an infrared detector; Receiving the ultraviolet thermal radiation intensity signal of the flame sent by an ultraviolet detector.

6. The combustion optimization control method based on flame intensity detection according to claim 4, characterized in that The determining the combustion efficiency of a combustible based on the flame intensity signals includes: Constructing an original three-dimensional flame intensity model based on the flame intensity signals of the multiple bands; Performing wavelet packet transformation on the original three-dimensional flame intensity model to obtain a new three-dimensional flame intensity model containing different frequencies; Sending the new three-dimensional flame intensity model to a convolutional neural network, so that the convolutional neural network outputs a time-varying feature vector of the new three-dimensional flame intensity model; Sending the time-varying feature vector to a pre-trained combustion state classifier, so that the combustion state classifier outputs the combustion efficiency of the combustible material.

7. The combustion optimization control method based on flame intensity detection according to claim 6, wherein The time-varying feature vector includes: flame front position, flame brightness gradient distribution, and characteristic radiation wavelength.

8. The combustion optimization control method based on flame intensity detection according to claim 4, characterized in that, The predetermined combustion parameter solving model is a multi-objective genetic model. The step of sending the coupling index to the predetermined combustion parameter solving model enables the combustion parameter solving model to use maximizing combustion efficiency and minimizing pollutant emissions as the objective functions, and the combustion parameters are solved through the following method: Send the coupling index to the multi-objective genetic model, so that the multi-objective genetic model uses maximizing combustion efficiency and minimizing pollutant emissions as the objective functions to solve the combustion parameters.

9. The combustion optimization control method based on flame intensity detection according to claim 4, characterized in that After the step of sending the coupling index to the predetermined combustion parameter solving model to enable the combustion parameter solving model to use maximizing combustion efficiency and minimizing pollutant emissions as the objective functions to solve the combustion parameters, the method further includes: Send the optimized solution set to the non-dominated sorting and crowding distance calculation model, so that the non-dominated sorting and crowding distance calculation model outputs the frontier solution set of the optimized solution set.

10. The combustion optimization control method based on flame intensity detection according to claim 9, wherein, After the step of sending the optimized solution set to the non-dominated sorting and crowding distance calculation model to enable the non-dominated sorting and crowding distance calculation model to output the frontier solution set of the optimized solution set, the method further includes: Generate a control instruction according to the frontier solution set, where the control instruction carries the combustion parameters to control the combustion of the combustion material through the combustion parameters.

Images