Reactor in and out pressure determination method, model construction method, vehicle, medium and product

Abstract

The invention discloses an in-and-out stack pressure determination method, a model construction method, a vehicle, a medium and a product, the in-and-out stack pressure determination method comprises the following steps: obtaining current target parameter data of a fuel cell hydrogen subsystem of the vehicle, the fuel cell hydrogen subsystem comprising a fuel cell stack; on the basis of the current target parameter data and a preset linear variable parameter identification model, the current stack-out pressure and the current stack-in pressure of the fuel cell stack are determined, and the preset linear variable parameter identification model depends on the output power of the fuel cell stack; and determining the current state of the fuel cell hydrogen subsystem on the basis of the current out-pile pressure and the current in-pile pressure, and controlling the vehicle to run on the basis of the current state. According to the scheme, the accurate control of the in-out stack pressure of the fuel cell hydrogen subsystem is realized.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a method for determining inlet and outlet stack pressures, a model building method, a vehicle, a medium and a product. Background Art

[0002] With the continuous development of science and technology, the use of new energy hydrogen fuel vehicles is becoming more and more widespread. For new energy hydrogen fuel vehicles, they are equipped with a fuel cell hydrogen subsystem. The fuel cell hydrogen subsystem needs to control the pressure of the fuel cell in and out of the stack during operation. If the control is improper, it will cause the cathode and anode pressure difference of the fuel cell stack to be too large, and then the life of the proton exchange membrane will decay rapidly. Therefore, it is necessary to control the pressure regulating proportional valve and the hydrogen circulation pump to adjust the pressure of hydrogen in and out of the stack during the operation of the fuel cell. However, for complex fuel cell systems, it is difficult to accurately describe the dynamics of the hydrogen subsystem in the full power range, resulting in inaccurate control of the pressure of the fuel cell in and out of the stack. Summary of the invention

[0003] Embodiments of the present invention provide a method for determining inlet and outlet stack pressures, a model building method, a vehicle, a medium, and a product.

[0004] In a first aspect, an embodiment of the present invention provides a method for determining the inlet and outlet pressures of a fuel cell hydrogen subsystem, comprising:

[0005] Acquiring current target parameter data of a fuel cell hydrogen subsystem of a vehicle, wherein the fuel cell hydrogen subsystem includes a fuel cell stack;

[0006] Determining a current outlet pressure and a current inlet pressure of the fuel cell stack based on the current target parameter data and a preset linear variable parameter identification model, wherein the linear variable parameter identification model depends on the output power of the fuel cell stack;

[0007] Based on the current stack outlet pressure and the current stack inlet pressure, a current state of the fuel cell hydrogen subsystem is determined, and the vehicle operation is controlled based on the current state.

[0008] In some embodiments, the preset linear variable parameter identification model is determined by the following steps:

[0009] Acquiring model input data, model output data, and output power data of the fuel cell stack;

[0010] Construct an initial linear variable parameter identification model;

[0011] Solving the model parameter matrix of the initial linear variable parameter identification model based on the model input data, the model output data and the output power data to obtain a target model parameter matrix;

[0012] The model corresponding to the target model parameter matrix is ​​verified, and if the verification is successful, the successfully verified model is used as the preset linear variable parameter identification model.

[0013] In some embodiments, obtaining model input data includes:

[0014] Obtaining N parameter data and inlet and outlet stack pressure data of the vehicle within a preset time period, where N is a positive integer;

[0015] Based on each parameter data of the N types of parameter data, a correlation analysis is performed on the parameter data and the inlet and outlet stack pressure data to obtain a correlation analysis result between the parameter data and the inlet and outlet stack pressure data;

[0016] The K types of parameter data whose correlation analysis results meet the preset range are used as the model input data, where K is a positive integer.

[0017] In some embodiments, the N types of parameter data include load current data corresponding to the fuel cell hydrogen subsystem, system power data, ambient temperature data, proportional valve opening data, hydrogen circulation pump speed data, drain valve switch signal data, nitrogen exhaust valve switch signal data, drain valve temperature data, nitrogen exhaust valve temperature data, fuel cell stack temperature data and medium pressure data.

[0018] In some implementations, solving the model parameter matrix of the initial linear variable parameter identification model based on the model input data, the model output data, and the output power data to obtain a target model parameter matrix includes:

[0019] Based on the model input data, the model output data and the output power data, a subspace identification method is used to solve the mode parameters of the initial linear variable parameter identification model to obtain the target model parameter matrix.

[0020] In some embodiments, the preset linear variable parameter identification model corresponds to system state data, and based on the model input data, the model output data and the output power data, the mode parameters of the initial linear variable parameter identification model are solved by using a subspace identification method to obtain a target model parameter matrix, including:

[0021] estimating system state data in the preset linear variable parameter identification model based on the model input data, the model output data and the output power data;

[0022] The target model parameter matrix is ​​determined based on the estimated system state data, the model input data, the model output data, and the output power data.

[0023] In a second aspect, an embodiment of the present invention provides a method for constructing a linear variable parameter identification model, comprising:

[0024] Acquire N types of parameter data corresponding to the vehicle fuel cell hydrogen subsystem, inlet and outlet data of the fuel cell stack in the fuel cell hydrogen subsystem, and output power data of the fuel cell stack collected within a preset time period;

[0025] Determining model input data based on the N parameter data, and determining model output data based on the in-and-out stack data of the fuel cell stack;

[0026] Construct an initial linear variable parameter identification model;

[0027] Solving the model parameter matrix of the initial linear variable parameter identification model based on the model input data, the model output data and the output power data to obtain a target model parameter matrix;

[0028] The model corresponding to the target model parameter matrix is ​​verified, and if the verification is successful, the successfully verified model is used as a preset linear variable parameter identification model.

[0029] In a third aspect, the present invention provides a vehicle comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for determining the inlet and outlet stack pressures of the fuel cell hydrogen subsystem and any one of the methods described in the method for constructing a linear variable parameter identification model are implemented.

[0030] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the method for determining the inlet and outlet stack pressures of the above-mentioned fuel cell hydrogen subsystem and the method for constructing a linear variable parameter identification model.

[0031] In a fifth aspect, an embodiment of the present invention provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it is used to load and execute the steps in the method for determining the inlet and outlet stack pressures of the above-mentioned fuel cell hydrogen subsystem and the method for constructing a linear variable parameter identification model.

[0032] The above one or at least one technical solution in the embodiments of the present application has at least the following technical effects:

[0033] The embodiment of this specification provides a method for determining the inlet and outlet pressures of a fuel cell hydrogen subsystem, which obtains the current target parameter data of the fuel cell hydrogen subsystem of the vehicle, and outputs the current outlet pressure and the current inlet pressure of the fuel cell stack based on the current target parameter data and a preset linear variable parameter identification model, wherein the preset linear variable parameter identification model depends on the output power of the fuel cell stack; based on the current outlet pressure and the current inlet pressure, the current state of the fuel cell hydrogen subsystem is determined, and the vehicle operation is controlled based on the current state. This solution, by establishing a preset linear variable parameter identification model that depends on the output power of the fuel cell stack, can estimate the outlet pressure and inlet pressure of the fuel cell hydrogen subsystem in real time, thereby determining the changes of the fuel cell hydrogen subsystem under different power conditions, and more accurately determining the inlet and outlet pressures of the fuel cell hydrogen subsystem, thereby improving the accuracy of vehicle control. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A schematic diagram of the architecture of a fuel cell hydrogen subsystem provided in an embodiment of this specification;

[0035] Figure 2 A flow chart of a method for determining the inlet and outlet pressures of a fuel cell hydrogen subsystem provided in an embodiment of this specification;

[0036] Figure 3 A flowchart of a method for constructing a linear variable parameter identification model provided in an embodiment of this specification;

[0037] Figure 4 A schematic diagram of a vehicle provided in an embodiment of this specification. DETAILED DESCRIPTION

[0038] The overall idea of ​​the technical solution of the embodiment of the present application is as follows: obtaining current target parameter data of a vehicle's fuel cell hydrogen subsystem, wherein the fuel cell hydrogen subsystem includes a fuel cell stack; determining a current stack outlet pressure and a current stack inlet pressure of the fuel cell stack based on the current target parameter data and a preset linear variable parameter identification model, wherein the preset linear variable parameter identification model depends on the output power of the fuel cell stack; determining a current state of the fuel cell hydrogen subsystem based on the current stack outlet pressure and the current stack inlet pressure, and controlling the vehicle operation based on the current state.

[0039] The solution of the embodiments of this specification, by establishing a preset linear variable parameter identification model that depends on the output power of the fuel cell stack, can estimate the stack outlet pressure and stack inlet pressure of the fuel cell hydrogen subsystem in real time, thereby determining the changes of the fuel cell hydrogen subsystem under different power conditions, and more accurately determining the stack inlet and outlet pressures of the fuel cell hydrogen subsystem, thereby improving the accuracy of vehicle control.

[0040] In order to better understand the above technical scheme, the technical scheme of the embodiments of this specification is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical scheme of the embodiments of this specification, rather than limitations on the technical scheme of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0041] First of all, the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0042] First, the architecture of a fuel cell hydrogen subsystem provided in an embodiment of this specification is described. Figure 1 The figure shows a schematic diagram of the hydrogen subsystem of a fuel cell. Figure 1 The fuel cell hydrogen subsystem includes a proportional valve 101, a PCT (Positive Temperature Coefficient, positive temperature coefficient thermistor heater) 102, a stop valve 103, a hydrogen circulation pump 104, an ejector 105, a stack inlet pressure sensor 106, a fuel cell stack 107, a mixed discharge 108, a hydrogen and water discharge valve 109, a nitrogen discharge valve 110, a gas-liquid separator 111, and a stack outlet pressure sensor 112. The connection method of each of the above components is as follows: Figure 1 As shown. During the operation of the fuel cell hydrogen subsystem, hydrogen is transported from the hydrogen storage bottle to the anode flow channel of the fuel cell stack 107 through the proportional valve 101 and the supply manifold. The incompletely reacted hydrogen passes through the gas-liquid separator 111 from the return manifold to separate the liquid water from the gas. The separated liquid water gathers at the bottom of the gas-liquid separator 111 and is regularly drained through the hydrogen drain valve 109. According to the estimation of the nitrogen concentration of the stack, the nitrogen drain valve 110 is opened regularly to discharge the gas in the pipeline to increase the hydrogen concentration. The liquid water that has not been separated continues to enter the hydrogen circulation pump 104 to increase the gas pressure. The outlet of the hydrogen circulation pump 104 is connected to the secondary flow inlet of the ejector 105, and is sucked through the ejector 105 to participate in the circulation to the anode of the fuel cell stack 107, and continues to participate in the electrochemical reaction to generate electricity.

[0043] In this process, the proportional valve 101 and the hydrogen circulation pump 104 cooperate to regulate hydrogen and control the inlet and outlet pressures of the stack, which can be detected by the inlet pressure sensor 106 and the outlet pressure sensor 112. In addition, the periodic opening and closing of the hydrogen discharge and water discharge valve 109 with the change of the load current signal will also affect the hydrogen pressure. In some embodiments, the switching cycle of the hydrogen discharge and water discharge valve 109 can be determined by calibrating the MAP diagram. The MAP diagram can be used to characterize the correspondence between the load current and the switching cycle. The current switching cycle of the corresponding hydrogen discharge and water discharge valve 109 can be queried in the MAP diagram through the current load current.

[0044] It should be noted that the control of hydrogen pressure is closely related to the performance, life and efficiency of the fuel cell stack. If the pressure is not properly controlled, resulting in excessive pressure difference between the cathode and the anode, the life of the proton exchange membrane will be rapidly attenuated. Therefore, in the embodiments of this specification, in order to accurately control the inlet and outlet pressures of the stack, a method for determining the inlet and outlet pressures of the fuel cell hydrogen subsystem is provided, such as Figure 2 FIG. 1 is a flow chart of a method for determining the inlet and outlet pressures of a fuel cell hydrogen subsystem, the method comprising the following steps:

[0045] Step S201: acquiring current target parameter data of a fuel cell hydrogen subsystem of a vehicle, wherein the fuel cell hydrogen subsystem includes a fuel cell stack;

[0046] Step S202: determining a current outlet pressure and a current inlet pressure of the fuel cell stack based on the current target parameter data and a preset linear variable parameter identification model, wherein the preset linear variable parameter identification model depends on the output power of the fuel cell stack;

[0047] Step S203: Determine the current state of the fuel cell hydrogen subsystem based on the current stack outlet pressure and the current stack inlet pressure, and control the vehicle operation based on the current state.

[0048] The method provided in the embodiments of this specification can be applied in a vehicle, in a server connected to the vehicle for communication, or in a system consisting of a vehicle and a server, without limitation here.

[0049] In step S201, the current target parameter data may include multiple types of parameter data, and the current target parameter data may be data related to the inlet and outlet pressure of the fuel cell stack. In some embodiments, the current target parameter data may include the hydrogen pump speed, the proportional valve opening, the nitrogen exhaust valve switch signal, the drain valve switch signal, and the load current. The current target parameter data may be obtained by a sensor provided in the fuel cell hydrogen subsystem, or by a preset parameter calculation method, which is not limited here.

[0050] It should be noted that, since the solution in the embodiments of this specification processes the current target parameter data through a preset linear variable parameter identification model, the type of the current target parameter data can be determined based on the input data type of the preset linear variable parameter identification model.

[0051] In step S202, the preset linear variable parameter identification model may be pre-built. After obtaining the current target parameter data, the current target parameter data may be directly input into the preset linear variable parameter identification model to output the current stack outlet pressure and the current stack inlet pressure of the fuel cell stack. In some embodiments, the current target parameter data may also be filtered, and the filtered data may be used as the input data of the model to obtain the current stack outlet pressure and the current stack inlet pressure output by the model.

[0052] In step S203, after obtaining the current stack-out pressure and the current stack-in pressure, it can be further determined whether the current stack-out pressure and the current stack-in pressure are normal. In some embodiments, the current stack-out pressure can be compared with a preset stack-out pressure range. If the current stack-out pressure is within the preset stack-out pressure range, it indicates that the stack-out pressure is in a normal state. In other embodiments, the current stack-in pressure can be compared with a preset stack-in pressure range. If the current stack-in pressure is within the preset stack-in pressure range, it indicates that the stack-in pressure is in a normal state. In other embodiments, the current stack-in and stack-out pressure difference can also be determined based on the current stack-out pressure and the current stack-in pressure, and the current stack-in and stack pressure difference can be compared with a preset pressure difference range. If the current stack-in and stack pressure difference is within the preset pressure difference range, it indicates that the pressure difference is in a normal state. Among them, the preset stack-in pressure range, the preset stack-out pressure range, and the preset pressure difference range can be set according to actual conditions, and are not limited here.

[0053] In some embodiments, if the current inlet pressure and the current outlet pressure of the fuel cell stack are both in a normal state, or the current inlet pressure and the current inlet and outlet pressure difference of the fuel cell stack are in a normal state, or the current outlet pressure and the current inlet and outlet pressure difference of the fuel cell stack are in a normal state, it can be indicated that the current state of the fuel cell hydrogen subsystem is normal, and the vehicle operation can continue to be controlled according to the current operating parameters. If at least one parameter among the current inlet pressure, the current outlet pressure, and the current inlet and outlet pressure difference of the fuel cell stack is in an abnormal state, it indicates that the current state of the fuel cell hydrogen subsystem is abnormal, and it is necessary to adjust the proportional valve or the hydrogen circulation pump and other components to ensure that the inlet and outlet pressure data of the fuel cell hydrogen subsystem are normal.

[0054] In the embodiments of this specification, the preset linear variable parameter identification model can be a dynamic model in which the pressure of hydrogen entering and leaving the stack changes with the system operation amount. Specifically, the output power of the fuel cell stack can be used as a scheduling variable in the preset linear variable parameter identification model. In some embodiments, the preset linear variable parameter identification model can be determined by the following steps: obtaining model input data, model output data, and output power data of the fuel cell stack; constructing an initial linear variable parameter identification model; solving the model parameter matrix of the initial linear variable parameter identification model based on the model input data, the model output data, and the output power data to obtain a target model parameter matrix; verifying the model corresponding to the target model parameter matrix, and if the verification is successful, the successfully verified model is used as the preset linear variable parameter identification model.

[0055] In the embodiments of the present specification, the model output data may include the inlet and outlet pressure data of the fuel cell, for example, the inlet pressure data and outlet pressure data collected at a set collection frequency within a preset time period are used as the model output data.

[0056] In some embodiments, the model input data can be selected according to actual needs, for example, data that can affect the inlet and outlet stack pressures are selected as model input data through empirical values. In other embodiments, the model input data can be screened by the following steps: obtaining N types of parameter data and inlet and outlet stack pressure data of the vehicle within a preset time, where N is a positive integer; based on each of the N types of parameter data, performing a correlation analysis between the parameter data and the inlet and outlet stack pressure data, and obtaining a correlation analysis result between the parameter data and the inlet and outlet stack pressure data; using K types of parameter data whose correlation analysis results meet the preset range as the model input data, where K is a positive integer.

[0057] It should be noted that the preset duration can be set according to actual needs, for example, the preset duration can be the past day, week or month. In some embodiments, the N types of parameter data may include but are not limited to: load current data corresponding to the fuel cell hydrogen subsystem, system power data, ambient temperature data, proportional valve opening data, hydrogen circulation pump speed data, drain valve switch signal data, nitrogen exhaust valve switch signal data, drain valve temperature data, nitrogen exhaust valve temperature data, stack temperature data and medium pressure data.

[0058] In the embodiments of the present specification, when determining N types of parameter data, data can be collected for each parameter at a set data collection frequency within a preset time length to obtain a set of parameter data corresponding to each parameter. For each type of parameter data, the parameter data corresponding to the parameter can be subjected to correlation analysis with the in-and-out stack pressure data. It should be noted that the in-and-out stack pressure data may include the in-and-out stack pressure data and the out-and-in stack pressure data collected within a preset time length, and the collection frequency of the in-and-out stack pressure data is the same as the collection frequency of the N types of parameter data collected above.

[0059] When performing correlation analysis, for each parameter data, the correlation between the parameter data and the stack-in pressure data and / or the stack-out pressure data can be calculated to obtain a first correlation analysis result between the parameter data and the stack-in pressure data and / or a second correlation analysis result between the parameter data and the stack-out pressure data. For each parameter data, if only the first correlation analysis result is calculated, then if the first correlation analysis result meets the first preset range, then the parameter data can be used as a model input. If only the second correlation analysis result is calculated, then if the second correlation analysis result meets the second preset range, then the parameter data can be used as a model input. If the first correlation analysis result and the second correlation analysis result are calculated, then if the first correlation analysis result meets the first preset range and the second correlation analysis result meets the second preset range, then the parameter data can be used as a model input. Among them, the first preset range and the second preset range can be set according to actual needs, for example, the first preset range is greater than 90%, 95%, etc. in correlation with the stack-in pressure data, and the second preset range is greater than 85%, 90%, 92%, etc. in correlation with the stack-out pressure data.

[0060] In the above manner, K types of parameter data can be screened out from N types of parameter data as model input. In some embodiments, the screened K types of parameter data may include: hydrogen circulation pump speed data, proportional valve opening data, nitrogen exhaust valve switch signal data, drain valve switch signal data, and load current data.

[0061] In the embodiments of this specification, since the scheduling scalar in the preset linear variable parameter identification model is the output power of the fuel cell stack, it is also necessary to obtain the output power data of the fuel cell stack during the process of establishing the model. In some embodiments, the output power data may also be the output power data collected within the above-mentioned preset time length according to the N parameter data collection frequencies.

[0062] When establishing the initial model, a linear variable parameter model is used, that is, the output matrix and the state matrix in the state space model are dependent on the system state parameters. In the embodiment of this specification, the parameter matrix of the initial linear variable parameter identification model is dependent on the output power of the fuel cell stack. Specifically, the initial linear variable parameter identification model can be expressed by the following formula:

[0063]

[0064] Among them, x(k) is the system state data, which is a fictitious intermediate variable and has no actual physical meaning. u(k) is the model input data, which can be a vector composed of hydrogen circulation pump speed data, proportional valve opening data, nitrogen exhaust valve switch signal data, drain valve switch signal data and load current data. y(k) is the model output data, which can be a vector composed of stack inlet pressure data and stack outlet pressure data. p(k) represents the output power data. The target model parameter matrix that needs to be identified includes four model matrices, namely the first parameter matrix A, the second parameter matrix B, the third parameter matrix C and the fourth parameter matrix D.

[0065] In an embodiment of the present specification, when identifying the target model parameter matrix, the following steps can be adopted: based on the model input data, the model output data and the output power data, the mode parameters of the initial linear variable parameter identification model are solved using a subspace identification method to obtain the target model parameter matrix.

[0066] In the process of solving the target model parameter matrix through the subspace identification method, the following steps can be performed: estimating the system state data in the preset linear variable parameter identification model based on the model input data, the model output data and the output power data; determining the target model parameter matrix based on the estimated system state data, the model input data, the model output data and the output power data.

[0067] For the sake of convenience, the process of the identification method of the linear variable parameter model is described below, wherein the identification method of the linear variable parameter model may include the following five steps:

[0068] Step 1: Create matrices U, Y, Z, X.

[0069] U=[u p+1 ,…,u N ],

[0070] Y=[y p+1 , ..., y N ],

[0071]

[0072] X=[x p+1 , ..., x N ]

[0073] u k The model input data u(k), y at sampling point k k is the model output data y(k) at sampling point k, x k is the system state data x(k) at sampling point k, which needs to be estimated by the identification algorithm. The value of p is greater than 1 and less than 10, and is one of the hyperparameters of the algorithm. The parameters in the matrix Z are as follows:

[0074]

[0075]

[0076]

[0077] Among them, μ k is p(k), which is the sampled output power data.

[0078] Step 2: Solve the following optimization problem to estimate the matrix CK p and D, where the optimization problem can be solved by determining CK p The values ​​of and D minimize the norm value in the formula, and the optimization problem can be described as follows:

[0079]

[0080] Among them, ||…|| F represents the Frobenius norm, CK p is the matrix to be solved, which is composed of the p-th power of the parameter matrix C to be identified in the model and the intermediate variable matrix K.

[0081] Step 3: Construct the matrix Γ through the following relationship p K p Z, by definition, is equal to the extended observability matrix multiplied by the system state sequence, i.e., Γ p X.

[0082]

[0083]

[0084] Among them, CK p =[CΛ p ,CΛ p-1 ,…,CΛ1],CΛ p =[CAΛ p-1 ,…,CA m Λ1]

[0085] From the above relationship, we can get the matrix Γ p K p Estimate of Z

[0086] Step 4: Obtain the matrix Σ through singular value decomposition n and V.

[0087]

[0088] Among them, the singular value decomposition can decompose the original matrix into a unitary matrix [υυ σ⊥ ], a diagonal matrix The elements on the diagonal are the singular values. is a unitary matrix. n The subscript n represents the order of the identification model, that is, the number of elements in the model system state data x(k), which is determined according to the model accuracy requirements. Generally, to ensure the calculation speed, its size does not exceed 10. n The diagonal matrix containing the n largest singular values, V is the corresponding row space. The remaining parameter matrix is ​​the matrix element value corresponding to the number of rows and columns.

[0089] Furthermore, the matrix X of the system state can be estimated as:

[0090]

[0091] Through the above steps, the estimated system status data can be obtained.

[0092] Step 5: For a model described by the following form:

[0093]

[0094] If the values ​​of u(k), y(k), p(k), and x(k) at all times in the formula are known, the values ​​of A, B, C, and D can be estimated. The size of the D matrix in the model can be obtained from step 2, and all the estimated values ​​of x(k) at times p+1 to N have been obtained in step 4. The matrix C can be obtained by combining the model input data u(k), the model output data y(k), and the output power data p(k). Similarly, since the matrices A, B and x(k), u(k) satisfy a linear relationship, the data sampling values ​​from time p+1 to N can be used to form a linear equation group and solve it.

[0095] Through the above steps, the target model parameter matrices A, B, C, and D can be solved to obtain a linear variable parameter identification model. Further, the obtained linear variable parameter identification model can be verified. In some embodiments, model verification data can be constructed, and the model verification data can include input data and output data. The model verification data is actually collected data that is consistent with the type of model input data and the type of model output data. The input data in the model verification data is input into the above linear variable parameter identification model, and the in-pile data and out-pile data output by the model are compared with the output data in the verification data to determine the accuracy of the model. In some embodiments, if the comparison result shows that the error between the in-pile data and out-pile data output by the model and the output data in the verification data is less than the preset error, it indicates that the accuracy of the model meets the requirements, and it can be used as a preset linear variable parameter identification model for subsequent vehicle control.

[0096] In summary, the scheme in the embodiments of this specification can estimate the out-stack pressure and in-stack pressure of the fuel cell hydrogen subsystem in real time by establishing a preset linear variable parameter identification model that depends on the output power of the fuel cell stack, so as to determine the changes of the fuel cell hydrogen subsystem under different power conditions, and more accurately determine the in-stack pressure and out-stack pressure of the fuel cell hydrogen subsystem, thereby improving the accuracy of vehicle control. In addition, the preset linear variable parameter identification model in the embodiments of this specification is a dynamic model of the hydrogen subsystem obtained based on data, without relying on process mechanisms and system structures. The model takes into account the changes of the hydrogen subsystem under different power conditions, and uses the system output power to adjust the model parameters, which can more accurately cover the full power operating point, thereby effectively improving the overall accuracy of the model, and providing a basis for the design of subsequent vehicle controllers.

[0097] Based on the same inventive concept, the embodiment of the present invention also provides a method for constructing a linear variable parameter identification model, such as Figure 3 As shown, the method comprises the following steps:

[0098] Step S301: acquiring N types of parameter data corresponding to a vehicle fuel cell hydrogen subsystem, inlet and outlet data of a fuel cell stack in the fuel cell hydrogen subsystem, and output power data of the fuel cell stack collected within a preset time period;

[0099] Step S302: determining model input data based on the N types of parameter data, and determining model output data based on the in-and-out data of the fuel cell stack;

[0100] Step S303: constructing an initial linear variable parameter identification model;

[0101] Step S304: solving the model parameter matrix of the initial linear variable parameter identification model based on the model input data, the model output data and the output power data to obtain a target model parameter matrix;

[0102] Step S305: verifying the model corresponding to the target model parameter matrix. If the verification is successful, the successfully verified model is used as a preset linear variable parameter identification model.

[0103] Regarding the above method, the specific implementation of each step has been described in detail in the embodiment of the method for determining the inlet and outlet stack pressures of a fuel cell hydrogen subsystem provided in the embodiment of the specification, and will not be elaborated here.

[0104] Based on the same inventive concept, an embodiment of the present invention further provides a vehicle, such as Figure 4 The method includes a memory 404, a processor 402, and a computer program stored in the memory 404 and executable on the processor 402. When the processor 402 executes the program, any one of the methods for determining the inlet and outlet stack pressures of a fuel cell hydrogen subsystem and the method for constructing a linear variable parameter identification model is implemented.

[0105] Among them, Figure 4 In the embodiment of the present invention, a bus architecture (represented by bus 400) is shown, which may include any number of interconnected buses and bridges, and bus 400 links various circuits including one or more processors represented by processor 402 and memory represented by memory 404. Bus 400 may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. Bus interface 405 provides an interface between bus 400 and receiver 401 and transmitter 403. Receiver 401 and transmitter 403 may be the same element, namely a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 402 is responsible for managing bus 400 and general processing, while memory 404 may be used to store data used by processor 402 when performing operations.

[0106] Based on the same inventive concept, an embodiment of this specification provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method for determining the inlet and outlet stack pressures of the above-mentioned fuel cell hydrogen subsystem and the method for constructing a linear variable parameter identification model are implemented.

[0107] Based on the same inventive concept, an embodiment of this specification provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it is used to load and execute the steps of a method for determining the inlet and outlet stack pressures of a fuel cell hydrogen subsystem and a method for constructing a linear variable parameter identification model.

[0108] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on a computer-readable medium or transmitted via a computer-readable medium. Other examples and implementations are within the scope and spirit of the present invention and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hard wiring, or a combination of any of these. In addition, each functional unit may be integrated into a processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit.

[0109] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0110] The units described as separate components may or may not be physically separated, and the components of the control device may or may not be physical units, that is, they may be located in one place or distributed in multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0111] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0112] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the scope of the claims of the present invention.

Claims

1. A method for determining the inlet and outlet pressures of a fuel cell hydrogen subsystem, characterized in that: include: Acquiring current target parameter data of a fuel cell hydrogen subsystem of a vehicle, wherein the fuel cell hydrogen subsystem includes a fuel cell stack; Determining a current outlet pressure and a current inlet pressure of the fuel cell stack based on the current target parameter data and a preset linear variable parameter identification model, wherein the preset linear variable parameter identification model depends on the output power of the fuel cell stack; Based on the current stack outlet pressure and the current stack inlet pressure, a current state of the fuel cell hydrogen subsystem is determined, and the vehicle operation is controlled based on the current state.

2. The method according to claim 1, characterized in that The preset linear variable parameter identification model is determined by the following steps: Acquiring model input data, model output data, and output power data of the fuel cell stack; Construct an initial linear variable parameter identification model; Solving the model parameter matrix of the initial linear variable parameter identification model based on the model input data, the model output data and the output power data to obtain a target model parameter matrix; The model corresponding to the target model parameter matrix is ​​verified, and if the verification is successful, the successfully verified model is used as the preset linear variable parameter identification model.

3. The method according to claim 2, characterized in that The obtaining of model input data comprises: Obtaining N parameter data and inlet and outlet stack pressure data of the vehicle within a preset time period, where N is a positive integer; Based on each parameter data of the N types of parameter data, a correlation analysis is performed on the parameter data and the inlet and outlet stack pressure data to obtain a correlation analysis result between the parameter data and the inlet and outlet stack pressure data; The K types of parameter data whose correlation analysis results meet the preset range are used as the model input data, where K is a positive integer.

4. The method according to claim 3, characterized in that The N types of parameter data include load current data, system power data, ambient temperature data, proportional valve opening data, hydrogen circulation pump speed data, drain valve switch signal data, nitrogen exhaust valve switch signal data, drain valve temperature data, nitrogen exhaust valve temperature data, stack temperature data and medium pressure data corresponding to the fuel cell hydrogen subsystem.

5. The method according to claim 2, characterized in that The step of solving the model parameter matrix of the initial linear variable parameter identification model based on the model input data, the model output data, and the output power data to obtain a target model parameter matrix includes: Based on the model input data, the model output data and the output power data, a subspace identification method is used to solve the mode parameters of the initial linear variable parameter identification model to obtain the target model parameter matrix.

6. The method according to claim 5, characterized in that The preset linear variable parameter identification model corresponds to system state data. Based on the model input data, the model output data and the output power data, the mode parameters of the initial linear variable parameter identification model are solved by using a subspace identification method to obtain a target model parameter matrix, including: estimating system state data in the preset linear variable parameter identification model based on the model input data, the model output data and the output power data; The target model parameter matrix is ​​determined based on the estimated system state data, the model input data, the model output data, and the output power data.

7. A method for constructing a linear variable parameter identification model, characterized in that: include: Acquire N types of parameter data corresponding to the vehicle fuel cell hydrogen subsystem, inlet and outlet data of the fuel cell stack in the fuel cell hydrogen subsystem, and output power data of the fuel cell stack collected within a preset time period; Determining model input data based on the N parameter data, and determining model output data based on the in-and-out stack data of the fuel cell stack; Construct an initial linear variable parameter identification model; Solving the model parameter matrix of the initial linear variable parameter identification model based on the model input data, the model output data and the output power data to obtain a target model parameter matrix; The model corresponding to the target model parameter matrix is ​​verified, and if the verification is successful, the successfully verified model is used as a preset linear variable parameter identification model.

8. A vehicle, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the program.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program is used to load and execute the method according to any one of claims 1 to 7.

Images