A fuel cell cold start control method, system, device and emergency power supply vehicle

Abstract

The present application relates to the field of information technology, and discloses a fuel cell cold start control method, system, equipment and emergency power supply vehicle, the method comprising: obtaining the initial state parameters of the fuel cell; establishing a multi-physical field state model for the fuel cell; solving the multi-physical field state model to obtain the actual state parameters of the fuel cell; taking the cold start time of the fuel cell as the objective function, searching through the ant colony optimization algorithm to obtain the optimal temperature rise control strategy; setting the step target control parameters according to the optimal temperature rise control strategy and the safety parameter threshold of the fuel cell to obtain the control instruction sequence of the fuel cell; numerically optimizing the step target control parameters through the target parameter optimization model. Its beneficial effect is that it solves the technical problem of the long time consumption of the cold start of the fuel cell, achieves the technical effect of enabling the fuel cell to start quickly under low temperature conditions, and improves the reliability of the fuel cell start.

Description

Technical Field

[0001] The present application relates to the field of information technology, and in particular to a fuel cell cold start control method, system, equipment and emergency power supply vehicle. Background Art

[0002] As a clean energy, hydrogen energy is an important development direction in the current energy and science and technology fields. During the startup process of the emergency power supply vehicle, there is a complex interactive effect between the temperature and current density of the fuel cell. Therefore, when the fuel cell is started in a low temperature environment, there will be problems such as slow electrode reaction kinetics and large activation overpotential, resulting in a low starting voltage. Simply increasing the current density can easily aggravate the electrode reaction, causing flooding and membrane dehydration of the fuel cell, resulting in increased membrane resistance, generating large ohmic heat, and causing local hot spots. In addition, the uneven distribution of current density will also lead to uneven temperature distribution inside the fuel cell, resulting in large thermal stress and affecting the mechanical stability of the fuel cell. In the related technology, there is an urgent need for a control method that can shorten the cold start time while meeting the safety constraints of the fuel cell. Summary of the invention

[0003] The present application provides a fuel cell cold start control method, system and emergency power supply vehicle, which solves the technical problem of long cold start time of fuel cells, achieves the technical effect of enabling fuel cells to start quickly under low temperature conditions and improving the reliability of fuel cell start-up.

[0004] In order to achieve the above objectives, the main technical solutions adopted in this application include:

[0005] In a first aspect, an embodiment of the present application provides a fuel cell cold start control method, the method comprising:

[0006] Acquiring initial state parameters of the fuel cell;

[0007] Iteratively optimizing the initial state parameters of the fuel cell to obtain actual state parameters of the fuel cell; wherein the degree of conformity between the actual state parameters and the actual state of the fuel cell is higher than the degree of conformity between the initial state parameters and the actual state of the fuel cell;

[0008] According to the actual state parameters, taking minimizing the cold start time of the fuel cell as the objective function, searching by an ant colony optimization algorithm to obtain an optimal temperature rise control strategy for the fuel cell; according to the optimal temperature rise control strategy and the safety parameter threshold of the fuel cell, setting a step target control parameter to obtain a control instruction sequence for the fuel cell;

[0009] When the fuel cell is cold-started according to the control instruction sequence, the step target control parameters are numerically optimized through a target parameter optimization model; and an optimized control instruction sequence of the fuel cell is obtained according to the numerically optimized step target control parameters to control the fuel cell to cold-start.

[0010] The fuel cell cold start control method proposed in the embodiment of the present application searches for the optimal temperature rise control strategy through an ant colony optimization algorithm based on the actual state data of the fuel cell; and while performing cold start control according to the optimal temperature rise control strategy, the step target control parameters in the optimal temperature rise control strategy are optimized through a target parameter optimization model to comprehensively consider various state factors of the fuel cell, thereby achieving optimal control of the fuel cell cold start process while satisfying safety constraints, allowing the fuel cell to start quickly under low temperature conditions and improving the reliability of fuel cell startup.

[0011] In a second aspect, an embodiment of the present application provides a fuel cell cold start control system, the system comprising:

[0012] An initial acquisition module, used to obtain the initial state parameters of the fuel cell;

[0013] A model calculation module, used for iteratively optimizing the initial state parameters of the fuel cell to obtain the actual state parameters of the fuel cell; wherein the degree of conformity between the actual state parameters and the real state of the fuel cell is higher than the degree of conformity between the initial state parameters and the real state of the fuel cell;

[0014] an optimization search module, configured to search by an ant colony optimization algorithm according to the actual state parameters and taking minimizing the cold start time of the fuel cell as the objective function, so as to obtain an optimal temperature rise control strategy for the fuel cell; and to set a step target control parameter according to the optimal temperature rise control strategy and the safety parameter threshold of the fuel cell to obtain a control instruction sequence for the fuel cell;

[0015] A numerical optimization module is used to numerically optimize the step target control parameters through a target parameter optimization model when the fuel cell is cold-started according to the control instruction sequence; and obtain an optimized control instruction sequence of the fuel cell according to the numerically optimized step target control parameters to control the fuel cell to cold-start.

[0016] In a third aspect, an embodiment of the present application provides an emergency power supply vehicle, wherein a pure electric chassis, a hydrogen carrying system, a hydrogen fuel cell system, a lithium battery pack, a power inverter system, an air conditioning system, a cooling system, an air intake and exhaust system, and a centralized control cabinet are provided in the compartment of the emergency power supply vehicle, and the fuel cell cold start control method described in any one of the above embodiments is executed on the hydrogen fuel cell system to perform a cold start.

[0017] In a fourth aspect, an embodiment of the present application provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the fuel cell cold start control method described in any one of the above embodiments by executing the computer instructions.

[0018] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the fuel cell cold start control method described in any one of the above embodiments.

[0019] In a sixth aspect, an embodiment of the present application provides a computer program product, including computer instructions, wherein the computer instructions are used to enable a computer to execute the fuel cell cold start control method described in any one of the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1a A schematic diagram of an emergency power supply vehicle provided in an embodiment of the present application;

[0022] Figure 1b An energy transmission topology diagram of an emergency power supply vehicle provided in an embodiment of the present application;

[0023] Figure 1c A top view of the emergency power supply vehicle provided in an embodiment of the present application;

[0024] Figure 1d A topological diagram of the intelligent control system of the emergency power supply vehicle provided in the embodiment of the present application;

[0025] Figure 2 A step diagram of a fuel cell cold start control method provided in an embodiment of the present application;

[0026] Figure 3A diagram showing steps for iteratively optimizing initial state parameters according to an embodiment of the present application;

[0027] Figure 4 A step diagram for establishing a multi-physics field state model for an embodiment of the present application;

[0028] Figure 5 This is a flowchart optimized by the ant colony optimization algorithm in an embodiment of the present application;

[0029] Figure 6 A step diagram of the dynamic security optimization model in the embodiment of the present application;

[0030] Figure 7 A step diagram of the operation of the historical prediction optimization model in the embodiment of the present application;

[0031] Figure 8 A step diagram of the degradation prediction optimization model working in the embodiment of the present application;

[0032] Fig. 9 A diagram showing the steps of obtaining performance degradation data by using a degradation prediction optimization model in an embodiment of the present application;

[0033] Fig.10 A module diagram of a fuel cell cold start control system provided in an embodiment of the present application;

[0034] Fig.11 A schematic diagram of the structure of a computer device provided in an embodiment of the present application.

[0035] Among them, the figure numbers of the drawings in the specification are as follows: 101. Pure electric chassis, 102. Hydrogen carrying system, 103. Hydrogen fuel cell system, 104. Lithium battery pack, 105. Power inverter system, 106. Air conditioning system, 107. Cooling system, 108. Air intake and exhaust system, 109. Centralized control cabinet, 201. Initial acquisition module, 202. Model calculation module, 203. Optimization search module, 204. Numerical optimization module. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0037] As a clean energy, hydrogen energy has the advantages of high energy density and high energy conversion efficiency. In addition, hydrogen energy does not produce greenhouse gases during use and can reduce air pollution. It is an important direction for the development of the current energy and technology fields. Hydrogen fuel cells are an important application of hydrogen energy. They take advantage of the high energy density and cleanliness of hydrogen energy, provide an energy source that can meet the requirements of long-term endurance and low carbon emissions, and show great potential and application prospects in transportation, power generation, industry and other fields.

[0038] With the development of society, people's demand for electricity has gradually increased, and the stability of the power system has become one of the most concerned focuses of the society. For example, during the peak period of seasonal electricity consumption, it is necessary to provide users with comprehensive and reliable power protection through certain technical means; in addition, in scenarios such as important meetings, large-scale events, important examinations and power maintenance, additional energy storage technology is needed to provide load power protection for the above scenarios to ensure that the power supply will not be interrupted in important scenarios. In the face of major and emergency tasks, emergency power supply vehicles have emerged as a power supply solution for "non-stop operation". Emergency power supply vehicles can be flexibly deployed to the power outage site to provide temporary power for key equipment and facilities to ensure the continuity of power supply. Common energy types used for emergency power supply vehicles include diesel and lithium batteries. The application of traditional diesel generators has the problem of a large amount of polluting gas emissions, and lithium battery generators also have the problems of low energy replenishment efficiency, low temperature resistance and insufficient support for continuous operation.

[0039] Based on the above problems, the present application provides an emergency power supply vehicle, referring to Figure 1a , Figure 1a A schematic diagram of an emergency power supply vehicle provided in an embodiment of the present application is shown in the figure. A pure electric chassis 101, a hydrogen carrying system 102, a hydrogen fuel cell system 103, a lithium battery pack 104 and a power inverter system 105 are provided in the compartment of the emergency power supply vehicle.

[0040] Specifically, the hydrogen carrying system 102 is used to store hydrogen energy, including a hydrogen filling system, a hydrogen storage system and a hydrogen supply system. Exemplarily, the hydrogen storage system consists of 16 210L aluminum alloy liner carbon fiber wrapped Class III composite hydrogen cylinders, each of which is equipped with a bottle tail combination valve and a bottle mouth combination valve. The bottle tail combination valve is equipped with a PRD device, which can release hydrogen at a set pressure threshold (35MPa) to achieve over-temperature and over-pressure protection. The hydrogen supply system is mainly composed of a main solenoid valve, a pressure reducing valve, a pressure sensor, a safety valve, etc. The main solenoid valve and the pressure reducing valve control the hydrogen flow and hydrogen pressure through the control signal of the fuel cell stack ECU to meet the working requirements of the stack.

[0041] Furthermore, the hydrogen fuel cell system 103 is used to output electrical energy to the outside for emergency power supply operations. For example, the hydrogen fuel cell group is composed of two hydrogen fuel cell reactors with an output power of 130kW in parallel, with a power density of 700W / kg and a service life of up to 30,000h. In the parallel output mode, the two hydrogen fuel cell reactors are required to operate at the same operating voltage and ensure current balance to ensure that the two reactors share the load evenly. In addition, the hydrogen fuel cell group also integrates a monitoring system to detect the working status of the fuel cell in real time, and complete the safety isolation between the two reactors when necessary to ensure the stability of the system operation.

[0042] Reference Figure 1b , Figure 1b The energy transmission topology diagram of the emergency power supply vehicle provided in the embodiment of the present application is shown in the figure. When the emergency power supply vehicle provided in the present application is working, it mainly outputs electrical energy to the outside through the hydrogen fuel cell system 103 for emergency power supply operations; at the same time, the hydrogen fuel cell system 103 can also output excess electricity to the power battery of the emergency power supply vehicle, thereby charging the power battery and providing power for the emergency power supply vehicle.

[0043] Specifically, the emergency power supply vehicle allocates fuel cell output power and lithium battery output power according to the actual power demand and the SOC of the lithium battery pack 104. The emergency power supply vehicle has two working conditions: off-grid power supply and grid-connected power supply. Under the off-grid power supply condition, the emergency power supply vehicle outputs AC400V power to the outside, and its power comes from fuel cells and lithium batteries; when it is grid-connected, if the mains power is normal, the external output power comes from the power grid, and the inverter power supply PCS is in a backup state. If the mains power fails, the inverter power supply PCS switches from grid-connected to off-grid, and the external output power comes from fuel cells and lithium batteries.

[0044] Furthermore, during the external power supply startup stage, the transient performance of the fuel cell is poor, and the output is externally provided through the buffer lithium battery; when entering the hybrid power generation stage, the buffer lithium battery and the fuel cell jointly output, and the energy management system adjusts the output power of the lithium battery pack 104 according to the SOC of the buffer lithium battery, and the output of the lithium battery pack 104 plays a role in peak shaving and valley filling; when entering the fuel cell rated power generation stage, the fuel cell's power generation redundancy can also charge the vehicle-mounted power battery.

[0045] Reference Figure 1c , Figure 1c The top view of the emergency power supply vehicle provided in the embodiment of the present application is shown in the figure. The emergency power supply vehicle provided in the present application also includes an air conditioning system 106, a cooling system 107, an air intake and exhaust system 108, and a centralized control cabinet 109. Specifically, the centralized control cabinet 109 is used to control the electric control system of the emergency power supply vehicle, including a central controller and a control harness, and is the hardware foundation of the intelligent electric control system of the whole vehicle.

[0046] Further, refer to Figure 1d , Figure 1d The topology diagram of the intelligent control system of the emergency power supply vehicle provided in the embodiment of the present application is shown in the figure. The intelligent electronic control system includes a central control management system, a mobile monitoring system, a real-time monitoring system, etc. For example, in order to make the electronic control system of the emergency power supply vehicle stable and reliable, Siemens' S7-1200 series PLC is selected as the central control unit of the system. The data detected in real time by the temperature sensor and pressure sensor installed on the emergency power supply vehicle is transmitted to the PLC for digital-to-analog conversion and acquisition, and then the data signal is transmitted to the human-computer interaction screen through the Modbus protocol. The operator can observe the operating data of the emergency power supply vehicle through the screen. Two fuel cells and lithium batteries are controlled through CAN communication to realize the energy management of the emergency power supply vehicle. Use the WiFi expansion module for networking operation, and upload the operating data of the emergency power supply vehicle to the operation log of the cloud server.

[0047] The emergency power supply vehicle provided by the present application uses hydrogen fuel cells as an energy source to generate electricity through the chemical reaction of hydrogen and oxygen, and its main emission is water. Compared with traditional fuel vehicles, the operation of fuel cells is not limited by the Carnot cycle effect, and the efficiency can reach 40%-60%, which improves the user's convenience and overall travel efficiency. Compared with the internal combustion engine in the traditional diesel generator vehicle, the emergency power supply vehicle provided by the present application has a smaller environmental impact and less working noise in the hydrogen fuel cell; compared with the lithium battery generator vehicle, the hydrogen fuel cell has stronger low-temperature performance, higher energy density, and shorter charging time, and is more suitable for application in emergency power supply vehicles in emergency power supply operations. Application and promotion.

[0048] During the startup process of the emergency power supply vehicle, there is a complex interactive effect between the temperature and current density of the fuel cell. Therefore, when the fuel cell is started in a low-temperature environment, problems such as slow electrode reaction kinetics and large activation overpotential will occur, resulting in a low starting voltage. During the cold start process, simply increasing the current density can easily aggravate the electrode reaction, causing flooding and membrane dehydration of the fuel cell, resulting in increased membrane resistance, generating large ohmic heat, and causing local hot spots. In addition, uneven current density distribution will also lead to uneven temperature distribution inside the fuel cell, generating large thermal stress and affecting the mechanical stability of the fuel cell. Therefore, during the low-temperature startup process of the fuel cell, it is necessary to reasonably regulate the temperature and current density of the stack, and avoid local hot spots and thermal stress problems caused by high current density to achieve fast, safe and efficient startup.

[0049] Based on this problem, the present application also provides a fuel cell cold start control method, which includes: obtaining the initial state parameters of the fuel cell; establishing a multi-physical field state model for the fuel cell; solving the multi-physical field state model to obtain the actual state parameters of the fuel cell; taking minimizing the cold start time of the fuel cell as the objective function, searching through an ant colony optimization algorithm to obtain an optimal temperature rise control strategy; setting step target control parameters according to the optimal temperature rise control strategy and the safety parameter threshold of the fuel cell to obtain a control instruction sequence of the fuel cell; and numerically optimizing the step target control parameters through the target parameter optimization model.

[0050] The fuel cell cold start control method proposed in the embodiment of the present application searches for the optimal temperature rise control strategy through an ant colony optimization algorithm based on the actual state data of the fuel cell; and while performing cold start control according to the optimal temperature rise control strategy, the step target control parameters in the optimal temperature rise control strategy are optimized through a target parameter optimization model to comprehensively consider various state factors of the fuel cell, thereby solving the technical problem of long cold start time of the fuel cell, and achieving optimal control of the fuel cell cold start process while satisfying safety constraints, so that the fuel cell can start quickly under low temperature conditions and improve the start-up reliability of the fuel cell.

[0051] The fuel cell cold start control method provided in this specification can be applied to the above-mentioned emergency power supply vehicle to control the hydrogen fuel cell system 103 therein to achieve cold start under low temperature conditions. It is understandable that, in the case of adaptive modification of this method, this method can also be used to control other equipment and devices including hydrogen fuel cells.

[0052] According to an embodiment of the present application, an embodiment of a fuel cell cold start control method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0053] In this embodiment, a fuel cell cold start control method is provided, which can be used for emergency power supply vehicles and other equipment and devices including hydrogen fuel cells. Figure 2 , Figure 2 The step diagram of the fuel cell cold start control method provided in the embodiment of the present application, as shown in the figure, includes the following steps:

[0054] S100. Obtaining initial state parameters of the fuel cell.

[0055] S200. Iteratively optimize the initial state parameters of the fuel cell to obtain actual state parameters of the fuel cell; wherein the degree of conformity between the actual state parameters and the true state of the fuel cell is higher than the degree of conformity between the initial state parameters and the true state of the fuel cell.

[0056] S300. Based on the actual state parameters, taking minimizing the cold start time of the fuel cell as the objective function, a search is performed through an ant colony optimization algorithm to obtain the optimal temperature rise control strategy of the fuel cell; based on the optimal temperature rise control strategy and the safety parameter threshold of the fuel cell, a step target control parameter is set to obtain a control instruction sequence of the fuel cell.

[0057] S400. When the fuel cell is cold-started according to the control instruction sequence, the step target control parameters are numerically optimized through the target parameter optimization model; the optimized control instruction sequence of the fuel cell is obtained according to the numerically optimized step target control parameters to control the fuel cell to cold-start.

[0058] Specifically, the ant colony optimization algorithm is used to search and obtain the optimal temperature rise control strategy of the fuel cell, wherein the optimal temperature rise control strategy includes a continuous curve of the state parameters of the fuel cell changing over time. In other embodiments, other release optimization algorithms may be selected according to actual scene requirements, including but not limited to: genetic algorithm, particle swarm optimization algorithm, bat algorithm, wolf pack algorithm, etc.

[0059] Furthermore, under the premise of not exceeding the safety parameter threshold of the fuel cell, the corresponding step target control parameters are set according to the optimal temperature rise control strategy to form a control instruction sequence for the fuel cell. It can be understood that the control instruction sequence is a discretized optimal temperature rise control strategy, and the values ​​of the step target control parameters contained in the control instruction sequence are the same as the values ​​of the continuous curve in the optimal temperature rise control strategy. The more the number of step target control parameters, the higher the degree of conformity between the control instruction sequence and the optimal temperature rise control strategy, and the higher the accuracy of the fuel cell control. Compared with directly using the continuous curve in the optimal temperature rise control strategy for control, control through a discretized control instruction sequence can reduce system oscillation, increase system stability, and reduce control costs including hardware costs and maintenance costs.

[0060] In some embodiments, the control instruction sequence corresponding to the fuel cell under different actual working conditions can be obtained by storing and recording the historical control instruction sequence of the fuel cell, so as to form an instruction lookup table based on the actual working conditions, wherein the actual working conditions include the ambient temperature, etc. When controlling the fuel cell to cold start, the ambient temperature can be detected by the temperature sensor integrated in the hydrogen fuel cell system, and the corresponding control instruction sequence can be obtained from the instruction lookup table according to the measured ambient temperature, so as to directly perform cold start control and realize one-button adaptive cold start.

[0061] Specifically, when executing the control instruction sequence, the real-time temperature parameters of the fuel cell are collected in real time, the real-time temperature parameters are compared with the step target control parameters, and the heating power is adjusted through the PID algorithm, thereby realizing closed-loop control of the fuel cell. Furthermore, during the cold start control process, the step target control parameters are numerically optimized based on the real-time temperature parameters and the target parameter optimization model. The optimization conditions of the target parameter optimization model include but are not limited to: the safety threshold of the fuel cell, performance degradation data, and historical fault data.

[0062] In some embodiments, the target parameter optimization model for numerically optimizing the step-type target control parameters according to historical fault data includes a historical fault optimization model, in which the fault conditions and corresponding state parameters of the fuel cell during the historical working process are stored. When the fuel cell is controlled to perform a cold start, it is determined whether the fuel cell has a fault according to the real-time temperature parameters of the fuel cell. If the fuel cell has not failed, numerical optimization is performed; if the fuel cell has failed, corresponding processing is performed according to the fault condition; for minor fault conditions, the step-type target control parameters can be numerically optimized according to the specific fault condition to reduce the impact on the cold start of the fuel cell and avoid the deterioration of the fault condition; for serious fault conditions, the cold start process of the fuel cell is stopped and the user is warned.

[0063] In other embodiments, in the process of controlling the cold start of the fuel cell, an adaptive controller based on deep reinforcement learning is designed for the fuel cell according to the dynamic characteristics of water transport in the fuel cell membrane, wherein the membrane water content is used as the state variable, the heating power is used as the action variable, and the reward function is designed according to the temperature gradient and water content constraints in the fuel cell, and its form is as follows:

[0064]

[0065] in, The fuel cell is in the state parameter When The reward function when ; , , and To adjust the parameters, it can be obtained according to reinforcement learning; is the temperature field gradient; For example, the state parameter corresponding to the reward function may be a value that does not satisfy the safety constraint condition. At this time, an optimization action is taken on the fuel cell to reduce the state parameter so that it satisfies the safety constraint condition, thereby guiding the fuel cell to achieve a safe and efficient cold start process through the reward function.

[0066] The fuel cell cold start control method proposed in the embodiment of the present application searches for the optimal temperature rise control strategy through an ant colony optimization algorithm based on the actual state data of the fuel cell; and while performing cold start control according to the optimal temperature rise control strategy, the step target control parameters in the optimal temperature rise control strategy are optimized through a target parameter optimization model to comprehensively consider various state factors of the fuel cell, thereby achieving optimal control of the fuel cell cold start process while satisfying safety constraints, allowing the fuel cell to start quickly under low temperature conditions and improving the reliability of fuel cell startup.

[0067] As an embodiment of the present application, the initial state parameters include the initial temperature field and the initial current density distribution of the fuel cell; obtaining the initial state parameters of the fuel cell includes:

[0068] S110. Collect current temperature and current density at different locations inside the fuel cell.

[0069] S120. Using the Kalman filter algorithm, perform multi-sensor data fusion on the current temperature to obtain the current overall temperature of the fuel cell, and perform multi-sensor data fusion on the current current density to obtain the current overall current density of the fuel cell.

[0070] S130. Interpolate the current overall temperature to obtain an initial temperature field.

[0071] S140. Interpolate the current overall current density to obtain an initial current density distribution.

[0072] Specifically, temperature sensors are installed at key locations within the fuel cell to collect the current temperature at different locations within the fuel cell. Exemplarily, the temperature of key locations can directly reflect the reaction rate and current transmission of the fuel cell, including but not limited to: gas flow channels, catalyst layers, cooling systems, electrode areas, and current collecting plates. Further, based on the current temperature data obtained, multi-sensor data fusion is performed through the Kalman filter algorithm to obtain the current overall temperature of the fuel cell. The current overall temperature improves the reliability of the temperature data compared to the current temperature and can accurately describe the temperature distribution inside the fuel cell. Further, based on the location where the temperature sensor is set and the continuity conditions between different temperature sensors, the current overall temperature is interpolated to obtain the initial temperature field of the fuel cell.

[0073] Correspondingly, the processing of current density is the same as that of temperature data. After the current current distribution is acquired, the initial current density distribution in the fuel cell is obtained through Kalman filtering algorithm and interpolation processing.

[0074] Reference Figure 3 , Figure 3 The step diagram of iteratively optimizing the initial state parameters in the embodiment of the present application is shown in the figure. As an embodiment of the present application, the initial state parameters of the fuel cell are iteratively optimized to obtain the actual state parameters of the fuel cell, including:

[0075] S210. Establish a multi-physical field state model for the fuel cell based on the multi-physical quantity state equation of the fuel cell.

[0076] S220. Substitute the initial state parameters as initial conditions into the multi-physics field state model, and use the Newton iteration method to solve the multi-physics field state model to obtain the actual state parameters of the fuel cell.

[0077] Specifically, the initial state parameters are used to describe the overall state within the fuel cell, where the parameter types match the physical field types in the multi-physical quantity state equation and the multi-physical field state model, and both describe parameters in the same physical field. Exemplarily, the types of physical fields include, but are not limited to, temperature fields, electric fields, magnetic fields, and stress fields, etc., which can be selected according to the actual scenario. The multi-physical field state model is used to describe the working process of the fuel cell, including but not limited to, electrochemical reactions, heat and mass transfer, and fluid flow.

[0078] Furthermore, Newton's method, also known as Newton-Raphson method, is a method for approximating the solution of equations in real and complex domains, using the first few terms of the Taylor series of the function to find the roots of the equation. The initial state parameters are substituted into the multi-physics state model as initial conditions, and the multi-physics state model is solved using the Newton iteration method to obtain the actual state parameters of the fuel cell, including: for the input initial state parameters, the corresponding calculated values ​​and derivative values ​​are obtained according to the multi-physics state equation; based on the obtained calculated values ​​and derivative values, the initial state parameters are updated using the Newton iteration formula to obtain the updated state parameters; it is determined whether the obtained updated state parameters meet the convergence conditions. If they meet the convergence conditions, the updated state parameters are used as the approximate solution of the multi-physics state model, otherwise the iteration is continued until the obtained updated state parameters meet the convergence conditions.

[0079] Exemplarily, the convergence condition is that the Euclidean norm obtained from the residual of the updated state parameter is less than a preset threshold value. In this embodiment, the preset threshold value is 10 -6 It should be noted that the residuals of the updated state parameters include but are not limited to: absolute residuals, relative residuals and function value residuals, etc. The actual state parameters of the fuel cell obtained by the Newton iteration method correspond to the physical fields in the multi-physical quantity state equation, including but not limited to: temperature, current density, component concentration and displacement, etc.

[0080] Reference Figure 4 , Figure 4 The step diagram of establishing a multi-physics field state model for an embodiment of the present application is shown in the figure. As an embodiment of the present application, a multi-physics field state model is established for a fuel cell according to a multi-physics quantity state equation of the fuel cell, including:

[0081] S212. Based on the structural parameters and material properties of the fuel cell, the fuel cell is spatially discretized to generate an unstructured grid.

[0082] S214. Determine the unit state equation corresponding to each discrete unit in the unstructured grid to obtain a discretized grid state equation; wherein the unit state equation includes at least one of an energy conservation equation, a component conservation equation, a momentum conservation equation, and a charge conservation equation.

[0083] S216. Boundary conditions are set for the grid state equations based on the multi-physics field equations of the fuel cell to obtain a set of nonlinear equations to establish a multi-physics field state model; wherein the multi-physics field equations include at least one of the electrochemical reaction kinetics equations at the three-phase interface on the electrode surface, the proton conduction equation in the proton exchange membrane, and the multi-component diffusion equation in the gas diffusion layer.

[0084] Specifically, according to the structural parameters and material properties of the fuel cell, the geometric structure of the fuel cell is spatially discretized using tetrahedral units; for example, a finer grid unit needs to be set at the interface between different layers in the fuel cell to accurately reflect the changes in physical quantities there. Through spatial discretization, an unstructured grid that meets the grid independence requirements is generated for the fuel cell, ensuring that the simulation results obtained by the unstructured grid are not significantly affected by the grid size and distribution.

[0085] Furthermore, the unstructured grid includes multiple discrete units, and the obtained unit state equations are combined according to the position of each discrete unit and the corresponding unit state equation to obtain the grid state equation. The unit state equation includes at least one of the energy conservation equation, the component conservation equation, the momentum conservation equation and the charge conservation equation, wherein the energy conservation equation is in the form of:

[0086]

[0087] in, is the porosity; For pressure; is the fluid density; is the specific heat capacity at constant pressure; is temperature; is the fluid velocity; is the effective thermal conductivity; is the energy source term, which is in the following form:

[0088]

[0089] in, is the current; is the ohmic impedance; is the ratio of the enthalpy change of the electrochemical reaction to heat energy; is the gaseous water source term; is the enthalpy change of the reaction; is the condensation rate of water vapor; is the condensation enthalpy of water; is the overpotential of the battery; is the exchange current density.

[0090] The conservation equation for the components is of the form:

[0091]

[0092] in, For components concentration; For components The effective diffusion coefficient of For components The source term. The form is as follows:

[0093]

[0094] in, is the water saturation, i.e. the volume ratio of liquid water per unit volume; , and is the correction factor; is standard pressure; is the standard temperature. When the components are hydrogen, oxygen and water vapor, The forms are as follows:

[0095]

[0096] in, is the Faraday constant; is the exchange current density of the battery anode; is the exchange current density at the battery cathode.

[0097] The momentum conservation equation has the following form:

[0098]

[0099] in, is the fluid viscosity; is the momentum source term. According to Darcy's theorem, the momentum conservation equation can be simplified to:

[0100]

[0101] in, is the gas permeability in porous media.

[0102] The charge conservation equation has the following form:

[0103]

[0104] in, is the current source term of the solid phase; is the current source term of the proton exchange membrane; is the electrical conductivity of the solid phase; is the conductivity of the proton exchange membrane, satisfying the following formula:

[0105]

[0106] in, is the water content, i.e. the number of water molecules adsorbed on each sulfonate group. and Satisfy the following formula:

[0107]

[0108] in, is the exchange current density of the battery anode; is the exchange current density at the battery cathode.

[0109] Furthermore, after obtaining the grid state equation, the finite volume method and the second-order upwind scheme are used to discretize the grid state equation. The finite volume method is a commonly used numerical algorithm in computational fluid dynamics. The finite volume method is based on the conservation equation in integral form rather than the differential equation. The conservation equation in integral form describes each control volume defined by the computational grid. The finite volume method focuses on constructing discrete equations from a physical point of view. Each discrete equation is an expression of the conservation of a certain physical quantity on a finite volume. The introduction of the upwind scheme is to overcome the situation where the numerical solution oscillates due to the number of grids being less than 0. The second-order upwind scheme can obtain a more accurate solution and is absolutely stable.

[0110] Furthermore, multi-physics field equations are introduced as boundary conditions for the discretized grid state equations. The multi-physics field equations include at least one of the electrochemical reaction kinetic equations at the three-phase interface on the electrode surface, the proton conduction equation in the proton exchange membrane, and the multi-component diffusion equation in the gas diffusion layer, wherein the electrochemical reaction kinetic equations at the three-phase interface on the electrode surface are in the form described by the Butler-Volmer equation, which is as follows:

[0111]

[0112] in, is the specific volume current density; is the active specific area of ​​the porous catalytic layer; is the exchange current density; is the anode transfer coefficient; is the cathode transfer coefficient; is the activation overpotential, which has the following form:

[0113]

[0114] in, is the electron potential; is the ionic potential; is the equilibrium potential. The Butler-Volmer equation is one of the most fundamental kinetic relationships in electrochemistry. It describes how the current at an electrode varies with the electrode potential, taking into account that cathodic and anodic reactions can occur at the same electrode.

[0115] The proton conduction equation in the proton exchange membrane is established according to the Springer model, and its form is as follows:

[0116]

[0117] in, is the water content in the proton exchange membrane; is the current density; is the Faraday constant; is the diffusion coefficient of water in the proton exchange membrane; is the concentration of sulfonic acid groups; is the hydraulic permeability coefficient in the proton exchange membrane; is the concentration of water in the proton exchange membrane.

[0118] The Maxwell-Stefan equation is used to describe the diffusion of gas in the multi-component diffusion equation in the gas diffusion layer. The Maxwell-Stefan equation is a set of equations used to describe the component transport phenomenon in a multi-component gas or liquid mixture. Its form is as follows:

[0119]

[0120] in, For components The driving force of For components With components The friction coefficient between For components The mole fraction of and The components and components diffusion rate.

[0121] The multi-component diffusion equation in the gas diffusion layer obtained according to the Maxwell-Stefan equation is as follows:

[0122]

[0123] in, is the diffusion flux; is the gas constant; is the viscous flow parameter; is the radius of the gas diffusion layer pore; is the position coordinate along the diffusion direction; is the dynamic viscosity of the mixed gas; matrix and is a function of the binary diffusion coefficient, the Knudsen diffusion coefficient, and the mole fraction. Dynamic viscosity It can be calculated by the following formula:

[0124]

[0125] in, is the molar mass; is the critical state molar volume; is the viscous collision integral; is the correction parameter. The form is as follows:

[0126]

[0127] matrix The form is as follows:

[0128]

[0129] in, is the binary diffusion coefficient, which has the following form:

[0130]

[0131] in, is the sum of the diffusion volumes of each atom in the component; The form is as follows:

[0132]

[0133] The above equations specify the boundary conditions between different layers in the fuel cell. By applying the boundary conditions to the nonlinear system of equations, a multi-physics state model is obtained.

[0134] As an embodiment of the present application, the actual state parameters include the actual temperature field and the actual current density distribution of the fuel cell; according to the actual state parameters, with minimizing the cold start time of the fuel cell as the objective function, searching by an ant colony optimization algorithm to obtain the optimal temperature rise control strategy of the fuel cell includes:

[0135] S310. Calculate the performance parameters of the fuel cell based on the actual temperature field and the actual current density distribution; wherein the cold start time is related to the value of the performance parameter, and the performance parameter includes at least one of activation polarization loss, ohmic polarization loss and concentration polarization loss.

[0136] S320. According to the performance parameters and the safety constraints of the fuel cell, the temperature rise control parameters of the fuel cell are iteratively searched through the ant colony optimization algorithm to obtain the optimal temperature rise control strategy; wherein the temperature rise control parameters include temperature control parameters and current density control parameters.

[0137] Specifically, the activation polarization loss is in the form of:

[0138]

[0139] in, is the transfer coefficient; is the reference molar concentration; is the ice volume fraction; is the exchange current density; is the thickness of the catalytic layer; is the molar concentration of the reactants.

[0140] Ohmic polarization losses are of the following form:

[0141]

[0142] in, is the impedance of electrons passing through the current collecting plate; is the equivalent impedance of electrons passing through the proton exchange membrane, which is in the following form:

[0143]

[0144] in, is the reaction area of ​​the proton exchange membrane; is the thickness of the proton exchange membrane; is the resistivity of the proton exchange membrane, which can be calculated by the following formula:

[0145]

[0146] in, is the membrane electrode temperature.

[0147] The concentration polarization loss is in the form of:

[0148]

[0149] in, is the limiting current density, which is in the following form:

[0150]

[0151] in, is the thickness of the gas diffusion layer; is the effective mass diffusivity of the gas diffusion layer; is the thickness of the catalytic layer; is the effective mass diffusion rate of the catalyst layer; and Make a correction in the following form:

[0152]

[0153] in, is the porosity of the gas diffusion layer; is the porosity of the catalytic layer; For gas components The diffusion rate of, when the components are hydrogen and oxygen, The form is as follows:

[0154]

[0155] in, is the hydrogen pressure; is the oxygen pressure.

[0156] Furthermore, activation polarization loss is the activation energy required to overcome the reaction when electrons pass through the proton exchange membrane. It is particularly effective in limiting the electrochemical reaction rate when the fuel cell is started and working at low load; ohmic polarization loss is the energy loss caused by the internal resistance during charge transfer; concentration polarization loss is caused by reactant transfer and mainly occurs on the electrode surface of the electrochemical reaction. The output voltage of the fuel cell is affected by the performance parameters. The larger the value of the performance parameter, the faster the output voltage decreases, which will cause the fuel cell to fail to start cold. During the cold start process, as the current density gradually increases, the value of the performance parameter increases, exacerbating the decrease in output voltage. Therefore, it is necessary to iteratively search the temperature control parameters of the fuel cell through an optimization algorithm to obtain the optimal temperature control strategy.

[0157] Further, refer to Figure 5 , Figure 5 This is a flowchart optimized by the ant colony optimization algorithm in the embodiment of the present application. As shown in the figure, in the process of optimizing and searching by the ant colony optimization algorithm, the position coordinates of the individual ants in the ant colony represent the temperature control parameters at each time step, including temperature and current density. The ant positions are randomly generated for the ant colony in the initial state, and each ant has different temperature control strategies according to the position, indicating different temperature control strategies; the temperature control strategies are substituted into the multi-physics field model, and the cold start time and safety performance corresponding to the temperature control strategies are evaluated through simulation.

[0158] Furthermore, after each optimization search, a roulette wheel selection operator is used to select the optimal ant individual. The roulette wheel selection operator is also called the proportional selection operator, in which the probability of each individual being selected is proportional to the value of its fitness function. After obtaining the optimal ant individual, the subsequent ant search optimization control strategy is guided by the ant colony pheromone update mechanism. In some embodiments, the optimization search process also determines whether the optimal temperature rise control strategy corresponding to the optimal ant individual meets the safety constraints. The safety constraints include temperature, current density, water content and reaction rate. When the optimal temperature rise control strategy does not meet the safety constraints, a penalty coefficient is set for the cold start time. The value of the penalty coefficient is proportional to the degree of deviation between the optimal temperature rise control strategy and the safety constraints. The penalty coefficient enables the search direction of the optimization algorithm to converge toward the temperature rise control strategy that meets the safety constraints.

[0159] Reference Figure 6 , Figure 6 This is a step diagram of the working of the dynamic safety optimization model in the embodiment of the present application. As shown in the figure, as an embodiment of the present application, the step target control parameter includes a step target temperature; the target parameter optimization model includes a dynamic safety optimization model; the step of numerically optimizing the step target control parameter by the dynamic safety optimization model includes:

[0160] S410. Obtain real-time temperature parameters of the fuel cell.

[0161] S412. If the real-time temperature parameter does not meet the safety parameter threshold of the fuel cell, the step target temperature is lowered by reducing the heating power of the fuel cell.

[0162] Specifically, in the process of controlling the cold start of the fuel cell, the temperature of the fuel cell is gradually increased by a heating device, and due to the influence of the actual heating device and environmental factors, uneven temperature rise will occur in the fuel cell, resulting in damage to the membrane electrode of the fuel cell due to thermal stress. Therefore, in the process of cold start of the fuel cell, it is necessary to measure the temperature of the fuel cell in real time, and numerically optimize the step target control parameters according to the real-time temperature parameters of the fuel cell. In some embodiments, after obtaining the real-time temperature parameters of the fuel cell, the real-time temperature parameters are input into a multi-physics field model related to the fuel cell, and the multi-physics field model is solved by the Newton iteration method, so as to iteratively optimize the real-time temperature parameters and obtain real-time temperature parameters that are more in line with the actual situation.

[0163] Furthermore, if the real-time temperature parameter does not meet the safety parameter threshold of the fuel cell, the adjustment method includes reducing the heating power of the fuel cell and extending the heating time of the fuel cell, thereby reducing the probability of uneven heating of the fuel cell. In some embodiments, the uneven heating of the fuel cell may also be caused by a fault in the fuel cell itself. In this case, it is necessary to diagnose the fault of the fuel cell and input the fault condition into the historical fault optimization model to execute corresponding measures.

[0164] Reference Figure 7 , Figure 7 This is a step diagram of the historical prediction optimization model in the embodiment of the present application. As shown in the figure, as an embodiment of the present application, the step target control parameter also includes a step target current density; the target parameter optimization model also includes a historical prediction optimization model; the step of numerically optimizing the step target control parameter by the historical prediction optimization model includes:

[0165] S420. Predict the control instruction sequence of the fuel cell through the historical prediction optimization model to obtain the predicted target temperature and the predicted target current density; wherein the historical prediction optimization model is obtained by learning the historical control instruction sequence of the fuel cell through a machine learning algorithm.

[0166] S422. Numerically optimize the step target temperature according to the predicted target temperature.

[0167] S424. Numerically optimize the step target current density based on the predicted target current density.

[0168] Specifically, the historical control instruction sequence of the fuel cell is learned through a machine learning algorithm to obtain a historical prediction optimization model, which can be used to predict the temperature field and stress field in the fuel cell. When predicting, it is necessary to input the environmental conditions and the current control instruction sequence into the historical prediction optimization model to obtain the changes in the temperature field and stress field in the fuel cell during the cold start time, and obtain the predicted target temperature and predicted target current density.

[0169] Furthermore, the step target temperature is numerically optimized according to the predicted target temperature, and the step target current density is numerically optimized according to the predicted target current density. The numerical optimization methods include linear optimization, gradient descent, and genetic algorithm, etc. Through numerical optimization, the step target temperature is made to approach the predicted target temperature, and the step target current density is made to approach the predicted target current density.

[0170] Reference Figure 8 , Figure 8This is a step diagram of the degradation prediction optimization model in the embodiment of the present application. As shown in the figure, as an embodiment of the present application, the target parameter optimization model also includes a degradation prediction optimization model; the step of numerically optimizing the step target control parameter by the degradation prediction optimization model includes:

[0171] S430. Predict the performance degradation of the fuel cell according to the performance degradation data of the fuel cell, and obtain the degradation target temperature and degradation target current density of the fuel cell.

[0172] S432. Numerically optimize the step target temperature according to the degraded target temperature.

[0173] S434. Numerically optimize the step target current density according to the degraded target current density.

[0174] Specifically, the degradation target temperature and degradation target current density obtained through performance degradation prediction reflect the degradation of the fuel cell after a period of operation under various environmental conditions and operating conditions. The step target control parameters are numerically optimized through the degradation prediction optimization model, taking the performance degradation of the fuel cell itself into consideration, thereby improving the reliability of cold start control.

[0175] Furthermore, the step target temperature is numerically optimized according to the degradation target temperature, and the step target current density is numerically optimized according to the degradation target current density. The numerical optimization methods include linear optimization, gradient descent, and genetic algorithm, etc. Through numerical optimization, the step target temperature is made to approach the degradation target temperature, and the step target current density is made to approach the degradation target current density.

[0176] Reference Fig. 9 , Fig. 9 This is a step diagram of obtaining performance degradation data by using a degradation prediction optimization model in an embodiment of the present application. As shown in the figure, as an embodiment of the present application, the performance degradation data of a fuel cell is obtained by the following method:

[0177] S440. Perform simulation analysis on the working state of the fuel cell under different environmental conditions and different working conditions to obtain the degradation simulation result of the fuel cell.

[0178] S442. Use machine learning to analyze the degradation mechanism of the degradation simulation results and obtain performance degradation data.

[0179] Specifically, the performance degradation data of the fuel cell can be obtained through simulation. When the performance degradation data is obtained through simulation, the working performance of the fuel cell is simulated with a combination of different environmental conditions and working conditions, and the working performance of the fuel cell after a period of time is compared with the working performance before the simulation. The comparison results are learned through a machine learning algorithm to obtain the performance degradation data.

[0180] In some embodiments, the performance degradation data of the fuel cell can also be obtained through test detection. When the performance degradation data is obtained through test detection, the fuel cell is placed under various environmental conditions and operated under different working conditions, and the working performance of the fuel cell is detected over a period of time, including heating performance, reaction rate, and output performance. The working performance at this time is compared with the working performance of the fuel cell before the test, and the comparison results are learned through a machine learning algorithm to obtain performance degradation data. Exemplarily, the types of machine learning algorithms include, but are not limited to, support vector machines and neural networks.

[0181] Accordingly, please refer to Fig.10 , an embodiment of the present application provides a fuel cell cold start control system, the system comprising:

[0182] The initial acquisition module 201 is used to obtain the initial state parameters of the fuel cell.

[0183] The model calculation module 202 is used to iteratively optimize the initial state parameters of the fuel cell to obtain the actual state parameters of the fuel cell; wherein the degree of conformity between the actual state parameters and the actual state of the fuel cell is higher than the degree of conformity between the initial state parameters and the actual state of the fuel cell.

[0184] The optimization search module 203 is used to search through an ant colony optimization algorithm based on actual state parameters and taking minimizing the cold start time of the fuel cell as the objective function to obtain the optimal temperature rise control strategy of the fuel cell; according to the optimal temperature rise control strategy and the safety parameter threshold of the fuel cell, a step target control parameter is set to obtain a control instruction sequence of the fuel cell.

[0185] The numerical optimization module 204 is used to numerically optimize the step target control parameters through the target parameter optimization model when the fuel cell is cold-started according to the control instruction sequence; and obtain the optimized control instruction sequence of the fuel cell according to the numerically optimized step target control parameters to control the fuel cell to cold-start.

[0186] In some optional embodiments, the initial state parameters include the initial temperature field and the initial current density distribution of the fuel cell; the initial acquisition module 201 includes:

[0187] The state data acquisition unit is used to collect the current temperature and current density at different positions inside the fuel cell.

[0188] The state data fusion unit is used to use the Kalman filter algorithm to perform multi-sensor data fusion on the current temperature to obtain the current overall temperature of the fuel cell, and to perform multi-sensor data fusion on the current current density to obtain the current overall current density of the fuel cell.

[0189] The temperature data interpolation unit is used to interpolate the current overall temperature to obtain the initial temperature field.

[0190] The current density interpolation unit is used to interpolate the current overall current density to obtain the initial current density distribution.

[0191] In some optional implementations, the model calculation module 202 includes:

[0192] The model building unit is used to build a multi-physical field state model for the fuel cell according to the multi-physical quantity state equation of the fuel cell.

[0193] The actual solution unit is used to substitute the initial state parameters as initial conditions into the multi-physics field state model, and solve the multi-physics field state model using the Newton iteration method to obtain the actual state parameters of the fuel cell.

[0194] In some optional embodiments, the model building unit includes:

[0195] The discrete grid generation subunit is used to spatially discretize the fuel cell according to the structural parameters and material properties of the fuel cell and generate an unstructured grid.

[0196] The state equation determination subunit is used to determine the unit state equation corresponding to each discrete unit in the unstructured grid to obtain a discretized grid state equation; wherein the unit state equation includes at least one of an energy conservation equation, a component conservation equation, a momentum conservation equation, and a charge conservation equation.

[0197] The state model establishment subunit is used to set boundary conditions for the grid state equations based on the multi-physics field equations of the fuel cell to obtain a set of nonlinear equations to establish a multi-physics field state model; wherein the multi-physics field equations include at least one of the electrochemical reaction kinetics equations at the three-phase interface of the electrode surface, the proton conduction equations in the proton exchange membrane, and the multi-component diffusion equations in the gas diffusion layer.

[0198] In some optional embodiments, the actual state parameters include the actual temperature field and the actual current density distribution of the fuel cell; the optimization search module 203 includes:

[0199] A performance parameter calculation unit is used to calculate the performance parameters of the fuel cell according to the actual temperature field and the actual current density distribution; wherein the cold start time is related to the value of the performance parameter, and the performance parameter includes at least one of activation polarization loss, ohmic polarization loss and concentration polarization loss.

[0200] The control strategy search unit is used to iteratively search the temperature rise control parameters of the fuel cell through an ant colony optimization algorithm according to the performance parameters and the safety constraints of the fuel cell to obtain the optimal temperature rise control strategy; wherein the temperature rise control parameters include temperature control parameters and current density control parameters.

[0201] In some optional embodiments, the step target control parameter includes a step target temperature; the target parameter optimization model includes a dynamic safety optimization model; and the numerical optimization module 204 includes:

[0202] The real-time model solving unit is used to obtain the real-time temperature parameters of the fuel cell.

[0203] The dynamic safety optimization unit is used to reduce the step target temperature by reducing the heating power of the fuel cell if the real-time temperature parameter does not meet the safety parameter threshold of the fuel cell.

[0204] In some optional implementations, the step target control parameter further includes a step target current density; and the numerical optimization module 204 further includes:

[0205] A control instruction prediction unit is used to predict the control instruction sequence of the fuel cell through a historical prediction optimization model to obtain a predicted target temperature and a predicted target current density; wherein the historical prediction optimization model is obtained by learning the historical control instruction sequence of the fuel cell through a machine learning algorithm.

[0206] The temperature prediction optimization unit is used to numerically optimize the step target temperature according to the predicted target temperature.

[0207] The current prediction optimization unit is used to numerically optimize the step target current density according to the predicted target current density.

[0208] In some optional implementations, the target parameter optimization model further includes a degradation prediction optimization model; and the numerical optimization module 204 further includes:

[0209] The performance degradation prediction unit is used to predict the performance degradation of the fuel cell according to the performance degradation data of the fuel cell, and obtain the degradation target temperature and degradation target current density of the fuel cell.

[0210] The temperature degradation optimization unit is used to numerically optimize the step target temperature according to the degradation target temperature.

[0211] The current degradation optimization unit is used to numerically optimize the step target current density according to the degradation target current density.

[0212] In some optional implementations, the performance degradation prediction unit includes:

[0213] The degradation simulation subunit is used to simulate and analyze the working state of the fuel cell under different environmental conditions and different working conditions, and obtain the degradation simulation results of the fuel cell.

[0214] The degradation analysis subunit is used to use machine learning to analyze the degradation mechanism of the degradation simulation results and obtain performance degradation data.

[0215] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0216] The fuel cell cold start control system in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0217] See also Fig.11 , Fig.11 It is a structural diagram of a computer device provided by an embodiment of the present application. As shown in the figure, the computer device includes: one or more processors 10, a memory 20, and an interface for connecting various components, including a high-speed interface and a low-speed interface. Each component uses different buses to communicate with each other, and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig.11 A processor 10 is taken as an example.

[0218] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0219] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0220] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0221] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0222] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0223] The embodiment of the present application also provides a computer-readable storage medium. The above method according to the embodiment of the present application can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0224] The embodiment of the present application provides a computer program product, which includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method of any embodiment of the present application.

[0225] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0226] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0227] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0228] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate a device for implementing the functions specified in one process or multiple processes in the flowchart and / or one box or multiple boxes in the block diagram.

[0229] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0230] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0231] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0232] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0233] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

[0234] Although the embodiments of the present application have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A fuel cell cold start control method, characterized in that: The method comprises: Acquiring the initial state parameters of the fuel cell, including: collecting the current temperature and current current density at different positions inside the fuel cell; using the Kalman filter algorithm, performing multi-sensor data fusion on the current temperature to obtain the current overall temperature of the fuel cell, and performing multi-sensor data fusion on the current current density to obtain the current overall current density of the fuel cell; interpolating the current overall temperature to obtain an initial temperature field; interpolating the current overall current density to obtain an initial current density distribution; wherein the initial state parameters include the initial temperature field and initial current density distribution of the fuel cell; Iteratively optimizing the initial state parameters of the fuel cell to obtain the actual state parameters of the fuel cell, including: establishing a multi-physical field state model for the fuel cell according to the multi-physical quantity state equation of the fuel cell; substituting the initial state parameters as initial conditions into the multi-physical field state model, and solving the multi-physical field state model using the Newton iteration method to obtain the actual state parameters of the fuel cell; wherein the actual state parameters include the actual temperature field and the actual current density distribution of the fuel cell, and the degree of conformity between the actual state parameters and the actual state of the fuel cell is higher than the degree of conformity between the initial state parameters and the actual state of the fuel cell; According to the actual state parameters, taking minimizing the cold start time of the fuel cell as the objective function, searching is performed through an ant colony optimization algorithm to obtain an optimal temperature rise control strategy for the fuel cell; according to the optimal temperature rise control strategy and the safety parameter threshold of the fuel cell, a step target control parameter is set to obtain a control instruction sequence for the fuel cell; specifically, the optimal temperature rise control strategy includes a continuous curve of the state parameters of the fuel cell changing with time; under the premise of not exceeding the safety parameter threshold of the fuel cell, the corresponding step target control parameters are set according to the optimal temperature rise control strategy to form a control instruction sequence for the fuel cell, the control instruction sequence is a discretized optimal temperature rise control strategy, and the values ​​of the step target control parameters contained in the control instruction sequence are the same as the values ​​of the continuous curve in the optimal temperature rise control strategy; wherein the step target control parameters include a step target temperature and a step target current density; When the fuel cell is cold-started according to the control instruction sequence, the step target control parameters are numerically optimized through a target parameter optimization model; and an optimized control instruction sequence of the fuel cell is obtained according to the numerically optimized step target control parameters to control the fuel cell to cold-start.

2. The method according to claim 1, characterized in that The step of establishing a multi-physical field state model for the fuel cell according to the multi-physical quantity state equation of the fuel cell comprises: According to the structural parameters and material properties of the fuel cell, the fuel cell is spatially discretized to generate an unstructured grid; Determine the unit state equation corresponding to each discrete unit in the unstructured grid to obtain a discretized grid state equation; wherein the unit state equation includes at least one of an energy conservation equation, a component conservation equation, a momentum conservation equation, and a charge conservation equation; Boundary conditions are set for the grid state equation based on the multi-physics field equation of the fuel cell to obtain a group of nonlinear equations to establish the multi-physics field state model; wherein the multi-physics field equation includes at least one of the electrochemical reaction kinetics equation of the three-phase interface on the electrode surface, the proton conduction equation in the proton exchange membrane, and the multi-component diffusion equation in the gas diffusion layer.

3. The method according to claim 1, characterized in that: The method of searching by an ant colony optimization algorithm based on the actual state parameters and taking minimizing the cold start time of the fuel cell as the objective function to obtain the optimal temperature rise control strategy of the fuel cell comprises: Calculating the performance parameters of the fuel cell according to the actual temperature field and the actual current density distribution; wherein the cold start time is related to the value of the performance parameter, and the performance parameter includes at least one of activation polarization loss, ohmic polarization loss and concentration polarization loss; According to the performance parameters and the safety constraints of the fuel cell, the temperature rise control parameters of the fuel cell are iteratively searched through an ant colony optimization algorithm to obtain the optimal temperature rise control strategy; wherein the temperature rise control parameters include temperature control parameters and current density control parameters.

4. The method according to claim 1, characterized in that: The target parameter optimization model includes a dynamic safety optimization model; The step of numerically optimizing the step-type target control parameters by using the dynamic safety optimization model comprises: Acquiring real-time temperature parameters of the fuel cell; If the real-time temperature parameter does not meet the safety parameter threshold of the fuel cell, the step target temperature is reduced by reducing the heating power of the fuel cell.

5. The method according to claim 4, characterized in that The target parameter optimization model also includes a historical prediction optimization model; the step of numerically optimizing the step-type target control parameter by using the historical prediction optimization model includes: The control instruction sequence of the fuel cell is predicted by a historical prediction optimization model to obtain a predicted target temperature and a predicted target current density; wherein the historical prediction optimization model is obtained by learning the historical control instruction sequence of the fuel cell by a machine learning algorithm; numerically optimizing the step target temperature according to the predicted target temperature; The step target current density is numerically optimized according to the predicted target current density.

6. The method according to claim 5, characterized in that The target parameter optimization model also includes a degradation prediction optimization model; the step of numerically optimizing the step-type target control parameter by using the degradation prediction optimization model includes: According to the performance degradation data of the fuel cell, predicting the performance degradation of the fuel cell, and obtaining a degradation target temperature and a degradation target current density of the fuel cell; numerically optimizing the step target temperature according to the degradation target temperature; The step target current density is numerically optimized according to the degraded target current density.

7. The method according to claim 6, characterized in that The performance degradation data of the fuel cell is obtained by: Performing simulation analysis on the working state of the fuel cell under different environmental conditions and different working conditions to obtain a degradation simulation result of the fuel cell; Machine learning is used to perform degradation mechanism analysis on the degradation simulation results to obtain the performance degradation data.

8. A fuel cell cold start control system, characterized in that: The system comprises: An initial acquisition module, used to obtain the initial state parameters of the fuel cell; wherein the initial state parameters include the initial temperature field and initial current density distribution of the fuel cell; the initial acquisition module includes: a state data acquisition unit, used to acquire the current temperature and current current density at different positions inside the fuel cell; a state data fusion unit, used to perform multi-sensor data fusion on the current temperature using a Kalman filter algorithm to obtain the current overall temperature of the fuel cell, and to perform multi-sensor data fusion on the current current density to obtain the current overall current density of the fuel cell; a temperature data interpolation unit, used to interpolate the current overall temperature to obtain the initial temperature field; a current density interpolation unit, used to interpolate the current overall current density to obtain the initial current density distribution; A model calculation module, used for iteratively optimizing the initial state parameters of the fuel cell to obtain the actual state parameters of the fuel cell; wherein the actual state parameters include the actual temperature field and the actual current density distribution of the fuel cell, and the degree of conformity between the actual state parameters and the actual state of the fuel cell is higher than the degree of conformity between the initial state parameters and the actual state of the fuel cell; the model calculation module includes: a model establishment unit, used for establishing a multi-physical field state model for the fuel cell according to the multi-physical quantity state equation of the fuel cell; an actual solution unit, used for substituting the initial state parameters as initial conditions into the multi-physical field state model, and solving the multi-physical field state model using the Newton iteration method to obtain the actual state parameters of the fuel cell; An optimization search module is used to search through an ant colony optimization algorithm based on the actual state parameters and taking minimizing the cold start time of the fuel cell as the objective function to obtain an optimal temperature rise control strategy for the fuel cell; according to the optimal temperature rise control strategy and the safety parameter threshold of the fuel cell, a step target control parameter is set to obtain a control instruction sequence for the fuel cell; specifically, the optimal temperature rise control strategy includes a continuous curve of the state parameters of the fuel cell changing with time; under the premise of not exceeding the safety parameter threshold of the fuel cell, the corresponding step target control parameters are set according to the optimal temperature rise control strategy to form a control instruction sequence for the fuel cell, the control instruction sequence is a discretized optimal temperature rise control strategy, and the values ​​of the step target control parameters contained in the control instruction sequence are the same as the values ​​of the continuous curve in the optimal temperature rise control strategy; wherein the step target control parameters include a step target temperature and a step target current density; A numerical optimization module is used to numerically optimize the step target control parameters through a target parameter optimization model when the fuel cell is cold-started according to the control instruction sequence; and obtain an optimized control instruction sequence of the fuel cell according to the numerically optimized step target control parameters to control the fuel cell to cold-start.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the fuel cell cold start control method according to any one of claims 1 to 7 by executing the computer instructions.

10. An emergency power supply vehicle, characterized in that: The emergency power supply vehicle is provided with a pure electric chassis, a hydrogen carrying system, a hydrogen fuel cell system, a lithium battery pack, a power inverter system, an air conditioning system, a cooling system, an air intake and exhaust system and a centralized control cabinet in the compartment of the emergency power supply vehicle. The hydrogen fuel cell system is cold started by executing the fuel cell cold start control method described in any one of claims 1 to 7.

Images