Oxygen-enriched combustion system based on CFD analogue simulation optimization and control method thereof

Abstract

The invention discloses an oxygen-enriched combustion system based on CFD analogue simulation optimization and a control method of the oxygen-enriched combustion system, and relates to the technical field of electric digital processing. The method comprises the steps that a sensor is configured to collect real-time combustion data under the current working condition; a structured grid of the combustion device is set, the real-time operation state of the combustion control unit is obtained, and a dynamic simulation model is constructed according to the real-time operation state, the real-time combustion data and the structured grid; obtaining a current simulation result through the dynamic simulation model; the current simulation result comprises a temperature field, a flow velocity field and a chemical concentration field; inputting the ideal simulation result, the current simulation result and the real-time operation state into a neural network model, and obtaining a regulation and control parameter instruction; and controlling the combustion control unit according to the regulation and control parameter instruction. According to the method, the simulation precision and the calculation efficiency of the combustion device can be remarkably improved, and accurate capture and real-time control optimization of complex flow characteristics are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic digital processing, and in particular to an oxygen-enriched combustion system based on CFD simulation optimization and a control method thereof. Background Art

[0002] In the process of energy utilization in traditional society, combustion technology is a basic and widely used part. Conventional combustion methods have problems such as low energy utilization efficiency and high pollutant emissions, which not only wastes precious energy resources, but also causes serious pollution to the environment. Especially in the fields of thermal power generation, industrial boilers and automobile engines, the efficiency and environmental protection requirements of the combustion process are becoming increasingly stringent, but traditional combustion control methods are difficult to achieve both high efficiency and low emissions at the same time.

[0003] In response to the above problems, scientists and engineers have proposed a variety of improvement methods in recent years to improve combustion efficiency and environmental performance. In oxygen-enriched combustion technology, combustion conditions are improved by increasing the oxygen concentration, thereby improving combustion efficiency and reducing pollution emissions. At the same time, computational fluid dynamics (CFD) simulation technology has also been introduced to simulate and optimize the combustion process, helping to design more efficient and environmentally friendly combustion systems.

[0004] However, the existing oxygen-rich combustion control methods still have shortcomings in capturing complex flow characteristics and real-time control optimization. In other words, current technologies often find it difficult to balance simulation accuracy and computing resource limitations, resulting in the reliability and practicality of simulation results to be improved. Summary of the invention

[0005] The present invention provides an oxygen-enriched combustion system and a control method thereof based on CFD simulation optimization to solve at least one of the problems mentioned in the above background technology.

[0006] The specific technical solutions provided by the present invention are as follows:

[0007] An oxygen-rich combustion control method based on CFD simulation optimization includes the following steps:

[0008] Configure sensors to collect real-time combustion data under current working conditions;

[0009] Set the structured grid of the combustion device, obtain the real-time operating status of the combustion control unit, and build a dynamic simulation model based on the real-time operating status, real-time combustion data and structured grid;

[0010] Acquire current simulation results through a dynamic simulation model; the current simulation results include temperature field, flow velocity field and chemical concentration field;

[0011] The ideal simulation results, current simulation results and real-time operation status are input into the neural network model to obtain control parameter instructions;

[0012] Controlling the combustion control unit according to the control parameter instructions;

[0013] The setting of the structured grid of the combustion device specifically comprises the steps of:

[0014] Set the flow characteristics, computing resource limitations and accuracy requirements that the dynamic simulation model needs to capture; configure the weight parameters of the fitness function according to the flow characteristics, computing resource limitations and accuracy requirements;

[0015] Initialize and set the particle swarm parameters of the particle swarm optimization algorithm; the particle swarm parameters include the position and velocity of the particles, the inertia weight, the first learning factor and the second learning factor; the position of the particles is used to represent the configuration parameters of each structured grid; the configuration parameters include the number of grid points in each coordinate direction, grid boundary conditions, grid alignment geometric features and auxiliary configuration parameters;

[0016] Generate a corresponding structured grid according to the position of each particle and perform simulation, and calculate the fitness value of each particle according to the fitness function and simulation results;

[0017] Update the personal best position and the group best position of each particle according to the fitness value, and update the speed and position of each particle according to the personal best position and the group best position;

[0018] The iteration is repeated until the maximum number of iterations is reached or the fitness value is less than a set threshold, and the optimal position of the group is set as the configuration parameter of the structured grid of the combustion device.

[0019] As a preferred solution, the real-time operating status includes fuel supply rate, fan speed and valve opening; the real-time combustion data includes temperature, pressure, oxygen concentration, fuel flow and flue gas component concentration of each sampling point.

[0020] As a preferred embodiment, the dynamic simulation model includes a turbulence model, a combustion model and a gas radiation model; the turbulence model is used to describe the turbulence characteristics of the fluid in the combustion device; the combustion model is used to describe the interaction between the fuel and the oxidant and the generation state of the reaction products during the chemical reaction; the gas radiation model is used to describe the radiation heat transfer of the gas.

[0021] As a preferred solution, the turbulence model adopts a Realizable k-ε model; the Realizable k-ε model is used to describe the process of turbulent energy transfer through turbulent kinetic energy and turbulent kinetic energy dissipation rate;

[0022] The turbulent kinetic energy is expressed as:

[0023]

[0024] in, It represents the sum of the variances of the velocity fluctuation components and is used to quantify the overall intensity of velocity fluctuations; u′1, u′2 and u′3 represent velocity fluctuation components in the first direction, the second direction and the third direction respectively; the first direction, the second direction and the third direction are perpendicular to each other;

[0025] The turbulent kinetic energy dissipation rate is expressed as:

[0026]

[0027] Where ν represents the dynamic viscosity, u′ i represents the i-th direction component of velocity fluctuation, x j Represents the j-th direction coordinate.

[0028] As a preferred solution, the combustion model is a Finite-Rate model; the Finite-Rate model describes the relationship between the reaction rate and the temperature change through the Arrhenius equation; the Arrhenius equation is expressed as:

[0029]

[0030] Among them, K represents the reaction rate, T represents the temperature, n represents the temperature index, E represents the activation energy, R represents the gas constant, A represents the set characteristic constant, and C represents the concentration of the substance participating in the reaction.

[0031] As a preferred solution, the gas radiation model adopts a DO model; the DO model discretizes the radiation transfer equation into multiple directions in space and solves it; the radiation transfer equation is expressed as:

[0032]

[0033] Where I(r,s) represents the radiation intensity at position r and direction s, k a represents the absorption coefficient, I b Represents the blackbody radiation intensity, I represents the current radiation intensity; σ s represents the scattering coefficient, I(r,s ′ ) indicates direction s ′ The transmitted radiation intensity, Φ(s,s ′ ) indicates direction s ′ The probability of radiation being scattered into direction s.

[0034] As a preferred solution, the fitness value is expressed as:

[0035] f=α·E ε +β·E c +γ·E q ,

[0036] Among them, E ε Represents the simulation accuracy index, E c represents the computational cost index, E q represents the mesh quality index, α, β and γ are the weight parameters of the simulation accuracy index, computational cost index and mesh quality index respectively.

[0037] As a preferred solution, the grid quality index is expressed as:

[0038]

[0039] Where U represents the number of grids, T u,SM represents the node smoothness index of the u-th grid, T u,OR represents the grid orthogonality index of the u-th grid, T u,AR represents the aspect ratio index of the u-th grid; w1, w2 and w3 represent the weight parameters of the node smoothness index, grid orthogonality index and aspect ratio index respectively.

[0040] As a preferred solution, the velocity of the particle is expressed as:

[0041]

[0042] Where ω is the inertia weight, k is the iteration round; c1 and c2 are the first learning factor and the second learning factor, respectively. The first learning factor is used to control the amplitude of the particle moving toward the individual optimal position, and the second learning factor is used to control the amplitude of the particle moving toward the group optimal position. is the personal best position of particle i; is the optimal position of the group; r1 and r2 are both random numbers in the interval [0,1].

[0043] The present invention also provides an oxygen-enriched combustion system based on CFD simulation optimization, including a data acquisition module, a dynamics simulation module, a distributed control module and a combustion control unit;

[0044] The data acquisition module is used to collect real-time combustion data under current working conditions through sensors, and obtain the real-time operating status of the combustion control unit;

[0045] The dynamic simulation module is used to construct a dynamic simulation model according to the real-time operating state, real-time combustion data and the structured grid by setting the structured grid of the combustion device, and to obtain the current simulation result through the dynamic simulation model; the current simulation result includes the temperature field, the flow velocity field and the chemical concentration field;

[0046] The distributed control module is used to input the ideal simulation results, current simulation results and real-time operation status into the neural network model, obtain the control parameter instructions and transmit them to the combustion control unit;

[0047] The combustion control unit is used to control the corresponding actuator according to the control parameter instruction.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] The present invention sets the flow characteristics, computing resource limitations and accuracy requirements that need to be captured by the dynamic simulation model, so as to ensure that the grid generation scheme can not only accurately reflect the core characteristics of the combustion process, but also operate efficiently under the condition that the computing resources allow; by configuring the weight parameters of the fitness function, the limitations of accuracy and computing resources are comprehensively considered to ensure the multi-objective balance in the optimization process, and improve the reliability and practicality of the simulation results; by continuously iteratively updating the speed and position of the particles, the optimal position of the group finally output represents the optimal configuration parameters of the structured grid, which can significantly improve the simulation accuracy and computing efficiency of the combustion device, and ensure the accurate capture of complex flow characteristics and real-time control optimization.

[0050] The present invention outputs temperature field, velocity field and chemical concentration field through the dynamic simulation model, which can fully reflect the complex characteristics of the combustion process and provide an accurate data basis for the control system; through the neural network model, the ideal simulation results, current simulation results and real-time operating status are input into the model, and accurate control parameter instructions are automatically generated, thereby optimizing combustion control and improving the response speed and control accuracy of the system; by controlling the corresponding actuator through the control parameter instructions, the combustion rate and combustion uniformity can be effectively improved, the emission of harmful gases can be reduced, and the environmental protection performance and economic benefits of oxygen-enriched combustion can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0053] Figure 1 A schematic flow chart of an oxygen-rich combustion control method based on CFD simulation optimization provided in one embodiment of the present invention;

[0054] Figure 2A schematic diagram of a process for setting a structured grid of a combustion device provided by an embodiment of the present invention;

[0055] Figure 3 A schematic diagram of the structure of an oxygen-rich combustion control system based on CFD simulation optimization is provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0058] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least the feature. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0059] In the process of energy utilization in traditional society, combustion technology is a basic and widely used part. Conventional combustion methods have problems such as low energy utilization efficiency and high pollutant emissions, which not only wastes precious energy resources, but also causes serious pollution to the environment. Especially in the fields of thermal power generation, industrial boilers and automobile engines, the efficiency and environmental protection requirements of the combustion process are becoming increasingly stringent, but traditional combustion control methods are difficult to achieve both high efficiency and low emissions at the same time.

[0060] In response to the above problems, scientists and engineers have proposed a variety of improvement methods in recent years to improve combustion efficiency and environmental performance. In oxygen-enriched combustion technology, combustion conditions are improved by increasing the oxygen concentration, thereby improving combustion efficiency and reducing pollution emissions. At the same time, computational fluid dynamics (CFD) simulation technology has also been introduced to simulate and optimize the combustion process, helping to design more efficient and environmentally friendly combustion systems.

[0061] However, the existing oxygen-rich combustion control methods still have shortcomings in capturing complex flow characteristics and real-time control optimization. In other words, current technologies often find it difficult to balance simulation accuracy and computing resource limitations, resulting in the reliability and practicality of simulation results to be improved.

[0062] See also Figure 1 The present invention provides an oxygen-rich combustion control method based on CFD simulation optimization, comprising:

[0063] S1. Configure sensors to collect real-time combustion data under current working conditions;

[0064] S2. Setting a structured grid of the combustion device, obtaining the real-time operating status of the combustion control unit, and constructing a dynamic simulation model according to the real-time operating status, real-time combustion data and the structured grid;

[0065] The real-time operating status includes fuel supply rate, fan speed and valve opening; the real-time combustion data includes temperature, pressure, oxygen concentration, fuel flow rate and flue gas component concentration of each sampling point.

[0066] Among them, the dynamic simulation model includes a turbulence model, a combustion model and a gas radiation model; the turbulence model is used to describe the turbulence characteristics of the fluid in the combustion device; the combustion model is used to describe the interaction between the fuel and the oxidant and the generation state of the reaction products during the chemical reaction; the gas radiation model is used to describe the radiation heat transfer of the gas.

[0067] In one embodiment, the turbulence model adopts the Realizable k-ε model; the Realizable k-ε model is used to describe the process of turbulent energy transfer through turbulent kinetic energy and turbulent kinetic energy dissipation rate. The Realizable k-ε model is a turbulence model improved based on the k-ε model, which can truly capture physical phenomena, especially in high shear zones and flow separation zones. Among them, turbulent kinetic energy represents the intensity of velocity fluctuations in turbulence, and the turbulent kinetic energy dissipation rate represents the rate at which turbulent kinetic energy per unit mass is converted into heat energy, that is, the rate at which turbulent energy is lost due to viscosity.

[0068] The turbulent kinetic energy is expressed as:

[0069]

[0070] in, It represents the sum of the variances of the velocity fluctuation components and is used to quantify the overall intensity of velocity fluctuations; u′1, u′2 and u′3 represent velocity fluctuation components in a first direction, a second direction and a third direction respectively; the first direction, the second direction and the third direction are perpendicular to each other.

[0071] The turbulent kinetic energy dissipation rate is expressed as:

[0072]

[0073] Where ν represents the dynamic viscosity, u′ i represents the i-th direction component of velocity fluctuation, x j Represents the j-th direction coordinate.

[0074] In this embodiment, through the calculation and interaction of turbulent kinetic energy and turbulent kinetic energy dissipation rate, the Realizable k-ε model can accurately describe the turbulent characteristics in the flow field, making the simulation results more reliable and realistic.

[0075] In one embodiment, the combustion model is a Finite-Rate model; the Finite-Rate model describes the relationship between the reaction rate and the temperature change through the Arrhenius equation; the Arrhenius equation is expressed as:

[0076]

[0077] Among them, K represents the reaction rate, T represents the temperature, n represents the temperature index, E represents the activation energy, R represents the gas constant, A represents the set characteristic constant, and C represents the concentration of the substance participating in the reaction.

[0078] In the Finite Rate model of this embodiment, the Arrhenius equation is used to calculate the reaction rate constant at different temperatures, thereby affecting the actual reaction rate. In combustion simulation, a large part of the kinetic properties, such as ignition delay, combustion rate, etc., are highly controlled by temperature changes. The Arrhenius equation takes into account the effects of molecular collisions and energy barriers, and can effectively capture the effect of temperature on chemical reaction rates.

[0079] In one embodiment, the gas radiation model adopts the DO model (Discrete Ordinates Model), which discretizes the radiation transfer equation into multiple directions in space and solves the radiation transfer equation in each direction accordingly. The radiation transfer equation is expressed as:

[0080]

[0081] Where I(r,s) represents the radiation intensity at position r and direction s, k a represents the absorption coefficient, I b Represents the blackbody radiation intensity, I represents the current radiation intensity; σ s represents the scattering coefficient, I(r,s ′ ) indicates direction s ′ The transmitted radiation intensity, Φ(s,s ′) indicates direction s ′ The probability of radiation being scattered into direction s.

[0082] In one embodiment, please refer to Figure 2 The setting of the structured grid of the combustion device specifically comprises the steps of:

[0083] S21, setting the flow characteristics, computing resource limitations and accuracy requirements that the dynamic simulation model needs to capture; configuring the weight parameters of the fitness function according to the flow characteristics, computing resource limitations and accuracy requirements;

[0084] Among them, the fitness function is used to evaluate the pros and cons of the configuration parameters of each structured grid. The fitness function consists of a simulation accuracy index, a computational cost index, and a mesh quality index, and each index reflects the performance of a certain flow feature. This embodiment sets the weight of each index in the fitness function according to the importance and accuracy requirements of the flow feature. Among them, complex flow features may require more detailed calculations, which will increase the computational cost; for these features, the computational cost may require appropriate weight adjustments to ensure balance; for certain flow features, high-quality meshes are required (such as in the eddy flow area), so the weights of related mesh quality indicators may need to be increased to ensure that the mesh can accurately capture these features; computational resource limitations can reduce simulation time by affecting the weight parameters of the computational cost index within a tight time frame when computer resources are insufficient.

[0085] Furthermore, the fitness value is expressed as:

[0086] f=α·E ε +β·E c +γ·E q ,

[0087] Among them, E ε Represents the simulation accuracy index, E c represents the computational cost index, E q represents the mesh quality index, α, β and γ are the weight parameters of the simulation accuracy index, computational cost index and mesh quality index respectively.

[0088] In one embodiment, the grid quality index is expressed as:

[0089]

[0090] Where U represents the number of grids, T u,SM represents the node smoothness index of the u-th grid, T u,OR represents the grid orthogonality index of the u-th grid, T u,AR represents the aspect ratio index of the u-th grid; w1, w2 and w3 represent the weight parameters of the node smoothness index, grid orthogonality index and aspect ratio index respectively.

[0091] The node smoothness index is used to describe the uniformity of the spatial distribution of grid points. Excessive changes in node spacing will reduce simulation accuracy. The measurement method of the present invention is the rate of change of adjacent node spacing. The node smoothness index is expressed as:

[0092]

[0093] Among them, T u,SM represents the node smoothness index of the u-th grid, d x,x+1 represents the distance between node x and node x+1 in the u-th grid, and n represents the number of grid nodes.

[0094] Grid orthogonality is used to represent the angle between the surface normal vector of each grid unit and the adjacent surface normal vector. The ideal orthogonality is 90 degrees. The grid orthogonality is expressed as:

[0095]

[0096] Among them, T u,OR represents the grid orthogonality index of the u-th grid, n1 represents the surface normal vector of the u-th grid; M represents the number of grids adjacent to the u-th grid, n m Represents the face normal vector of the mth adjacent mesh.

[0097] The aspect ratio is used to measure the uniformity of the unit shape. Ideally, the lengths of the sides of the unit should be as close as possible. To calculate the aspect ratio, calculate all the side lengths, find the longest side length and the shortest side length, and then calculate the ratio of the longest side length to the shortest side length as the aspect ratio. The closer the aspect ratio of the grid is to 1, the closer the unit is to equilibrium and has better shape quality; a high aspect ratio usually means that the unit shape is poor, which may affect the accuracy and stability of the calculation results.

[0098] S22, initializing and setting the particle swarm parameters of the particle swarm optimization algorithm; wherein the particle swarm parameters include the number of particles, the position and velocity of the particles, the inertia weight for particle update, the first learning factor and the second learning factor, etc.; the position of the particle represents the coordinates of a possible solution in the search space of the problem. In the present invention, the position of the particle is used to represent the configuration parameters of each structured grid; the configuration parameters include the number of grid points in each coordinate direction, the grid boundary conditions, the grid alignment geometric features and the auxiliary configuration parameters.

[0099] Furthermore, the auxiliary configuration parameters include a grid stretching coefficient, smoothness and aspect ratio; the grid stretching coefficient is used to determine the change of the grid from sparse to dense, the smoothness is used to determine the smoothness of the grid change, and the aspect ratio is used to determine the shape ratio of the grid unit.

[0100] S23, generating a corresponding structured grid according to the position of each particle and performing simulation, and calculating the fitness value of each particle according to the fitness function and the simulation result;

[0101] S24, updating the personal best position and the group best position of each particle according to the fitness value, and updating the speed and position of each particle according to the personal best position and the group best position;

[0102] The velocity of the particle is expressed as:

[0103]

[0104] Where ω is the inertia weight, k is the iteration round; c1 and c2 are the first learning factor and the second learning factor, respectively. The first learning factor is used to control the amplitude of the particle moving toward the individual optimal position, and the second learning factor is used to control the amplitude of the particle moving toward the group optimal position. is the personal best position of particle i; is the optimal position of the group; r1 and r2 are both random numbers in the interval [0,1].

[0105] S25, repeating the iteration until the maximum number of iterations is reached or the fitness value is less than a set threshold, and setting the optimal position of the group as the configuration parameter of the structured grid of the combustion device.

[0106] The threshold value can be set according to the accuracy requirement of step S21, and the maximum number of iterations can be set according to the computing resource limit of step S21. Repeat the iteration, that is, repeat the steps of S23 and S24, until the preset maximum number of iterations is reached or the fitness value reaches the set threshold, and the current group optimal position is the configuration parameter of the final combustion device structured grid. These parameters will be used to generate the optimal grid to meet the accuracy requirements and computing efficiency of the simulation.

[0107] The present invention sets the flow characteristics, computing resource limitations and accuracy requirements that need to be captured by the dynamic simulation model, so as to ensure that the grid generation scheme can not only accurately reflect the core characteristics of the combustion process, but also operate efficiently under the condition that the computing resources allow; by configuring the weight parameters of the fitness function, the limitations of accuracy and computing resources are comprehensively considered to ensure the multi-objective balance in the optimization process, and improve the reliability and practicality of the simulation results; by continuously iteratively updating the speed and position of the particles, the optimal position of the group finally output represents the optimal configuration parameters of the structured grid, which can significantly improve the simulation accuracy and computing efficiency of the combustion device, and ensure the accurate capture of complex flow characteristics and real-time control optimization.

[0108] S3. Obtaining current simulation results through a dynamic simulation model; the current simulation results include temperature field, flow velocity field and chemical concentration field;

[0109] This step runs the simulation model to obtain the current simulation results. The simulation results include:

[0110] Temperature field: temperature distribution during the combustion process, showing the temperature changes in different areas through grid nodes;

[0111] Flow velocity field: the velocity and direction distribution of the airflow during the combustion process, and the flow field characteristics are also represented by grid nodes;

[0112] Chemical concentration field: The concentration distribution of gas components (such as oxygen, fuel, combustion products, etc.), showing the distribution changes of chemical components through nodes.

[0113] S4, inputting the ideal simulation result, the current simulation result and the real-time operation status into the neural network model to obtain the control parameter instruction;

[0114] Among them, the ideal simulation result is the simulation result obtained based on the design or optimal operating conditions, representing the performance of the system under the optimal or expected working conditions. The ideal simulation result can be determined by using a genetic algorithm, a particle swarm optimization algorithm, etc., with combustion efficiency and pollutant emissions as optimization targets; the current simulation result is based on the simulation result of the current actual working condition parameters, reflecting the performance of the system at the current moment. In this embodiment, the ideal simulation result is used as a target or benchmark, and the current simulation result monitors the system status in real time, and is compared with the ideal simulation result to determine the identification deviation or abnormality.

[0115] In this step, the ideal simulation results, current simulation results and real-time operating status are input into the neural network model as feature vectors, and the input data is nonlinearly transformed through multiple hidden layers to extract deep-level features in the data; the deep-level features generate control parameter instructions through the output layer, and the control parameter instructions include continuous values ​​(such as adjusting the fuel supply rate) and discrete values ​​(such as switch control).

[0116] The present invention obtains control parameter instructions by inputting ideal simulation results, current simulation results and real-time operating status into a neural network model. Since the combustion process involves multiple nonlinear relationships, the neural network effectively captures these complex relationships through nonlinear activation functions and stacked hidden layer structures, and can generate accurate control parameters in real time and efficiently, thereby optimizing the performance and efficiency of the combustion system.

[0117] S5. Control the combustion control unit according to the control parameter instruction.

[0118] In this embodiment, the combustion control unit includes a fuel supply module, an oxygen supply module and a fan module; the fuel supply module is used to store and transport various fuels (such as natural gas, coal, liquid fuel, etc.) to the combustion device; the oxygen supply module is used to provide oxygen-enriched air of a set concentration to help the combustion device achieve oxygen-enriched combustion and enhance combustion efficiency; the fan module is used to control the air volume, air pressure and air flow temperature of the primary air, central air, swirl air and axial air to ensure the normal progress of the combustion process.

[0119] An oxygen-enriched combustion control system based on CFD simulation optimization is used to implement the above oxygen-enriched combustion method based on CFD simulation optimization, including a data acquisition module, a dynamics simulation module, a distributed control module and a combustion control unit;

[0120] The data acquisition module is used to collect real-time combustion data under current working conditions through sensors, and obtain the real-time operating status of the combustion control unit;

[0121] The dynamic simulation module is used to construct a dynamic simulation model according to the real-time operating state, real-time combustion data and the structured grid by setting the structured grid of the combustion device, and to obtain the current simulation result through the dynamic simulation model; the current simulation result includes the temperature field, the flow velocity field and the chemical concentration field;

[0122] The distributed control module is used to input the ideal simulation results, current simulation results and real-time operation status into the neural network model, obtain the control parameter instructions and transmit them to the combustion control unit;

[0123] The combustion control unit is used to control the corresponding actuator according to the control parameter instruction.

[0124] The embodiment of the present invention adopts a particle swarm optimization algorithm to generate and optimize a structured grid, so that the grid can accurately capture the flow characteristics in the combustion process, while ensuring the effective use of computing resources, thereby improving the efficiency and accuracy of the simulation; through the dynamic simulation model, multiple parameters such as temperature field, velocity field and chemical concentration field are combined, which can fully reflect the complex characteristics of the combustion process and provide an accurate data basis for the control system; through the neural network model, the ideal simulation results, the current simulation results and the real-time operating status are input into the model, and accurate control parameter instructions are automatically generated, thereby optimizing the combustion control and improving the response speed and control accuracy of the system; by controlling the corresponding actuator through the control parameter instructions, the combustion rate and combustion uniformity can be effectively improved, and the emission of harmful gases can be reduced, thereby improving the environmental protection performance and economic benefits of oxygen-enriched combustion.

[0125] In the embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, the indirect coupling or communication connection of the modules can be electrical, mechanical or other forms.

[0126] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of software functional modules.

[0128] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), disk or optical disk and other media that can store program codes.

[0129] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. An oxygen-enriched combustion control method based on CFD simulation optimization, characterized in that: Includes steps: Configure sensors to collect real-time combustion data under current working conditions; Set the structured grid of the combustion device, obtain the real-time operating status of the combustion control unit, and build a dynamic simulation model based on the real-time operating status, real-time combustion data and structured grid; Acquire current simulation results through a dynamic simulation model; the current simulation results include temperature field, flow velocity field and chemical concentration field; The ideal simulation results, current simulation results and real-time operation status are input into the neural network model to obtain control parameter instructions; Controlling the combustion control unit according to the control parameter instructions; The setting of the structured grid of the combustion device specifically comprises the steps of: Set the flow characteristics, computing resource limitations and accuracy requirements that the dynamic simulation model needs to capture; configure the weight parameters of the fitness function according to the flow characteristics, computing resource limitations and accuracy requirements; Initialize and set the particle swarm parameters of the particle swarm optimization algorithm; the particle swarm parameters include the position and velocity of the particles, the inertia weight, the first learning factor and the second learning factor; the position of the particles is used to represent the configuration parameters of each structured grid; the configuration parameters include the number of grid points in each coordinate direction, grid boundary conditions, grid alignment geometric features and auxiliary configuration parameters; Generate a corresponding structured grid according to the position of each particle and perform simulation, and calculate the fitness value of each particle according to the fitness function and simulation results; Update the personal best position and the group best position of each particle according to the fitness value, and update the speed and position of each particle according to the personal best position and the group best position; The iteration is repeated until the maximum number of iterations is reached or the fitness value is less than a set threshold, and the optimal position of the group is set as the configuration parameter of the structured grid of the combustion device.

2. The oxygen-rich combustion control method based on CFD simulation optimization according to claim 1 is characterized in that: The real-time operating status includes fuel supply rate, fan speed and valve opening; the real-time combustion data includes temperature, pressure, oxygen concentration, fuel flow rate and flue gas component concentration of each sampling point.

3. The oxygen-rich combustion control method based on CFD simulation optimization according to claim 1 is characterized in that: The dynamic simulation model includes a turbulence model, a combustion model and a gas radiation model; the turbulence model is used to describe the turbulence characteristics of the fluid in the combustion device; the combustion model is used to describe the interaction between the fuel and the oxidant and the generation state of the reaction products during the chemical reaction; the gas radiation model is used to describe the radiation heat transfer of the gas.

4. The oxygen-rich combustion control method based on CFD simulation optimization according to claim 3 is characterized in that: The turbulence model adopts the Realizable k-ε model; the Realizable k-ε model is used to describe the process of turbulent energy transfer through turbulent kinetic energy and turbulent kinetic energy dissipation rate; The turbulent kinetic energy is expressed as: in, It represents the sum of the variances of the velocity fluctuation components and is used to quantify the overall intensity of velocity fluctuations; u′1, u′2 and u′3 represent velocity fluctuation components in the first direction, the second direction and the third direction respectively; the first direction, the second direction and the third direction are perpendicular to each other; The turbulent kinetic energy dissipation rate is expressed as: Where ν represents the dynamic viscosity, u i represents the i-th direction component of velocity fluctuation, x j Represents the j-th direction coordinate.

5. The oxygen-rich combustion control method based on CFD simulation optimization according to claim 3 is characterized in that: The combustion model is a Finite-Rate model; the Finite-Rate model describes the relationship between the reaction rate and the temperature change through the Arrhenius equation; the Arrhenius equation is expressed as: Among them, K represents the reaction rate, T represents the temperature, n represents the temperature index, E represents the activation energy, R represents the gas constant, A represents the set characteristic constant, and C represents the concentration of the substance participating in the reaction.

6. The oxygen-rich combustion control method based on CFD simulation optimization according to claim 3 is characterized in that: The gas radiation model adopts the DO model; the DO model discretizes the radiation transfer equation into multiple directions in space and solves it; the radiation transfer equation is expressed as: Where I(r,s) represents the radiation intensity at position r and direction s, k a represents the absorption coefficient, I b Represents the blackbody radiation intensity, I represents the current radiation intensity; σ s represents the scattering coefficient, I(r,s ′ ) indicates direction s ′ The transmitted radiation intensity, Φ(s,s ′ ) indicates direction s ′ The probability of radiation being scattered in direction s.

7. The oxygen-rich combustion control method based on CFD simulation optimization according to claim 1 is characterized in that: The fitness value is expressed as: f=α·E ε +β·E c +γ·E q , Among them, E ε Represents the simulation accuracy index, E c represents the computational cost index, E q represents the mesh quality index, α, β and γ are the weight parameters of the simulation accuracy index, computational cost index and mesh quality index respectively.

8. The oxygen-rich combustion control method based on CFD simulation optimization according to claim 7 is characterized in that: The mesh quality index is expressed as: Where U represents the number of grids, T u,SM represents the node smoothness index of the u-th grid, T u,OR represents the grid orthogonality index of the u-th grid, T u,AR represents the aspect ratio index of the u-th grid; w1, w2 and w3 represent the weight parameters of the node smoothness index, grid orthogonality index and aspect ratio index respectively.

9. The oxygen-rich combustion control method based on CFD simulation optimization according to claim 1 is characterized in that: The velocity of the particle is expressed as: Where ω is the inertia weight, k is the iteration round; c1 and c2 are the first learning factor and the second learning factor, respectively. The first learning factor is used to control the amplitude of the particle moving toward the individual optimal position, and the second learning factor is used to control the amplitude of the particle moving toward the group optimal position. is the personal best position of particle i; is the optimal position of the group; r1 and r2 are both random numbers in the interval [0,1].

10. An oxygen-enriched combustion system based on CFD simulation optimization, characterized in that: Used to implement the oxygen-enriched combustion method based on CFD simulation optimization as described in any one of claims 1 to 9, comprising a data acquisition module, a dynamic simulation module, a distributed control module and a combustion control unit; The data acquisition module is used to collect real-time combustion data under current working conditions through sensors, and obtain the real-time operating status of the combustion control unit; The dynamic simulation module is used to construct a dynamic simulation model according to the real-time operating state, real-time combustion data and the structured grid by setting the structured grid of the combustion device, and to obtain the current simulation result through the dynamic simulation model; the current simulation result includes the temperature field, the flow velocity field and the chemical concentration field; The distributed control module is used to input the ideal simulation results, current simulation results and real-time operation status into the neural network model, obtain the control parameter instructions and transmit them to the combustion control unit; The combustion control unit is used to control the corresponding actuator according to the control parameter instruction.

Images