Data-driven calculation method, device and equipment for hydrogen storage capacity of solid-state hydrogen storage device

Abstract

The invention discloses a data-driven calculation method, device and equipment for hydrogen storage capacity of a solid-state hydrogen storage device, and belongs to the technical field of solid-state hydrogen storage. The method comprises the steps that distributed parameters of the solid-state hydrogen storage device are obtained through a multi-physical-field full-coupling model of the solid-state hydrogen storage device, and the multi-physical-field full-coupling model is constructed based on structural characteristics of the solid-state hydrogen storage device; obtaining a dynamic response database of the multi-physics field full-coupling model, wherein the dynamic response database is used for representing a corresponding relation between distributed parameters of the multi-physics field full-coupling model and the hydrogen storage capacity of the solid hydrogen storage device; performing dynamic identification on the multi-physical field full-coupling model through a dynamic response database to obtain an identification model of the solid hydrogen storage device; and inputting the target distributed parameters of the solid-state hydrogen storage device into the identification model, and performing data driving calculation on the target distributed parameters through the identification model so as to output the predicted hydrogen storage amount of the solid-state hydrogen storage device. According to the method, the calculation cost and the solving time can be reduced.

Description

Technical Field

[0001] The present application belongs to the field of solid-state hydrogen storage technology, and in particular, relates to a data-driven calculation method, device and equipment for the hydrogen storage capacity of a solid-state hydrogen storage device. Background Art

[0002] Compared with traditional high-pressure gas storage and liquefaction technologies, the storage of hydrogen in metal compounds shows greater potential in commercial and automotive applications due to its superior safety and reliability. The formation of metal hydrides is closely linked to gas pressure and temperature, and requires a suitable high temperature to catalyze chemical reactions. The pressure of hydrogen must exceed the equilibrium pressure of adsorption or desorption in order to promote the reaction. At the same time, the adsorption or desorption process of hydrogen by metals is usually accompanied by the release or absorption of heat, which may lead to uneven temperature distribution. Due to the complex interaction of these thermal effects and chemical reactions, optimizing the kinetic characteristics of metal hydrogen storage requires a lot of experimental research and simulation analysis.

[0003] Current research mainly focuses on the effects of operating conditions and structural parameters on the performance of metal hydrogen storage, while the study of its dynamic behavior is relatively lacking. Rapid chemical reaction kinetics and slow material transfer processes may lead to instability in the dynamic response, thereby affecting the stability of hydrogen supply. Therefore, in-depth research on the dynamic process of metal hydrogen storage is particularly critical.

[0004] However, although multiphysics modeling technology can provide internal distributed parameters, it has the disadvantages of high computational cost and long solution time. Summary of the invention

[0005] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a data-driven calculation method, device and apparatus for the hydrogen storage capacity of a solid-state hydrogen storage device, which can reduce the calculation cost and solution time.

[0006] In a first aspect, the present application provides a data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device, the method comprising:

[0007] Obtaining distributed parameters of the solid-state hydrogen storage device through a multi-physics field fully coupled model of the solid-state hydrogen storage device, wherein the multi-physics field fully coupled model is constructed based on the structural characteristics of the solid-state hydrogen storage device;

[0008] Acquire a dynamic response database of the multi-physics field fully coupled model, wherein the dynamic response database is used to characterize the corresponding relationship between the distributed parameters of the multi-physics field fully coupled model and the hydrogen storage capacity of the solid-state hydrogen storage device;

[0009] Dynamically identifying the multi-physics field fully coupled model through a dynamic response database to obtain an identification model of the solid-state hydrogen storage device;

[0010] The target distributed parameters of the solid-state hydrogen storage device are input into the identification model, and the target distributed parameters are data-driven calculated by the identification model to output the predicted hydrogen storage capacity of the solid-state hydrogen storage device.

[0011] According to one embodiment of the present application, the multi-physics field fully coupled model is dynamically identified through a dynamic response database to obtain an identification model of the solid-state hydrogen storage device, including:

[0012] Based on the dynamic response database, the multi-physics field fully coupled model is identified to obtain a dynamic model, wherein the dynamic model is constructed based on an input-error model;

[0013] The input nonlinearity of the dynamic model is expanded through polynomial chaos, and the output nonlinearity of the dynamic model is represented through a wavelet network to obtain the identification model.

[0014] According to an embodiment of the present application, the step of expanding the input nonlinearity of the dynamic model through a polynomial chaos includes:

[0015]

[0016] in, is the input nonlinearity, is the space of input parameter distribution, n is the dimension of input parameter, b is the index of n dimension, ψ b (x) is a multidimensional polynomial basis given by the tensor product of univariate orthogonal shifted Legendre polynomials, a b are the polynomial coefficients, b i is a univariate polynomial The number of times.

[0017] According to one embodiment of the present application, the output nonlinearity of the dynamic model is represented by a wavelet network, including:

[0018]

[0019] where μ(y) is the output nonlinearity, l and m are node indices, h(i) is the output value of node i in the hidden layer, and ω ik is the weight connecting the hidden layer and the output layer, k and i are the number of nodes in the output layer and the hidden layer respectively, h i is the mother wavelet function, ω i is the weight connecting the input layer and the hidden layer, d i is the translation factor, a i is the stretch factor.

[0020] According to one embodiment of the present application, after inputting the target distributed parameters of the solid-state hydrogen storage device into the identification model, performing data-driven calculation on the target distributed parameters through the identification model to output the predicted hydrogen storage capacity of the solid-state hydrogen storage device, the method further includes:

[0021] Inputting a plurality of test distributed parameters into the multi-physics field fully coupled model in sequence to obtain a first hydrogen storage capacity response process output by the multi-physics field fully coupled model;

[0022] Inputting the plurality of test distributed parameters into the identification model in sequence to obtain a second hydrogen storage capacity response process output by the identification model;

[0023] An updated identification model is constructed according to an error between the first hydrogen storage amount response process and the second hydrogen storage amount response process.

[0024] According to an embodiment of the present application, after constructing the update identification model, the method further includes:

[0025] Predicting the hydrogen storage capacity of the solid-state hydrogen storage device by using the identification model to obtain a first prediction result;

[0026] Predicting the hydrogen storage capacity of the solid-state hydrogen storage device by using the updated identification model to obtain a second prediction result;

[0027] When the error of the first prediction result is greater than the error of the second prediction result, or the error of the first prediction result exceeds an error range, the identification model is replaced by the updated identification model.

[0028] According to one embodiment of the present application, the multi-physics field fully coupled model includes a mass and momentum transfer module, a chemical reaction module, and a heat transfer module.

[0029] According to one embodiment of the present application, the structural features of the solid-state hydrogen storage device include a reaction zone, an expansion volume, and a hydrogen inlet and outlet channel;

[0030] The mass and momentum transfer module is used to characterize the hydrogen flow process of the expansion volume;

[0031] The chemical reaction module is used to characterize the motion state of the metal hydride reaction bed in the reaction zone;

[0032] The heat transfer module is used to characterize the heat transfer state of the metal hydride reaction bed in the reaction zone.

[0033] In a second aspect, the present application provides a data-driven calculation device for the hydrogen storage capacity of a solid-state hydrogen storage device, the device comprising:

[0034] A first processing module is used to obtain distributed parameters of the solid-state hydrogen storage device through a multi-physics field fully coupled model of the solid-state hydrogen storage device, wherein the multi-physics field fully coupled model is constructed based on the structural characteristics of the solid-state hydrogen storage device;

[0035] An acquisition module, used to acquire a dynamic response database of the multi-physics field fully coupled model, wherein the dynamic response database is used to characterize the corresponding relationship between the distributed parameters of the multi-physics field fully coupled model and the hydrogen storage capacity of the solid-state hydrogen storage device;

[0036] A second processing module is used to dynamically identify the multi-physics field fully coupled model through a dynamic response database to obtain an identification model of the solid-state hydrogen storage device;

[0037] The third processing module is used to input the target distributed parameters of the solid-state hydrogen storage device into the identification model, and perform data-driven calculation on the target distributed parameters through the identification model to output the predicted hydrogen storage capacity of the solid-state hydrogen storage device.

[0038] In a third aspect, 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 when the processor executes the computer program, the data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device as described in the first aspect above is implemented.

[0039] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device as described in the first aspect above.

[0040] In a fifth aspect, the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device as described in the first aspect.

[0041] In a sixth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device as described in the first aspect above.

[0042] 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.

[0043] The data-driven calculation method, device and equipment for the hydrogen storage capacity of a solid-state hydrogen storage device provided by the present invention have the following beneficial effects compared with the prior art:

[0044] (1) By dynamically identifying the multi-physics field fully coupled model, a high-speed analysis of the multi-physics field distribution inside the solid-state hydrogen storage device is achieved. The simplified identification model obtained can predict the hydrogen storage capacity of the solid-state hydrogen storage device with high precision, low cost and fast response. It can compress the several hours of calculation time required for finite element calculation to tens of seconds, solving the problems of high computational cost and long solution time in multi-physics field modeling technology, reducing computational cost and guiding experimental implementation, and has the potential to be extended to the dynamic research of other nonlinear systems.

[0045] (2) The multi-physics field fully coupled model is identified through a dynamic response database, and the obtained dynamic model has lower complexity, which can more accurately predict the hydrogen storage capacity of the solid-state hydrogen storage device, enhance the understanding of the dynamic characteristics of the solid-state hydrogen storage device, and help to effectively control the solid-state hydrogen storage device;

[0046] (3) By using polynomial chaotic expansion to represent input nonlinearity, it is possible to effectively capture nonlinear characteristics and identify chaotic regions and their boundaries, thereby reducing computational complexity and improving the predictive ability of the identification model. By using wavelet networks to represent output nonlinearity, it is possible to achieve efficient feature extraction, enhance the flexibility of the identification model, improve the predictive accuracy of the identification model, simplify the model, and improve computational efficiency, while also having good interpretability. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0048] Figure 1 This is one of the flow charts of the data-driven calculation method of the hydrogen storage capacity of the solid-state hydrogen storage device provided in the embodiment of the present application;

[0049] Figure 2 is a structural schematic diagram of a longitudinal section of a solid-state hydrogen storage device provided in an embodiment of the present application;

[0050] Figure 3 This is the second flow chart of the data-driven calculation method of the hydrogen storage capacity of the solid-state hydrogen storage device provided in the embodiment of the present application;

[0051] Figure 4 is a schematic diagram of the structure of the identification model provided in the embodiment of the present application;

[0052] Figure 5 It is a schematic diagram for predicting the hydrogen adsorption process of a solid-state hydrogen storage device provided in an embodiment of the present application;

[0053] Figure 6 It is a schematic diagram for predicting the hydrogen desorption process of the solid-state hydrogen storage device provided in an embodiment of the present application;

[0054] Figure 7 It is a structural schematic diagram of a data-driven calculation device for the hydrogen storage capacity of a solid-state hydrogen storage device provided in an embodiment of the present application;

[0055] Figure 8 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0057] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0058] In conjunction with the accompanying drawings, the data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device, the data-driven calculation device for the hydrogen storage capacity of a solid-state hydrogen storage device, the electronic device and the readable storage medium provided in the embodiments of the present application are described in detail through specific embodiments and their application scenarios.

[0059] Among them, the data-driven calculation method of the hydrogen storage capacity of the solid-state hydrogen storage device can be applied to the terminal, and can be specifically executed by hardware or software in the terminal.

[0060] The terminal includes, but is not limited to, a portable communication device such as a mobile phone or tablet computer with a touch-sensitive surface (e.g., a touch screen display and / or a touch pad). It should also be understood that in some embodiments, the terminal may not be a portable communication device, but a desktop computer with a touch-sensitive surface (e.g., a touch screen display and / or a touch pad).

[0061] In the following various embodiments, a terminal including a display and a touch-sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, a mouse and a joystick.

[0062] The data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device provided in the embodiment of the present application, the execution subject of the data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device may be an electronic device or a functional module or functional entity in the electronic device that can implement the data-driven calculation method for the hydrogen storage capacity of the solid-state hydrogen storage device. The electronic devices mentioned in the embodiment of the present application include but are not limited to mobile phones, tablet computers, computers, cameras, and wearable devices. The data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device provided in the embodiment of the present application is described below using an electronic device as an example of the execution subject.

[0063] like Figure 1 As shown, the method includes: steps 110 to 140.

[0064] Step 110: Obtain distributed parameters of the solid-state hydrogen storage device through a multi-physics field fully coupled model of the solid-state hydrogen storage device, wherein the multi-physics field fully coupled model is constructed based on the structural characteristics of the solid-state hydrogen storage device.

[0065] The reaction rate is the speed at which reactants are converted into products during the formation or decomposition of metal hydrides.

[0066] Solid-state hydrogen storage devices are used to store hydrogen storage materials such as metal hydrides, such as Figure 2 As shown, by rotating the longitudinal section along the z axis, a solid hydrogen storage device can be obtained, and hydrogen (H2) is injected from the hydrogen inlet and outlet channel above. in Indicates the inlet radius, H ex Represents the expansion volume height, H mb represents the height of the metal hydride reaction bed. The solid-state hydrogen storage device constructed using the COMSOL multi-physics field simulation software presents a cylindrical structure. The structural features of the solid-state hydrogen storage device are characterized by, from bottom to top, the reaction zone of the metal hydride, the expansion volume, and the hydrogen inlet and outlet channels at the top. When hydrogen needs to be output, the metal oxide undergoes a chemical reaction in the reaction zone to generate hydrogen. The expansion volume is used to accommodate the volume change generated during the metal hydride reaction, and the generated hydrogen is output through the hydrogen inlet and outlet channels.

[0067] In this step, the multi-physics field fully coupled model of the solid-state hydrogen storage device is meshed, and distributed parameters such as reaction rate, temperature and pressure of each grid can be extracted.

[0068] In the multi-physics fully coupled model, distributed parameters are set as multiple key boundary conditions to configure the multi-physics fully coupled model. These distributed parameters include initial temperature, initial hydrogen flow rate, initial density of metal hydride, and initial hydrogen pressure. Once these distributed parameters are accurately input, the calculation process of the chemical reaction can be activated, thereby advancing the simulation.

[0069] Step 120: Acquire a dynamic response database of the multi-physics field fully coupled model, wherein the dynamic response database is used to characterize the corresponding relationship between the distributed parameters of the multi-physics field fully coupled model and the hydrogen storage capacity of the solid-state hydrogen storage device.

[0070] Among them, the distributed parameters are very comprehensive sets of data that can cover various operating scenarios of solid-state hydrogen storage devices. The dynamic response database includes distributed parameters and the hydrogen storage capacity of the solid-state hydrogen storage device corresponding to the distributed parameters.

[0071] The hydrogen storage capacity of the solid-state hydrogen storage device is characterized by a hydrogen storage capacity response process. By changing the distributed parameters input to the multi-physics field fully coupled model, the hydrogen storage capacity response process of the solid-state hydrogen storage device can be obtained, that is, the dynamic process of the numerical change of the hydrogen storage capacity.

[0072] In this step, the distributed parameters are input into the multi-physics field full coupling model on the COMSOL simulation platform, and the damped Newton method is used to solve the multi-physics field model of the solid-state hydrogen storage device. The accuracy of the multi-physics field full coupling model is verified to determine that the multi-physics field full coupling model is accurate. High damping is used at the beginning, and then the damping coefficient is gradually reduced to improve the convergence of the solution. The dynamic response process of the hydrogen storage capacity of the solid-state hydrogen storage device corresponding to each set of distributed parameters is obtained to construct a dynamic response database, which corresponds to the structure of the solid-state hydrogen storage device.

[0073] Step 130: Dynamically identify the multi-physics field fully coupled model through a dynamic response database to obtain an identification model of the solid-state hydrogen storage device.

[0074] Among them, the identification model is used to characterize the dynamic kinetic relationship of the solid-state hydrogen storage device.

[0075] In this step, the three-dimensional field model is simplified by dynamically identifying the multi-physics field fully coupled model, and the obtained identification model can calculate the hydrogen storage capacity of the solid-state hydrogen storage device in a data-driven manner.

[0076] Step 140: input the target distributed parameters of the solid-state hydrogen storage device into the identification model, and perform data-driven calculation on the target distributed parameters through the identification model to output the predicted hydrogen storage capacity of the solid-state hydrogen storage device.

[0077] Among them, the identification model can be a nonlinear model built based on data driving.

[0078] In this step, the identification model is configured, and the target distributed parameters of the solid-state hydrogen storage device to be predicted are input into the identification model. The identification model performs data dynamic calculation on the target distributed parameters to obtain and output the predicted hydrogen storage capacity of the solid-state hydrogen storage device.

[0079] According to the data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device provided in the embodiment of the present application, a high-speed analysis of the multi-physical field distribution inside the solid-state hydrogen storage device is achieved by dynamically identifying the multi-physical field fully coupled model. The obtained simplified identification model can predict the hydrogen storage capacity of the solid-state hydrogen storage device with high precision, low cost and fast response, and can compress the several hours of calculation time required for finite element calculation to tens of seconds, thereby solving the problems of high computational cost and long solution time in multi-physical field modeling technology, reducing computational cost and guiding experimental implementation, and has the potential to be extended to dynamic research on other nonlinear systems.

[0080] In some embodiments, the multi-physics fully coupled model includes a mass and momentum transfer module, a chemical reaction module, and a heat transfer module.

[0081] In some embodiments, the structural features of the solid-state hydrogen storage device include a reaction zone, an expansion volume, and hydrogen inlet and outlet channels;

[0082] The mass and momentum transfer module is used to characterize the hydrogen flow process of the expansion volume;

[0083] The chemical reaction module is used to characterize the motion state of the metal hydride reaction bed in the reaction zone;

[0084] The heat transfer module is used to characterize the heat transfer state of the metal hydride reaction bed in the reaction zone.

[0085] It should be noted that the mass and momentum transfer module is represented by formulas (1)-(4) and (6)-(8), the chemical reaction module is represented by formulas (12)-(15), and the heat transfer module is represented by formulas (5), (9)-(11).

[0086] In the Mass and Momentum Transfer Module, since only hydrogen flows in the expansion volume, it can be described by the continuity and Navier-Stokes equations:

[0087]

[0088] Among them, ρ g is the gas density, t is the time, is the symbol for gradient calculation, p g is the gas pressure, is the gas velocity vector, I is the identity tensor, μ g is the fluid viscosity, V is the gas velocity vector, and g is the gravitational acceleration of the fluid.

[0089] Fluid viscosity μ g and gas density ρ g is a function of temperature and can be expressed as:

[0090]

[0091] Where T is the temperature, M g is the molecular mass, R g is the universal gas constant.

[0092] The temperature field of the expansion volume can be expressed as:

[0093]

[0094] Among them, C p,g is the specific heat, k g is the thermal conductivity.

[0095] In the chemical reaction module, the momentum conservation of the metal hydride reaction bed is expressed as:

[0096]

[0097] Among them, ε b is the porosity of the reactor bed, ρ g is the density of hydrogen, is the reaction source term, is the gas velocity vector.

[0098] Gas velocity vector Calculated by Darcy's theorem:

[0099]

[0100] Where κ is the permeability, μ g is the fluid viscosity, p g is the gas pressure.

[0101] The mass conservation of the metal hydride reaction bed is expressed as:

[0102]

[0103] Among them, ρ s is the solid density, ε b is the porosity, S s is the mass source term and t is the time.

[0104] The heat transfer module of the metal hydride reactor bed uses energy conservation:

[0105]

[0106] Among them, (ρc p ) eff is the effective heat capacity, k eff is the effective thermal conductivity, ΔH is the enthalpy change, ρg is the gas density, C p,g is the specific heat capacity of hydrogen, C s is the specific heat of the metal.

[0107] Effective heat capacity (ρc p ) eff and the effective thermal conductivity k eff It can be expressed as:

[0108] (ρc p ) eff =ε b ρ g C p,g +(1-ε b )ρ s C s (10)

[0109] k eff =ε b k g +(1-ε b ) s (11)

[0110] Among them, ε b is the porosity, C p,g is the specific heat capacity of hydrogen, k eff is the effective thermal conductivity, k g is the thermal conductivity of the gas, k s is the thermal conductivity of the solid, p g is the gas density, ρ s is the solid density, C s is the specific heat of the metal.

[0111] After meshing the fully coupled multiphysics model, the local reaction of the metal hydride at each grid can be a hydrogenation or dehydrogenation process, depending on whether the local gas pressure of the grid is higher / lower than the equilibrium pressure. The reaction rate m of the local reaction of each grid can be expressed as:

[0112]

[0113] m=0,p eq,a > g > eq ,d (13)

[0114]

[0115] Among them, R g is the universal gas constant, C a is the absorption rate constant, E a is the activation energy of the absorption process, R g is the universal gas constant, T is the temperature, pg is the gas pressure, p eq,a is the equilibrium pressure of the absorption process, ρ sat is the saturation density of the metal hydride, ρ s is the density of the metal hydride, C d is the desorption rate constant, E d is the activation energy of the desorption process, p eq,d is the equilibrium pressure of the absorption process, ρ emp is the density at which the metal hydride is completely desorbed.

[0116] The equilibrium pressure is determined by the Van't Hoff relationship. When the solid-state hydrogen storage device is a LaNi5-H2 metal hydrogen storage system, the effect of hydrogen composition on the change of equilibrium pressure can be ignored. The equilibrium pressure is a function of temperature and can be expressed as:

[0117]

[0118] Among them, p eq is the equilibrium pressure, p ref is the reference pressure, A and B are the equilibrium pressure coefficients.

[0119] The values ​​of hydrogen absorption and dehydrogenation processes are different under the reference pressure. ref =1 MPa, for the adsorption process A = 10.700, B = 3704.6, for the desorption process A = 10.570, B = 3704.6. The difference between the A values ​​is due to the hysteresis between absorption and desorption.

[0120] In this embodiment, by constructing a multi-physics field fully coupled model including a mass and momentum transfer module, a chemical reaction module and a heat transfer module, the hydrogen storage scenarios of the solid-state hydrogen storage device can be fully covered, so that the multi-physics field fully coupled model can accurately predict the hydrogen storage capacity of the solid-state hydrogen storage device based on distributed parameters.

[0121] In some embodiments, in order to ensure that the distributed parameters in the dynamic response database can fully reflect the dynamic behavior characteristics of the solid-state hydrogen storage device, it is usually necessary to collect the dynamic transition process between the random and non-periodic steady-state operation points. Moreover, the time interval between adjacent dynamic transition processes should be set to allow the dynamic transition of the solid-state hydrogen storage device to reach a steady state, so as to obtain the time constant of the dynamic process.

[0122] The sampling rate is set as follows:

[0123] In order to accurately describe the strong coupling of multi-physics fields, the synergy angle equation is constructed according to the gradient vector in the multi-physics field. The synergy angle β between velocity and temperature can be expressed as follows:

[0124]

[0125] Where U is the velocity vector, is the temperature gradient vector. The parameter region with a smaller synergy angle indicates a stronger mutual coupling, and the parameter region with a larger synergy angle indicates a weaker coupling.

[0126] The parameter region with a smaller coordination angle β indicates a stronger mutual coupling effect, and the parameter region with a larger coordination angle β indicates a smaller coupling effect. When sampling in the operating parameter interval where the coordination angle β is less than 45°, the sampling rate is When the coordination angle β is greater than 45° in the operating range, the sampling rate is

[0127] The actual sampling frequency f re as follows:

[0128]

[0129] Among them, f min is the minimum sampling frequency.

[0130] The combination of distributed parameters collected at the actual sampling frequency and the hydrogen storage capacity calculated by the multi-physics field fully coupled model is used as the sampling data.

[0131] like Figure 3 As shown, according to the chemical reaction process, mass transfer process, momentum transfer process and heat transfer process of the solid-state hydrogen storage device, a multi-physics field simulation is performed on the solid-state hydrogen storage device to obtain a multi-physics field fully coupled model and generate a dynamic response database (dynamic characteristic database).

[0132] In the model verification stage, the Hammerstein-Wiener model is used to identify the dynamic model of the multi-physics field fully coupled model to obtain an identification model, and data-driven dynamic prediction is performed based on the identification model.

[0133] In the case where model verification is required, the dynamic response database (dynamic characteristic database) is regenerated according to the dynamic behavior characteristics of the solid-state hydrogen storage device to obtain an updated identification model;

[0134] The original identification model is compared with the updated identification model, and according to the error between the two, the original identification model is updated in real time by updating the identification model.

[0135] In some embodiments, the multi-physics field fully coupled model is dynamically identified through a dynamic response database to obtain an identification model of the solid-state hydrogen storage device, including:

[0136] Based on the dynamic response database, the multi-physics field fully coupled model is identified to obtain a dynamic model, wherein the dynamic model is constructed based on an input-error model;

[0137] The input nonlinearity of the dynamic model is expanded through polynomial chaos, and the output nonlinearity of the dynamic model is represented through a wavelet network to obtain the identification model.

[0138] The dynamic response database includes the corresponding relationship between the distributed parameters and the hydrogen storage capacity of the solid-state hydrogen storage device. In the process of dynamic identification of the multi-physical field fully coupled model, the distributed parameters are used as input data and the hydrogen storage capacity is used as output data.

[0139] In the actual implementation, the data in the dynamic response database are sorted according to the time series through the Hammerstein-Wiener identification method, and the Hammerstein model and the Wiener model are constructed. Both the Hammerstein model and the Wiener model include nonlinear parts and linear parts.

[0140] Select polynomial, piecewise linear, neural network, etc. as the nonlinear part, and use input data to fit the nonlinear function through regression analysis or neural network training as the nonlinear part.

[0141] After the nonlinear part is determined, linear modeling is performed on the nonlinear output using linear regression, state space model or autoregressive model, and the least square method or other optimization algorithms are used to identify the parameters of the linear part.

[0142] The obtained combination of the linear part and the nonlinear part is used as a dynamic model to realize the identification of the multi-physical field fully coupled model.

[0143] The kinetic model of the solid-state hydrogen storage device is described as:

[0144]

[0145] Among them, u(t) is the temperature and inlet pressure of the solid-state hydrogen storage device, y(t) is the adsorption / desorption reaction rate of solid-state hydrogen storage, e(t) is the system disturbance, n is the system delay, is the input nonlinearity, μ(y) is the output nonlinearity, F(z) and B(z) are z -1 The polynomial of the operator, b i is the numerator coefficient, i = 1, 2, ..., kb-1, kb-1 is the number of terms in the numerator; f j is the denominator coefficient and kf is the index of the denominator term.

[0146] The data-driven calculation is performed using the sampled data (distributed parameters and hydrogen storage) in the dynamic response database. The output-error model used in the structure of the kinetic model is expressed as:

[0147]

[0148] Where u(t) is the system input, y(t) is the system output, e(t) is the system disturbance, and n is the system delay. F(z) and B(z) are z -1 Polynomial of the operator:

[0149]

[0150] Among them, u(t) is the temperature and inlet pressure of the solid-state hydrogen storage device, y(t) is the adsorption / desorption reaction rate of solid-state hydrogen storage, e(t) is the system disturbance, n is the system delay, is the input nonlinearity, μ(y) is the output nonlinearity, F(z) and B(z) are z -1 The polynomial of the operator.

[0151] Solid-state hydrogen storage devices are typical nonlinear systems due to their inherent complexity. In order to accurately capture their dynamic behavior, nonlinear elements must be incorporated into the traditional linear system model.

[0152] The dynamic model is constructed based on the Hammerstein-Wiener model, which is effective in describing the dynamic characteristics of nonlinear systems.

[0153] like Figure 4 As shown in the figure, the kinetic model consists of three key parts: a core linear kinetic model of the solid-state hydrogen storage device, and nonlinear links at the input and output ends. The linear kinetic model is responsible for simulating the basic kinetic characteristics of the solid-state hydrogen storage device, while the nonlinear links at the input and output are specifically used to capture and express the nonlinear behavior of the system, thus providing a faster and easier simulation method for system analysis.

[0154] In some embodiments, the input nonlinearity of the kinetic model is expressed by a chaotic expansion of a polynomial, that is, the input nonlinearity of the kinetic model of the solid-state hydrogen storage device is expressed by a chaotic expansion of a polynomial:

[0155]

[0156] Among them, ψ b (x) is a multidimensional polynomial basis given by the tensor product of univariate orthogonal shifted Legendre polynomials, a b are the polynomial coefficients, b i is a univariate polynomial The number of times.

[0157] Then, an ablation experiment is carried out to transform the polynomial into a sparse polynomial, and the calculation accuracy is guaranteed to be no less than 95%.

[0158] In some embodiments, the output nonlinearity of the kinetic model is represented by a wavelet network, that is, the output nonlinearity of the kinetic model of the solid-state hydrogen storage device is represented by a wavelet network:

[0159]

[0160] where μ(y) is the output nonlinearity, l and m are node indices, h(i) is the output value of node i in the hidden layer, and ω ik is the weight connecting the hidden layer and the output layer, k and i are the number of nodes in the output layer and the hidden layer respectively, h i is the mother wavelet function, ω i is the weight connecting the input layer and the hidden layer, d i is the translation factor, a i is the stretch factor.

[0161] The identification model calculates distributed parameters such as input temperature and inlet pressure, and can calculate the amount of hydrogen adsorption / desorption of the solid-state hydrogen storage device.

[0162] In the embodiment of the present application, the identification model is constructed on the basis of the multi-physics field fully coupled model, and the dynamic calculation process is simulated by COMSOL software. A relative tolerance is set in the identification model as a standard for calculation accuracy.

[0163] The relative tolerance is used as a judgment condition for the calculation result output by the identification model during the iterative calculation of the identification model.

[0164] During the calculation process, the identification model uses the finite element method to iterate the calculation based on these input distributed parameters to obtain iterative results. When the difference between two consecutive iterative results drops below the relative tolerance, the iterative process will terminate. Through this process, key information such as hydrogen adsorption / desorption rate, temperature distribution of metal hydride, and hydrogen flow rate distribution related to distributed parameters (boundary conditions) can be obtained.

[0165] The predicted hydrogen storage capacity output by the identification model reflects the dynamic characteristics of metal hydrides.

[0166] The identification model consists of a calculation unit and a judgment unit. The calculation unit first uses the input distributed parameters as initial parameters to start the iterative process of finite element analysis. In each iteration, based on the result values ​​of the previous iteration, the calculation unit generates new parameter values, which are then used as the starting point for the next iteration. This continuous iterative process continues until the accuracy standard set by the identification model is reached, ensuring the accuracy and reliability of the calculation results.

[0167] The judgment unit plays a vital role in the identification model. It is responsible for maintaining the preset relative tolerance and capturing the result value after each iteration. The judgment unit carefully compares the result obtained from the current iteration with the result of the previous iteration to ensure the accuracy of the calculation. When the difference between the result values ​​of two consecutive iterations drops to or below the preset relative tolerance threshold, the judgment unit will issue an instruction to the calculation module to terminate the calculation. This mechanism ensures that the calculation process stops in time after reaching the required accuracy, avoiding unnecessary waste of resources. Finally, the result value obtained from the last iteration is identified as the key parameter value of the solid-state hydrogen storage device at that specific moment, providing reliable data support for the analysis and optimization of the system.

[0168] In this embodiment, the multi-physics field fully coupled model is identified through the dynamic response database, and the obtained dynamic model has lower complexity, can more accurately predict the hydrogen storage capacity of the solid-state hydrogen storage device, enhance the understanding of the dynamic characteristics of the solid-state hydrogen storage device, and help to effectively control the solid-state hydrogen storage device, solving the problems of high computational cost and long solution time in multi-physics field modeling technology.

[0169] By using polynomial chaotic expansion to represent input nonlinearity, we can effectively capture nonlinear characteristics and identify chaotic regions and their boundaries, reduce computational complexity, and improve the prediction capability of the identification model. By using wavelet networks to represent output nonlinearity, we can achieve efficient feature extraction, enhance the flexibility of the identification model, improve the prediction accuracy of the identification model, simplify the model, and improve computational efficiency, while having good interpretability.

[0170] In addition, the identification model and the multi-physics field full coupling model can be compared and verified, and the multi-physics field full coupling model can update the identification model to calculate the hydrogen storage capacity of the solid-state hydrogen storage device.

[0171] In some embodiments, after inputting the target distributed parameters of the solid-state hydrogen storage device into the identification model, performing data-driven calculation on the target distributed parameters through the identification model to output the predicted hydrogen storage capacity of the solid-state hydrogen storage device, the method further includes:

[0172] Inputting a plurality of test distributed parameters into the multi-physics field fully coupled model in sequence to obtain a first hydrogen storage capacity response process output by the multi-physics field fully coupled model;

[0173] Inputting the plurality of test distributed parameters into the identification model in sequence to obtain a second hydrogen storage capacity response process output by the identification model;

[0174] An updated identification model is constructed according to an error between the first hydrogen storage amount response process and the second hydrogen storage amount response process.

[0175] In actual implementation, a first hydrogen storage response process and a second hydrogen storage response process are obtained by inputting a plurality of test distributed parameters into a multi-physics field fully coupled model and an identification model respectively;

[0176] The first hydrogen storage response process is compared with the second hydrogen storage response process. When the error between the two is too large, the dynamic response database of the multi-physics field fully coupled model is reacquired to identify the multi-physics field fully coupled model to obtain an updated identification model.

[0177] In this embodiment, the calculation accuracy of the identification model is verified, and an updated identification model is constructed when the error is too large, so as to achieve control over the calculation accuracy of the identification model.

[0178] In some embodiments, after constructing the update recognition model, the method further includes:

[0179] Predicting the hydrogen storage capacity of the solid-state hydrogen storage device by using the identification model to obtain a first prediction result;

[0180] Predicting the hydrogen storage capacity of the solid-state hydrogen storage device by using the updated identification model to obtain a second prediction result;

[0181] When the error of the first prediction result is greater than the error of the second prediction result, or the error of the first prediction result exceeds an error range, the identification model is replaced by the updated identification model.

[0182] In actual implementation, the dynamic update method of the identification model of the solid-state hydrogen storage device is:

[0183] When online updating is used, the identification model f is updated new and the original identification model f old At the same time, the prediction is performed, if the identification model f is updated new The error of the second prediction result in the cumulative time period is less than that of the original identification model f old The error of the first prediction result, or the original identification model f oldThe error of the first prediction result is greater than the boundary value ε of the acceptable error range i , then the model is updated and replaced by updating the identification model f new Replace the original identification model f old .

[0184] Among them, ε i It is the acceptable boundary value of the accumulated error of temperature, velocity, pressure, and hydrogen mass in metal hydride under the physical field. When any physical field error reaches the acceptable boundary value, the model is updated. The specific rules are as follows:

[0185] (∑(|f old (I)-O r |>|f new (I)-O r |))>d t1 (twenty two)

[0186] d t2 <(∑(|f old (I)-O r |>|f new (I)-O r |)) <d t1 (twenty three)

[0187] ∑(|f old (I)-O r |-|f new (I)-O r |)>ε i (twenty four)

[0188] Among them, ε i is the acceptable boundary value of cumulative error under different physical fields, f old (I) is the original identification model, I is the distributed parameter of the model input (inlet temperature, pressure), f new (I) is the updated identification model, d t1 ,d t2 is the cumulative duration boundary value of the model update, O r is the actual value of the hydrogen storage capacity corresponding to the distributed parameter.

[0189] According to the parameter space of temperature, speed, pressure, and hydrogen mass in metal hydride, the accumulated error under different physical fields is set, ε i Is set to indicate the following:

[0190] ε i =|z max -z min |×γ (25)

[0191] Among them, z maxis the maximum value of temperature, pressure, flow rate, and mass of hydrogen in the metal hydride, z min Temperature, pressure, flow rate, minimum value of hydrogen mass in metal hydride, γ is the error tolerance.

[0192] In this embodiment, the calculation accuracy of the identification model is guaranteed by updating the identification model.

[0193] After dividing the multi-physics field fully coupled model into a grid, the distribution of the actual reactant concentration along the flow direction is considered, and the reactivity concentration in each grid block is used to obtain the set of parameter values ​​in the grid block as distributed parameters, which can better reflect the local characteristics of solid-state hydrogen storage operation, making the model multi-physics coupling process more complete, and improving accuracy and application value. The combination of data-driven methods and multi-physics field models is conducive to the development of solid-state hydrogen storage models, promotes the development of practical application fields, and realizes the prediction of solid-state hydrogen storage operation.

[0194] This example is based on COMSOL Multiphysics TM 6.1 is realized with Matlab simulation platform, and the parameters related to the solid-state hydrogen storage device during the simulation are shown in Table 1:

[0195] Table 1 Parameters related to solid-state hydrogen storage device

[0196] parameter Numeric Hydrogen adsorption rate constant <![CDATA[59.187s -1 ]]> Hydrogen desorption rate constant <![CDATA[9.57s -1 ]]> Specific heat capacity of hydrogen 14890J / (mol K) Specific heat capacity of metal 419J / (mol K) Hydrogen adsorption activation energy 21179.6J / mol Hydrogen desorption activation energy 16473J / mol Effective heat convection coefficient <![CDATA[1652W / (m 2 K)]]> Metal Permeability <![CDATA[10 -8 m 2 ]]> Thermal conductivity of hydrogen 0.1815W / (m K) Thermal conductivity of metals 1.087W / (m K) Molecular mass of hydrogen <![CDATA[2.01588·10 -3 kg / mol]]> Porosity of metal 0.5 Density of metal hydride without hydrogen adsorption <![CDATA[7164kg / m 3 ]]> Density of metal hydride saturated with hydrogen adsorption <![CDATA[7259kg / m 3 ]]> Reference pressure 1Mpa

[0197] like Figure 5 As shown, the horizontal axis is time, unit s, and the vertical axis is the mass of hydrogen in the metal hydride, unit Kg. The dynamic process of hydrogen adsorption of metal hydride is predicted at a temperature of 293K and an inlet pressure of 0.8Mpa.

[0198] like Figure 6 As shown, the horizontal axis is time, unit s, and the vertical axis is the mass of hydrogen in the metal hydride, unit Kg. The dynamic process of hydrogen desorption of metal hydride is predicted at a temperature of 313K and an inlet pressure of 0.025Mpa.

[0199] The simulation period can be set to 4000s, and the dynamic response starts at 0s. The purpose of the experiment is to predict the dynamic process of hydrogen adsorption / desorption of the metal hydride system under different working conditions.

[0200] The data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device provided in the embodiment of the present application can be executed by a data-driven calculation device for the hydrogen storage capacity of a solid-state hydrogen storage device. In the embodiment of the present application, the data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device is executed by a data-driven calculation device for the hydrogen storage capacity of a solid-state hydrogen storage device as an example to illustrate the data-driven calculation device for the hydrogen storage capacity of a solid-state hydrogen storage device provided in the embodiment of the present application.

[0201] The embodiment of the present application also provides a data-driven calculation device for the hydrogen storage capacity of a solid-state hydrogen storage device.

[0202] like Figure 7 As shown, the data-driven calculation device for the hydrogen storage amount of the solid-state hydrogen storage device includes: a first processing module 710 , an acquisition module 720 , a second processing module 730 and a third processing module 740 .

[0203] A first processing module 710 is used to obtain distributed parameters of the solid-state hydrogen storage device through a multi-physics field fully coupled model of the solid-state hydrogen storage device, wherein the multi-physics field fully coupled model is constructed based on the structural characteristics of the solid-state hydrogen storage device;

[0204] An acquisition module 720 is used to acquire a dynamic response database of the multi-physics field fully coupled model, wherein the dynamic response database is used to characterize the corresponding relationship between the distributed parameters of the multi-physics field fully coupled model and the hydrogen storage capacity of the solid-state hydrogen storage device;

[0205] The second processing module 730 is used to dynamically identify the multi-physics field fully coupled model through a dynamic response database to obtain an identification model of the solid-state hydrogen storage device;

[0206] The third processing module 740 is used to input the target distributed parameters of the solid-state hydrogen storage device into the identification model, and perform data-driven calculation on the target distributed parameters through the identification model to output the predicted hydrogen storage capacity of the solid-state hydrogen storage device.

[0207] According to the data-driven calculation device for the hydrogen storage capacity of a solid-state hydrogen storage device provided in the embodiment of the present application, by dynamically identifying the multi-physical field fully coupled model, a high-speed analysis of the multi-physical field distribution inside the solid-state hydrogen storage device is achieved. The simplified identification model obtained can predict the hydrogen storage capacity of the solid-state hydrogen storage device with high precision, low cost and fast response, and can compress the several hours of calculation time required for finite element calculation to tens of seconds, thereby solving the problems of high computational cost and long solution time in multi-physical field modeling technology, reducing computational cost and guiding experimental implementation, and has the potential to be extended to dynamic research on other nonlinear systems.

[0208] The data-driven calculation device for the hydrogen storage amount of the solid-state hydrogen storage device in the embodiment of the present application can be an electronic device, or a component in the electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or a device other than a terminal. Exemplarily, the electronic device can be a mobile phone, a tablet computer, a laptop computer, or a personal computer (PC), etc., which is not specifically limited in the embodiment of the present application.

[0209] The data-driven calculation device for the hydrogen storage amount of the solid-state hydrogen storage device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, a Linux operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0210] The data-driven calculation device for the hydrogen storage capacity of a solid-state hydrogen storage device provided in the embodiment of the present application can implement each process implemented in the above-mentioned data-driven calculation method embodiment for the hydrogen storage capacity of a solid-state hydrogen storage device. To avoid repetition, they will not be described here.

[0211] In some embodiments, Figure 8 As shown, an embodiment of the present application further provides an electronic device 800, including a processor 801, a memory 802, and a computer program stored in the memory 802 and executable on the processor 801. When the program is executed by the processor 801, each process of the data-driven calculation method for the hydrogen storage capacity of the solid-state hydrogen storage device is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0212] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0213] The embodiment of the present application also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the data-driven calculation method for the hydrogen storage capacity of the above-mentioned solid-state hydrogen storage device are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0214] The processor is the processor in the electronic device in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0215] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the data-driven calculation method for the hydrogen storage capacity of the solid-state hydrogen storage device.

[0216] The processor is the processor in the electronic device in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0217] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the various processes of the data-driven calculation method for the hydrogen storage capacity of the above-mentioned solid-state hydrogen storage device, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0218] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0219] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0220] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the data-driven calculation method of the hydrogen storage capacity of the solid-state hydrogen storage device of each embodiment of the present application.

[0221] In the description of this application, "first feature" or "second feature" may include one or more of the features.

[0222] In the description of the present application, “plurality” means two or more.

[0223] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0224] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" 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 representation of the above terms does 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 more embodiments or examples in a suitable manner.

[0225] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device, characterized in that: include: Obtaining distributed parameters of the solid-state hydrogen storage device through a multi-physics field fully coupled model of the solid-state hydrogen storage device, wherein the multi-physics field fully coupled model is constructed based on the structural characteristics of the solid-state hydrogen storage device; Acquire a dynamic response database of the multi-physics field fully coupled model, wherein the dynamic response database is used to characterize the corresponding relationship between the distributed parameters of the multi-physics field fully coupled model and the hydrogen storage capacity of the solid-state hydrogen storage device; Dynamically identifying the multi-physics field fully coupled model through a dynamic response database to obtain an identification model of the solid-state hydrogen storage device; The target distributed parameters of the solid-state hydrogen storage device are input into the identification model, and the target distributed parameters are data-driven calculated by the identification model to output the predicted hydrogen storage capacity of the solid-state hydrogen storage device.

2. The data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device according to claim 1, characterized in that: The method of dynamically identifying the multi-physics field fully coupled model through a dynamic response database to obtain an identification model of the solid-state hydrogen storage device includes: Based on the dynamic response database, the multi-physics field fully coupled model is identified to obtain a dynamic model, wherein the dynamic model is constructed based on an input-error model; The input nonlinearity of the dynamic model is expanded through polynomial chaos, and the output nonlinearity of the dynamic model is represented through a wavelet network to obtain the identification model.

3. The data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device according to claim 2, characterized in that: The nonlinearity of the input of the dynamic model is expanded through polynomial chaos, comprising: in, is the input nonlinearity, is the space of input parameter distribution, n is the dimension of input parameter, b is the index of n dimension, ψ b (x) is a multidimensional polynomial basis given by the tensor product of univariate orthogonal shifted Legendre polynomials, a b are the polynomial coefficients, b i is a univariate polynomial The number of times.

4. The data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device according to claim 2, characterized in that: The output of the kinetic model has been modified to include: where μ(y) is the output nonlinearity, l and m are node indices, h(i) is the output value of node i in the hidden layer, and ω ik is the weight connecting the hidden layer and the output layer, k and i are the number of nodes in the output layer and the hidden layer respectively, h i is the mother wavelet function, ω i is the weight connecting the input layer and the hidden layer, d i is the translation factor, a i is the stretch factor.

5. The data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device according to claim 1, characterized in that: After inputting the target distributed parameters of the solid-state hydrogen storage device into the identification model and performing data-driven calculation on the target distributed parameters through the identification model to output a predicted hydrogen storage capacity of the solid-state hydrogen storage device, the method further includes: Inputting a plurality of test distributed parameters into the multi-physics field fully coupled model in sequence to obtain a first hydrogen storage capacity response process output by the multi-physics field fully coupled model; Inputting the plurality of test distributed parameters into the identification model in sequence to obtain a second hydrogen storage capacity response process output by the identification model; An updated identification model is constructed according to an error between the first hydrogen storage amount response process and the second hydrogen storage amount response process.

6. The data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device according to claim 5, characterized in that: After constructing and updating the identification model, the method further includes: Predicting the hydrogen storage capacity of the solid-state hydrogen storage device by using the identification model to obtain a first prediction result; Predicting the hydrogen storage capacity of the solid-state hydrogen storage device by using the updated identification model to obtain a second prediction result; When the error of the first prediction result is greater than the error of the second prediction result, or the error of the first prediction result exceeds an error range, the identification model is replaced by the updated identification model.

7. The data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device according to claim 1, characterized in that: The multi-physics field fully coupled model includes a mass and momentum transfer module, a chemical reaction module and a heat transfer module.

8. The data-driven calculation method for the hydrogen storage capacity of a solid-state hydrogen storage device according to claim 7, characterized in that: The structural features of the solid-state hydrogen storage device include a reaction zone, an expansion volume, and hydrogen inlet and outlet channels; The mass and momentum transfer module is used to characterize the hydrogen flow process of the expansion volume; The chemical reaction module is used to characterize the motion state of the metal hydride reaction bed in the reaction zone; The heat transfer module is used to characterize the heat transfer state of the metal hydride reaction bed in the reaction zone.

9. A data-driven calculation device for the hydrogen storage capacity of a solid-state hydrogen storage device, characterized in that: include: A first processing module is used to obtain distributed parameters of the solid-state hydrogen storage device through a multi-physics field fully coupled model of the solid-state hydrogen storage device, wherein the multi-physics field fully coupled model is constructed based on the structural characteristics of the solid-state hydrogen storage device; An acquisition module, used to acquire a dynamic response database of the multi-physics field fully coupled model, wherein the dynamic response database is used to characterize the corresponding relationship between the distributed parameters of the multi-physics field fully coupled model and the hydrogen storage capacity of the solid-state hydrogen storage device; A second processing module is used to dynamically identify the multi-physics field fully coupled model through a dynamic response database to obtain an identification model of the solid-state hydrogen storage device; The third processing module is used to input the target distributed parameters of the solid-state hydrogen storage device into the identification model, and perform data-driven calculation on the target distributed parameters through the identification model to output the predicted hydrogen storage capacity of the solid-state hydrogen storage device.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the data-driven calculation method for the hydrogen storage capacity of the solid-state hydrogen storage device according to any one of claims 1 to 8 is implemented.

Images