Combustion optimization method and device for ammonia-coal mixed combustion boiler, electronic equipment and storage medium

Abstract

The invention discloses a combustion optimization method and device for an ammonia-coal co-combustion boiler, electronic equipment and a storage medium, the method and device are applied to the electronic equipment, and specifically, various parameters of the ammonia-coal co-combustion boiler are obtained, a typical working condition data set is constructed based on the various parameters, and the typical working condition data set comprises a training set and a test set; model training is carried out based on the typical working condition data set, a combustion optimization model is obtained, and the combustion optimization model comprises a boiler efficiency model, a nitrogen oxide prediction model and an optimization model; and real-time operation parameters of the ammonia-coal mixed combustion boiler are input into the combustion optimization model to be processed, optimal operation parameters are obtained, the optimal operation parameters are used as control parameters of the ammonia-coal mixed combustion boiler, and therefore a control system can control the ammonia-coal mixed combustion boiler to operate under the optimal working condition. According to the scheme, mixed ammonia combustion factors are considered on the basis of an original coal-fired boiler, so that optimized operation parameters for the ammonia-coal mixed combustion boiler are obtained, and low-carbon, efficient and environment-friendly operation of the ammonia-coal mixed combustion boiler can be achieved.

Description

Technical Field

[0001] The present application relates to the field of automatic control technology, and more specifically, to a combustion optimization method, device, electronic device, and storage medium for an ammonia-coal co-fired boiler. Background Art

[0002] When coal-fired boilers burn coal, they release a large amount of greenhouse gases, exacerbating climate change. However, given that wind power, photovoltaic power generation, nuclear power, and hydropower cannot fully meet the electricity demand of the national economy, coal cannot be completely replaced in the long term. In order to achieve energy conservation and emission reduction while using coal, further research and improvement on coal-fired boilers are needed.

[0003] Currently, coal-ammonia co-firing is a potential low-carbon combustion technology. By combining the advantages of coal and ammonia, it can achieve lower costs and less pollution emissions. Since coal-ammonia co-firing is realized on the basis of existing coal-fired boilers, where ammonia is added to the original coal, and the original boiler control means are realized based on pure coal combustion, it is necessary to further improve the boiler control means to achieve low-carbon, efficient, and environmentally friendly operation of the ammonia-coal co-fired boiler. Summary of the Invention

[0004] In view of this, the present application provides a combustion optimization method, device, electronic device, and storage medium for an ammonia-coal co-fired boiler, which are used to provide optimized operating parameters for the ammonia-coal co-fired boiler to achieve low-carbon, efficient, and environmentally friendly operation of the ammonia-coal co-fired boiler.

[0005] To achieve the above object, the following solutions are proposed:

[0006] A combustion optimization method for an ammonia-coal co-fired boiler, applied to an electronic device, the combustion optimization method comprising the steps of:

[0007] Obtain various parameters of the ammonia-coal co-fired boiler, and construct a typical operating condition data set based on the various parameters, the typical operating condition data set including a training set and a test set;

[0008] Perform model training based on the typical operating condition data set to obtain a combustion optimization model, the combustion optimization model including a boiler efficiency model, a nitrogen oxide prediction model, and an optimization model;

[0009] Input the real-time operating parameters of the ammonia-coal co-fired boiler into the combustion optimization model for processing to obtain the optimal operating parameters, the optimal operating parameters being used as the control parameters of the ammonia-coal co-fired boiler so that the control system can control the ammonia-coal co-fired boiler to operate under the optimal operating conditions.

[0010] Optionally, obtaining various parameters of the ammonia-coal co-firing boiler and constructing a typical operating condition dataset based on the various parameters, where the typical operating condition dataset includes a training set and a test set, includes the steps:

[0011] Collect key data of the ammonia-coal co-firing boiler under the ammonia injection combustion condition, and through processing and feature extraction of the key data, obtain an operating data typical operating condition dataset. The typical operating condition dataset includes the operating data typical operating condition dataset and a simulation data typical operating condition dataset. The operating data typical operating condition dataset includes a first training set and a first test set. The training set includes the first training set and a second training set. The test set includes the first test set and a second test set;

[0012] Perform simulation calculations on the typical operating conditions through a coal-fired boiler ammonia co-combustion calculation model, and construct the simulation data typical operating condition dataset according to the calculation results. The simulation data typical operating condition dataset includes the second training set and the second test set.

[0013] Optionally, the step of collecting key data of the ammonia-coal co-firing boiler under the ammonia injection combustion condition and obtaining an operating data typical operating condition dataset through processing and feature extraction of the key data includes the steps:

[0014] Obtain the key data of its ammonia injection combustion condition based on the unit DCS system of the ammonia-coal co-firing boiler and the experimental report;

[0015] Sort out a typical operating condition group dataset from the key data;

[0016] Use machine learning algorithms to preprocess and extract features from the typical operating condition group dataset to obtain the operating data typical operating condition dataset.

[0017] Optionally, the step of performing simulation calculations on the typical operating conditions through a coal-fired boiler ammonia co-combustion calculation model and constructing the simulation data typical operating condition dataset according to the calculation results includes the steps:

[0018] Construct the coal-fired boiler ammonia co-combustion calculation model;

[0019] Perform calculations on the typical operating conditions based on the coal-fired boiler ammonia co-combustion calculation model to obtain multiple simulation data under the typical operating conditions;

[0020] And calculate the boiler efficiency under the typical operating conditions according to the boiler heat balance method;

[0021] Use machine learning methods to extract features from the multiple simulation data to obtain the simulation data typical operating condition dataset.

[0022] Optionally, training a model based on the typical operating condition dataset to obtain a combustion optimization model, where the combustion optimization model includes a boiler efficiency model, a nitrogen oxide prediction model, and an optimization model, including the steps of:

[0023] Constructing models based on the training set and a preset algorithm to obtain the boiler efficiency model, the nitrogen oxide prediction model, and the optimization model;

[0024] Testing the boiler efficiency model, the nitrogen oxide prediction model, and the optimization model based on the test set to optimize the models.

[0025] Optionally, constructing models based on the training set and a preset algorithm to obtain the boiler efficiency model, the nitrogen oxide prediction model, and the optimization model, including the steps of:

[0026] Training a model using the random forest algorithm and the training set to obtain the boiler efficiency model;

[0027] Training a long short-term memory neural network model based on the training set to obtain the nitrogen oxide prediction model;

[0028] Training a model using the decomposed multi-objective evolutionary algorithm and the training set to obtain the optimization model.

[0029] Optionally, during the training process of the optimization model, a multi-head attention mechanism is introduced into the optimization model, and the weight vector of the target feature value is dynamically adjusted to better approximate the Pareto optimal solution.

[0030] A combustion optimization device for an ammonia-coal co-fired boiler, applied to an electronic device, the combustion optimization device includes:

[0031] A parameter acquisition module, configured to acquire various parameters of the ammonia-coal co-fired boiler, and construct a typical operating condition dataset based on the various parameters, where the typical operating condition dataset includes a training set and a test set;

[0032] A model training module, configured to train a model based on the typical operating condition dataset to obtain a combustion optimization model, where the combustion optimization model includes a boiler efficiency model, a nitrogen oxide prediction model, and an optimization model;

[0033] A parameter processing module, configured to input the real-time operating parameters of the ammonia-coal co-fired boiler into the combustion optimization model for processing to obtain the optimal operating parameters, and the optimal operating parameters are used as the control parameters of the ammonia-coal co-fired boiler so that the control system can control the ammonia-coal co-fired boiler to operate under optimal conditions.

[0034] An electronic device, the electronic device includes at least one processor and a memory connected to the processor, wherein:

[0035] The memory is used to store computer programs or instructions;

[0036] The processor is used to execute the computer programs or instructions so that the electronic device implements the combustion optimization method as described above.

[0037] A computer-readable storage medium, applied to an electronic device, the storage medium carries one or more computer programs, and the one or more computer programs can be executed by the electronic device, so that the electronic device can implement the combustion optimization method as described above.

[0038] As can be seen from the above technical solutions, the present application discloses a combustion optimization method, device, electronic device and storage medium for an ammonia-coal co-fired boiler. The method and device are applied to an electronic device. Specifically, various parameters of the ammonia-coal co-fired boiler are obtained, and a typical working condition data set is constructed based on the various parameters. The typical working condition data set includes a training set and a test set; model training is performed based on the typical working condition data set to obtain a combustion optimization model. The combustion optimization model includes a boiler efficiency model, a nitrogen oxide prediction model and an optimization model; the real-time operation parameters of the ammonia-coal co-fired boiler are input into the combustion optimization model for processing to obtain the optimal operation parameters, and the optimal operation parameters are used as the control parameters of the ammonia-coal co-fired boiler, so that the control system can control the ammonia-coal co-fired boiler to operate under the optimal working conditions. This solution considers the factors of ammonia co-combustion on the basis of the original coal-fired boiler, so as to obtain the optimized operation parameters that can be used for the ammonia-coal co-fired boiler, and can enable the ammonia-coal co-fired boiler to achieve low-carbon, high-efficiency and environmentally friendly operation. Description of the Drawings

[0039] 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 description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0040] Figure 1 It is the schematic diagram of the combustion optimization method for the ammonia-coal co-fired boiler in the embodiment of the present application;

[0041] Figure 2 It is the flowchart of a combustion optimization method for an ammonia-coal co-fired boiler in the embodiment of the present application;

[0042] Figure 3 It is the block diagram of a combustion optimization device for an ammonia-coal co-fired boiler in the embodiment of the present application;

[0043] Figure 4 It is a block diagram of an electronic device according to an embodiment of the present application. Detailed implementation manners

[0044] 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 making creative efforts belong to the scope of protection of the present application.

[0045] To solve the technical problems provided by the present application, the present application proposes a combustion optimization method for an ammonia-coal co-fired boiler based on hybrid deep learning, which can simultaneously achieve the coordinated optimization of the unit carbon emission reduction ratio, boiler efficiency, and NOx (nitrogen oxides) emissions. This solution is used to calculate the combustion control parameters of the ammonia-coal co-fired unit to obtain the optimal control parameters, specifically as Figure 1 shown. The boiler in the ammonia-coal co-fired unit here is essentially a coal-fired boiler, but ammonia is added to the fuel. The specific content of this combustion optimization method is as follows:

[0046] Figure 2 It is a flowchart of a combustion optimization method for an ammonia-coal co-fired boiler according to an embodiment of the present application.

[0047] As Figure 2 shown, the combustion optimization method provided in this embodiment is applied to an electronic device and is used to optimize the combustion parameters of an ammonia-coal co-fired boiler. This electronic device can be understood as a computer, server, embedded device, or control device of the boiler with data calculation and information processing capabilities. This combustion optimization method specifically includes the following steps:

[0048] S1. Construct a typical working condition data set for model training based on various parameters of the ammonia-coal co-fired boiler.

[0049] That is, by collecting various parameters of the ammonia-coal co-fired boiler and constructing a typical working condition data set for training the model based on various parameters, this typical working condition data set includes a training set A and a test set B. The typical working condition data set in the present application includes a typical working condition data set of operation data and a typical working condition data set of simulation data. Among them, this typical working condition data set of operation data includes a first training set A1 and a first test set B1, and the typical working condition data set of simulation data includes a second training set A2 and a second test set. The first training set A1 and the second training set A2 constitute the training set A, and the first test set B1 and the second test set B2 constitute the test set B. The construction process of this typical working condition data set is as described below:

[0050] On the one hand, a typical working condition data set of operation data including the first training set and the first test set is constructed based on the key parameters of the ammonia-coal co-fired boiler. The specific process is as follows:

[0051] First, obtain the key data of the boiler under the ammonia-coal co-firing condition from the DCS system of the ammonia-coal co-fired boiler and its experimental reports and other materials, including but not limited to the structural parameters, design performance parameters, operation parameters, etc. of the boiler;

[0052] Then, sort out the typical working condition group data set from the above key data;

[0053] Finally, use machine learning methods to perform data preprocessing and feature extraction on the typical working condition group data set, so as to obtain the typical working condition data set of operation data. The typical working condition data set of operation data includes at least multiple parameters arranged in time series, and the parameter values should cover the actual operation condition range of the boiler, and each parameter has no less than 4 values; the number of operation conditions for each parameter group is no less than 10, for example, including 5 different parameters such as load, ammonia mixing ratio, mill operation mode, air distribution mode, and coal quality.

[0054] On the other hand, the typical working condition data set of simulation data is obtained based on simulation calculation. The specific technical means are as follows:

[0055] First, combine numerical simulation calculations to construct a calculation model for ammonia-coal co-combustion in a coal-fired boiler.

[0056] Then, calculate the typical working conditions of the ammonia-coal co-fired boiler based on the calculation model for ammonia-coal co-combustion in a coal-fired boiler to obtain multiple simulation data under typical working conditions, including but not limited to data such as temperature field, velocity field, and NO X field, etc.

[0057] Next, calculate the boiler efficiency under the typical working condition according to the boiler heat balance method.

[0058] Finally, use machine learning methods to perform feature extraction on multiple simulation data to obtain the typical working condition data set of simulation data.

[0059] S2. Perform model training based on the above typical working condition data set to obtain a combustion optimization model.

[0060] The combustion optimization model in this application includes a boiler efficiency model, a nitrogen oxide prediction model, and an optimization model. The specific training process is as follows:

[0061] First, perform model training based on the training set and a preset algorithm, so as to obtain the boiler efficiency model, the nitrogen oxide prediction model, and the optimization model. The optimization model uses a machine learning algorithm, with the carbon emission reduction ratio, boiler efficiency, and NOx emission value as the target values, to obtain the optimal operation parameters of the boiler. The specific training means include the following:

[0062] A boiler efficiency model is constructed using the random forest method, with the carbon content in the slag measured at the measuring points as the input. Further, the measured value of CO in the flue gas at the tail of the furnace is used as a post-processing step to fine-tune the boiler efficiency model, achieving a boiler efficiency error within 5%.

[0063] Parameters such as load, ammonia mixing ratio, mill operation mode, air distribution mode, coal quality parameters, oxygen content, and NOx value at the furnace outlet in the operation history dataset A1 are used as input quantities to form a time series dataset. A boiler NOx prediction model based on the LSTM long short-term memory neural network is constructed, and the model parameters are fine-tuned using the simulation dataset A2, ultimately achieving a boiler NOx prediction error within 5%.

[0064] Based on the decomposition-based multi-objective evolutionary algorithm (MOEA / D), a dataset A is used to construct an optimization model. A multi-head attention mechanism is introduced into the optimization model to dynamically adjust the weight vector of the target feature values, so as to better approximate the Pareto optimal solution.

[0065] Among them, dynamically adjusting the weight vector of the target feature values includes: performing global average pooling on the boiler carbon reduction ratio, boiler efficiency, and NOx emission value, extracting features and calculating the importance coefficients αco2, η, and βNOx; weighting the target feature values according to the importance coefficients. Specifically, an attention mechanism is introduced to adjust the importance coefficient of the boiler carbon reduction ratio to be greater than the importance coefficients of the boiler efficiency and NOx emission value, that is, αco2≥η and αco2≥βNOx; learning the importance coefficients through a fully connected layer to obtain the weight vector; superimposing the weight vector on the initial target value, and the finally optimized best operation strategy is output as the best operation parameters that can achieve the ammonia mixing ratio of the boiler under the current load.

[0066] The ammonia-coal co-firing boiler in this application includes, but is not limited to, tangentially fired boilers, wall-mounted swirl boilers, etc.

[0067] Then, the boiler efficiency model, nitrogen oxide prediction model, and optimization model are tested using the test set B to achieve the preset accuracy, for example, controlling their errors within 5%.

[0068] S3. Use the combustion optimization model to process the real-time operation parameters to obtain the best operation parameters.

[0069] That is, input the real-time operation parameters of the ammonia-coal co-firing boiler into the combustion optimization model. Through the processing of the real-time operation parameters by the combustion optimization model, the best operation parameters suitable for the operation of this boiler are obtained. During the operation of the boiler, these best operation parameters can be configured in the control system of the boiler, enabling the boiler to operate under the optimal working conditions.

[0070] The above real-time operating parameters include, but are not limited to, the load parameter of the ammonia-coal co-firing boiler, the ammonia blending ratio, the grinding operation mode, the air distribution mode, the coal quality parameter, etc.

[0071] As can be seen from the above technical solution, this embodiment provides a combustion optimization method for an ammonia-coal co-firing boiler. This method is applied to an electronic device, specifically to obtain various parameters of the ammonia-coal co-firing boiler, and construct a typical operating condition data set based on the various parameters. The typical operating condition data set includes a training set and a test set; perform model training based on the typical operating condition data set to obtain a combustion optimization model, and the combustion optimization model includes a boiler efficiency model, a nitrogen oxide prediction model, and an optimization model; input the real-time operating parameters of the ammonia-coal co-firing boiler into the combustion optimization model for processing to obtain the optimal operating parameters, and the optimal operating parameters are used as the control parameters of the ammonia-coal co-firing boiler so that the control system can control the ammonia-coal co-firing boiler to operate under the optimal conditions. This solution considers the ammonia co-combustion factor on the basis of the original coal-fired boiler, so as to obtain the optimized operating parameters that can be used for the ammonia-coal co-firing boiler, and enable the ammonia-coal co-firing boiler to achieve low-carbon, high-efficiency, and environmentally friendly operation.

[0072] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0073] Although the operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in a sequential order. In certain circumstances, multitasking and parallel processing may be advantageous.

[0074] It should be understood that the various steps recorded in the method embodiments of the present disclosure can be executed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.

[0075] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the C language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer.

[0076] Figure 3 It is a block diagram of a combustion optimization device for an ammonia-coal co-fired boiler according to an embodiment of the present application.

[0077] As Figure 3 shown, the combustion optimization device provided in this embodiment is applied to an electronic device and is used to optimize the combustion parameters of an ammonia-coal co-fired boiler. The electronic device can be understood as a computer, server, embedded device or a control device of the boiler with data calculation capabilities and information processing capabilities. The combustion optimization device specifically includes a parameter acquisition module 10, a model training module 20, and a parameter processing module 30.

[0078] The parameter acquisition module is used to construct a typical working condition data set for model training based on various parameters of the ammonia-coal co-fired boiler.

[0079] That is, by collecting various parameters of the ammonia-coal co-fired boiler and constructing a typical working condition data set for training the model based on various parameters, the typical working condition data set includes a training set A and a test set B. The typical working condition data set in the present application includes an operating data typical working condition data set and a simulation data typical working condition data set. Among them, the operating data typical working condition data set includes a first training set A1 and a first test set B1, and the simulation data typical working condition data set includes a second training set A2 and a second test set. The first training set A1 and the second training set A2 constitute the training set A, and the first test set B1 and the second test set B2 constitute the test set B. The construction process of the typical working condition data set itself is as follows:

[0080] On the one hand, construct the operating data typical working condition data set including the first training set and the first test set based on the key parameters of the ammonia-coal co-fired boiler. The specific process is as follows:

[0081] First, obtain the key data of the boiler under the ammonia-coal co-firing condition from the DCS system of the ammonia-coal co-firing boiler and its experimental reports, including but not limited to the structural parameters, design performance parameters, operation parameters, etc. of the boiler;

[0082] Then, sort out the data set of typical working condition groups from the above key data;

[0083] Finally, use machine learning methods to preprocess and extract features from the data set of typical working condition groups, so as to obtain the data set of typical working conditions of the operation data. The data set of typical working conditions of the operation data includes at least 5 different parameters such as load, ammonia mixing ratio, mill operation mode, air distribution mode, and coal quality.

[0084] On the other hand, obtain the data set of typical working conditions of the simulation data based on simulation calculations. The specific technical means are as follows:

[0085] First, combine numerical simulation calculations to construct a calculation model for ammonia-coal co-firing in a coal-fired boiler.

[0086] Then, calculate the typical working conditions of the ammonia-coal co-firing boiler based on the calculation model for ammonia-coal co-firing in a coal-fired boiler to obtain multiple simulation data under typical working conditions, including but not limited to data such as temperature field, velocity field, and NO X field, etc.

[0087] Next, calculate the boiler efficiency under the typical working conditions according to the boiler heat balance method.

[0088] Finally, use machine learning methods to extract features from multiple simulation data to obtain the data set of typical working conditions of the simulation data.

[0089] The model training module is used to train the model based on the above data set of typical working conditions to obtain a combustion optimization model.

[0090] The combustion optimization model in this application includes a boiler efficiency model, a nitrogen oxide prediction model, and an optimization model. The specific training process is as follows:

[0091] First, train the model based on the training set and a preset algorithm to obtain the boiler efficiency model, the nitrogen oxide prediction model, and the optimization model. The optimization model uses machine learning algorithms and takes the carbon emission reduction ratio, boiler efficiency, and NOx emission value as target values to obtain the best operation parameters of the boiler. The specific training means include the following:

[0092] Use the random forest method to construct a boiler efficiency model, use the measured carbon content in the slag measured by the measuring point as the input, and further use the measured value of CO in the flue gas at the tail of the furnace as a post-processing step to fine-tune the boiler efficiency model to achieve a boiler efficiency error within 5%.

[0093] Parameters such as load, ammonia blending ratio, mill operation mode, air distribution mode, coal quality parameters, oxygen content, and furnace outlet NOx value in the operation history dataset A1 are used as input quantities to form a time series dataset. A boiler NOx prediction model based on the LSTM long short-term memory neural network is constructed, and the model parameters are fine-tuned with the simulation dataset A2. Finally, the boiler NOx prediction error is achieved within 5%.

[0094] The decomposition-based multi-objective evolutionary algorithm (MOEA / D) uses the dataset A to construct an optimization model, and a multi-head attention mechanism is introduced into the optimization model to dynamically adjust the weight vector of the target feature values to better approximate the Pareto optimal solution.

[0095] Among them, dynamically adjusting the weight vector of the target feature values includes: performing global average pooling on the boiler carbon reduction ratio, boiler efficiency, and NOx emission value, extracting features and calculating the importance coefficients αco2, η, and βNOx; weighting the target feature values according to the importance coefficients. Specifically, the attention mechanism is introduced to adjust the importance coefficient of the boiler carbon reduction ratio to be greater than the importance coefficients of the boiler efficiency and NOx emission value, that is, αco2≥η and αco2≥βNOx; learning the importance coefficients through the fully connected layer to obtain the weight vector; superimposing the weight vector on the initial target value, and the finally optimized best operation strategy is output as the best operation parameters that can achieve the ammonia blending ratio of the boiler under the current load.

[0096] The ammonia-coal co-firing boiler in this application includes, but is not limited to, tangentially fired boilers, wall-fired swirl boilers, etc.

[0097] Then, the boiler efficiency model, nitrogen oxide prediction model, and optimization model are tested with the test set B to achieve the preset accuracy, for example, controlling their errors within 5%.

[0098] The parameter processing module is used to process the real-time operation parameters by using the combustion optimization model to obtain the best operation parameters.

[0099] That is, the real-time operation parameters of the ammonia-coal co-firing boiler are input into the combustion optimization model, and through the processing of the real-time operation parameters by the combustion optimization model, the best operation parameters suitable for the operation of this boiler are obtained. During the operation of the boiler, this best operation parameter can be configured in the control system of this boiler, and the boiler can operate under the optimal working conditions.

[0100] The above-mentioned real-time operation parameters include, but are not limited to, the load parameters, ammonia blending ratio, mill operation mode, air distribution mode, and coal quality parameters of this ammonia-coal co-firing boiler.

[0101] As can be seen from the above technical solution, this embodiment provides a combustion optimization device for an ammonia-coal co-fired boiler. This device is applied to an electronic device, specifically to obtain various parameters of the ammonia-coal co-fired boiler, and construct a typical working condition data set based on the various parameters. The typical working condition data set includes a training set and a test set; perform model training based on the typical working condition data set to obtain a combustion optimization model, and the combustion optimization model includes a boiler efficiency model, a nitrogen oxide prediction model, and an optimization model; input the real-time operation parameters of the ammonia-coal co-fired boiler into the combustion optimization model for processing to obtain the optimal operation parameters, and the optimal operation parameters are used as the control parameters of the ammonia-coal co-fired boiler so that the control system can control the ammonia-coal co-fired boiler to operate under the optimal working conditions. This solution takes into account the factors of ammonia co-combustion on the basis of the original coal-fired boiler, so as to obtain the optimized operation parameters that can be used for the ammonia-coal co-fired boiler, and enable the ammonia-coal co-fired boiler to achieve low-carbon, high-efficiency, and environmentally friendly operation.

[0102] The units involved in the embodiments described in the present disclosure can be implemented in software or in hardware. Among them, the name of the unit does not constitute a limitation to the unit itself in some cases. For example, the first acquisition unit can also be described as "the unit for acquiring at least two Internet protocol addresses".

[0103] The functions described above in this article can be at least partially executed by one or more hardware logic components. For example, without limitation, the exemplary types of hardware logic components that can be used include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Product (ASSP), System on Chip (SOC), Complex Programmable Logic Device (CPLD), and so on.

[0104] Figure 4 It is a block diagram of an electronic device according to an embodiment of the present application.

[0105] Next, refer to Figure 4 , which shows a schematic structural diagram of an electronic device suitable for implementing the embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. This electronic device is only an example and should not bring any limitations to the functions and usage scopes of the embodiments of the present disclosure.

[0106] An electronic device may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory ROM 402 or a program loaded from an input device 406 into a random access memory RAM 403. In the RAM, various programs and data required for the operation of the electronic device are also stored. The processing device, the ROM, and the RAM are connected to each other through a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0107] Generally, the following devices may be connected to the I / O interface: input devices including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 408 including, for example, magnetic tapes, hard disks, etc.; and a communication device 409. The communication device 409 may allow the electronic device to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows an electronic device with various devices, it should be understood that it is not required to implement or have all the shown devices. More or fewer devices may be implemented or had alternatively.

[0108] This embodiment also provides an embodiment of a computer-readable storage medium.

[0109] The above computer-readable storage medium is applied to an electronic device and carries one or more computer programs. When the above one or more computer programs are executed by the electronic device, the electronic device is caused to: A combustion optimization method for an ammonia-coal co-fired boiler, which is applied to an electronic device. Specifically, various parameters of the ammonia-coal co-fired boiler are obtained, and a typical operating condition data set is constructed based on the various parameters. The typical operating condition data set includes a training set and a test set; model training is performed based on the typical operating condition data set to obtain a combustion optimization model, and the combustion optimization model includes a boiler efficiency model, a nitrogen oxide prediction model, and an optimization model; the real-time operating parameters of the ammonia-coal co-fired boiler are input into the combustion optimization model for processing to obtain the optimal operating parameters, and the optimal operating parameters are used as the control parameters for the ammonia-coal co-fired boiler so that the control system can control the ammonia-coal co-fired boiler to operate under the optimal operating conditions. This solution considers the ammonia co-combustion factor on the basis of the original coal-fired boiler, so as to obtain the optimized operating parameters that can be used for the ammonia-coal co-fired boiler, and can enable the ammonia-coal co-fired boiler to achieve low-carbon, high-efficiency, and environmentally friendly operation.

[0110] It should be noted that the computer-readable medium described above in the present disclosure may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. 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 of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0111] In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. And in the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0112] Each embodiment in this specification is described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the embodiments, reference may be made to each other.

[0113] Although the preferred embodiments of the embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they know the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0114] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or terminal device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising said element.

[0115] The technical solutions provided by the present invention have been introduced in detail above. Specific examples are used in this text to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A combustion optimization method for an ammonia-coal co-fired boiler, applied to an electronic device, characterized in that The combustion optimization method includes the steps of: Obtaining various parameters of the ammonia-coal co-firing boiler and constructing a typical operating condition data set based on the various parameters, where the typical operating condition data set includes a training set and a test set; Performing model training based on the typical operating condition data set to obtain a combustion optimization model, where the combustion optimization model includes a boiler efficiency model, a nitrogen oxide prediction model, and an optimization model; Inputting the real-time operating parameters of the ammonia-coal co-firing boiler into the combustion optimization model for processing to obtain the optimal operating parameters, and the optimal operating parameters are used as the control parameters of the ammonia-coal co-firing boiler so that the control system can control the ammonia-coal co-firing boiler to operate under the optimal operating conditions.

2. The combustion optimization method according to claim 1, wherein, The step of obtaining various parameters of the ammonia-coal co-firing boiler and constructing a typical operating condition data set based on the various parameters, where the typical operating condition data set includes a training set and a test set, includes the steps of: Collecting key data of the ammonia injection combustion condition of the ammonia-coal co-firing boiler, and through processing and feature extraction of the key data, obtaining an operating data typical operating condition data set, where the typical operating condition data set includes the operating data typical operating condition data set and a simulation data typical operating condition data set, the operating data typical operating condition data set includes a first training set and a first test set, the training set includes the first training set and a second training set, and the test set includes the first test set and a second test set; Performing simulation calculations on the typical operating conditions through a coal-fired boiler ammonia mixing combustion calculation model, and constructing the simulation data typical operating condition data set according to the calculation results, where the simulation data typical operating condition data set includes the second training set and the second test set.

3. The combustion optimization method according to claim 2, wherein The step of collecting key data of the ammonia injection combustion condition of the ammonia-coal co-firing boiler and obtaining an operating data typical operating condition data set through processing and feature extraction of the key data includes the steps of: Obtaining the key data of its ammonia injection combustion condition based on the unit DCS system of the ammonia-coal co-firing boiler and the experimental report; Sorting out a typical operating condition group data set from the key data; Using a machine learning algorithm to perform preprocessing and feature extraction on the typical operating condition group data set to obtain the operating data typical operating condition data set.

4. The combustion optimization method according to claim 2, wherein, The step of performing simulation calculations on the typical operating conditions through a coal-fired boiler ammonia mixing combustion calculation model and constructing the simulation data typical operating condition data set according to the calculation results includes the steps of: Constructing the coal-fired boiler ammonia mixing combustion calculation model; Performing calculations on the typical operating conditions based on the coal-fired boiler ammonia mixing combustion calculation model to obtain multiple simulation data under the typical operating conditions; And calculating the boiler efficiency under the typical operating conditions according to the boiler heat balance method; Using a machine learning method to perform feature extraction on the multiple simulation data to obtain the simulation data typical operating condition data set.

5. The combustion optimization method according to claim 1, wherein The step of performing model training based on the typical operating condition data set to obtain a combustion optimization model, where the combustion optimization model includes a boiler efficiency model, a nitrogen oxide prediction model, and an optimization model, includes the steps of: Performing model construction based on the training set and a preset algorithm to obtain the boiler efficiency model, the nitrogen oxide prediction model, and the optimization model; Test the boiler efficiency model, the nitrogen oxide prediction model, and the optimization model based on the test set to optimize the models.

6. The combustion optimization method according to claim 5, characterized in that, The model construction based on the training set and a preset algorithm to obtain the boiler efficiency model, the nitrogen oxide prediction model, and the optimization model includes the steps of: Use the random forest algorithm and the training set to train the model to obtain the boiler efficiency model; Train the long short-term memory neural network based on the training set to obtain the nitrogen oxide prediction model; Use the decomposed multi-objective evolutionary algorithm and the training set to train the model to obtain the optimization model.

7. The combustion optimization method according to claim 6, characterized in that, During the training of the optimization model, introduce a multi-head attention mechanism into the optimization model and dynamically adjust the weight vector of the target feature value to better approximate the Pareto optimal solution.

8. A combustion optimization device for an ammonia-coal co-fired boiler, applied to electronic equipment, characterized in that, The combustion optimization device includes: A parameter acquisition module configured to acquire various parameters of the ammonia-coal co-firing boiler and construct a typical working condition data set based on the various parameters. The typical working condition data set includes a training set and a test set; A model training module configured to train a model based on the typical working condition data set to obtain a combustion optimization model. The combustion optimization model includes a boiler efficiency model, a nitrogen oxide prediction model, and an optimization model; A parameter processing module configured to input the real-time operating parameters of the ammonia-coal co-firing boiler into the combustion optimization model for processing to obtain the optimal operating parameters. The optimal operating parameters are used as the control parameters of the ammonia-coal co-firing boiler so that the control system can control the ammonia-coal co-firing boiler to operate under the optimal working conditions.

9. An electronic device, characterized in that, The electronic device includes at least one processor and a memory connected to the processor, where: The memory is used to store computer programs or instructions; The processor is used to execute the computer programs or instructions so that the electronic device implements the combustion optimization method according to any one of claims 1 to 7.

10. A computer-readable storage medium, applied to an electronic device, characterized in that, The storage medium carries one or more computer programs that can be executed by the electronic device, so that the electronic device can implement the combustion optimization method according to any one of claims 1 to 7.

Images