A hydrogen fuel conditioning system component level volume effect model

Abstract

The application provides a hydrogen fuel regulating system component-level volume effect model, belonging to the technical field of aeroengines, and specifically comprising a liquid hydrogen pump model, a heat exchanger model, a first cavity model, a pressure stabilizing valve model, a second cavity model and a regulating valve model, the first cavity model being obtained by abstracting a first pipeline assembly between the heat exchanger and the pressure stabilizing valve into an accessory module, the second cavity model being obtained by abstracting a second pipeline assembly between the pressure stabilizing valve and the regulating valve into an accessory module, the cavities being abstracted into input and output modules at the same level as other components, the dynamic changes of key parameters such as temperature, pressure and flow rate caused by hydrogen compressibility can be predicted, the input and output characteristics of the heat exchanger are characterized by using a gated recurrent network, and the problems of complex phase change process characteristics and heat transfer process inertia are solved.

Description

Technical Field

[0001] The present application relates to the field of aircraft engines, and in particular to a component-level volume effect model of a hydrogen fuel regulation system. Background Art

[0002] Hydrogen fuel undergoes a two-phase process within the conditioning system, transitioning from liquid hydrogen to gaseous hydrogen and then to gas / liquid. This involves complex nonlinear flow and heat transfer processes. Traditional zero-dimensional parameter models struggle to accurately reflect the steady-state, dynamic, and typical characteristics of hydrogen fuel within the pipeline. Currently, research on the multiphase mechanisms and conditioning process modeling of hydrogen fuel conditioning systems is limited, both domestically and internationally, resulting in limited reference material. These issues and difficulties pose significant challenges to the numerical simulation of hydrogen fuel conditioning systems. Summary of the Invention

[0003] In view of this, the present application provides a component-level volume effect model of a hydrogen fuel regulation system, which solves the problems in the prior art and provides accurate state prediction and data input for the intelligent control strategy of the hydrogen fuel system to support the regulation system in making efficient decisions during operation.

[0004] The component-level volume effect model of a hydrogen fuel conditioning system provided in this application adopts the following technical solution:

[0005] A component-level volume effect model of a hydrogen fuel regulating system, including a liquid hydrogen pump model, a heat exchanger model, a first volume cavity model, a pressure regulating valve model, a second volume cavity model, and a regulating valve model;

[0006] The input of the liquid hydrogen pump model is the liquid hydrogen pump speed, and the output of the liquid hydrogen pump model is the liquid hydrogen pump outlet flow rate and temperature;

[0007] The input of the heat exchanger model is the heat input rate, the liquid hydrogen pump outlet flow rate and the outlet temperature. The output of the heat exchanger model is the heat exchanger inlet pressure, the heat exchanger outlet flow rate and the temperature. The heat exchanger inlet pressure output by the heat exchanger model is input into the liquid hydrogen pump model.

[0008] The first cavity model is obtained by abstracting the first pipeline assembly between the heat exchanger and the pressure regulating valve into an accessory module. The input of the first cavity model is the heat exchanger outlet flow and temperature. The output of the first cavity model is the internal temperature and pressure of the first pipeline assembly. The internal pressure of the first pipeline assembly output by the first cavity model is input into the heat exchanger model.

[0009] The input of the pressure regulating valve model is the opening area of ​​the pressure regulating valve, the internal temperature and pressure of the first pipeline assembly, and the output of the pressure regulating valve model is the outlet flow and temperature of the pressure regulating valve and the inlet flow of the pressure regulating valve. The inlet flow of the pressure regulating valve output by the pressure regulating valve model is input into the first cavity model;

[0010] The second cavity model is obtained by abstracting the second pipeline assembly between the pressure-stabilizing valve and the regulating valve into an accessory module. The input of the second cavity model is the outlet flow and temperature of the pressure-stabilizing valve. The output of the second cavity model is the internal temperature and pressure of the second pipeline assembly. The internal pressure of the second pipeline assembly output by the second cavity model is input into the pressure-stabilizing valve model.

[0011] The inputs of the regulating valve model are the regulating valve opening area, the outlet pressure of the regulating valve, and the internal temperature and pressure of the second pipeline assembly. The outputs of the regulating valve model are the outlet flow and temperature of the regulating valve and the inlet flow of the regulating valve. The inlet flow of the regulating valve output by the regulating valve model is input into the second cavity model.

[0012] Optionally, the mathematical expression of the liquid hydrogen pump model is:

[0013] ;

[0014] Where, is the outlet flow of the liquid hydrogen pump, is the volume of each chamber of the liquid hydrogen pump, is the number of cavities per revolution of the liquid hydrogen pump, is the density of liquid hydrogen, is the liquid hydrogen pump speed, is the volumetric efficiency of the liquid hydrogen pump, is the outlet pressure of the liquid hydrogen pump.

[0015] Optionally, the heat exchanger model characterizes the dynamic characteristics of the heat exchanger model through a gated loop network.

[0016] Optionally, the reset gate and update gate of the gated recurrent network are both sigmoid nonlinear activation functions, and the reset gate and update gate outputs are Interval, analog gate switch;

[0017] The output data of the reset gate is integrated with the cyclic hidden layer vector update mechanism of the original cyclic unit to obtain The candidate recurrent hidden layer vector at time t;

[0018] The candidate recurrent hidden layer vector is combined with the update gate to calculate the final recurrent hidden layer vector of the gated recurrent unit.

[0019] Optionally, the mathematical expression of the pressure regulating valve model is:

[0020] ;

[0021] Where, is the outlet flow of the pressure regulating valve, is the flow correction coefficient, is the opening area of ​​the pressure regulating valve, is the inlet pressure of the pressure regulating valve, is the gas hydrogen adiabatic index, is the inlet temperature of the pressure regulating valve, is the compression coefficient, is the density of gaseous hydrogen relative to air, is the outlet pressure of the pressure regulating valve.

[0022] Optionally, the mathematical expression of the regulating valve model is:

[0023] ;

[0024] Where, To regulate the valve outlet flow, is the flow correction coefficient, is the regulating valve opening area, is the regulating valve inlet pressure, is the gas hydrogen adiabatic index, To adjust the inlet temperature, is the compression coefficient, is the density of gaseous hydrogen relative to air, It is the ratio of the outlet pressure to the inlet pressure of the regulating valve.

[0025] Optionally, the first cavity model and the second cavity model are characterized by a mechanism formula, and gas and hydrogen parameters in the first cavity model and the second cavity model satisfy an ideal gas state formula;

[0026] The mathematical expression of the cavity model is:

[0027] ;

[0028] Where, The pressure inside the chamber About Time The derivative of is the mass gas constant, is the gas temperature in the cavity, is the volume of the cavity, is the mass of gas in the cavity, is the gas mass flow rate at the cavity inlet, is the gas mass flow rate at the cavity outlet, The temperature inside the cavity About Time The partial derivative of .

[0029] Optionally, a Newton-Raphson iteration method is used to calculate the steady state of the component-level volume effect model of the hydrogen fuel conditioning system to solve the algebraic loop problem of the steady state calculation.

[0030] In summary, this application has the following beneficial technical effects:

[0031] Abstracting the cavity as an input and output module at the same level as other components can predict the dynamic changes of key parameters such as temperature, pressure, and flow caused by the compressibility of gas and hydrogen.

[0032] The gated loop network is used to characterize the input and output characteristics of the heat exchanger, solving the problems of complex phase change characteristics and inertia in the heat transfer process.

[0033] The Newton-Raphson iterative algorithm is used to solve the interactions and influences between the components of the hydrogen fuel regulation system, and the steady-state / transition-state parameter prediction of key sections is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0035] Figure 1 This is a structural block diagram of the hydrogen fuel regulation system in an embodiment of the present application;

[0036] Figure 2 For this application, a component-level volume effect model for the hydrogen fuel conditioning system is provided;

[0037] Figure 3 This is a block diagram of the gated recurrent network structure in an embodiment of the present application. DETAILED DESCRIPTION

[0038] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0039] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, in the absence of conflict, the features in the following embodiments and embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative work are within the scope of protection of this application.

[0040] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on this application, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement an apparatus and / or practice a method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this apparatus and / or practice this method.

[0041] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. The illustrations only show components related to the present application and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0042] Additionally, in the following description, specific details are provided to provide a thorough understanding of the examples. However, one skilled in the art will appreciate that the aspects described can be practiced without these specific details.

[0043] An embodiment of the present application provides a component-level volume effect model for a hydrogen fuel conditioning system.

[0044] like Figure 1 As shown, the model established in this application targets a specific hydrogen fuel regulation system. The hydrogen fuel regulation system includes a liquid hydrogen tank, a liquid hydrogen pump, a heat exchanger, a pressure regulating valve, and a regulating valve. The liquid hydrogen tank can be approximated as a constant-pressure liquid hydrogen source. The liquid hydrogen is pressurized by the liquid hydrogen pump and enters the heat exchanger. After the liquid hydrogen is heated in the heat exchanger, it changes phase into gaseous hydrogen and enters the pressure regulating valve. After being throttled by the pressure regulating valve, the gaseous hydrogen flows to the regulating valve and finally to the outlet.

[0045] like Figure 2 As shown in Figure 1, a component-level volumetric effect model for a hydrogen fuel conditioning system is presented. The liquid hydrogen pump speed, heat exchanger heat input rate, pressure regulating valve opening area, and regulating valve opening area are variable as model inputs, and the inlet / outlet temperature, pressure, and flow parameters of each component are model outputs. The model assumes the following: the liquid hydrogen tank is a constant pressure source, the liquid hydrogen storage capacity is unlimited, and the outlet liquid hydrogen pressure and temperature are stable; the effects of the liquid hydrogen pump, pressure regulating valve, and regulating valve on the hydrogen fuel temperature are ignored, such that the inlet and outlet temperatures of the liquid hydrogen pump, pressure regulating valve, and regulating valve are equal; and the fluid in the hydrogen fuel conditioning system satisfies the ideal gas state equation: ,in, is the pressure inside the chamber, is the volume of the cavity, is the mass of gas in the cavity, is the mass gas constant, is the gas temperature in the cavity; in the hydrogen fuel regulating system, the hydrogen fuel before the heat exchanger is liquid hydrogen, and the hydrogen fuel after the heat exchanger is gaseous hydrogen; the heat exchange process between the hydrogen fuel and the outside world only exists in the heat exchanger, and the liquid hydrogen and gaseous hydrogen pipelines do not exchange heat with the outside world; the temperature and pressure are equal at all points in the cavity.

[0046] The component-level volume effect model of the hydrogen fuel regulation system of the present application includes a liquid hydrogen pump model, a heat exchanger model, a first cavity model, a pressure-stabilizing valve model, a second cavity model and a regulating valve model.

[0047] The input of the liquid hydrogen pump model is the liquid hydrogen pump speed, and the output of the liquid hydrogen pump model is the liquid hydrogen pump outlet flow rate and temperature.

[0048] The input of the heat exchanger model is the heat input rate, the liquid hydrogen pump outlet flow rate and the outlet temperature. The output of the heat exchanger model is the heat exchanger inlet pressure, the heat exchanger outlet flow rate and the temperature. The heat exchanger inlet pressure output by the heat exchanger model is input into the liquid hydrogen pump model.

[0049] The first cavity model is obtained by abstracting the first pipeline assembly between the heat exchanger and the pressure-regulating valve into an accessory module. The input of the first cavity model is the heat exchanger outlet flow and temperature, and the output of the first cavity model is the internal temperature and pressure of the first pipeline assembly. The internal pressure of the first pipeline assembly output by the first cavity model is input into the heat exchanger model.

[0050] The input of the pressure-stabilizing valve model is the opening area of ​​the pressure-stabilizing valve, the internal temperature and pressure of the first pipeline assembly. The output of the pressure-stabilizing valve model is the outlet flow and temperature of the pressure-stabilizing valve and the inlet flow of the pressure-stabilizing valve. The inlet flow of the pressure-stabilizing valve output by the pressure-stabilizing valve model is input into the first cavity model.

[0051] The second cavity model is obtained by abstracting the second pipeline assembly between the pressure-stabilizing valve and the regulating valve into an accessory module. The input of the second cavity model is the outlet flow and temperature of the pressure-stabilizing valve, and the output of the second cavity model is the internal temperature and pressure of the second pipeline assembly. The internal pressure of the second pipeline assembly output by the second cavity model is input into the pressure-stabilizing valve model.

[0052] The inputs of the regulating valve model are the regulating valve opening area, the outlet pressure of the regulating valve, and the internal temperature and pressure of the second pipeline assembly. The outputs of the regulating valve model are the outlet flow and temperature of the regulating valve and the inlet flow of the regulating valve. The inlet flow of the regulating valve output by the regulating valve model is input into the second cavity model.

[0053] The density of hydrogen gas is significantly affected by temperature and pressure, and it is highly compressible. Key cross-sectional parameters of the hydrogen fuel conditioning system are significantly affected by the volumetric effect. This application addresses this issue by considering the volumetric effect. The pipeline volume is abstracted into an accessory module, placed at the same level as the liquid hydrogen pump, pressure regulating valve, and control valve models. The interrelationships between these modules are described using common working equations.

[0054] Specifically, the liquid hydrogen pump model is proposed to be characterized by a mechanism formula. The input of the liquid hydrogen pump model is the outlet pressure and the liquid hydrogen pump speed. The output of the liquid hydrogen pump is the liquid hydrogen pump flow rate and the liquid hydrogen pump outlet temperature. The outlet pressure of the liquid hydrogen pump is the heat exchanger inlet pressure output by the heat exchanger model. Assuming that the liquid hydrogen pump is a positive displacement pump, the mathematical expression of the liquid hydrogen pump model is:

[0055] ;

[0056] Where, is the outlet flow of the liquid hydrogen pump, is the volume of each chamber of the liquid hydrogen pump, is the number of cavities per revolution of the liquid hydrogen pump, is the density of liquid hydrogen, is the liquid hydrogen pump speed, is the volumetric efficiency of the liquid hydrogen pump. Volumetric efficiency is related to the speed of the liquid hydrogen pump. and liquid hydrogen pump outlet pressure Function of volumetric efficiency It is difficult to express accurately using mathematical expressions. This application constructs a two-dimensional interpolation table through experimental data to approximate volumetric efficiency.

[0057] The specific construction method of the heat exchanger model is as follows:

[0058] Affected by the inertial characteristics of temperature, the dynamic characteristics of the heat exchanger have a large lag and are affected by many factors, making it difficult to establish a mechanism model. This application uses a gated recurrent network to characterize its dynamic characteristics. The gated recurrent network improves the calculation mechanism of the recurrent hidden layer, which can effectively suppress the gradient disappearance and significantly improve the prediction quality of the recurrent network while only slightly increasing the calculation difficulty.

[0059] The gated recurrent network structure is as follows Figure 3 As shown, the key point of the structure is the introduction of the reset gate and the update gate. The reset gate and the update gate are sigmoid nonlinear activation functions, which control the output value to The expressions for the interval, analog gated switch, reset gate, and update gate are as follows:

[0060] ;

[0061] ;

[0062] Where, To reset the gate output, is the update gate output, is the hyperbolic sine function, To reset the gate input coefficient matrix, To update the gate input coefficient matrix, To reset the gate hidden coefficient matrix, To update the gate hidden coefficient matrix, To reset the gate threshold, To update the gate threshold, for The gated recurrent network input vector at time t, for The gated recurrent network recurrent hidden layer vector at time t.

[0063] Get reset gate output After the data is obtained, it is integrated with the cyclic hidden layer vector update mechanism of the original cyclic unit to obtain The candidate recurrent hidden layer vector at time :

[0064] ;

[0065] Where, for The candidate recurrent hidden layer vector at time t, is the candidate input coefficient matrix, is the candidate hidden coefficient matrix, is the candidate threshold, Represents the Hadamard product, that is, the corresponding position elements of two vectors are multiplied to form a new vector, is a hyperbolic tangent function, which ensures that the value of the candidate cycle hidden layer vector remains in the interval Inside, for The gated recurrent network input vector at time t, for The gated recurrent network recurrent hidden layer vector at time t.

[0066] The candidate recurrent hidden layer vector is combined with the update gate to calculate the final recurrent hidden layer vector of the gated recurrent unit :

[0067] ;

[0068] in, is the update gate output, for The gated recurrent network recurrent hidden layer vector at time t, for The candidate recurrent hidden layer vector at time , represents the Hadamard product.

[0069] The network inputs are the heat exchanger inlet mass flow, heat exchanger outlet pressure, heat exchanger inlet temperature, and heat flux density:

[0070] ;

[0071] Where, for The mass flow rate at the heat exchanger inlet at that moment, for The heat exchanger outlet pressure at the moment, for Heat exchanger inlet temperature at the moment, for The heat flux density at the moment, T is the vector transpose operator;

[0072] The network output is selected as the heat exchanger outlet mass flow, heat exchanger inlet pressure, and heat exchanger outlet temperature:

[0073] ;

[0074] Where, for The mass flow rate at the heat exchanger outlet at the moment, for Heat exchanger inlet pressure at all times, for The heat exchanger outlet temperature at time t, T is the vector transposition operator;

[0075] The heat exchanger inlet flow rate is the liquid hydrogen pump outlet flow rate, the heat exchanger outlet pressure is the internal pressure of the first pipeline assembly output by the first cavity model, and the medium inlet temperature is the liquid hydrogen pump outlet temperature.

[0076] The hydrogen fuel regulation system involves a phase change process from liquid hydrogen to gaseous hydrogen. The characteristics of this process change in a complex way and are difficult to characterize using specific mathematical expressions. Moreover, the phase change process of the hydrogen fuel regulation system involves heat transfer. This dynamic process has a large inertia and is greatly affected by the previous control variables at the current moment. This application solves this problem by introducing a gated loop network. Both the hydrogen fuel phase change process and the heat exchange process occur in the heat exchanger, so this application uses a gated loop network to characterize the input and output characteristics of the heat exchanger. The gated loop network has a strong nonlinear characterization capability and is sufficient to characterize the complex characteristics of the phase change process. The input of the gated loop network is time series data, and it has the ability to characterize both long-term and short-term effects, which is suitable for processing parameter prediction problems under the inertia of the heat exchange process.

[0077] The pressure regulating valve model is proposed to be characterized by a mechanism formula. The input of the pressure regulating valve model is the pressure regulating valve opening area, the pressure regulating valve inlet pressure, the pressure regulating valve outlet pressure, and the pressure regulating valve inlet temperature. The output of the pressure regulating valve model is the pressure regulating valve outlet flow and temperature, as well as the pressure regulating valve inlet flow. Among them, the pressure regulating valve inlet pressure is the internal pressure of the first pipeline component output by the first cavity model, the pressure regulating valve inlet temperature is the internal temperature of the first pipeline component output by the first cavity model, and the pressure regulating valve outlet pressure is the internal pressure of the second pipeline component output by the second cavity model. The pressure regulating valve is essentially a throttling element. Since the fluid flowing through the pressure regulating valve is gaseous hydrogen with variable density, it can be characterized by a variable density throttling flow formula. The mathematical expression of the pressure regulating valve model is:

[0078] ;

[0079] Where, is the outlet flow of the pressure regulating valve, is the flow correction coefficient, is the opening area of ​​the pressure regulating valve, is the inlet pressure of the pressure regulating valve, is the gas hydrogen adiabatic index, is the inlet temperature of the pressure regulating valve, is the compression coefficient, is the density of gaseous hydrogen relative to air, is the outlet pressure of the pressure regulating valve.

[0080] The regulating valve model is proposed to be characterized by a mechanism formula. The input of the regulating valve model is the regulating valve opening area, the regulating valve inlet pressure, the regulating valve outlet pressure, and the regulating valve inlet temperature. The output of the regulating valve model is the outlet flow and temperature of the regulating valve and the inlet flow of the regulating valve. Among them, the inlet pressure of the regulating valve is the internal pressure of the second pipeline component output by the second cavity model, and the inlet temperature of the regulating valve is the internal temperature of the second pipeline component output by the second cavity model. The regulating valve and the pressure regulating valve are essentially the same. Both are throttling elements. The difference is that: in order to facilitate the regulation and metering of the flow, the throat of the regulating valve is a sonic cross section. In theory, it can be guaranteed that the throat cross section parameters of the regulating valve are not affected by the outlet parameters, and the outlet pressure of the regulating valve is With inlet pressure Ratio is a fixed value, Therefore, the control valve model can be characterized as:

[0081] ;

[0082] Where, To regulate the valve outlet flow, is the flow correction coefficient, is the regulating valve opening area, is the regulating valve inlet pressure, is the gas hydrogen adiabatic index, To adjust the inlet temperature, is the compression coefficient, is the density of gaseous hydrogen relative to air.

[0083] Cavity models are set up inside the heat exchanger, between the heat exchanger and the pressure-stabilizing valve, between the pressure-stabilizing valve and the regulating valve, and between the regulating valve and the outlet. The cavity model is intended to be characterized by a mechanism formula. The input of the cavity model is the cavity inlet flow rate, the cavity outlet flow rate, and the cavity temperature. The output of the cavity model is the cavity pressure. It is assumed that the temperature and pressure at each point in the cavity are the same, there is no heat exchange between the cavity wall and the outside world, and the gas and hydrogen parameters in the cavity satisfy the ideal gas state formula: ,in, is the pressure inside the chamber, is the volume of the cavity, is the mass of gas in the cavity, is the mass gas constant, is the gas temperature in the cavity. The heat exchanger outlet flow rate and temperature output by the heat exchanger model serve as the inlet flow rate and temperature of the first cavity model. The pressure regulating valve inlet flow rate output by the pressure regulating valve model serves as the outlet flow rate of the first cavity model. The pressure regulating valve outlet flow rate and temperature output by the pressure regulating valve model, as well as the inlet flow rate of the pressure regulating valve, serve as the inlet flow rate and temperature of the second cavity model. The regulating valve inlet flow rate output by the regulating valve model serves as the outlet flow rate of the second cavity model.

[0084] The mathematical expression of the cavity model is:

[0085] ;

[0086] Where, The pressure inside the chamber About Time The derivative of is the mass gas constant, is the gas temperature in the cavity, is the volume of the cavity, is the mass of gas in the cavity, is the gas mass flow rate at the cavity inlet, is the gas mass flow rate at the cavity outlet, The temperature inside the cavity About Time The partial derivative of .

[0087] This application establishes a component-level quasi-one-dimensional model of a hydrogen fuel regulation system that takes into account the volume effect. Through a gated circulation network, it solves the slow-changing characteristics of the hydrogen fuel temperature change and the phase change uncertainty problem in the heat exchanger, and predicts the dynamic change process of parameters of key sections of the hydrogen fuel regulation system, such as the section after the liquid hydrogen pump and the section before and after the regulating valve, which are affected by the system's controlled variables.

[0088] This application accurately captures the dynamic characteristics of volumetric effects: the volume of hydrogen fuel in various components, such as tanks, pipelines, and mixers, fluctuates with changes in temperature, pressure, and other operating conditions. This application's component-level volumetric effect model for the hydrogen fuel conditioning system is designed to capture these nonlinear dynamic changes and provide accurate data support for the operation of the conditioning system.

[0089] Volumetric effects are influenced by the coupling of multiple variables, such as temperature, pressure, and flow, and their variations exhibit nonlinear characteristics. This application establishes a high-precision model using a gated recurrent network to characterize these complex relationships, addressing the shortcomings of traditional physical models in handling multivariable coupling.

[0090] Volume changes within each component are time-dependent and delayed. Gated recurrent networks excel at processing time series data. This application builds a model capable of predicting future states by learning from historical data, providing predictive support for fuel regulation and achieving predictive capabilities for time series data.

[0091] The ultimate goal of the component-level volume effect model of the hydrogen fuel regulation system in this application is to provide accurate state prediction and data input for the intelligent control strategy of the hydrogen fuel system, provide basic support for system control and optimization, and support the regulation system to make efficient decisions during operation.

[0092] For the calculation of the component-level volume effect model of the hydrogen fuel regulation system, the application uses the Newton-Raphson iteration method to solve the algebraic loop problem of the system steady-state calculation.

[0093] The hydrogen fuel regulation system meets the requirements of stable flow, stable pressure and stable temperature during steady state, namely:

[0094] ;

[0095] ;

[0096] ;

[0097] Where, is the gas temperature, is the gas pressure, is the gas mass flow rate, Indicates the cross-sections, represents the discrete moment when the system is stable, Take a positive integer.

[0098] The hydrogen fuel regulation system satisfies the common working equation, that is, the outlet cross-sectional parameters of any component model are equal to the inlet cross-sectional parameters of the component model connected thereto.

[0099] Based on the above, select Initial guess value of time , initial guess of heat exchanger outlet pressure , Preliminary estimate of the inlet pressure of the pressure regulating valve , Preliminary estimate of the regulating valve inlet pressure , where T is the vector transpose operator.

[0100] Setting the adjustment system Time input: liquid hydrogen pump speed , opening area of ​​pressure regulating valve , regulating valve opening area .

[0101] Based on the heat exchanger model, initial guess values, and control system input, a hydrogen fuel control system flow calculation can be performed. Since the initial guess values ​​are not true steady-state values, there is a deviation in the inlet and outlet flow rates of the two interconnected components in the calculated parameters, which is the residual. , where T is the vector transpose operator;

[0102] ;

[0103] ;

[0104] ;

[0105] Newton-Raphson iteration is used to minimize As the goal, update the initial guess value, and eventually make the cross-section parameters of the hydrogen fuel regulation system converge to the true value:

[0106] ;

[0107] Where, Indicates that the initial guess value is The updated value at It means that the initial guess value is The value of represents the iteration step size, is the Jacobian matrix:

[0108] ;

[0109] Where, express Iterative calculation value of heat exchanger outlet pressure at time, express Iterative calculation value of the pressure regulating valve inlet pressure at time, Indicates the iterative calculation value of the regulating valve inlet pressure.

[0110] There is coupling between the import and export parameters of the various components in the hydrogen fuel regulating system. The dynamic characteristics are difficult to represent using mathematical expressions and cannot be solved directly. This application solves this problem by combining component modeling and system modeling. For typical components of the hydrogen fuel regulating system, approximate formulas, interpolation tables, deep networks, etc. are used to describe the input and output characteristics, and the accuracy of the models of each component is improved through correction of experimental data. For the hydrogen fuel regulating system, the interaction relationship between the various components is described by a common working equation, and appropriate initial guess values ​​are selected and introduced to avoid algebraic loops in mathematical expressions. The key parameters of each section of the hydrogen fuel regulating system, such as temperature, pressure, and flow, are converged and solved through engineering means such as Newton-Raphson iteration.

[0111] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A component-level volume effect model for a hydrogen fuel conditioning system, characterized by: Including liquid hydrogen pump model, heat exchanger model, first cavity model, pressure stabilizing valve model, second cavity model and regulating valve model; The input of the liquid hydrogen pump model is the liquid hydrogen pump speed, and the output of the liquid hydrogen pump model is the liquid hydrogen pump outlet flow rate and temperature; The input of the heat exchanger model is the heat input rate, the liquid hydrogen pump outlet flow rate and the outlet temperature. The output of the heat exchanger model is the heat exchanger inlet pressure, the heat exchanger outlet flow rate and the temperature. The heat exchanger inlet pressure output by the heat exchanger model is input into the liquid hydrogen pump model. The first cavity model is obtained by abstracting the first pipeline assembly between the heat exchanger and the pressure regulating valve into an accessory module. The input of the first cavity model is the heat exchanger outlet flow and temperature. The output of the first cavity model is the internal temperature and pressure of the first pipeline assembly. The internal pressure of the first pipeline assembly output by the first cavity model is input into the heat exchanger model. The input of the pressure regulating valve model is the opening area of ​​the pressure regulating valve, the internal temperature and pressure of the first pipeline assembly, and the output of the pressure regulating valve model is the outlet flow and temperature of the pressure regulating valve and the inlet flow of the pressure regulating valve. The inlet flow of the pressure regulating valve output by the pressure regulating valve model is input into the first cavity model; The second cavity model is obtained by abstracting the second pipeline assembly between the pressure-stabilizing valve and the regulating valve into an accessory module. The input of the second cavity model is the outlet flow and temperature of the pressure-stabilizing valve. The output of the second cavity model is the internal temperature and pressure of the second pipeline assembly. The internal pressure of the second pipeline assembly output by the second cavity model is input into the pressure-stabilizing valve model. The inputs of the regulating valve model are the regulating valve opening area, the outlet pressure of the regulating valve, and the internal temperature and pressure of the second pipeline assembly. The outputs of the regulating valve model are the outlet flow and temperature of the regulating valve and the inlet flow of the regulating valve. The inlet flow of the regulating valve output by the regulating valve model is input into the second cavity model. The mathematical expression of the liquid hydrogen pump model is: ； Where, is the outlet flow of the liquid hydrogen pump, is the volume of each chamber of the liquid hydrogen pump, is the number of cavities per revolution of the liquid hydrogen pump, is the density of liquid hydrogen, is the liquid hydrogen pump speed, is the volumetric efficiency of the liquid hydrogen pump, is the outlet pressure of the liquid hydrogen pump; The heat exchanger model characterizes the dynamic characteristics of the heat exchanger model through a gated loop network; The Newton-Raphson iteration method is used to calculate the steady-state of the component-level volume effect model of the hydrogen fuel conditioning system to solve the algebraic loop problem of the steady-state calculation.

2. The component-level volume effect model of the hydrogen fuel conditioning system according to claim 1, characterized in that: The reset gate and update gate of the gated recurrent network are both sigmoid nonlinear activation functions, and the reset gate and update gate outputs are Interval, analog gate switch; The output data of the reset gate is integrated with the cyclic hidden layer vector update mechanism of the original cyclic unit to obtain The candidate recurrent hidden layer vector at time t; The candidate recurrent hidden layer vector is combined with the update gate to calculate the final recurrent hidden layer vector of the gated recurrent unit.

3. The component-level volume effect model of the hydrogen fuel conditioning system according to claim 1, characterized in that: The mathematical expression of the pressure regulating valve model is: ； Where, is the outlet flow of the pressure regulating valve, is the flow correction coefficient, is the opening area of ​​the pressure regulating valve, is the inlet pressure of the pressure regulating valve, is the gas hydrogen adiabatic index, is the inlet temperature of the pressure regulating valve, is the compression coefficient, is the density of gaseous hydrogen relative to air, is the outlet pressure of the pressure regulating valve.

4. The component-level volume effect model of the hydrogen fuel conditioning system according to claim 1, characterized in that: The mathematical expression of the regulating valve model is: ； Where, To regulate the valve outlet flow, is the flow correction coefficient, is the regulating valve opening area, is the regulating valve inlet pressure, is the gas hydrogen adiabatic index, To adjust the inlet temperature, is the compression coefficient, is the density of gaseous hydrogen relative to air, It is the ratio of the outlet pressure to the inlet pressure of the regulating valve.

5. The component-level volume effect model of the hydrogen fuel conditioning system according to claim 1, characterized in that: The first cavity model and the second cavity model are characterized by a mechanism formula, and the gas and hydrogen parameters in the first cavity model and the second cavity model satisfy the ideal gas state formula; The mathematical expression of the cavity model is: ； Where, The pressure inside the chamber About Time The derivative of is the mass gas constant, is the gas temperature in the cavity, is the volume of the cavity, is the mass of gas in the cavity, is the gas mass flow rate at the cavity inlet, is the gas mass flow rate at the cavity outlet, The temperature inside the cavity About Time The partial derivative of .

Images