Fuel cell cold start optimization method, device, computer equipment and program product

Abstract

This application relates to a fuel cell cold start optimization method, apparatus, computer equipment, computer-readable storage medium, and computer program product. The method includes: constructing a dynamic model of the fuel cell; determining a set of safety constraints during the fuel cell cold start process based on the dynamic model; constructing an objective function for the fuel cell with the goals of shortening the heating time, suppressing temperature differences between different regions, stabilizing fuel utilization, reducing oxidation risk, and minimizing actuator energy consumption; performing rolling prediction and optimization solutions based on the dynamic model, the set of safety constraints, and the objective function to determine the optimal control sequence for airflow, fuel flow, and heating power; executing the optimal control sequence until the fuel cell reaches steady-state operating conditions, and switching the fuel cell control mode to a steady-state power generation model. This method improves the reliability of fuel cell start-up.

Description

Technical Field

[0001] This application relates to the field of high-temperature fuel cell control technology, and in particular to a fuel cell cold start optimization method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] Solid oxide fuel cells (SOFCs) typically operate at high temperatures of 650-850°C. Internal electrochemical reactions, gas diffusion, and heat conduction are highly coupled. When starting up in a cold state (ambient temperature 20-40°C), the system needs to transition from a low temperature to a high temperature stable range. This process involves multiple physical processes such as material thermal expansion, gas concentration changes, and heat transfer rate limitations, making cold start a key bottleneck in SOFC applications.

[0003] In related technologies, cold starts are achieved through methods such as fixed heating curves, PID multi-segment control, phase switching strategies, and adding heaters for forced heating. However, existing solutions share common drawbacks: they cannot dynamically coordinate multiple variables such as heating rate, temperature gradient, and gas supply; they cannot ensure that all physical quantities remain within safety constraints during the startup process; the algorithms lack predictive capabilities and cannot adjust in advance if anomalies occur; and they are difficult to adapt to fuel cell stack aging, resulting in high maintenance costs and ultimately poor cold start performance. Summary of the Invention

[0004] Therefore, it is necessary to provide a fuel cell cold start optimization method, device, computer equipment, computer-readable storage medium, and computer program product that can achieve optimal control of fuel cell cold start throughout the entire process from ambient temperature to operating temperature, in order to address the above-mentioned technical problems.

[0005] In a first aspect, this application provides a method for optimizing cold start of a fuel cell, including:

[0006] Construct a dynamic model of the fuel cell;

[0007] Based on the dynamic model, the set of safety constraints during the cold start process of the fuel cell is determined;

[0008] The objective function of the fuel cell is constructed with the goals of shortening the heating time, suppressing the temperature difference between different regions, stabilizing fuel utilization, reducing oxidation risk, and minimizing actuator energy consumption.

[0009] Based on the dynamic model, the safety constraint set, and the objective function, rolling prediction and optimization are performed to determine the optimal control sequence for air flow, fuel flow, and heating power.

[0010] The optimal control sequence is executed until the fuel cell reaches steady-state operating conditions, at which point the control mode of the fuel cell is switched to a steady-state power generation model.

[0011] In one embodiment, the dynamic model includes a thermodynamic model, an electrochemical model, a gas dynamics model, and an actuator dynamic model.

[0012] In one embodiment, the process of constructing the thermodynamic model includes:

[0013] Based on the temperature field of the fuel cell stack, the fuel cell stack is divided into multiple regions, and the heat balance equation of each region is determined based on the heat absorption, heat dissipation and heat conduction characteristics of the region.

[0014] Based on the aforementioned heat balance equation, a thermodynamic model of the fuel cell is established.

[0015] In one embodiment, the set of safety constraints includes the upper and lower limits of the fuel cell stack temperature, the temperature difference limit between different regions, the fuel utilization rate range, the upper limit of the anode oxygen partial pressure, and the actuator action limit.

[0016] In one embodiment, executing the optimal control sequence until the fuel cell reaches steady-state operating conditions and switching the fuel cell control mode to a steady-state power generation model includes:

[0017] The optimal control sequence is executed to determine the predicted temperature field, predicted gas composition, predicted fuel utilization rate, and predicted anode oxygen partial pressure of the fuel cell.

[0018] Based on the predicted temperature field, predicted gas composition, predicted fuel utilization rate, and predicted anode oxygen partial pressure, the weight parameters in the dynamic model, the safety constraint set, and the objective function are adjusted until the fuel cell temperature reaches the target operating temperature, the temperature difference between regions stabilizes within the safety threshold, the fuel utilization rate stabilizes within the preset utilization rate range, and the output voltage stabilizes within the preset voltage range. Then, the control mode of the fuel cell is switched to a steady-state power generation model.

[0019] In one embodiment, the method further includes:

[0020] The cold start process of the fuel cell is divided into different stages; the different stages include the low temperature preheating stage, the fuel introduction stage, the intermediate temperature crossing stage, the high temperature stabilization approach stage, and the steady-state transition stage.

[0021] Different preset weight parameters are assigned to the dynamic model, the set of security constraints, and the objective function in each stage.

[0022] Secondly, this application also provides a fuel cell cold start optimization device, comprising:

[0023] Building blocks are used to construct dynamic models of fuel cells;

[0024] The determination module is used to determine the set of safety constraints during the cold start process of the fuel cell based on the dynamic model.

[0025] The construction module is also used to construct the objective function of the fuel cell with the goals of shortening the heating time, suppressing the temperature difference between different regions, stabilizing the fuel utilization rate, reducing the oxidation risk and minimizing the actuator energy consumption.

[0026] The solution module is used to perform rolling prediction and optimization based on the dynamic model, the safety constraint set, and the objective function to determine the optimal control sequence of air flow, fuel flow, and heating power;

[0027] The switching module is used to execute the optimal control sequence until the fuel cell reaches steady-state operating conditions, and then switch the control mode of the fuel cell to a steady-state power generation model.

[0028] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0029] Construct a dynamic model of the fuel cell;

[0030] Based on the dynamic model, the set of safety constraints during the cold start process of the fuel cell is determined;

[0031] The objective function of the fuel cell is constructed with the goals of shortening the heating time, suppressing the temperature difference between different regions, stabilizing fuel utilization, reducing oxidation risk, and minimizing actuator energy consumption.

[0032] Based on the dynamic model, the safety constraint set, and the objective function, rolling prediction and optimization are performed to determine the optimal control sequence for air flow, fuel flow, and heating power.

[0033] The optimal control sequence is executed until the fuel cell reaches steady-state operating conditions, at which point the control mode of the fuel cell is switched to a steady-state power generation model.

[0034] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0035] Construct a dynamic model of the fuel cell;

[0036] Based on the dynamic model, the set of safety constraints during the cold start process of the fuel cell is determined;

[0037] The objective function of the fuel cell is constructed with the goals of shortening the heating time, suppressing the temperature difference between different regions, stabilizing fuel utilization, reducing oxidation risk, and minimizing actuator energy consumption.

[0038] Based on the dynamic model, the safety constraint set, and the objective function, rolling prediction and optimization are performed to determine the optimal control sequence for air flow, fuel flow, and heating power.

[0039] The optimal control sequence is executed until the fuel cell reaches steady-state operating conditions, at which point the control mode of the fuel cell is switched to a steady-state power generation model.

[0040] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0041] Construct a dynamic model of the fuel cell;

[0042] Based on the dynamic model, the set of safety constraints during the cold start process of the fuel cell is determined;

[0043] The objective function of the fuel cell is constructed with the goals of shortening the heating time, suppressing the temperature difference between different regions, stabilizing fuel utilization, reducing oxidation risk, and minimizing actuator energy consumption.

[0044] Based on the dynamic model, the safety constraint set, and the objective function, rolling prediction and optimization are performed to determine the optimal control sequence for air flow, fuel flow, and heating power.

[0045] The optimal control sequence is executed until the fuel cell reaches steady-state operating conditions, at which point the control mode of the fuel cell is switched to a steady-state power generation model.

[0046] The aforementioned fuel cell cold start optimization method, apparatus, computer equipment, computer-readable storage medium, and computer program product first construct a dynamic model of the fuel cell; based on the dynamic model, determine the set of safety constraints during the fuel cell cold start process; construct an objective function for the fuel cell with the goals of shortening the heating time, suppressing temperature differences between different regions, stabilizing fuel utilization, reducing oxidation risk, and minimizing actuator energy consumption; based on the dynamic model, the set of safety constraints, and the objective function, perform rolling prediction and optimization to determine the optimal control sequence for air flow, fuel flow, and heating power; execute the optimal control sequence until the fuel cell reaches steady-state operating conditions, and then switch the fuel cell control mode to a steady-state power generation model. Thus, by constructing a dynamic model, the coordinated optimization of key variables such as air flow, fuel flow, heating rate, stack temperature gradient, and anode / cathode gas distribution during the cold start process is achieved. Utilizing rolling prediction and constraint processing capabilities, the optimal heating path is dynamically calculated, avoiding start-up risks such as local hot spots, sudden increases in thermal stress, and excessively low or high fuel utilization, thereby significantly reducing start-up time and improving fuel cell stack life and start-up reliability. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is an application environment diagram of the fuel cell cold start optimization method in one embodiment;

[0049] Figure 2 This is a flowchart illustrating a fuel cell cold start optimization method in one embodiment;

[0050] Figure 3 This is a structural block diagram of a fuel cell cold start optimization device in one embodiment;

[0051] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0053] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0054] The fuel cell cold start optimization method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located in the cloud or on other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart vehicle devices, projection devices, etc. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0055] In one embodiment, the fuel cell cold start optimization method provided in this application can be applied to a cold start optimization system. The terminal 102 in the cold start optimization system includes a hardware layer, a physical process layer, a state perception layer, and an optimization control layer. The layers are efficiently coupled through data interfaces and control signals.

[0056] The cold start optimization system also includes the fuel cell stack, air supply system (blower, compressor, heat exchanger, etc.), fuel supply system (valve, controller, premix module), multi-sensor system, etc.

[0057] The fuel cell stack consists of multiple individual cells, including an anode, a cathode, and an electrolyte layer. The air supply system includes an air compressor, a blower, an air preheating module, and gas pipelines. The air supply system is mainly used for heat management in the early stages of cold start, and in the middle and later stages, it works with the fuel supply to adjust the mixed gas ratio. The fuel supply system includes gas valves, flow meters, and fuel premixing devices. The multi-sensor system includes temperature sensors, pressure sensors, gas composition sensors, flow sensors, voltage and current acquisition modules, etc.

[0058] In one exemplary embodiment, such as Figure 2 As shown, a cold start optimization method for fuel cells is provided, which can be applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps 202 to 210. Wherein:

[0059] Step 202: Construct a dynamic model of the fuel cell.

[0060] The fuel cell is a solid oxide fuel cell (SOFC), but other fuel cells can also be used, depending on the requirements. This application does not limit this. The dynamic model includes a thermodynamic model, an electrochemical model, a gas dynamics model, and an actuator dynamic model.

[0061] For example, a thermodynamic model is constructed to describe temperature changes and heat transfer behavior inside the fuel cell stack, an electrochemical model is constructed to predict voltage generation, polarization loss and reaction rate, a gas dynamic model is constructed to characterize the transport, mixing and consumption processes of fuel and air, and an actuator dynamic model is constructed to describe the dynamic response of air valves, fuel valves and compressor.

[0062] The dynamic model can be discretized into a state-space form suitable for MPC (Model Predictive Control).

[0063] Step 204: Based on the dynamic model, determine the set of safety constraints during the cold start process of the fuel cell.

[0064] The safety constraint set includes the upper and lower limits of fuel cell stack temperature, temperature difference limits between different regions, fuel utilization rate range, upper limit of anode oxygen partial pressure, and actuator operation limits.

[0065] Optionally, based on the constraints of the dynamic model, the upper and lower limits of the fuel cell stack temperature are determined to prevent material overheating; the temperature difference limit between different regions of the fuel cell is determined to limit thermal stress; the fuel utilization rate range is determined to maintain a suitable reaction environment; the upper limit of the anode oxygen partial pressure is determined to avoid anode re-oxidation; and the actuator action limit is determined to ensure the stability of flow regulation.

[0066] Step 206: Construct the objective function of the fuel cell with the goals of shortening the heating time, suppressing the temperature difference between different regions, stabilizing fuel utilization, reducing oxidation risk, and minimizing actuator energy consumption.

[0067] For example, the objective function of a fuel cell is constructed with the goals of shortening the heating time, suppressing the temperature difference between different regions, stabilizing fuel utilization, reducing oxidation risk, and minimizing actuator energy consumption.

[0068] Step 208: Based on the dynamic model, safety constraint set, and objective function, perform rolling prediction and optimization to determine the optimal control sequence for air flow, fuel flow, and heating power.

[0069] Optionally, based on the dynamic model, safety constraint set, and objective function, a preset prediction model is used to predict the temperature distribution, fuel utilization rate, gas concentration, voltage change, and safety index change trends of the fuel cell stack within a preset time period, and to perform optimization solutions to determine the optimal control sequence of air flow, fuel flow, and heating power.

[0070] The preset prediction model can be the MPC prediction model or other prediction models, and this application embodiment does not limit it; the solver for optimization can be SQP, IPOPT, OSQP or other optimization algorithms suitable for fast solution, and this application embodiment does not limit it.

[0071] In one embodiment, the system behavior is relatively stable in the low and medium temperature stages, and a linear quadratic programming solver can be used; when entering the high temperature stage and the nonlinear effects are significant, a nonlinear solver is used for optimization.

[0072] Step 210: Execute the optimal control sequence until the fuel cell reaches steady-state operating conditions, and then switch the control mode of the fuel cell to the steady-state power generation model.

[0073] For example, an optimal control sequence is executed to determine the predicted temperature field, predicted gas composition, predicted fuel utilization rate, and predicted anode oxygen partial pressure of the fuel cell. Based on the predicted temperature field, predicted gas composition, predicted fuel utilization rate, and predicted anode oxygen partial pressure, the weight parameters in the dynamic model, safety constraint set, and objective function are adjusted until the temperature of the fuel cell reaches the target operating temperature, the temperature difference between regions stabilizes within the safety threshold, the fuel utilization rate stabilizes within the preset utilization rate range, and the output voltage stabilizes within the preset voltage range. Then, the control mode of the fuel cell is switched to a steady-state power generation model.

[0074] The aforementioned fuel cell cold start optimization method involves constructing a dynamic model of the fuel cell; determining a set of safety constraints during the cold start process based on the dynamic model; constructing an objective function for the fuel cell with the goals of shortening the heating time, suppressing temperature differences between different regions, stabilizing fuel utilization, reducing oxidation risk, and minimizing actuator energy consumption; and performing rolling prediction and optimization based on the dynamic model, safety constraint set, and objective function to determine the optimal control sequence for airflow, fuel flow, and heating power. The optimal control sequence is executed until the fuel cell reaches steady-state operating conditions, at which point the fuel cell control mode is switched to a steady-state power generation model. Thus, by constructing a dynamic model, the coordinated optimization of key variables such as airflow, fuel flow, heating rate, stack temperature gradient, and anode / cathode gas distribution during cold start is achieved. Utilizing rolling prediction and constraint processing capabilities, the optimal heating path is dynamically calculated, avoiding start-up risks such as local hot spots, sudden increases in thermal stress, and excessively low or high fuel utilization, thereby significantly reducing start-up time and improving fuel cell stack life and start-up reliability.

[0075] In one exemplary embodiment, the dynamic model includes a thermodynamic model, an electrochemical model, a gas dynamics model, and an actuator dynamic model.

[0076] In practical implementation, the thermodynamic model of the fuel cell is determined based on the heat generated by the internal reaction of the fuel cell, the heat input from the external heater, and the heat lost through the outer wall.

[0077] Based on the Nernst equation and polarization loss, the steady-state voltage V of the fuel cell is determined, and the specific formula is shown in formula (1):

[0078]

[0079] Where E0 is the Nernst voltage, η act To activate the polarization overpotential, η ohmic For ohmic polarization overpotential, η conc This is the concentration polarization overpotential.

[0080] The dynamic part of electrochemistry in a fuel cell includes the electric double-layer effect, as shown in formula (2):

[0081]

[0082] Among them, C dl The double-layer capacitance represents the equivalent capacitance of the double layer formed at the electrode / electrolyte interface, in V. thermo It is a thermodynamically reversible voltage.

[0083] A gas dynamics model is established by describing the dynamic balance between the supply, discharge, and chemical reaction consumption of gas on the anode and cathode sides. Fuel utilization rate is a key indicator in the gas dynamics model, and the dynamic change formula of fuel utilization rate FU is shown in formulas (3) and (4):

[0084]

[0085]

[0086] in, This refers to the hydrogen inlet mass flow rate of the fuel cell. This represents the mass flow rate of hydrogen in the exhaust gas of the fuel cell. The hydrogen in the formula can also be other gases, such as oxygen, CO / H2 synthesis gas, etc.

[0087] The gas mass balance is represented by a first-order dynamic model, and the specific formula is shown in formula (5):

[0088]

[0089] Where xi represents the mole fraction of component i; Fin and Fout represent the inlet and outlet gas volume flow rates; xin and xout represent the mole fractions of the inlet and outlet gas components, respectively; and Ri(T,P) represents the generation or consumption of substances due to electrochemical reactions.

[0090] Actuators such as air valves, gas valves, and compressors all exhibit response lag and dynamic limitations. The behavior of the actuator is described by the dynamic difference between the target command and the actual executed quantity. Air valves, fuel valves, and compressors all have first-order inertia, as shown in formula (6).

[0091]

[0092] Where u represents the current actual output of the actuator (such as valve opening, compressor speed, etc.); ucmd represents the target control command calculated by MPC, which is the target output that the actuator should achieve; τ is the time constant of the actuator, representing the speed at which the actuator adjusts from the current state to the target state.

[0093] In the above embodiments, by constructing a dynamic model, the coupling behavior of heat, electricity, and gas during the cold start process of a fuel cell can be accurately described.

[0094] In an exemplary embodiment, the process of constructing the thermodynamic model includes: dividing the fuel cell stack into multiple regions based on the temperature field of the fuel cell stack, and determining the heat balance equation for each region based on the heat absorption, heat dissipation and heat conduction characteristics of the regions; and establishing a thermodynamic model of the fuel cell based on the heat balance equation.

[0095] In practical implementation, the temperature field is divided into multiple regions, and each region forms an independent heat balance equation based on its heat absorption, heat dissipation and heat conduction characteristics. The temperature difference change trend and the heating rate change are taken as additional state variables. The specific formula of the heat balance model of the stack temperature is shown in formula (7):

[0096]

[0097] Among them, C th For equivalent heat capacity, Q gen Q is the heat generated by the electrochemical reaction. loss Q represents the heat dissipation from the environment. trans Internal heat transfer includes interlayer heat transfer and gas convection.

[0098] Among them, the heat Q generated by the electrochemical reaction gen The calculation formula is shown in formula (8):

[0099]

[0100] Where I is the operating current of the fuel cell, η act To activate the polarization overpotential, η ohmic For ohmic polarization overpotential, η conc This is the concentration polarization overpotential.

[0101] In the above embodiments, by dividing the fuel cell stack into multiple temperature zones and establishing a dynamic energy balance, the model can predict the two-dimensional or three-dimensional non-uniform temperature distribution and its dynamic evolution within the fuel cell stack. This breaks through the limitation of traditional methods that only focus on the overall average temperature, enabling the controller (MPC) to accurately grasp the risk of local hot spots and the trend of regional temperature differences, laying a predictive foundation for suppressing thermal stress.

[0102] In one exemplary embodiment, the set of safety constraints includes upper and lower limits for the fuel cell stack temperature, temperature difference limits between different regions, fuel utilization range, upper limit for anode oxygen partial pressure, and actuator action limits.

[0103] In practical implementation, each region of the fuel cell needs to be kept within the allowable range of the materials, not exceeding the maximum tolerable temperature of the stack structure, nor falling too low, thus determining the upper and lower limits of the stack temperature; the temperature difference limit between different regions of the fuel cell is determined based on the fact that the temperature difference between different regions inside the stack cannot exceed the set maximum allowable value; to avoid the risk of fuel cell anode oxidation, instantaneous fuel shortage, reaction instability, or temperature fluctuations, the fuel utilization rate range of the fuel cell is determined; the upper limit of the anode oxygen partial pressure of the fuel cell is determined based on the fact that the oxygen concentration in the anode region cannot exceed the upper limit acceptable to the materials; and the actuator action limit of the fuel cell is determined based on the physical limitations of the actuator's action speed and action amplitude.

[0104] In the above embodiments, by limiting the temperature difference between different regions, structural damage caused by inconsistent local expansion is avoided; furthermore, multiple safety constraints ensure the safety of the operating environment and reduce the risk of accidents caused by human misjudgment or improper operation.

[0105] In an exemplary embodiment, an optimal control sequence is executed until the fuel cell reaches steady-state operating conditions, and the control mode of the fuel cell is switched to a steady-state power generation model. This includes: executing the optimal control sequence to determine the predicted temperature field, predicted gas composition, predicted fuel utilization rate, and predicted anode oxygen partial pressure of the fuel cell; and adjusting the weight parameters in the dynamic model, safety constraint set, and objective function based on the predicted temperature field, predicted gas composition, predicted fuel utilization rate, and predicted anode oxygen partial pressure until the fuel cell temperature reaches the target operating temperature, the inter-regional temperature difference stabilizes within a safety threshold, the fuel utilization rate stabilizes within a preset utilization rate range, and the output voltage stabilizes within a preset voltage range, and the control mode of the fuel cell is switched to a steady-state power generation model.

[0106] In practical implementation, the optimal control sequence is executed, and real-time state estimation is performed through a state observer. The state observer uses measured information such as temperature, pressure, voltage, and current, combined with a preset prediction model, to determine the predicted temperature field, predicted gas composition, predicted fuel utilization rate, and predicted anode oxygen partial pressure of the fuel cell. Based on the predicted temperature field, predicted gas composition, predicted fuel utilization rate, and predicted anode oxygen partial pressure, the weight parameters in the dynamic model, safety constraint set, and objective function are adjusted, and the system is continuously run until the fuel cell temperature reaches the target operating temperature, the temperature difference between regions stabilizes within the safety threshold (the temperature difference between each region is within the safe range and changes slowly), the fuel utilization rate stabilizes within the preset utilization rate range, and the output voltage stabilizes within the preset voltage range (the output voltage remains stable for a period of time). At this point, the control mode of the fuel cell is switched to a steady-state power generation model.

[0107] In one embodiment, the temperature field, gas composition, fuel utilization rate and oxygen partial pressure are estimated by methods such as extended Kalman filtering or moving window estimation, and the parameters of the preset prediction model are corrected according to the changes in the system state, such as the heat transfer coefficient changing with temperature and the gas diffusion rate changing, so that the preset prediction model always remains consistent with the actual system.

[0108] In the above embodiments, multiple conditions are used to ensure that the fuel cell stack enters normal operation when all safety conditions are met, thus guaranteeing safety during operation.

[0109] In an exemplary embodiment, the fuel cell cold start optimization method further includes: dividing the fuel cell cold start process into different stages; the different stages include a low temperature preheating stage, a fuel introduction stage, a medium temperature transition stage, a high temperature stable approach stage, and a steady-state transition stage; and assigning different preset weight parameters to the dynamic model, safety constraint set, and objective function in each stage.

[0110] In practical implementation, based on the specific physical characteristics, control difficulties and corresponding safety boundaries of different stages in the cold start process of fuel cells, the cold start process is divided into low temperature preheating stage, fuel introduction stage, medium temperature transition stage, high temperature stability approach stage and steady state transition stage, and different preset weight parameters are assigned to the dynamic model, safety constraint set and objective function in each stage.

[0111] For example, in the low-temperature preheating stage, the fuel cell temperature is raised from the ambient temperature to 200-300°C by using a small flow of air and external heating; in the fuel introduction stage, fuel is gradually introduced and the initial electrochemical reaction is formed while keeping the partial pressure of oxygen at the fuel cell anode below the critical value; in the intermediate temperature transition stage, peak thermal stress is avoided; in the high-temperature stable approach stage, the fuel cell is smoothly approached to the operating temperature (650-750°C) and the fuel utilization rate (FU) is stabilized; in the steady-state transition stage, the fuel utilization rate (FU), stack temperature, and output voltage are ensured to be stable.

[0112] In the above embodiments, cold start involves a complex sequence of multiple critical operations, such as fuel introduction timing, heating power adjustment, and load connection point. This sequence is encoded into a phase switching logic that is automatically triggered based on state (such as temperature and voltage), replacing the crude operation that relies on human experience or fixed timing. This ensures that critical safety logic is executed automatically without omission or error, greatly improving the standardization and robustness of the start-up process.

[0113] To illustrate the fuel cell cold start optimization method in this application in detail, an embodiment is described below. For example, this application describes a fuel cell cold start optimization method in a specific scenario.

[0114] First, a thermodynamic model is constructed to describe temperature changes and heat transfer behavior inside the fuel cell stack; an electrochemical model is constructed to predict voltage generation, polarization loss and reaction rate; a gas dynamic model is constructed to characterize the transport, mixing and consumption processes of fuel and air; and an actuator dynamic model is constructed to describe the dynamic response of air valves, fuel valves and compressor.

[0115] Based on the constraints of the dynamic model, the upper and lower limits of the fuel cell stack temperature are determined to prevent material overheating; the temperature difference limit between different regions of the fuel cell is determined to limit thermal stress; the fuel utilization rate range is determined to maintain a suitable reaction environment; the upper limit of the anode oxygen partial pressure is determined to avoid anode re-oxidation; and the actuator action limit is determined to ensure the stability of flow regulation.

[0116] The objective function of the fuel cell is constructed with the goals of shortening the heating time, suppressing the temperature difference between different regions, stabilizing fuel utilization, reducing oxidation risk, and minimizing actuator energy consumption.

[0117] Based on a dynamic model, a set of safety constraints, and an objective function, the system predicts the temperature distribution, fuel utilization, gas concentration, voltage changes, and safety index trends of the fuel cell stack within a predetermined time period using a pre-defined prediction model. It then performs optimization to determine the optimal control sequence for air flow, fuel flow, and heating power.

[0118] The optimal control sequence is executed to determine the predicted temperature field, predicted gas composition, predicted fuel utilization rate, and predicted anode oxygen partial pressure of the fuel cell. Based on the predicted temperature field, predicted gas composition, predicted fuel utilization rate, and predicted anode oxygen partial pressure, the weight parameters in the dynamic model, safety constraint set, and objective function are adjusted until the fuel cell temperature reaches the target operating temperature, the temperature difference between regions stabilizes within the safety threshold, the fuel utilization rate stabilizes within the preset utilization rate range, and the output voltage stabilizes within the preset voltage range. Then, the control mode of the fuel cell is switched to a steady-state power generation model.

[0119] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0120] Based on the same inventive concept, this application also provides a fuel cell cold start optimization device for implementing the aforementioned fuel cell cold start optimization method. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the fuel cell cold start optimization device provided below can be found in the limitations of the fuel cell cold start optimization method described above, and will not be repeated here.

[0121] In one exemplary embodiment, such as Figure 3 As shown, a fuel cell cold start optimization device is provided, comprising: a construction module 301, a determination module 302, a solution module 303, and a switching module 304, wherein:

[0122] The building block is used to build dynamic models of fuel cells.

[0123] The determination module is used to determine the set of safety constraints during the cold start process of the fuel cell based on the dynamic model.

[0124] The construction module is also used to construct the objective function of the fuel cell with the goals of shortening the heating time, suppressing the temperature difference between different regions, stabilizing fuel utilization, reducing oxidation risk, and minimizing actuator energy consumption.

[0125] The solution module is used to perform rolling prediction and optimization based on the dynamic model, the safety constraint set, and the objective function to determine the optimal control sequence of air flow, fuel flow, and heating power.

[0126] The switching module is used to execute the optimal control sequence until the fuel cell reaches steady-state operating conditions, and then switch the control mode of the fuel cell to a steady-state power generation model.

[0127] In one exemplary embodiment, the dynamic model includes a thermodynamic model, an electrochemical model, a gas dynamics model, and an actuator dynamic model.

[0128] In one exemplary embodiment, the above-described building module is further configured to:

[0129] Based on the temperature field of the fuel cell stack, the fuel cell stack is divided into multiple regions, and the heat balance equation of each region is determined based on the heat absorption, heat dissipation and heat conduction characteristics of each region.

[0130] A thermodynamic model of a fuel cell is established based on the heat balance equation.

[0131] In one exemplary embodiment, the set of safety constraints includes upper and lower limits for fuel cell stack temperature, temperature difference limits between different regions, fuel utilization range, upper limit for anode oxygen partial pressure, and actuator action limits.

[0132] In one exemplary embodiment, the switching module is further configured to:

[0133] Execute the optimal control sequence to determine the predicted temperature field, predicted gas composition, predicted fuel utilization rate, and predicted anode oxygen partial pressure of the fuel cell;

[0134] Based on the predicted temperature field, gas composition, fuel utilization rate, and anolyte oxygen partial pressure, the weight parameters in the dynamic model, safety constraint set, and objective function are adjusted until the fuel cell temperature reaches the target operating temperature, the temperature difference between regions stabilizes within the safety threshold, the fuel utilization rate stabilizes within the preset utilization rate range, and the output voltage stabilizes within the preset voltage range. Then, the control mode of the fuel cell is switched to a steady-state power generation model.

[0135] In one exemplary embodiment, the above-described apparatus further includes a dispensing module for:

[0136] The cold start process of a fuel cell is divided into different stages; these stages include the low temperature preheating stage, the fuel introduction stage, the intermediate temperature transition stage, the high temperature stability approach stage, and the steady-state transition stage.

[0137] Different preset weight parameters are assigned to the dynamic model, safety constraint set, and objective function in each stage.

[0138] Each module in the aforementioned fuel cell cold start optimization device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0139] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a fuel cell cold start optimization method.

[0140] The display unit of this computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of this computer device can be a touch layer covering the display screen, or buttons, a trackball, or a touchpad set on the casing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0141] Those skilled in the art will understand that Figure 4The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0142] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0143] Construct a dynamic model of the fuel cell;

[0144] Based on the dynamic model, the set of safety constraints during the cold start process of the fuel cell is determined;

[0145] The objective function of the fuel cell is constructed with the goals of shortening the heating time, suppressing the temperature difference between different regions, stabilizing fuel utilization, reducing oxidation risk, and minimizing actuator energy consumption.

[0146] Based on the dynamic model, the safety constraint set, and the objective function, rolling prediction and optimization are performed to determine the optimal control sequence for air flow, fuel flow, and heating power.

[0147] The optimal control sequence is executed until the fuel cell reaches steady-state operating conditions, at which point the control mode of the fuel cell is switched to a steady-state power generation model.

[0148] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0149] Construct a dynamic model of the fuel cell;

[0150] Based on the dynamic model, the set of safety constraints during the cold start process of the fuel cell is determined;

[0151] The objective function of the fuel cell is constructed with the goals of shortening the heating time, suppressing the temperature difference between different regions, stabilizing fuel utilization, reducing oxidation risk, and minimizing actuator energy consumption.

[0152] Based on the dynamic model, the safety constraint set, and the objective function, rolling prediction and optimization are performed to determine the optimal control sequence for air flow, fuel flow, and heating power.

[0153] The optimal control sequence is executed until the fuel cell reaches steady-state operating conditions, at which point the control mode of the fuel cell is switched to a steady-state power generation model.

[0154] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0155] Construct a dynamic model of the fuel cell;

[0156] Based on the dynamic model, the set of safety constraints during the cold start process of the fuel cell is determined;

[0157] The objective function of the fuel cell is constructed with the goals of shortening the heating time, suppressing the temperature difference between different regions, stabilizing fuel utilization, reducing oxidation risk, and minimizing actuator energy consumption.

[0158] Based on the dynamic model, the safety constraint set, and the objective function, rolling prediction and optimization are performed to determine the optimal control sequence for air flow, fuel flow, and heating power.

[0159] The optimal control sequence is executed until the fuel cell reaches steady-state operating conditions, at which point the control mode of the fuel cell is switched to a steady-state power generation model.

[0160] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0161] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0162] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0163] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for optimizing cold start of a fuel cell, characterized in that, The method includes: Construct a dynamic model of the fuel cell; Based on the dynamic model, the set of safety constraints during the cold start process of the fuel cell is determined; The objective function of the fuel cell is constructed with the goals of shortening the heating time, suppressing the temperature difference between different regions, stabilizing fuel utilization, reducing oxidation risk, and minimizing actuator energy consumption. Based on the dynamic model, the safety constraint set, and the objective function, rolling prediction and optimization are performed to determine the optimal control sequence for air flow, fuel flow, and heating power. The optimal control sequence is executed until the fuel cell reaches steady-state operating conditions, at which point the control mode of the fuel cell is switched to a steady-state power generation model.

2. The method according to claim 1, characterized in that, The dynamic model includes a thermodynamic model, an electrochemical model, a gas dynamics model, and an actuator dynamic model.

3. The method according to claim 2, characterized in that, The process of constructing the thermodynamic model includes: Based on the temperature field of the fuel cell stack, the fuel cell stack is divided into multiple regions, and the heat balance equation of each region is determined based on the heat absorption, heat dissipation and heat conduction characteristics of the region. Based on the aforementioned heat balance equation, a thermodynamic model of the fuel cell is established.

4. The method according to claim 1, characterized in that, The set of safety constraints includes the upper and lower limits of the fuel cell stack temperature, the temperature difference limit between different regions, the fuel utilization rate range, the upper limit of the anode oxygen partial pressure, and the actuator action limit.

5. The method according to claim 1, characterized in that, The process of executing the optimal control sequence until the fuel cell reaches steady-state operating conditions, and then switching the fuel cell control mode to a steady-state power generation model, includes: The optimal control sequence is executed to determine the predicted temperature field, predicted gas composition, predicted fuel utilization rate, and predicted anode oxygen partial pressure of the fuel cell. Based on the predicted temperature field, predicted gas composition, predicted fuel utilization rate, and predicted anode oxygen partial pressure, the weight parameters in the dynamic model, the safety constraint set, and the objective function are adjusted until the fuel cell temperature reaches the target operating temperature, the temperature difference between regions stabilizes within the safety threshold, the fuel utilization rate stabilizes within the preset utilization rate range, and the output voltage stabilizes within the preset voltage range. Then, the control mode of the fuel cell is switched to a steady-state power generation model.

6. The method according to claim 1, characterized in that, The method further includes: The cold start process of the fuel cell is divided into different stages; the different stages include the low temperature preheating stage, the fuel introduction stage, the intermediate temperature crossing stage, the high temperature stabilization approach stage, and the steady-state transition stage. Different preset weight parameters are assigned to the dynamic model, the set of security constraints, and the objective function in each stage.

7. A fuel cell cold start optimization device, characterized in that, The device includes: Building blocks are used to construct dynamic models of fuel cells; The determination module is used to determine the set of safety constraints during the cold start process of the fuel cell based on the dynamic model. The construction module is also used to construct the objective function of the fuel cell with the goals of shortening the heating time, suppressing the temperature difference between different regions, stabilizing the fuel utilization rate, reducing the oxidation risk and minimizing the actuator energy consumption. The solution module is used to perform rolling prediction and optimization based on the dynamic model, the safety constraint set, and the objective function to determine the optimal control sequence of air flow, fuel flow, and heating power; The switching module is used to execute the optimal control sequence until the fuel cell reaches steady-state operating conditions, and then switch the control mode of the fuel cell to a steady-state power generation model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images