Optimization design method of high-temperature air pre-heater for solid oxide fuel cell based on three-period minimal curved surface

Abstract

The invention discloses an optimal design method of a high-temperature air pre-heater for a solid oxide fuel cell based on a three-period minimum curved surface, which comprises the following steps of: firstly, establishing a sample database between a three-period minimum curved surface single crystal cell structure and hydraulic characteristic parameters and between an end socket structure and a local resistance coefficient; based on a sample database, an artificial neural network model of a single cell structure and hydraulic characteristics, and an end socket and local resistance is constructed, according to the model, on the basis of design requirements, a non-linear optimization algorithm is combined to design a cross-flow heat exchanger cell-by-cell self-adaptive heat balance calculation process, and pressure drop on the cold side and the hot side is used as an optimization target to optimize the cross-flow heat exchanger cell-by-cell self-adaptive heat balance calculation process. According to the method, the minimum curved surface structure air preheater optimization design method based on the multi-objective genetic optimization algorithm is developed, the geometric structure of the single crystal cell, the overall size of the air preheater and the corresponding thermal performance are finally obtained, the optimal matching scheme between the single crystal cell and the overall size can be automatically obtained, the design optimization efficiency is improved, and the design cost is reduced. And engineering application is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of high-temperature heat exchangers for solid oxide fuel cells, and in particular to an optimization design method for a high-temperature air preheater for solid oxide fuel cells based on a three-periodic minimal surface. Background Art

[0002] Solid oxide fuel cells have the advantages of wide fuel sources, high electrothermal efficiency and high exhaust temperature in the field of hydrogen energy applications. They are widely used in industrial parks and distributed energy systems. Because its operating temperature is usually 600-800℃, in order to maintain its normal operation, corresponding thermal balance components such as steam generators, air preheaters, reformers, burners and other equipment need to be configured. The air preheater is used to heat the air at room temperature to reach or approach the operating temperature of the stack to reduce the temperature gradient inside the stack and extend its service life. At present, the thermal balance components still have the problems of low compactness and high flow resistance, which hinders the miniaturization of solid oxide fuel cells and limits its application scenarios. The three-periodic minimal surface structure is composed of non-self-intersecting periodic surfaces in three directions, with an average curvature of zero, a large specific surface area and an interconnected internal structure. The smooth surface gives it excellent heat exchange capacity. This feature makes the three-periodic minimal surface structure have great application potential in the design of high-temperature air preheaters. The flow and heat transfer capacity of the three-period minimal surface are jointly affected by its own structural parameters and operating parameters. Compared with the traditional straight channel structure, its heat exchange capacity is improved, but it also brings an increase in flow resistance. Reasonable design of the unit structure and the overall structure according to the working state of the air preheater can improve the compactness of the thermal balance components and provide support for expanding the application scenarios of solid oxide fuel cells. The current design process for high-temperature air preheaters usually adopts the method of designing the single cell structure first and then designing the overall size, without considering the mutual influence between the single cell and the whole. In order to further improve the development efficiency of air preheaters for solid oxide fuel cells, it is of great significance to develop a comprehensive optimization design method. Summary of the invention

[0003] In view of the shortcomings or defects of the above-mentioned prior art, the purpose of the present invention is to provide an optimization design method for a high-temperature air preheater for a solid oxide fuel cell based on a three-periodic minimal surface, so as to achieve rapid, efficient and comprehensive optimization design of highly compact thermal balance components, thereby expanding the application scenarios of solid oxide fuel cells.

[0004] The purpose of the present invention is achieved through the following technical solutions.

[0005] A method for optimizing the design of a high-temperature air preheater for a solid oxide fuel cell based on a three-periodic minimal surface comprises the following steps:

[0006] S1: Build a sample database of single cell geometric parameters and hydraulic characteristic parameters, head structure and local resistance coefficient, and build the corresponding artificial neural network model based on the sample database;

[0007] S2: Based on the consideration of the head structure, a three-period minimal surface structure is selected according to the cross-flow heat exchange structure. The unit cell is used as the calculation unit, and the flow and heat transfer performance are calculated cell by cell, and the overall thermal performance is finally obtained;

[0008] S3: Based on the nonlinear optimization algorithm fmincon, adaptive heat balance calculation is realized for each unit cell, and the operating parameters of the dual-fluid heat exchanger under a given structure are obtained by solving each unit cell;

[0009] S4: Taking the single cell size, wall thickness, heat exchange core size, and head height as decision variables, the minimum pressure drop on both the cold and hot sides as the optimization goal, and the total size limit and the hot side temperature outlet as constraints, the high-temperature air preheater is optimized based on a multi-objective genetic algorithm;

[0010] S5: Calculate the optimal solution set, select the design scheme that meets the requirements, obtain the overall design parameters of the optimized three-period minimal surface structure heat exchanger, and complete the design of the high-temperature air preheater.

[0011] The single crystal cell geometric parameters include the single crystal cell size uc and wall thickness δ uc The hydraulic characteristic parameters of the single cell include the hydraulic diameter D h , Flow cross-sectional area A cross , Single-side heat exchange area HSA uc ; The head structure includes the head bundle tube diameter d bt , height δ along the fluid flow direction end , the length of the head l core and width w core , the local resistance coefficient of the head is ξ, which represents the pressure drop generated by the heads at both ends;

[0012] The sample database is a one-to-one correspondence library constructed after the corresponding parameters are calculated by the modeling software and the numerical simulation software. The single cell models under different unit size-wall thickness combinations are constructed by the modeling software, and the hydraulic characteristic parameters of the single cell under each combination are calculated to form the sample database. The local resistance coefficient of the head is calculated by the modeling software and the numerical simulation software, and together with the head structure, it constitutes the sample database.

[0013] The artificial neural network model includes two models, a single cell structure-hydraulic characteristic parameter prediction model and a head height-local resistance coefficient prediction model, which are constructed based on a double-layer feedforward network fitting model.

[0014] The model is used to calculate the flow and heat transfer performance of the heat exchanger under a given structure, which can be expressed as:

[0015] [D h ,A cross ,HSA uc ]=f(size uc ,δ uc )

[0016] ξ=f(l core ,w core ,d bt ,δ end )

[0017] Where: D h represents the hydraulic diameter of a unit cell, A cross Represents the cross-sectional area of ​​a single cell, HSA uc Indicates the heat transfer area on one side of a single cell, size uc represents the unit cell size, δ uc represents the thickness of the single cell wall, l core Indicates the length of the head, w core Indicates the width of the head, d bt Indicates the diameter of the head cluster tube, δ end It represents the height of the head along the fluid flow direction, and ξ represents the local resistance coefficient of the head.

[0018] The cross-flow heat exchange structure is a heat exchange core, which is a heat calculation area. The head is mainly used to calculate the total pressure drop, and the heat exchange at the head is ignored. The heat exchange is calculated by a cell layer-by-cell calculation method. The heat exchange in the normal direction of the cross surface in the flow direction of the cold and hot fluids is considered to be uniform. The single cell is used as the basic heat exchange unit, and the heat exchange state of each unit is solved layer by layer. The heat exchange inlet and outlet parameters of the unit are passed to the other two adjacent units as input parameters. After the cycle solution is completed, the total heat exchange and the temperature distribution at the outlets of the cold and hot sides are obtained, and the area average is taken as the final temperature result. The pressure drop is calculated according to the parallel pipeline.

[0019] The temperature parameter transfer process between adjacent unit cells:

[0020]

[0021] The relationship between the total heat transfer and the heat transfer of a single cell:

[0022]

[0023] The relationship between the total pressure drop of the heat exchanger and the pressure drop of the single cell and the head:

[0024]

[0025] Calculation of average temperature at heat exchanger outlet:

[0026]

[0027] In the formula, represents the temperature at the entrance of the i+1th row of cells, represents the temperature at the outlet of the i-th row of cells, represents the temperature at the entrance of the j+1th column unit cell, represents the temperature at the outlet of the jth column of cells; Q represents the total heat exchange, Q ij is the heat transfer of the unit cell in the i-th row and j-th column, m and n represent the total number of units along the hot and cold fluid directions, i and j represent the single unit cell in the i-th row and j-th column, ΔP represents the total pressure drop, ΔP 1,j represents the voltage drop of the unit cell in row 1 and column j, Respectively represent the total pressure drop of the first and second row of unit cells, Respectively represent the total pressure drop of the i-th row and the m-th row of cells, ΔP end Indicates the head pressure drop; t ave,out represents the average temperature at the outlet, A i represents the flow cross-sectional area of ​​the single cell in the i-th row and n-th column, A total It represents the total flow cross-sectional area at the outlet, t i,out represents the outlet temperature of the single unit cell in the i-th row and n-th column. The subscripts in, out and ave represent the unit inlet, outlet and total average temperature of the heat exchanger, respectively.

[0028] When calculating the flow and heat transfer performance of each single cell layer, that is, the heat exchange performance, the thermal balance is automatically calculated based on the fmincon algorithm to achieve adaptive thermal balance calculation for each cell. At this time, the objective function is the thermal balance error ERROR:

[0029]

[0030] In the formula, Q kAt is the heat transfer calculated based on the total heat transfer coefficient, Q hot is the heat transfer calculated based on the hot fluid flow rate, Q cold It represents the heat transfer calculated based on the flow rate of the cold fluid. The subscript hot represents the hot fluid, cold represents the cold fluid, and kAt represents the total heat transfer coefficient method. By calculating the heat balance state of each unit cell, the total heat transfer of the heat exchanger is finally obtained.

[0031] Based on the above heat exchanger design calculation process, the single cell unit size, wall thickness, length, width, height and head height of the heat exchange core are used as decision variables. The constraints include the outlet temperature requirements of the fluids on the hot and cold sides and the overall size requirements of the heat exchanger. The optimization target is set to the pressure drop on the hot and cold sides. The heat exchanger optimization design method is constructed based on the multi-objective genetic optimization algorithm, and finally the optimal solution set of the pressure drop on the hot and cold sides of the heat exchanger is obtained. In this solution set, the final design scheme is selected according to the heat exchange and pressure drop requirements to complete the design of the high-temperature air preheater.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] The purpose of the present invention is to develop a set of optimization design methods for solid oxide fuel cell air preheaters. Generally speaking, the hydraulic characteristics corresponding to the three-period minimal surface structure are difficult to be directly calculated by geometric parameters. Therefore, the present invention constructs a sample database and further develops an artificial neural network model to quickly predict and calculate the hydraulic characteristics of the single cell structure, providing input parameters for heat transfer calculation. In addition, the head is incorporated into the calculation process of flow resistance, and a corresponding sample library and artificial neural network model of the head structure and the local resistance coefficient are established to quickly calculate the flow characteristics at the head under different overall sizes. In view of the large influence of temperature on physical properties, the total heat transfer and flow performance of the heat exchange core are calculated by a cell-by-cell method, and the thermal balance conditions are automatically calculated at each single cell, which is closer to the actual heat exchange process. Finally, considering the interaction between the single cell and the whole, the single cell parameters and the overall size are used as decision variables, and the pressure drop on both the cold and hot sides is used as the optimization target. The high-temperature air preheater is optimized and designed based on a multi-objective genetic optimization algorithm, which can output the optimal solution set of the final design scheme according to the design requirements, improve the design efficiency, and provide a solution for the rapid and efficient development of highly compact solid oxide fuel cell thermal balance components. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] By reading the detailed description of the preferred specific embodiments below, various other advantages and benefits of the present invention will become clear to those of ordinary skill in the art. The drawings in the specification are only for the purpose of illustrating the preferred embodiments and are not considered to be limitations of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative work. Moreover, the same reference numerals are used to represent the same components throughout the drawings.

[0035] In the attached picture:

[0036] Figure 1 It is a schematic flow chart of a method for optimizing the design of a high-temperature air preheater for a solid oxide fuel cell based on a three-periodic minimal surface according to the present invention.

[0037] Figure 2 It is the optimal solution set distribution diagram calculated by the present invention. DETAILED DESCRIPTION

[0038] The specific embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the specific embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0039] It should be noted that certain words are used in the specification and claims to refer to specific components. Those skilled in the art should understand that technicians may use different nouns to refer to the same component. This specification and claims do not use the difference in nouns as a way to distinguish components, but use the difference in the functions of the components as the criterion for distinction. As mentioned throughout the specification and claims, "including" or "comprising" is an open term, so it should be interpreted as "including but not limited to". The subsequent description of the specification is a preferred embodiment of the present invention, but the description is based on the general principles of the specification and is not intended to limit the scope of the present invention. The scope of protection of the present invention shall be determined by the attached claims.

[0040] To facilitate understanding of the embodiments of the present invention, several specific embodiments will be further explained below with reference to the accompanying drawings, and each of the accompanying drawings does not constitute a limitation on the embodiments of the present invention.

[0041] For a better understanding, Figure 1 and Figure 2 As shown, a high temperature air preheater optimization design method for solid oxide fuel cells based on three-periodic minimal surfaces includes:

[0042] S1: Build a sample database of single cell geometric parameters and hydraulic characteristic parameters, head structure and local resistance coefficient, and build the corresponding artificial neural network model based on the sample database;

[0043] S2: Based on the consideration of the head structure, a three-period minimal surface structure is selected according to the cross-flow heat exchange structure. The unit cell is used as the calculation unit, and the flow and heat transfer performance are calculated cell by cell, and the overall thermal performance is finally obtained;

[0044] S3: Based on the nonlinear optimization algorithm fmincon, adaptive heat balance calculation is realized for each unit cell, and the operating parameters of the dual-fluid heat exchanger under a given structure are obtained by solving each unit cell;

[0045] S4: Taking the single cell size, wall thickness, heat exchange core size, and head height as decision variables, the minimum pressure drop on both the cold and hot sides as the optimization goal, and the total size limit and the hot side temperature outlet as constraints, the high-temperature air preheater is optimized based on a multi-objective genetic algorithm;

[0046] S5: Calculate the optimal solution set, select the design scheme that meets the requirements, obtain the overall design parameters of the optimized three-period minimal surface structure heat exchanger, and complete the design of the high-temperature air preheater.

[0047] The calculation method in the specific embodiment includes:

[0048] The single crystal cell geometric parameters include the single crystal cell size uc and wall thickness δ uc The hydraulic characteristic parameters of the single cell include the hydraulic diameter D h , Flow cross-sectional area A cross , single cell single side heat transfer area HSA uc ; According to the size of the single unit cell and the wall thickness, a three-periodic minimal surface unit structure with corresponding parameters can be designed. By checking the cross-sectional area of ​​the single unit cell solid wall through the modeling software, the flow cross-sectional area A can be obtained. cross , Single-side heat exchange area HSA uc , the hydraulic diameter is calculated according to the following formula:

[0049]

[0050] Where V f,s Indicates the fluid volume corresponding to the fluid on one side.

[0051] According to this method, the modeling software is used to build minimal surface single cell models of different structures, view and calculate their hydraulic characteristics, form a sample database, and combine the double-layer feedforward network fitting model to build the following artificial neural network model:

[0052] [D h ,A cross ,HSA uc ]=f(size uc ,δ uc )

[0053] The model quickly calculates the corresponding hydraulic characteristic parameters based on the size and wall thickness of the single cell, solving the problem of difficulty in directly calculating the hydraulic characteristics of the three-period minimal surface structure, and facilitating the subsequent optimization of the single cell structure.

[0054] The end cap structure includes the end cap cluster tube diameter d bt , height δ along the fluid flow direction end , the length of the head l core and width w core, the local resistance coefficient of the head is ξ, which represents the pressure drop generated by the heads at both ends; the length and width of the heads on the hot and cold sides are equal to the corresponding side dimensions of the heat exchanger core. First, the head model with different bundle tube diameters, lengths, widths and heights is established using modeling software, and the corresponding pressure drop ΔP is calculated using numerical simulation software. end , calculate the local resistance coefficient ξ according to the following formula:

[0055]

[0056] In the formula, ρ represents the average density of the fluid at the head, v ave Indicates the average inlet and outlet flow rate.

[0057] Based on this, different core ,w core ,d bt ,δ end The ξ sample database corresponding to the parameter combination is combined with the double-layer feedforward network fitting model to construct the following artificial neural network model:

[0058] ξ=f(l core ,w core ,d bt ,δ end )

[0059] The cross-flow heat exchange structure is a heat exchange core, which is a heat calculation area. The head is mainly used to calculate the total pressure drop, and the heat exchange at the head is ignored. The heat exchange is calculated by unit cell by unit cell. The heat exchange in the normal direction of the cross surface in the flow direction of the hot and cold fluids is considered to be uniform. The single unit cell is used as the basic heat exchange unit. The heat exchange state of each unit is solved one by one, and the heat exchange inlet and outlet parameters of the unit are passed to the other two adjacent units as input parameters. After the cycle solution is completed, the total heat exchange and the temperature distribution at the outlets of the hot and cold sides are obtained, and the area average is taken as the final temperature result. The pressure drop is calculated according to the parallel pipeline.

[0060] The single cell heat transfer correlation adopts the existing correlation in the literature.

[0061] Nu=0.471·Re 0.627 Pr 1 / 3

[0062] f=2.577·Re -0.095

[0063]

[0064] Where h is the convective heat transfer coefficient on the corresponding side, λ is the average thermal conductivity of the fluid, L is the length of the fluid flow direction in the single crystal cell, and v ucis the average flow velocity in the unit cell, Nu is the Nusselt number, Re is the Reynolds number, Pr is the Prandtl number of the corresponding fluid, f is the friction factor of the corresponding fluid channel, ρ is the density of the corresponding fluid, ΔP uc represents the pressure drop on the fluid side of the single crystal cell. The heat transfer of the single crystal cell is further calculated according to the above formula, including the heat exchange of the fluid on both the cold and hot sides (Q hot and Q cold ) and the heat transfer through the wall (Q kAt ), these three heat transfer rates follow the energy conservation rate, and the calculation formula is as follows:

[0065] Q kAt = k·HSA·ΔT m

[0066] Q hot =m hot ·c p,hot ·(t in,hot -t out,hot )

[0067] Q cold =m cold ·c p,cold ·(t out,cold -t in,cold )

[0068] In the formula, k represents the total heat transfer coefficient of the unit cell, HSA represents the total heat transfer area of ​​the unit cell, ΔT m is the logarithmic mean temperature difference, m hot represents the mass flow rate of thermal fluid, c p,hot is the specific heat capacity of the hot fluid at constant pressure, t in,hot represents the hot fluid inlet temperature, t out,hot represents the outlet temperature of the hot fluid, m cold is the mass flow rate of the cold fluid, c p,cold is the specific heat capacity of the cold fluid at constant pressure, t out,cold is the outlet temperature of the cold fluid, t in,cold is the cold fluid inlet temperature.

[0069] The above formula is the basic formula for calculating unit cell flow and heat transfer, but the input and output parameters of each unit cell are interrelated. The unit cells in the same row or column are connected in series, so the mass flow rate remains unchanged. The inlet temperature is the outlet temperature of the previous unit cell. Therefore, the temperature parameter transfer process between adjacent unit cells is:

[0070]

[0071] The relationship between the total heat transfer and the heat transfer of a single cell:

[0072]

[0073] The relationship between the total pressure drop of the heat exchanger and the pressure drop of the single cell and the head:

[0074]

[0075] Calculation of average temperature at heat exchanger outlet:

[0076]

[0077] In the formula, represents the temperature at the entrance of the i+1th row of cells, represents the temperature at the outlet of the i-th row of cells, represents the temperature at the entrance of the j+1th column unit cell, represents the temperature at the outlet of the jth column of cells; Q represents the total heat exchange, Q ij is the heat transfer of the unit cell in the i-th row and j-th column, m and n represent the total number of units along the hot and cold fluid directions, i and j represent the single unit cell in the i-th row and j-th column, ΔP represents the total pressure drop, ΔP 1,j represents the voltage drop of the unit cell in row 1 and column j, Respectively represent the total pressure drop of the first and second row of unit cells, Respectively represent the total pressure drop of the i-th row and the m-th row of cells, ΔP end Indicates the head pressure drop; t ave,out represents the average temperature at the outlet, A i represents the flow cross-sectional area of ​​the single cell in the i-th row and n-th column, A total It represents the total flow cross-sectional area at the outlet, t i,out represents the outlet temperature of the single unit cell in the i-th row and n-th column. The subscripts in, out and ave represent the unit inlet, outlet and total average temperature of the heat exchanger, respectively.

[0078] When calculating the heat transfer performance of each single cell layer, the thermal balance is automatically calculated based on the fmincon algorithm to achieve adaptive thermal balance calculation for each cell. At this time, the objective function is the thermal balance error ERROR:

[0079]

[0080] In the formula, Q kAt is the heat transfer calculated based on the total heat transfer coefficient, Q hot is the heat transfer calculated based on the hot fluid flow rate, Q cold It represents the heat transfer calculated based on the flow rate of cold fluid. The subscript hot represents hot fluid, cold represents cold fluid, and kAt represents the total heat transfer coefficient method. By calculating the heat balance state of each unit cell, the total heat transfer of the heat exchanger is finally obtained.

[0081] Based on the above heat exchanger design calculation process, the single cell size is uc , wall thickness δuc , the length of the heat exchange core l core 、Width core , height core 、Head height δ end is the decision variable. The constraints include the outlet temperature requirements of the fluids on both sides of the heat exchanger and the overall size requirements of the heat exchanger. The optimization target is set as the pressure drop (ΔP cold , ΔP hot ), combined with the multi-objective genetic optimization algorithm, a heat exchanger optimization design method is constructed based on this, and finally the optimal solution set of the pressure drop on both sides of the heat exchanger is obtained (such as Figure 2 In this solution set, the final design scheme is selected according to the heat exchange and pressure drop requirements to complete the design of the high-temperature air preheater.

[0082] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0083] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for optimizing the design of a high-temperature air preheater for a solid oxide fuel cell based on a three-periodic minimal surface, characterized in that: The steps include: S1: Build a sample database of single cell geometric parameters and hydraulic characteristic parameters, head structure and local resistance coefficient, and build the corresponding artificial neural network model based on the sample database; S2: Based on the consideration of the head structure, a three-period minimal surface structure is selected according to the cross-flow heat exchange structure. The unit cell is used as the calculation unit, and the flow and heat transfer performance are calculated cell by cell, and the overall thermal performance is finally obtained; S3: Based on the nonlinear optimization algorithm fmincon, adaptive heat balance calculation is realized for each unit cell, and the operating parameters of the dual-fluid heat exchanger under a given structure are obtained by solving each unit cell; S4: Taking the single cell size, wall thickness, heat exchange core size, and head height as decision variables, the minimum pressure drop on both the cold and hot sides as the optimization goal, and the total size limit and the hot side temperature outlet as constraints, the high-temperature air preheater is optimized based on a multi-objective genetic algorithm; S5: Calculate the optimal solution set, select the design scheme that meets the requirements, obtain the overall design parameters of the optimized three-period minimal surface structure heat exchanger, and complete the design of the high-temperature air preheater.

2. The optimization design method for a high temperature air preheater for a solid oxide fuel cell based on a three-periodic minimal surface according to claim 1, characterized in that: The single crystal cell geometric parameters include the single crystal cell size uc and wall thickness δ uc The hydraulic characteristic parameters of the single cell include the hydraulic diameter D h , Flow cross-sectional area A cross , Single-side heat exchange area HSA uc ; The head structure includes the head bundle tube diameter d bt , height δ along the fluid flow direction end , the length of the head l core and width w core , the local resistance coefficient of the head is ξ, which represents the pressure drop generated by the heads at both ends.

3. The optimization design method for a high temperature air preheater for a solid oxide fuel cell based on a three-periodic minimal surface according to claim 1, characterized in that: The sample database is a one-to-one correspondence library constructed after the corresponding parameters are calculated by modeling software and numerical simulation software. The single cell model under different unit size-wall thickness combinations is constructed using modeling software, and the hydraulic characteristic parameters of the single cell under each combination are calculated to form a sample database. The local resistance coefficient of the head is calculated by modeling software and numerical simulation software, and together with the head structure, it constitutes a sample database.

4. The optimization design method for a high temperature air preheater for a solid oxide fuel cell based on a three-periodic minimal surface according to claim 1, characterized in that: The artificial neural network model includes two models, a single cell structure-hydraulic characteristic parameter prediction model and a head height-local resistance coefficient prediction model, which are constructed based on a double-layer feedforward network fitting model. The model is used to calculate the flow and heat transfer performance of the heat exchanger under a given structure, and is expressed in the form of: [D h ,A cross ,HSA uc ]=f(size uc ,δ uc ) ξ=f(l core ,w core ,d bt ,d end ) Where: D h represents the hydraulic diameter of a unit cell, A cross Represents the cross-sectional area of ​​a single cell, HSA uc Indicates the heat transfer area on one side of a single cell, size uc represents the unit cell size, δ uc represents the thickness of the single cell wall, l core Indicates the length of the head, w core Indicates the width of the head, d bt Indicates the diameter of the head cluster tube, δ end Indicates seal The height of the head along the direction of fluid flow, ξ represents the local resistance coefficient of the head.

5. The optimization design method for a high temperature air preheater for a solid oxide fuel cell based on a three-periodic minimal surface according to claim 1, characterized in that: The cross-flow heat exchange structure is a heat exchange core, which is a heat calculation area. The head is mainly used to calculate the total pressure drop, and the heat exchange at the head is ignored. When calculating the heat exchange, a cell-by-cell layer calculation method is adopted. The heat exchange in the normal direction of the cross surface in the flow direction of the cold and hot fluids is considered to be uniform. The single cell is used as a basic heat exchange unit, and the heat exchange state of each unit is solved layer by layer. The heat exchange inlet and outlet parameters of the unit are passed to the other two adjacent units as input parameters. After the cycle solution is completed, the total heat exchange and the temperature distribution at the outlets of the cold and hot sides are obtained, and the area average is taken as the final temperature result. The pressure drop is calculated according to the parallel pipeline. The temperature parameter transfer process between adjacent unit cells: The relationship between the total heat transfer and the heat transfer of a single cell: The relationship between the total pressure drop of the heat exchanger and the pressure drop of the single cell and the head: Calculation of average temperature at heat exchanger outlet: In the formula, represents the temperature at the entrance of the i+1th row of cells, represents the temperature at the outlet of the i-th row of cells, represents the temperature at the entrance of the j+1th column of cells, represents the temperature at the outlet of the jth column of cells; Q represents the total heat exchange, Q ij is the heat transfer of the unit cell in the i-th row and j-th column, m and n represent the total number of unit cells along the hot and cold fluid directions, respectively, and i and j represent the single unit cell in the i-th row and j-th column, respectively; ΔP represents the total pressure drop, ΔP 1,j represents the voltage drop of the unit cell in row 1 and column j, Respectively represent the total pressure drop of the first and second row of unit cells, Respectively represent the total pressure drop of the i-th row and the m-th row of cells, ΔP end Indicates the head pressure drop; t ave,out represents the average temperature at the outlet, A i represents the flow cross-sectional area of ​​the single cell in the i-th row and n-th column, A total It represents the total flow cross-sectional area at the outlet, t i,out represents the outlet temperature of the single unit cell in the i-th row and n-th column. The subscripts in, out and ave represent the unit inlet, outlet and total average temperature of the heat exchanger, respectively.

6. The optimization design method for a high temperature air preheater for a solid oxide fuel cell based on a three-periodic minimal surface according to claim 1, characterized in that: When calculating the flow and heat transfer performance of each single cell layer, that is, the heat exchange performance, the thermal balance is automatically calculated based on the fmincon algorithm to achieve adaptive thermal balance calculation for each cell. At this time, the objective function is the thermal balance error ERROR: In the formula, Q kAt is the heat transfer calculated based on the total heat transfer coefficient, Q hot is the heat transfer calculated based on the hot fluid flow rate, Q cold It represents the heat transfer calculated based on the flow rate of cold fluid. The subscript hot represents hot fluid, cold represents cold fluid, and kAt represents the total heat transfer coefficient method. By calculating the heat balance state of each unit cell, the total heat transfer of the heat exchanger is finally obtained.

Images