Method and device for optimizing working condition of solid oxide electrolytic cell stack

Abstract

The invention relates to the technical field of solid oxide electrolytic cell working condition optimization, in particular to a solid oxide electrolytic cell electric pile working condition optimization method and device, and the method comprises the steps: obtaining a matched electrolytic cell electric pile calculation model based on the electrolysis mode and electric pile size of a solid oxide electrolytic cell electric pile to be optimized; determining a plurality of groups of input parameter values and operation boundaries of the to-be-optimized solid oxide electrolytic cell stack; respectively inputting each group of input parameter values into a matched electrolytic cell galvanic pile calculation model to obtain a plurality of groups of response parameter values; and based on the multiple groups of response parameter values and the operation boundary, obtaining an input parameter value meeting a certain scoring condition so as to obtain a working condition optimization result of the to-be-optimized solid oxide electrolytic cell stack. Therefore, the problems that in the prior art, optimization and prediction of the working condition in the electrolysis mode are not considered, prediction is carried out only for a single battery, working condition optimization of the electric pile level is not considered, and indexes are considered to be one-sided are solved.

Description

Technical Field

[0001] The present application relates to the technical field of solid oxide electrolytic cell operating condition optimization, and in particular to a method and device for optimizing the operating condition of a solid oxide electrolytic cell stack. Background Art

[0002] Solid oxide electrolysis cell is an electrolysis cell working under high temperature conditions. It has the advantages of high efficiency and no need for rare precious metal materials. It is considered to be one of the most promising hydrogen production technologies. In addition, solid oxide electrolysis cell can also electrolyze H2O and CO2 into H2 and CO, and then integrate with downstream chemical processes.

[0003] In the related technology, the target fuel cell response PINN (Physics-Informed Neural Networks) model can be matched according to the fuel type and size of the fuel cell to be analyzed, and each set of input parameter values ​​can be input into the target fuel cell response PINN model to obtain the response parameter values ​​of the fuel cell to be analyzed under each input parameter value, and then the optimized operating condition of the fuel cell to be analyzed can be determined; it is also possible to determine the test cycle of the whole vehicle based on the vehicle configuration information, and then calculate the fuel cell power curve with the lowest hydrogen consumption of the fuel cell, so as to determine the target operating point of the fuel cell.

[0004] However, the related technology does not consider the optimization and prediction of the operating conditions in the electrolysis mode. It only makes predictions for single cells, and does not consider the optimization of the operating conditions at the battery stack level. The indicators considered are relatively one-sided and urgently need to be improved. Summary of the invention

[0005] The present application provides a method and device for optimizing the operating conditions of a solid oxide electrolytic cell stack, in order to solve the problems in the related art that the optimization and prediction of the operating conditions in the electrolysis mode are not considered, the prediction is only performed for a single cell, the optimization of the operating conditions at the stack level is not considered, and the indicators are considered in a relatively one-sided manner.

[0006] The first aspect of the present application provides a method for optimizing the operating conditions of a solid oxide electrolyzer stack, comprising the following steps: based on the electrolysis mode and stack size of the solid oxide electrolyzer stack to be optimized, obtaining an electrolyzer stack calculation model that matches the solid oxide electrolyzer stack to be optimized; determining multiple groups of input parameter values ​​and operating boundaries of the solid oxide electrolyzer stack to be optimized; inputting each group of input parameter values ​​into the matching electrolyzer stack calculation model respectively to obtain multiple groups of response parameter values ​​of the solid oxide electrolyzer stack to be optimized; based on the multiple groups of response parameter values ​​and the operating boundaries, obtaining input parameter values ​​that meet preset scoring conditions, and obtaining operating condition optimization results of the solid oxide electrolyzer stack to be optimized based on the input parameter values ​​that meet the preset scoring conditions.

[0007] Optionally, in one embodiment of the present application, before inputting each set of input parameter values ​​into the matching electrolytic cell stack calculation model to obtain multiple sets of response parameter values ​​of the solid oxide electrolytic cell stack to be optimized, it also includes: based on the experimental and simulation results of the solid oxide electrolytic cell stack to be optimized, combined with the target neural network model, constructing an electrolytic cell single cell neural network proxy model of the electrolytic cell stack calculation model; based on the airway flow resistance calculation method of the solid oxide electrolytic cell stack to be optimized, constructing the electrolytic cell stack calculation model; The invention relates to an electrolytic cell stack airflow distribution calculation model for an electrolytic cell; based on the electrolytic cell stack heat balance calculation model, an electrolytic cell stack heat balance calculation model for the electrolytic cell stack calculation model is constructed; based on the electrolytic cell single cell multi-physical field calculation model, a three-dimensional multi-physical field calculation model for the electrolytic cell stack calculation model is constructed; based on the electrolytic cell single cell neural network proxy model, the electrolytic cell stack airflow distribution calculation model, the electrolytic cell stack heat balance calculation model and the electrolytic cell stack three-dimensional multi-physical field calculation model, the electrolytic cell stack calculation model is constructed.

[0008] Optionally, in one embodiment of the present application, each set of input parameter values ​​is input into the matching electrolytic cell stack calculation model to obtain multiple sets of response parameter values ​​of the solid oxide electrolytic cell stack to be optimized, including: determining the total current and the minimum water vapor mole fraction of the electrolytic cell stack in the solid oxide electrolytic cell stack to be optimized based on the electrolytic cell single cell neural network proxy model; determining the gas flow rate of the electrolytic cell stack in the solid oxide electrolytic cell stack to be optimized based on the electrolytic cell stack gas flow distribution calculation model; obtaining the average temperature of the electrolytic cell stack in the solid oxide electrolytic cell stack to be optimized based on the electrolytic cell stack thermal balance calculation model; obtaining the three-dimensional multi-physical field distribution of the solid oxide electrolytic cell stack to be optimized based on the three-dimensional multi-physical field calculation model of the electrolytic cell stack; and obtaining the multiple sets of response parameter values ​​based on the total current, the minimum water vapor mole fraction, the gas flow rate, the average temperature and the three-dimensional multi-physical field distribution of the electrolytic cell stack.

[0009] Optionally, in one embodiment of the present application, the step of obtaining input parameter values ​​that meet preset scoring conditions based on the multiple groups of response parameter values ​​and the operating boundaries includes: obtaining scoring results of the multiple groups of response parameter values; determining a scoring limit value of the scoring results based on the operating boundaries; and obtaining the input parameter value of the preset scoring condition based on the scoring limit value.

[0010] Optionally, in one embodiment of the present application, the gas flow rate of the single cell of the electrolytic cell stack in the solid oxide electrolytic cell stack to be optimized is determined based on the calculation model of the gas flow distribution of the electrolytic cell stack, including: obtaining the pure substance viscosity of each gas component in the fuel electrode and the oxygen electrode in the solid oxide electrolytic cell stack to be optimized; calculating the viscosity of the mixed gas in the fuel electrode and the oxygen electrode based on the pure substance viscosity of each gas component; calculating the airway flow resistance of the fuel electrode and the oxygen electrode of the single cell of the electrolytic cell stack based on the pure substance viscosity of each gas component and the viscosity of the mixed gas; and calculating the gas flow rate of the single cell of the electrolytic cell stack based on the airway flow resistance.

[0011] The second aspect of the present application provides an optimization device for the operating conditions of a solid oxide electrolyzer stack, comprising: a first generation module, used to obtain an electrolyzer stack calculation model that matches the solid oxide electrolyzer stack to be optimized based on the electrolysis mode and stack size of the solid oxide electrolyzer stack to be optimized; a determination module, used to determine multiple groups of input parameter values ​​and operating boundaries of the solid oxide electrolyzer stack to be optimized; an acquisition module, used to input each group of input parameter values ​​into the matching electrolyzer stack calculation model, so as to obtain multiple groups of response parameter values ​​of the solid oxide electrolyzer stack to be optimized; a second generation module, used to obtain input parameter values ​​that meet preset scoring conditions based on the multiple groups of response parameter values ​​and the operating boundaries, so as to obtain the operating condition optimization result of the solid oxide electrolyzer stack to be optimized based on the input parameter values ​​that meet the preset scoring conditions.

[0012] Optionally, in one embodiment of the present application, it also includes: a first construction module for constructing an electrolytic cell single cell neural network proxy model of the electrolytic cell stack calculation model based on the experimental and simulation results of the solid oxide electrolytic cell stack to be optimized and in combination with the target neural network model before inputting each set of input parameter values ​​into the matching electrolytic cell stack calculation model to obtain multiple sets of response parameter values ​​of the solid oxide electrolytic cell stack to be optimized; a second construction module for constructing an electrolytic cell single cell neural network proxy model of the electrolytic cell stack calculation model based on the airway flow resistance calculation method of the solid oxide electrolytic cell stack to be optimized a calculation model for airflow distribution of the electrolytic cell stack; a third construction module, for constructing a heat balance calculation model of the electrolytic cell stack of the electrolytic cell stack calculation model based on the heat balance equation of the electrolytic cell stack; a fourth construction module, for constructing a three-dimensional multi-physical field calculation model of the electrolytic cell stack of the electrolytic cell stack calculation model based on the multi-physical field calculation model of the electrolytic cell single cell; a fifth construction module, for constructing the calculation model of the electrolytic cell stack based on the single-cell neural network proxy model of the electrolytic cell, the airflow distribution calculation model of the electrolytic cell stack, the heat balance calculation model of the electrolytic cell stack and the three-dimensional multi-physical field calculation model of the electrolytic cell stack.

[0013] Optionally, in one embodiment of the present application, the acquisition module includes: a first determination unit, used to determine the total current and the minimum water vapor mole fraction of the electrolytic cell stack in the solid oxide electrolytic cell stack to be optimized based on the electrolytic cell single cell neural network proxy model; a second determination unit, used to determine the gas flow rate of the electrolytic cell stack in the solid oxide electrolytic cell stack to be optimized based on the electrolytic cell stack gas flow distribution calculation model; a first generation unit, used to obtain the average temperature of the electrolytic cell stack in the solid oxide electrolytic cell stack to be optimized based on the electrolytic cell stack thermal balance calculation model; a second generation unit, used to obtain the three-dimensional multi-physical field distribution of the solid oxide electrolytic cell stack to be optimized based on the three-dimensional multi-physical field calculation model of the electrolytic cell stack; a third generation unit, used to obtain the multiple groups of response parameter values ​​based on the total current, the minimum water vapor mole fraction, the gas flow rate, the average temperature and the three-dimensional multi-physical field distribution of the electrolytic cell stack.

[0014] Optionally, in one embodiment of the present application, the second generation module includes: an acquisition unit, used to obtain the scoring results of the multiple groups of response parameter values; a third determination unit, used to determine the scoring limit value of the scoring result based on the operating boundary; and a fourth generation unit, used to obtain the input parameter value of the preset scoring condition based on the scoring limit value.

[0015] Optionally, in one embodiment of the present application, the second determination unit includes: an acquisition subunit, used to acquire the pure substance viscosity of each gas component in the fuel electrode and the oxygen electrode in the solid oxide electrolyzer stack to be optimized; a first calculation subunit, used to calculate the viscosity of the mixed gas in the fuel electrode and the oxygen electrode based on the pure substance viscosity of each gas component; a second calculation subunit, used to calculate the gas flow resistance of the fuel electrode and the oxygen electrode of the electrolyzer stack single cell based on the pure substance viscosity of each gas component and the viscosity of the mixed gas; and a third calculation subunit, used to calculate the gas flow of the electrolyzer stack single cell based on the gas flow resistance.

[0016] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for optimizing the operating conditions of a solid oxide electrolytic cell stack as described in the above embodiment.

[0017] A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above-mentioned method for optimizing the operating conditions of a solid oxide electrolysis cell stack.

[0018] The fifth aspect of the present application provides a computer program product, including a computer program, which, when executed, implements the above-mentioned method for optimizing the operating conditions of a solid oxide electrolytic cell stack.

[0019] The embodiment of the present application can first match the corresponding electrolytic cell stack calculation model based on the electrolysis mode and stack size of the solid oxide electrolytic cell stack to be optimized, and then input each set of input parameter values ​​of the solid oxide electrolytic cell stack to be optimized into the matching electrolytic cell stack calculation model to obtain multiple sets of response parameter values, and based on the response parameter values ​​and the operating boundary, obtain the input parameter values ​​that meet certain scoring conditions, and then generate the operating condition optimization results of the solid oxide electrolytic cell stack to be optimized, so that the calculation results can be compatible with the calculation of different stack sizes and thermal boundary conditions, improve the accuracy and calculation efficiency, in addition, the electrolytic cell stack calculation model contains more abundant parameters, can more comprehensively consider the safe and efficient operation boundaries of the electrolytic cell stack, and the evaluation system of the response parameters is more complete and reasonable. Thus, the problems in the related art that the optimization and prediction of the operating conditions under the electrolysis mode are not considered, only the prediction is made for the single cell, the operating condition optimization at the stack level is not considered, and the indicators are considered to be one-sided.

[0020] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0022] Figure 1 A flowchart of a method for optimizing the operating conditions of a solid oxide electrolytic cell stack provided in accordance with an embodiment of the present application;

[0023] Figure 2 A schematic block diagram of an electrolytic cell stack calculation model provided according to an embodiment of the present application;

[0024] Figure 3 A flowchart of an iterative calculation process in an electrolytic cell stack calculation model provided according to an embodiment of the present application;

[0025] Figure 4 A flowchart of a calculation process of an electrolytic cell stack gas flow distribution calculation model provided according to an embodiment of the present application;

[0026] Figure 5(a)-Figure 5(e) A schematic diagram of contour lines of the electrolytic cell stack provided in one embodiment of the present application, including the average voltage per sheet, steam utilization rate, inlet gas temperature, inlet and outlet gas temperature difference, and maximum temperature gradient at different current densities and average fuel electrode flow rates per sheet;

[0027] FIG5( f ) is a block diagram of the safe and efficient operation boundary of an electrolytic cell stack at different current densities and average fuel electrode flow rates according to one embodiment of the present application;

[0028] Figure 6 A flowchart of the working principle of a method for optimizing the operating conditions of a solid oxide electrolytic cell stack provided in accordance with one embodiment of the present application;

[0029] Figure 7 A block diagram of a device for optimizing the working conditions of a solid oxide electrolytic cell stack provided in accordance with an embodiment of the present application;

[0030] Figure 8 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0031] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0032] The following describes a method and device for optimizing the operating conditions of a solid oxide electrolytic cell stack according to an embodiment of the present application with reference to the accompanying drawings. In response to the problems mentioned in the above background technology that the optimization and prediction of the operating conditions under the electrolysis mode are not considered, only the prediction is made for the single cell, the optimization of the operating conditions at the stack level is not considered, and the indicators are considered in a relatively one-sided manner, the present application provides a method for optimizing the operating conditions of a solid oxide electrolytic cell stack. In this method, the corresponding electrolytic cell stack calculation model can be matched based on the electrolysis mode and stack size of the solid oxide electrolytic cell stack to be optimized, and then each group of input parameter values ​​of the solid oxide electrolytic cell stack to be optimized is input into the matching electrolytic cell stack calculation model to obtain multiple groups of response parameter values, and based on the response parameter values ​​and operating boundaries, the input parameter values ​​that meet certain scoring conditions are obtained, and then the operating condition optimization results of the solid oxide electrolytic cell stack to be optimized are generated, so that the calculation results can be compatible with the calculation of different stack sizes and thermal boundary conditions, thereby improving accuracy and calculation efficiency. In addition, the electrolytic cell stack calculation model contains richer parameters, which can more comprehensively consider the safe and efficient operation boundaries of the electrolytic cell stack, and the evaluation system for the response parameters is more complete and reasonable. As a result, problems in related technologies such as not considering the optimization and prediction of operating conditions in the electrolysis mode, only making predictions for single cells, not considering the optimization of operating conditions at the battery stack level, and considering indicators in a rather one-sided manner are solved.

[0033] Specifically, Figure 1The present invention is a flow chart of a method for optimizing the operating conditions of a solid oxide electrolytic cell stack provided according to an embodiment of the present application.

[0034] like Figure 1 As shown, the method for optimizing the operating conditions of the solid oxide electrolytic cell stack includes the following steps:

[0035] In step S101, based on the electrolysis mode and stack size of the solid oxide electrolysis cell stack to be optimized, an electrolysis cell stack calculation model matching the solid oxide electrolysis cell stack to be optimized is obtained.

[0036] It can be understood that the embodiment of the present application establishes an electrolytic cell stack calculation model for different electrolysis modes and different stack sizes based on a multi-physics field reference model of the two working modes of electrolysis and co-electrolysis.

[0037] In some embodiments, the embodiments of the present application can match the corresponding electrolytic cell stack calculation model according to the electrolysis mode and stack size of the solid oxide electrolytic cell stack to be optimized.

[0038] In step S102, multiple groups of input parameter values ​​and operating boundaries of the solid oxide electrolysis cell stack to be optimized are determined.

[0039] It can be understood that in the embodiments of the present application, the input parameters may include but are not limited to single cell performance parameters of the battery stack, battery stack structural parameters, thermal boundary conditions, battery stack operating parameters, etc., and the present application does not impose specific limitations.

[0040] Further, in the embodiments of the present application, the operating boundaries may include, but are not limited to, maximum and minimum slice average voltages, maximum and minimum steam utilization rates, maximum temperature gradients, etc., and the present application does not impose specific limitations.

[0041] In some embodiments, the embodiments of the present application can determine multiple sets of input parameter values ​​of the solid oxide electrolysis cell stack to be optimized and the safe and efficient operation boundaries of the solid oxide electrolysis cell stack to be optimized.

[0042] Optionally, in one embodiment of the present application, before inputting each set of input parameter values ​​into the matching electrolytic cell stack calculation model to obtain multiple sets of response parameter values ​​of the solid oxide electrolytic cell stack to be optimized, it also includes: constructing an electrolytic cell single-cell neural network proxy model of the electrolytic cell stack calculation model based on the experimental and simulation results of the solid oxide electrolytic cell stack to be optimized and in combination with the target neural network model; constructing an electrolytic cell stack airflow distribution calculation model of the electrolytic cell stack calculation model based on the airway flow resistance calculation method of the solid oxide electrolytic cell stack to be optimized; constructing an electrolytic cell stack thermal balance calculation model of the electrolytic cell stack calculation model based on the electrolytic cell stack thermal balance equation; constructing an electrolytic cell stack three-dimensional multi-physical field calculation model of the electrolytic cell stack calculation model based on the electrolytic cell single-cell multi-physical field calculation model; constructing an electrolytic cell stack calculation model based on the electrolytic cell single-cell neural network proxy model, the electrolytic cell stack airflow distribution calculation model, the electrolytic cell stack thermal balance calculation model and the electrolytic cell stack three-dimensional multi-physical field calculation model.

[0043] As a possible implementation method, the electrolytic cell stack calculation model of the embodiment of the present application may include but is not limited to an electrolytic cell single battery neural network agent model, an electrolytic cell stack airflow distribution calculation model, an electrolytic cell stack thermal balance calculation model, an electrolytic cell stack three-dimensional multi-physics field calculation model, etc., and the present application does not make any specific restrictions.

[0044] Illustratively, in some embodiments, the embodiments of the present application can construct an electrolytic cell single-cell neural network proxy model based on a target neural network model, such as a feedforward neural network, for the experimental and simulation results of the solid oxide electrolytic cell stack to be optimized, such as different stack sizes and target input parameter values. Furthermore, the embodiments of the present application can calculate the electrolytic cell single-cell response parameter values ​​of the target input parameter values ​​based on the electrolytic cell single-cell neural network proxy model, and use different stack size input parameters and response parameter values ​​to train the parameters of the electrolytic cell single-cell neural network proxy model.

[0045] In some embodiments, the embodiments of the present application can construct an electrolytic cell stack airflow distribution calculation model based on an airway flow resistance calculation method, using a flow resistance calculation formula and electrolytic cell stack size parameters.

[0046] In some embodiments, the embodiments of the present application can establish an electrolytic cell stack thermal balance calculation model based on the electrolytic cell stack thermal balance equation and taking into account the thermal boundary conditions of the target input parameters.

[0047] In some embodiments, the embodiments of the present application can establish a three-dimensional multi-physical field calculation model of an electrolytic cell stack based on the multi-physical field calculation model of a single electrolytic cell, and then obtain an electrolytic cell stack calculation model with different electrolysis modes, different stack sizes and different thermal boundary conditions based on the neural network agent model of the single electrolytic cell, the airflow distribution calculation model of the electrolytic cell stack, the electrolytic cell stack thermal balance calculation model and the three-dimensional multi-physical field calculation model of the electrolytic cell stack.

[0048] For example, Figure 2 As shown, the electrolytic cell stack calculation model 20 constructed in the embodiment of the present application may include but is not limited to: an electrolytic cell single battery neural network agent model 201, an electrolytic cell stack airflow distribution calculation model 202, an electrolytic cell stack thermal balance calculation model 203 and an electrolytic cell stack three-dimensional multi-physics field calculation model 204.

[0049] In step S103, each set of input parameter values ​​is input into a matching electrolytic cell stack calculation model to obtain multiple sets of response parameter values ​​of the solid oxide electrolytic cell stack to be optimized.

[0050] In the actual implementation process, the embodiment of the present application can input each set of input parameter values ​​into a matching electrolytic cell stack calculation model to obtain the response parameter values ​​of the solid oxide electrolytic cell stack to be optimized under each input parameter value.

[0051] For example, in an embodiment of the present application, when the electrolysis mode is water electrolysis, the response parameter value may include but is not limited to: the average temperature of each single cell in the electrolytic cell stack, the maximum temperature gradient, the average voltage, the current density, the steam utilization rate, and the gas temperature difference between the fuel electrode inlet and outlet, etc. This application does not impose specific restrictions.

[0052] Optionally, in one embodiment of the present application, each set of input parameter values ​​is respectively input into a matching electrolytic cell stack calculation model to obtain multiple sets of response parameter values ​​for the solid oxide electrolytic cell stack to be optimized, including: determining the total current and minimum water vapor mole fraction of the electrolytic cell stack in the solid oxide electrolytic cell stack to be optimized based on the electrolytic cell single cell neural network proxy model; determining the gas flow rate of the electrolytic cell stack in the solid oxide electrolytic cell stack to be optimized based on the electrolytic cell stack gas flow distribution calculation model; obtaining the average temperature of the electrolytic cell stack in the solid oxide electrolytic cell stack to be optimized based on the electrolytic cell stack thermal balance calculation model; obtaining the three-dimensional multi-physical field distribution of the solid oxide electrolytic cell stack to be optimized based on the three-dimensional multi-physical field calculation model of the electrolytic cell stack; and obtaining multiple sets of response parameter values ​​based on the total current, minimum water vapor mole fraction, gas flow rate, average temperature and the three-dimensional multi-physical field distribution of the electrolytic cell stack.

[0053] In some embodiments, the electrolytic cell single cell neural network agent model of the present application embodiment can determine the total current and minimum water vapor mole fraction of the electrolytic cell stack single cell according to the input parameter values.

[0054] Illustratively, the electrolytic cell single-cell neural network proxy model of the embodiment of the present application can be based on a feedforward neural network framework. Since the training difficulty corresponding to different neural network structures is slightly different, it can be specifically set by technicians in this field according to actual conditions, and this application does not impose any specific restrictions.

[0055] Further, in the training process of the electrolytic cell single-cell neural network proxy model, the embodiment of the present application uses the electrolytic water mode as an example, and uses the electrolytic cell single-cell multi-physics field simulation calculation to generate a large number of data sets, and divides them into training sets and verification sets according to a certain ratio, wherein the training set and the verification set can be set by a technician in the field according to the actual situation, and the present application does not make specific restrictions. Among them, the embodiment of the present application can perform dimensionless processing on the input parameters and output parameters in the data set, and then train the neural network model.

[0056] Among them, the input parameter values ​​of the single-cell neural network agent model of the electrolytic cell in the embodiment of the present application may include but are not limited to the performance parameters of the single-cell stack and the operation parameters of the stack, etc., and the present application does not make specific restrictions; the response parameter values ​​may include but are not limited to the total current and the minimum water vapor mole fraction of the single-cell stack, etc., and the present application does not make specific restrictions.

[0057] In some embodiments, the electrolytic cell stack gas flow distribution calculation model of the embodiment of the present application can calculate the gas flow rate, such as water vapor and air flow rate, flowing through the electrolytic cell stack single cell according to the input parameter value, and the present application does not make specific limitations.

[0058] In some embodiments, the electrolytic cell stack thermal balance calculation model of the present application embodiment can calculate the average temperature of the electrolytic cell stack single cells based on the input parameter values.

[0059] For example, the present application embodiment can simplify the electrolytic cell stack into a number of interrelated lumped single cells, and obtain the average temperature of each single cell based on the electrolytic cell stack heat balance equation. In the calculation process of the present application embodiment, parameters such as the stack thermal conductivity and the single cell-gas equivalent heat transfer coefficient can be obtained through experimental fitting, which can be specifically set by a person skilled in the art according to actual conditions, and this application does not impose any specific restrictions.

[0060] In some embodiments, the three-dimensional multi-physical field calculation model of the electrolytic cell stack of the embodiment of the present application can calculate the three-dimensional multi-physical field distribution of the electrolytic cell stack based on the water vapor flow, air flow and average temperature of the single cells of the electrolytic cell stack.

[0061] Illustratively, the embodiments of the present application can couple the electrolytic cell single-cell neural network proxy model, the electrolytic cell stack airflow distribution calculation model and the electrolytic cell stack thermal balance calculation model to perform iterative solution, and iteratively calculate the water vapor flow, air flow and average temperature of the electrolytic cell stack single-cell. Using the iterative calculation results as input, the multi-physical field distribution of the electrolytic cell stack single-cell is calculated, and then the three-dimensional multi-physical field distribution of the stack is obtained.

[0062] For example, the embodiment of the present application couples the electrolytic cell single cell neural network proxy model, the electrolytic cell stack airflow distribution calculation model and the electrolytic cell stack thermal balance calculation model, and the iterative solution calculation process is as follows: Figure 3 As shown, the main steps include:

[0063] Step S301: setting initial values ​​and calculating convergence residuals.

[0064] Among them, the embodiment of the present application can use the total voltage average value, furnace temperature, and stack average flow rate as initial values, and set the calculation convergence residual.

[0065] Step S302: Calculate the gas flow rates of the fuel electrode and the air electrode of the electrolytic cell stack.

[0066] Among them, the embodiment of the present application can use the electrolytic cell stack airflow distribution calculation model to calculate the gas flow of the fuel electrode and the air electrode of the electrolytic cell stack single cell.

[0067] Step S303: Calculate the cell voltage of the single cell of the electrolytic cell stack.

[0068] Among them, the embodiment of the present application can use the electrolytic cell single cell neural network agent model to calculate the battery voltage of the electrolytic cell stack single cell.

[0069] Step S304: Calculate the average temperature of the single cells in the electrolytic cell stack.

[0070] Among them, the embodiment of the present application can use the electrolytic cell stack thermal balance calculation model to calculate the average temperature of the single cells of the electrolytic cell stack.

[0071] Step S305: Determine whether the convergence residual is less than a set value.

[0072] In this embodiment of the present application, when the convergence residual is less than a set value, step S306 is executed; otherwise, step S302 is executed.

[0073] Step S306: Output the calculation result.

[0074] Optionally, in one embodiment of the present application, based on the calculation model of the gas flow distribution of the electrolytic cell stack, the gas flow rate of a single cell in the solid oxide electrolytic cell stack to be optimized is determined, including: obtaining the pure viscosity of each gas component in the fuel electrode and the oxygen electrode in the solid oxide electrolytic cell stack to be optimized; calculating the viscosity of the mixed gas in the fuel electrode and the oxygen electrode based on the pure viscosity of each gas component; calculating the gas flow resistance of the fuel electrode and the oxygen electrode of the single cell of the electrolytic cell stack based on the pure viscosity of each gas component and the viscosity of the mixed gas; and calculating the gas flow rate of the single cell of the electrolytic cell stack based on the gas flow resistance.

[0075] In some embodiments, when calculating the gas flow rate of a single cell of an electrolytic cell stack based on an electrolytic cell stack gas flow distribution model, the embodiment of the present application involves the influence of gas viscosity on the flow distribution, and then calculates the gas flow rate of a single cell of an electrolytic cell stack. The execution process is as follows Figure 4 As shown, the main steps are:

[0076] Step S401: Calculate the pure viscosity of each gas component in the fuel electrode and the oxygen electrode.

[0077] Step S402: Calculate the viscosity of the mixed gas in the fuel electrode and the oxygen electrode respectively according to the Carr method.

[0078] Step S403: Calculate the gas flow resistance of the fuel electrode and oxygen electrode gas channels of the electrolytic cell stack according to the experimental correlation formula.

[0079] Step S403: Calculate the gas flow rates of the fuel electrode and the oxygen electrode of the electrolytic cell stack according to the characteristic that the flow rate is inversely proportional to the flow resistance.

[0080] In step S104, based on multiple groups of response parameter values ​​and operating boundaries, input parameter values ​​that meet preset scoring conditions are obtained, and based on the input parameter values ​​that meet the preset scoring conditions, operating condition optimization results of the solid oxide electrolytic cell stack to be optimized are obtained.

[0081] As a possible implementation method, the embodiment of the present application can obtain the operating condition optimization result of the solid oxide electrolytic cell stack to be optimized based on the response parameter values ​​of the solid oxide electrolytic cell stack to be optimized under each group of input parameter values, combined with the safe and efficient operation boundaries of the electrolytic cell stack.

[0082] For example, the present embodiment optimizes the working condition of the electrolytic cell stack at 750°C, excess air coefficient of 2, and steam concentration of 90%, and draws a graph based on the working condition optimization results. Figure 5(a)-Figure 5(f) Among them, in the embodiments of the present application, Figure 5(a)-Figure 5(e)Contour plots of the average voltage per sheet, steam utilization, inlet gas temperature, inlet and outlet gas temperature difference, and maximum temperature gradient of the electrolytic cell stack at different current densities and single-cell fuel electrode flow rates of the electrolytic cell stack are shown respectively; FIG5(f) shows the safe and efficient operation boundaries of the electrolytic cell stack at different current densities and average fuel electrode flow rates of the electrolytic cell stack.

[0083] Optionally, in one embodiment of the present application, based on multiple groups of response parameter values ​​and operating boundaries, to obtain input parameter values ​​that meet preset scoring conditions, including: obtaining scoring results of multiple groups of response parameter values; based on the operating boundaries, determining scoring limit values ​​of the scoring results; based on the scoring limit values, obtaining input parameter values ​​of preset scoring conditions.

[0084] In some embodiments, the embodiments of the present application may first utilize multiple groups of response parameter values ​​and operating boundaries to obtain input parameter values ​​that meet certain scoring conditions, wherein the certain scoring conditions may be set by technicians in this field according to actual conditions, and the present application does not impose any specific restrictions.

[0085] Illustratively, the embodiments of the present application can score the response parameter values ​​under each group of input parameter values ​​according to the response parameter values ​​of the solid oxide electrolytic cell stack to be optimized under each group of input parameter values, combined with the operating boundaries of the electrolytic cell stack, to obtain scoring results for different response parameter values.

[0086] Furthermore, the embodiments of the present application may set a score limit value of the score result according to the operating boundary of the electrolytic cell stack, such as a critical score lower limit, and the present application does not impose any specific limitation.

[0087] Furthermore, the embodiment of the present application can screen out the group with the highest scoring results and compare it with the critical score lower limit. If the highest scoring result is higher than the critical score lower limit, the input parameter values ​​of certain scoring conditions can be obtained, and the input parameter values ​​corresponding to the group with the highest scoring results are used as the operating condition optimization results of the solid oxide electrolytic cell stack to be optimized, and the efficient and safe operation of the electrolytic cell stack can be achieved; if the highest scoring result is lower than the critical score lower limit, the input parameter values ​​cannot achieve efficient and safe operation of the electrolytic cell stack, and the input parameter values ​​need to be reselected.

[0088] The working principle of the method for optimizing the stack operating conditions of a solid oxide electrolytic cell proposed in the embodiment of the present application is described in detail below with reference to a specific embodiment.

[0089] in, Figure 6 The present invention is a flow chart showing the working principle of a method for optimizing the operating conditions of a solid oxide electrolysis cell stack provided according to one embodiment of the present application.

[0090] Step S601: Select an electrolytic cell stack calculation model that matches the solid oxide electrolytic cell stack to be optimized.

[0091] Among them, the embodiment of the present application can select a matching electrolytic cell stack calculation model from the electrolytic cell stack calculation model library according to the electrolysis mode and stack size of the solid oxide electrolytic cell stack to be optimized.

[0092] Step S602: Determine multiple sets of input parameter values ​​of the solid oxide electrolysis cell stack to be optimized.

[0093] Step S603: Determine the operating boundary of the solid oxide electrolysis cell stack to be optimized.

[0094] Step S604: input each set of input parameter values ​​into a matching electrolytic cell stack calculation model to obtain multiple sets of response parameter values ​​for the solid oxide electrolytic cell stack to be optimized.

[0095] Step S605: Calculate the scoring results of the multiple groups of response parameter values, and determine the critical scoring lower limit of the scoring results according to the operation boundary.

[0096] Step S606: Compare the group with the highest score result with the critical score lower limit.

[0097] In this embodiment of the present application, when the highest score result is higher than the critical score lower limit, step S607 is executed; otherwise, step S604 is executed.

[0098] Step S607: obtaining the operating condition optimization result of the solid oxide electrolytic cell stack to be optimized based on a group of corresponding input parameter values ​​with the highest scoring result.

[0099] According to the optimization method of the working condition of the solid oxide electrolytic cell stack proposed in the embodiment of the present application, the corresponding electrolytic cell stack calculation model can be matched based on the electrolysis mode and stack size of the solid oxide electrolytic cell stack to be optimized, and then each group of input parameter values ​​of the solid oxide electrolytic cell stack to be optimized is input into the matching electrolytic cell stack calculation model to obtain multiple groups of response parameter values, and based on the response parameter values ​​and the operating boundary, the input parameter values ​​that meet certain scoring conditions are obtained, and then the working condition optimization results of the solid oxide electrolytic cell stack to be optimized are generated, so that the calculation results can be compatible with the calculation of different stack sizes and thermal boundary conditions, and the accuracy and calculation efficiency are improved. In addition, the electrolytic cell stack calculation model contains more abundant parameters, which can more comprehensively consider the safe and efficient operation boundaries of the electrolytic cell stack, and the evaluation system of the response parameters is more complete and reasonable. Therefore, the problems in the related art that the optimization and prediction of the working condition under the electrolysis mode are not considered, only the prediction is made for the single cell, the working condition optimization at the stack level is not considered, and the indicators are considered to be one-sided.

[0100] Next, a device for optimizing the operating conditions of a solid oxide electrolytic cell stack proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0101] Figure 7 A block diagram of a device for optimizing the operating conditions of a solid oxide electrolytic cell stack provided in accordance with an embodiment of the present application.

[0102] like Figure 7 As shown, the device 70 for optimizing the operating conditions of a solid oxide electrolytic cell stack includes: a first generating module 100 , a determining module 200 , an acquiring module 300 and a second generating module 400 .

[0103] The first generation module 100 is used to obtain an electrolytic cell stack calculation model that matches the solid oxide electrolytic cell stack to be optimized based on the electrolysis mode and stack size of the solid oxide electrolytic cell stack to be optimized.

[0104] The determination module 200 is used to determine multiple sets of input parameter values ​​and operating boundaries of the solid oxide electrolysis cell stack to be optimized.

[0105] The acquisition module 300 is used to input each set of input parameter values ​​into a matching electrolytic cell stack calculation model to obtain multiple sets of response parameter values ​​of the solid oxide electrolytic cell stack to be optimized.

[0106] The second generation module 400 is used to obtain input parameter values ​​that meet preset scoring conditions based on multiple groups of response parameter values ​​and operating boundaries, and to obtain operating condition optimization results of the solid oxide electrolysis cell stack to be optimized based on the input parameter values ​​that meet the preset scoring conditions.

[0107] Optionally, in one embodiment of the present application, it further includes: a first building module, a second building module, a third building module, a fourth building module and a fifth building module.

[0108] The first construction module is used to construct an electrolytic cell single cell neural network proxy model of the electrolytic cell stack calculation model based on the experimental and simulation results of the solid oxide electrolytic cell stack to be optimized and combined with the target neural network model before inputting each set of input parameter values ​​into the matching electrolytic cell stack calculation model to obtain multiple sets of response parameter values ​​of the solid oxide electrolytic cell stack to be optimized.

[0109] The second construction module is used to construct an electrolytic cell stack airflow distribution calculation model of the electrolytic cell stack calculation model based on the airway flow resistance calculation method of the solid oxide electrolytic cell stack to be optimized.

[0110] The third construction module is used to construct an electrolytic cell stack heat balance calculation model of the electrolytic cell stack calculation model based on the electrolytic cell stack heat balance equation.

[0111] The fourth construction module is used to construct a three-dimensional multi-physical field calculation model of the electrolytic cell stack based on the multi-physical field calculation model of the electrolytic cell single battery.

[0112] The fifth construction module is used to construct an electrolytic cell stack calculation model based on the electrolytic cell single battery neural network agent model, the electrolytic cell stack airflow distribution calculation model, the electrolytic cell stack thermal balance calculation model and the electrolytic cell stack three-dimensional multi-physics field calculation model.

[0113] Optionally, in one embodiment of the present application, the acquisition module includes: a first determination unit, a second determination unit, a first generation unit, a second generation unit and a third generation unit.

[0114] The first determination unit is used to determine the total current and the minimum water vapor mole fraction of the electrolytic cell stack in the solid oxide electrolytic cell stack to be optimized based on the electrolytic cell single cell neural network agent model.

[0115] The second determination unit is used to determine the gas flow rate of the electrolytic cell stack single cell in the solid oxide electrolytic cell stack to be optimized based on the electrolytic cell stack gas flow distribution calculation model.

[0116] The first generating unit is used to obtain the average temperature of the single cells in the solid oxide electrolytic cell stack to be optimized based on the electrolytic cell stack thermal balance calculation model.

[0117] The second generation unit is used to obtain the three-dimensional multi-physical field distribution of the solid oxide electrolytic cell stack to be optimized based on the three-dimensional multi-physical field calculation model of the electrolytic cell stack.

[0118] The third generation unit is used to obtain multiple groups of response parameter values ​​based on the total current, the minimum water vapor mole fraction, the gas flow rate, the average temperature and the three-dimensional multi-physical field distribution of the electrolytic cell stack.

[0119] Optionally, in one embodiment of the present application, the second generating module includes: an acquiring unit, a third determining unit and a fourth generating unit.

[0120] The obtaining unit is used to obtain the scoring results of multiple groups of response parameter values.

[0121] The third determining unit is used to determine a scoring limit value of the scoring result based on the running boundary.

[0122] The fourth generating unit is used to obtain an input parameter value of a preset scoring condition based on the scoring limit value.

[0123] Optionally, in one embodiment of the present application, the second determining unit includes: an acquiring subunit, a first calculating subunit, a second calculating subunit and a third calculating subunit.

[0124] The acquisition subunit is used to obtain the pure viscosity of each gas component in the fuel electrode and the oxygen electrode in the solid oxide electrolysis cell stack to be optimized.

[0125] The first calculation subunit is used to calculate the viscosity of the mixed gas in the fuel electrode and the oxygen electrode based on the viscosity of the pure substances of each gas component.

[0126] The second calculation subunit is used to calculate the gas flow resistance of the fuel electrode and the oxygen electrode of the single cell of the electrolytic cell stack based on the viscosity of the pure substance of each gas component and the viscosity of the mixed gas.

[0127] The third calculation subunit is used to calculate the gas flow rate of the electrolytic cell stack based on the gas channel flow resistance.

[0128] It should be noted that the aforementioned explanation of the embodiment of the method for optimizing the operating conditions of a solid oxide electrolytic cell stack is also applicable to the device for optimizing the operating conditions of a solid oxide electrolytic cell stack of this embodiment, and will not be repeated here.

[0129] According to the optimization device of the working condition of the solid oxide electrolytic cell stack proposed in the embodiment of the present application, the corresponding electrolytic cell stack calculation model can be matched based on the electrolysis mode and stack size of the solid oxide electrolytic cell stack to be optimized, and then each group of input parameter values ​​of the solid oxide electrolytic cell stack to be optimized is input into the matching electrolytic cell stack calculation model to obtain multiple groups of response parameter values, and based on the response parameter values ​​and the operating boundary, the input parameter values ​​that meet certain scoring conditions are obtained, and then the working condition optimization results of the solid oxide electrolytic cell stack to be optimized are generated, so that the calculation results can be compatible with the calculation of different stack sizes and thermal boundary conditions, and the accuracy and calculation efficiency are improved. In addition, the electrolytic cell stack calculation model contains more abundant parameters, which can more comprehensively consider the safe and efficient operation boundaries of the electrolytic cell stack, and the evaluation system of the response parameters is more complete and reasonable. Therefore, the problems in the related technology that the optimization and prediction of the working condition under the electrolysis mode are not considered, only the prediction is made for the single cell, the working condition optimization at the stack level is not considered, and the indicators are considered to be one-sided.

[0130] Figure 8 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. The electronic device may include:

[0131] A memory 801 , a processor 802 , and a computer program stored in the memory 801 and executable on the processor 802 .

[0132] When the processor 802 executes the program, the method for optimizing the operating conditions of the solid oxide electrolytic cell stack provided in the above embodiment is implemented.

[0133] Furthermore, the electronic device further comprises:

[0134] The communication interface 803 is used for communication between the memory 801 and the processor 802 .

[0135] The memory 801 is used to store computer programs that can be executed on the processor 802 .

[0136] The memory 801 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0137] If the memory 801, the processor 802 and the communication interface 803 are implemented independently, the communication interface 803, the memory 801 and the processor 802 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0138] Optionally, in a specific implementation, if the memory 801, the processor 802 and the communication interface 803 are integrated on a chip, the memory 801, the processor 802 and the communication interface 803 can communicate with each other through an internal interface.

[0139] The processor 802 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0140] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for optimizing the operating conditions of a solid oxide electrolytic cell stack.

[0141] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed, implements the above-mentioned method for optimizing the operating conditions of a solid oxide electrolytic cell stack.

[0142] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0143] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0144] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0145] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0146] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented by hardware, as in another embodiment, it can be implemented by any one or a combination of multiple of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0147] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0148] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0149] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for optimizing the operating conditions of a solid oxide electrolytic cell stack, characterized in that: The following steps are involved: Based on the electrolysis mode and stack size of the solid oxide electrolyzer stack to be optimized, an electrolyzer stack calculation model matching the solid oxide electrolyzer stack to be optimized is obtained; Determining multiple sets of input parameter values ​​and operating boundaries of the solid oxide electrolysis cell stack to be optimized; Inputting each set of input parameter values ​​into the matching electrolytic cell stack calculation model respectively to obtain multiple sets of response parameter values ​​of the solid oxide electrolytic cell stack to be optimized; Based on the multiple groups of response parameter values ​​and the operating boundaries, input parameter values ​​that meet preset scoring conditions are obtained, and based on the input parameter values ​​that meet the preset scoring conditions, operating condition optimization results of the solid oxide electrolysis cell stack to be optimized are obtained.

2. The method according to claim 1, characterized in that Before inputting each set of input parameter values ​​into the matching electrolytic cell stack calculation model to obtain multiple sets of response parameter values ​​of the solid oxide electrolytic cell stack to be optimized, the method further includes: Based on the experimental and simulation results of the solid oxide electrolytic cell stack to be optimized, combined with the target neural network model, a neural network proxy model of a single cell of the electrolytic cell stack calculation model is constructed; Based on the airway flow resistance calculation method of the solid oxide electrolytic cell stack to be optimized, constructing an electrolytic cell stack airflow distribution calculation model of the electrolytic cell stack calculation model; Based on the electrolytic cell stack heat balance equation, constructing the electrolytic cell stack heat balance calculation model of the electrolytic cell stack calculation model; Based on the electrolytic cell single-cell multi-physical field calculation model, construct an electrolytic cell stack three-dimensional multi-physical field calculation model of the electrolytic cell stack calculation model; The electrolytic cell stack calculation model is constructed based on the electrolytic cell single battery neural network agent model, the electrolytic cell stack airflow distribution calculation model, the electrolytic cell stack thermal balance calculation model and the electrolytic cell stack three-dimensional multi-physical field calculation model.

3. The method according to claim 2, characterized in that The step of inputting each set of input parameter values ​​into the matching electrolytic cell stack calculation model to obtain multiple sets of response parameter values ​​of the solid oxide electrolytic cell stack to be optimized comprises: Determining the total current and minimum water vapor mole fraction of the electrolytic cell stack in the solid oxide electrolytic cell stack to be optimized based on the electrolytic cell single cell neural network proxy model; Determining the gas flow rate of the electrolytic cell stack single cell in the solid oxide electrolytic cell stack to be optimized based on the electrolytic cell stack gas flow distribution calculation model; Obtaining the average temperature of the electrolytic cell stack single cells in the solid oxide electrolytic cell stack to be optimized based on the electrolytic cell stack thermal balance calculation model; Based on the three-dimensional multi-physical field calculation model of the electrolytic cell stack, the three-dimensional multi-physical field distribution of the solid oxide electrolytic cell stack to be optimized is obtained; The multiple groups of response parameter values ​​are obtained based on the total current, the minimum water vapor mole fraction, the gas flow rate, the average temperature and the three-dimensional multi-physical field distribution of the electrolytic cell stack.

4. The method according to claim 1, characterized in that: The step of obtaining input parameter values ​​that meet preset scoring conditions based on the multiple groups of response parameter values ​​and the operating boundaries includes: Obtaining scoring results of the multiple groups of response parameter values; Based on the operating boundary, determining a scoring limit value of the scoring result; Based on the scoring limit value, an input parameter value of the preset scoring condition is obtained.

5. The method according to claim 1, characterized in that The step of determining the gas flow rate of the electrolytic cell stack single cell in the solid oxide electrolytic cell stack to be optimized based on the electrolytic cell stack gas flow distribution calculation model comprises: Obtaining the pure viscosity of each gas component in the fuel electrode and the oxygen electrode in the solid oxide electrolysis cell stack to be optimized; Calculating the viscosity of the mixed gas in the fuel electrode and the oxygen electrode based on the pure substance viscosity of each gas component; Calculating the gas flow resistance of the fuel electrode and the oxygen electrode of the electrolytic cell stack based on the pure viscosity of each gas component and the viscosity of the mixed gas; The gas flow rate of the electrolytic cell stack is calculated based on the gas flow resistance.

6. A device for optimizing the working conditions of a solid oxide electrolytic cell stack, characterized in that: include: A first generation module is used to obtain an electrolytic cell stack calculation model that matches the solid oxide electrolytic cell stack to be optimized based on the electrolysis mode and stack size of the solid oxide electrolytic cell stack to be optimized; A determination module, used to determine multiple groups of input parameter values ​​and operation boundaries of the solid oxide electrolysis cell stack to be optimized; An acquisition module, used for inputting each set of input parameter values ​​into the matching electrolytic cell stack calculation model respectively, so as to obtain multiple sets of response parameter values ​​of the solid oxide electrolytic cell stack to be optimized; The second generation module is used to obtain input parameter values ​​that meet preset scoring conditions based on the multiple groups of response parameter values ​​and the operating boundaries, and to obtain the operating condition optimization results of the solid oxide electrolysis cell stack to be optimized based on the input parameter values ​​that meet the preset scoring conditions.

7. The device according to claim 6, characterized in that Also includes: A first construction module is used to construct an electrolytic cell single cell neural network proxy model of the electrolytic cell stack calculation model based on the experimental and simulation results of the solid oxide electrolytic cell stack to be optimized and in combination with the target neural network model before inputting each group of input parameter values ​​into the matching electrolytic cell stack calculation model to obtain multiple groups of response parameter values ​​of the solid oxide electrolytic cell stack to be optimized; A second construction module is used to construct an electrolytic cell stack airflow distribution calculation model of the electrolytic cell stack calculation model based on the airway flow resistance calculation method of the solid oxide electrolytic cell stack to be optimized; A third construction module is used to construct an electrolytic cell stack heat balance calculation model of the electrolytic cell stack calculation model based on the electrolytic cell stack heat balance equation; A fourth construction module is used to construct a three-dimensional multi-physical field calculation model of the electrolytic cell stack of the electrolytic cell stack calculation model based on the multi-physical field calculation model of the electrolytic cell single cell; The fifth construction module is used to construct the electrolytic cell stack calculation model based on the electrolytic cell single battery neural network agent model, the electrolytic cell stack airflow distribution calculation model, the electrolytic cell stack thermal balance calculation model and the electrolytic cell stack three-dimensional multi-physical field calculation model.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for optimizing the operating conditions of a solid oxide electrolytic cell stack as described in any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method for optimizing the operating conditions of a solid oxide electrolytic cell stack as described in any one of claims 1 to 5.

10. A computer program product, characterized in that It comprises a computer program, which, when executed, is used to implement the method for optimizing the operating conditions of the solid oxide electrolytic cell stack as described in any one of claims 1 to 5.

Images