Gas turbine natural gas hydrogen-doped combustion optimization method and system

Abstract

The invention discloses a natural gas hydrogen-doped combustion optimization method and system for a gas turbine, and the method comprises the steps: obtaining combustion state parameters of a mixed fuel under different mixing proportions under an experimental condition, the combustion state parameters comprising combustion characteristic data and emission characteristic data; establishing a numerical calculation model for describing the combustion process and emission characteristics of the mixed fuel on the basis of combustion science and fluid mechanics, and performing numerical simulation on the mixed fuel in different mixing proportions by adopting the numerical calculation model to obtain combustion state parameters of the mixed fuel; comparing and analyzing the combustion state parameters obtained by the experiment and the combustion state parameters obtained by the numerical simulation, and optimizing the numerical calculation model according to the analysis result; expanding the mixing proportion of the mixed fuel, and performing numerical simulation on the expanded mixed fuel by adopting the optimized numerical calculation model to obtain combustion state parameters of the mixed fuel and construct a training data set; and adopting the training data set to train the machine learning model, and adopting the trained machine learning model to predict the mixing proportion of the mixed fuel. According to the method, by updating a numerical calculation model and a machine learning model, optimal prediction under different fuel and combustion conditions can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of gas turbine combustion, and in particular to a method and system for optimizing natural gas hydrogen-blended combustion in a gas turbine. Background Art

[0002] As the global demand for clean energy and low-carbon emission technologies grows, gas turbines, as efficient energy conversion devices, play an important role in the fields of electricity, industry, and transportation. In order to further improve the energy efficiency of gas turbines and reduce environmental pollution, the use of hydrogen as a blending component of natural gas fuel has become a hot topic in current research. However, blending hydrogen into natural gas for gas turbine combustion has potential advantages such as improving combustion efficiency and reducing carbon emissions.

[0003] As a high-energy-density fuel, hydrogen has a much higher diffusion coefficient and flame speed than natural gas. As the hydrogen blending ratio increases, the flame front may move quickly and become unstable, causing the flame in the combustion chamber to fluctuate or flame out. This instability reduces combustion efficiency and may cause thermal stress shock to the combustion chamber components, which may not only damage the combustion chamber components, but also cause safety accidents, posing a serious threat to the stable operation of the gas turbine. In addition, the adiabatic flame temperature produced by hydrogen combustion is significantly higher than that of natural gas. Excessive combustion temperature leads to high-temperature corrosion and damage of materials in the combustion chamber, and may also promote the generation of harmful substances such as nitrogen oxides (NOx). NOx, as a major atmospheric pollutant, has adverse effects on the environment and human health.

[0004] In summary, although the gas turbine natural gas hydrogen-blended combustion technology has great development potential, it also faces many challenges such as unstable combustion and nitrogen oxide emissions. Therefore, how to optimize the blending ratio of hydrogen and natural gas to improve the stability and economy of gas turbine hydrogen-blended combustion is an urgent problem to be solved. Summary of the invention

[0005] In view of the problems existing in the prior art, the present invention provides a method and system for optimizing natural gas hydrogen-blended combustion in a gas turbine, which optimizes and controls the blending ratio of natural gas and hydrogen to achieve stability of hydrogen-blended combustion in a gas turbine.

[0006] The present invention is achieved through the following technical solutions: A method for optimizing the combustion of natural gas mixed with hydrogen in a gas turbine comprises the following steps: Step 1, obtaining combustion state parameters of mixed fuels at different blending ratios under experimental conditions, the combustion state parameters including combustion characteristic data and emission characteristic data; Step 2: Based on combustion science and fluid mechanics, a numerical calculation model is established to describe the combustion process and emission characteristics of the mixed fuel. The numerical calculation model is used to perform numerical simulation on the mixed fuel at different blending ratios to obtain the combustion state parameters of the mixed fuel. Step 3: Compare and analyze the combustion state parameters obtained by the experiment and the combustion state parameters obtained by the numerical simulation, and optimize the numerical calculation model according to the analysis results; Step 4: Expand the blending ratio of the mixed fuel, use the optimized numerical calculation model to perform numerical simulation on the expanded mixed fuel, obtain the combustion state parameters of the mixed fuel and construct a training data set; Step 5: Use the training data set to train the machine learning model, and use the trained machine learning model to predict the blending ratio of the mixed fuel.

[0007] Preferably, the combustion characteristics include combustion pressure, combustion speed and combustion temperature, and the emission characteristics include the emission of pollutants such as NOx and CO.

[0008] Preferably, the method for constructing the numerical calculation model in step 2 is as follows: Construct a geometric model with the same structure as the experimental device and discretize it into a grid, set the grid type and density; construct a fluid model and set the physical properties of the fluid according to the experimental conditions and fluid characteristics, set the boundary conditions of the fluid according to the experimental data, and obtain a numerical calculation model.

[0009] Preferably, the numerical calculation model optimization method in step 3 is as follows: Compare the combustion emission data obtained from the experiment with the combustion emission data obtained from the numerical simulation to obtain the data with differences, optimize the numerical calculation model according to the difference data, adjust the boundary conditions and grid parameters of the numerical calculation model, and repeat step 2 until the simulation data is consistent with the experimental data.

[0010] Preferably, the training data set includes blending ratios under different operating conditions, and corresponding combustion characteristics and emission characteristics.

[0011] Preferably, the machine learning model includes a linear regression model, a random forest model and a neural network model.

[0012] Preferably, the training method of the neural network model is as follows: The training data set is preprocessed to construct a convolutional neural network. The training data is input into the convolutional neural network and propagated forward layer by layer to calculate the output of each layer. The loss function is used to measure the difference between the model prediction result and the true label. When the actual output obtained by the forward propagation does not meet the expected result, the error between the actual output and the expected output is calculated, and the error is back-propagated from the output layer to the input layer. During the back-propagation process, the gradient of the loss function for each parameter is calculated, and the network parameters are updated using the optimization algorithm according to the gradient to reduce the value of the loss function. Through iterative training, until the preset number of iterations is reached or the loss function value reaches the threshold, a prediction model for the blending ratio of the mixed fuel is obtained.

[0013] A gas turbine natural gas hydrogen blended combustion optimization system, comprising: The first acquisition module is used to obtain the combustion state parameters of the mixed fuel under different blending ratios under experimental conditions, and the combustion state parameters include combustion characteristic data and emission characteristic data; The second acquisition module is used to establish a numerical calculation model that describes the combustion process and emission characteristics of the mixed fuel based on combustion science and fluid mechanics, and is used to use the numerical calculation model to numerically simulate the mixed fuel at different blending ratios to obtain the combustion state parameters of the mixed fuel; Model optimization module, used to compare and analyze the combustion state parameters obtained by experiments and those obtained by numerical simulation, and optimize the numerical calculation model according to the analysis results; The third acquisition module is used to expand the blending ratio of the mixed fuel, use the optimized numerical calculation model to perform numerical simulation on the expanded mixed fuel, obtain the combustion state parameters of the mixed fuel and construct a training data set; The training module is used to train the machine learning model using the training data set, and use the trained machine learning model to predict the blending ratio of the mixed fuel.

[0014] An electronic device, comprising: Memory for storing computer programs; A processor is used to implement the steps of the gas turbine natural gas hydrogen blended combustion optimization method when executing the computer program.

[0015] A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the gas turbine natural gas hydrogen-blended combustion optimization method are implemented.

[0016] Compared with the prior art, the present invention has the following beneficial technical effects: The invention provides a method for optimizing the combustion of natural gas mixed with hydrogen in a gas turbine. The method improves the reliability and accuracy of the experimental data by performing repeated experiments on a test bench and calculating the average value and standard deviation. Then, the experimental process is simulated by numerical simulation software such as computational fluid dynamics (CFD). By comparing the experimental data and the numerical simulation results, the numerical calculation model is iteratively optimized to improve the accuracy and applicability of the numerical calculation model. Finally, a machine learning model is used to predict the blending ratio of the mixed fuel, which makes full use of the advantages of the machine learning model in dealing with complex nonlinear problems. The neural network model can automatically learn the features in the data and continuously optimize the prediction performance through iterative training, thereby realizing accurate prediction of the blending ratio of the mixed fuel under combustion conditions. The method can realize optimized prediction under different fuels and combustion conditions by updating the numerical calculation model and the machine learning model. The technical solution combines the advantages of experiments, numerical simulations and machine learning, and reduces the cost and limitations of a single method. By reducing the number of experiments and the complexity of numerical simulations, the overall research cost and time cost are reduced.

[0017] The present application provides a method for optimizing the combustion of natural gas with hydrogen in a gas turbine, an electronic device, and a computer-readable storage medium, all of which have all the advantages of the above-mentioned method for optimizing the combustion of natural gas with hydrogen in a gas turbine. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The present invention is a flow chart of a method for optimizing natural gas hydrogen-blended combustion in a gas turbine. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0020] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0021] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0022] In the description of the embodiments of the present application, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the drawings, or the orientation or position relationship in which the invented product is usually placed when used. It is only for the convenience of describing the present application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0023] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0024] In the description of the embodiments of the present application, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0025] A method for optimizing the combustion of natural gas mixed with hydrogen in a gas turbine comprises the following steps: Step 1, obtaining the combustion characteristics and emission characteristics of the mixed fuel at different blending ratios under experimental conditions; On the combustion test bench, experiments were conducted one by one on the set blending ratios of hydrogen and natural gas, and the combustion characteristics (such as combustion pressure, combustion speed, combustion temperature, etc.) and emission characteristics (such as emissions of pollutants such as NOx and CO) under different blending ratios were recorded. In order to improve the reliability and accuracy of the data, the experiments were repeated multiple times for each blending ratio, and the average value and standard deviation were calculated.

[0026] Step 2: Based on combustion science and fluid mechanics, a numerical calculation model is established to describe the combustion process and emission characteristics of the mixed fuel. The numerical calculation model is used to perform numerical simulations on the mixed fuels at different blending ratios to obtain the combustion characteristics and emission characteristics of each mixed fuel.

[0027] During the simulation process, numerical simulation software such as computational fluid dynamics (CFD) is used to numerically simulate the experimental process to verify the rationality and accuracy of the experimental results.

[0028] The construction method of the numerical calculation model is as follows: Use the built-in geometric modeling tools of CAD software or CFD software to create or import the geometric model of the experimental device, and ensure that the model is consistent with the experimental device in terms of geometric size and shape. Discretize the geometric model into a grid. The quality and quantity of the grid have a great impact on the accuracy of the simulation results. Select the appropriate grid type and density according to the simulation requirements, and verify the grid independence. Select a fluid model, such as a turbulence model, a multiphase flow model, etc. Set the physical properties of the fluid according to the experimental conditions and fluid characteristics. Set the boundary conditions such as the inlet, outlet, and wall of the fluid according to the experimental data. Ensure that the boundary conditions are consistent with the experimental conditions to accurately simulate the experimental process, set the solution parameters, including the time step, number of iterations, convergence criteria, etc., and obtain the numerical calculation model.

[0029] Step 3: Compare and analyze the combustion characteristics and emission characteristics obtained from the experiment in step 1 with the combustion characteristics and emission characteristics obtained from the numerical simulation in step 2, and optimize the numerical calculation model according to the analysis results to improve the accuracy of the numerical calculation model simulation.

[0030] Determine the variables that are strongly correlated with the combustion characteristics and emission characteristics, including combustion rate, pressure and temperature, and emissions of carbon monoxide, nitrogen oxides, particulate matter, etc. The combustion characteristics and emission characteristics obtained from the experiment are taken as target values, and the combustion characteristics and emission characteristics obtained from numerical simulation are taken as reference values. Compare the variables that are strongly correlated with the combustion characteristics and emission characteristics obtained from the experiment with those obtained from the numerical simulation in step 2, obtain data with differences, adjust the optimization of the numerical calculation model according to the difference data, adjust the boundary conditions and grid parameters of the numerical calculation model, and repeat step 2 until the model data is consistent with the experimental data.

[0031] Step 4: Expand the blending ratio of the mixed fuel, use the updated numerical calculation model to perform numerical simulation on the expanded mixed fuel, and obtain the combustion characteristics and emission characteristics of the corresponding mixed fuel.

[0032] Step 5: Obtain the combustion characteristics and emission characteristics of the mixed fuel obtained in step 4 to construct a training data set, where the training data set includes the blending ratio, and strongly correlated variables corresponding to the combustion characteristics and emission characteristics.

[0033] Step 6: Use the training data set to train the machine learning model, and use the trained machine learning model to predict the corresponding mixed fuel blending ratio of the combustion condition.

[0034] The models are linear regression models, random forest models and neural network models. For problems with complex and nonlinear characteristics of the combustion process, the neural network model can often achieve better prediction results due to its powerful nonlinear mapping ability and self-learning ability. The neural network model is preferably used, including multi-layer perceptron neural network, convolutional neural network, recurrent neural network, LSTM model, deep neural network The following takes the convolutional neural network model as an example to explain the training process in detail.

[0035] Set the network parameters of the convolutional neural network model, such as the number of RNN layers, the number of neurons in each layer, and the activation function.

[0036] The training data set is preprocessed, including cleaning the data by removing missing values, filling missing values, and removing duplicate data, and then enhancing the cleaned data, and finally normalizing the data to obtain the preprocessed training data set.

[0037] Design the structure of the convolutional neural network, including convolutional layers, pooling layers, and fully connected layers. The convolutional layer is used to extract local features of the data, the pooling layer is used to reduce the spatial dimension of the feature map, and the fully connected layer is used to integrate and classify the extracted features.

[0038] The training data is input into the convolutional neural network and propagated forward layer by layer through the convolutional neural network to calculate the output of each layer. Use loss functions (such as mean square error MSE, cross entropy Cross-Entropy, etc.) to measure the difference between the model prediction result and the true label. When the actual output obtained by forward propagation does not meet the expected result, calculate the error between the actual output and the expected output, and propagate the error back from the output layer to the input layer. In this process, calculate the gradient of the loss function for each parameter. According to the calculated gradient, use optimization algorithms (such as gradient descent, stochastic gradient descent SGD, Adam, etc.) to update the network parameters to reduce the value of the loss function. Through iterative training until the preset number of iterations is reached or the loss function value reaches the threshold, a prediction model for the mixed fuel blending ratio is obtained, and the combustion condition is input into the prediction model, which outputs the optimal blending ratio of natural gas and hydrogen corresponding to the condition.

[0039] The above optimization method for natural gas hydrogen combustion in gas turbines improves the reliability and accuracy of experimental data by conducting multiple repeated experiments on the test bench and calculating the average and standard deviation. This helps to reduce the impact of random errors on the results and provide an accurate data basis for subsequent numerical calculation modeling and machine learning training; then, the experimental process is simulated using computational fluid dynamics numerical simulation software, which not only verifies the rationality and accuracy of the experimental results, but also enables predictions under a wider range of conditions, expanding the coverage of experimental data. By comparing the experimental data and numerical simulation results, the numerical calculation model is iteratively optimized to improve the accuracy and applicability of the numerical calculation model. This optimization process ensures that the model can more accurately reflect the actual combustion process and provides a reliable basis for subsequent predictions. Finally, a machine learning model (especially a neural network model) is used to predict the blending ratio of the mixed fuel, making full use of the advantages of the machine learning model in dealing with complex nonlinear problems. The neural network model can automatically learn the features in the data and continuously optimize the prediction performance through iterative training, thereby achieving accurate prediction of the blending ratio of the mixed fuel under combustion conditions. After the machine learning model is trained, its prediction process is usually much faster than the numerical simulation and experimental process. This makes it possible to quickly adjust the blending ratio of the mixed fuel according to the combustion conditions in practical applications, thereby improving the operating efficiency and environmental performance of the gas turbine.

[0040] The natural gas hydrogen-blended combustion optimization method of the present application is not only applicable to the mixed fuels and combustion conditions currently under study, but can also be easily extended to other types of fuels and combustion systems. By updating the numerical calculation model and the machine learning model, optimization predictions under different fuels and combustion conditions can be achieved. This technical solution combines the advantages of experiments, numerical simulations, and machine learning, reducing the cost and limitations of a single method. By reducing the number of experiments and the complexity of numerical simulations, the overall research cost and time cost are reduced.

[0041] Based on the above-mentioned gas turbine natural gas hydrogen blending combustion optimization method, the present application also proposes a gas turbine natural gas hydrogen blending combustion optimization system, which may include: The first acquisition module obtains the combustion state parameters of the mixed fuel under different blending ratios under experimental conditions, including combustion characteristic data and emission characteristic data; The second acquisition module establishes a numerical calculation model to describe the combustion process and emission characteristics of the mixed fuel based on combustion science and fluid mechanics, uses the numerical calculation model to perform numerical simulation on the mixed fuel at different blending ratios, and obtains the combustion state parameters of the mixed fuel; The model optimization module compares and analyzes the combustion state parameters obtained from the experiment and the combustion state parameters obtained from the numerical simulation, and optimizes the numerical calculation model according to the analysis results.

[0042] The third acquisition module is used to expand the blending ratio of the mixed fuel, use the updated numerical calculation model to perform numerical simulation on the expanded mixed fuel, obtain the combustion emission data of the mixed fuel and construct a training data set.

[0043] The training module is used to train the machine learning model using the training data set, and use the trained machine learning model to predict the blending ratio of the mixed fuel.

[0044] The division of modules in the embodiments of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present invention may be integrated into one processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0045] In another embodiment of the present invention, a computer device is provided, the computer device comprising a processor and a memory, the memory being used to store a computer program, the computer program comprising program instructions, and the processor being used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, which are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions in a computer storage medium to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the natural gas hydrogen blending combustion optimization method.

[0046] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It can be understood that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the natural gas hydrogen blending combustion optimization method in the above embodiment.

[0047] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0048] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0049] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0050] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0051] For the description of the relevant parts of the gas turbine natural gas hydrogen-blended combustion optimization system, electronic device, and computer-readable storage medium provided in the embodiments of the present application, please refer to the detailed description of the corresponding parts in the gas turbine natural gas hydrogen-blended combustion method provided in the embodiments of the present application, which will not be repeated here. In addition, the parts of the above technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive elaboration.

[0052] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A method for optimizing the combustion of natural gas mixed with hydrogen in a gas turbine, characterized in that: The following steps are involved: Step 1, obtaining combustion state parameters of mixed fuels at different blending ratios under experimental conditions, the combustion state parameters including combustion characteristic data and emission characteristic data; Step 2: Based on combustion science and fluid mechanics, a numerical calculation model is established to describe the combustion process and emission characteristics of the mixed fuel. The numerical calculation model is used to perform numerical simulation on the mixed fuel at different blending ratios to obtain the combustion state parameters of the mixed fuel. Step 3: Compare and analyze the combustion state parameters obtained by the experiment and the combustion state parameters obtained by the numerical simulation, and optimize the numerical calculation model according to the analysis results; Step 4: Expand the blending ratio of the mixed fuel, use the optimized numerical calculation model to perform numerical simulation on the expanded mixed fuel, obtain the combustion state parameters of the mixed fuel and construct a training data set; Step 5: Use the training data set to train the machine learning model, and use the trained machine learning model to predict the blending ratio of the mixed fuel.

2. A method for optimizing natural gas hydrogen-blended combustion in a gas turbine according to claim 1, characterized in that: The combustion characteristics include combustion pressure, combustion speed and combustion temperature, and the emission characteristics include the emission of pollutants such as NOx and CO.

3. The method for optimizing natural gas hydrogen-blended combustion in a gas turbine according to claim 1, characterized in that: The method for constructing the numerical calculation model in step 2 is as follows: Construct a geometric model with the same structure as the experimental device and discretize it into a grid, set the grid type and density; construct a fluid model and set the physical properties of the fluid according to the experimental conditions and fluid characteristics, set the boundary conditions of the fluid according to the experimental data, and obtain a numerical calculation model.

4. A method for optimizing natural gas hydrogen-blended combustion in a gas turbine according to claim 1, characterized in that: The numerical calculation model optimization method described in step 3 is as follows: Compare the combustion state parameters obtained from the experiment with those obtained from the numerical simulation to obtain the data with differences, optimize the numerical calculation model according to the difference data, adjust the boundary conditions and grid parameters of the numerical calculation model, and repeat step 2 until the simulation data is consistent with the experimental data.

5. The method for optimizing natural gas hydrogen-blended combustion in a gas turbine according to claim 1, characterized in that: The training data set includes the blending ratios under different operating conditions, and the corresponding combustion characteristics and emission characteristics.

6. A method for optimizing natural gas hydrogen-blended combustion in a gas turbine according to claim 1, characterized in that: The machine learning models include linear regression models, random forest models and neural network models.

7. A method for optimizing natural gas hydrogen-blended combustion in a gas turbine according to claim 6, characterized in that: The training method of the neural network model is as follows: The training data set is preprocessed to construct a convolutional neural network. The training data is input into the convolutional neural network and propagated forward layer by layer to calculate the output of each layer. The loss function is used to measure the difference between the model prediction result and the true label. When the actual output obtained by the forward propagation does not meet the expected result, the error between the actual output and the expected output is calculated, and the error is backpropagated from the output layer to the input layer. During the back propagation process, the gradient of the loss function for each parameter is calculated, and the network parameters are updated using an optimization algorithm based on the gradient to reduce the value of the loss function. Through iterative training, until the preset number of iterations is reached or the loss function value reaches a threshold, a prediction model for the blending ratio of the mixed fuel is obtained.

8. A gas turbine natural gas hydrogen blended combustion optimization system, characterized in that: include: The first acquisition module is used to obtain the combustion state parameters of the mixed fuel under different blending ratios under experimental conditions, and the combustion state parameters include combustion characteristic data and emission characteristic data; The second acquisition module is used to establish a numerical calculation model that describes the combustion process and emission characteristics of the mixed fuel based on combustion science and fluid mechanics, and is used to use the numerical calculation model to perform numerical simulation on the mixed fuel at different blending ratios to obtain the combustion state parameters of the mixed fuel; Model optimization module, used to compare and analyze the combustion state parameters obtained by experiments and those obtained by numerical simulation, and optimize the numerical calculation model according to the analysis results; The third acquisition module is used to expand the blending ratio of the mixed fuel, use the optimized numerical calculation model to perform numerical simulation on the expanded mixed fuel, obtain the combustion state parameters of the mixed fuel and construct a training data set; The training module is used to train the machine learning model using the training data set, and use the trained machine learning model to predict the blending ratio of the mixed fuel.

9. An electronic device, characterized in that: include: Memory for storing computer programs; A processor is used to implement the steps of the method for optimizing the combustion of natural gas blended with hydrogen in a gas turbine as claimed in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for optimizing the combustion of natural gas blended with hydrogen in a gas turbine according to any one of claims 1 to 7 are implemented.

Images