Fuel cell vehicle energy management modeling method, device, equipment and storage medium

Abstract

The application provides a fuel cell vehicle energy management modeling method, device, equipment and storage medium, and relates to the technical field of new energy vehicles. The method comprises the following steps: constructing a multi-dimensional dynamic coupling model framework, establishing an electrical and mechanical coupling node equation; establishing a high-fidelity quasi-two-dimensional dynamic model of a fuel cell system integrating electrochemical, mass transfer, membrane water management and thermal management sub-models; establishing an equivalent circuit vehicle energy storage system dynamic model with state of charge and temperature as parameters; based on the time constant difference, dividing into fast, medium and slow multiple time dimensions, using variable step size collaborative simulation to solve the model framework and generating a vehicle reduced order model; taking the model framework or the reduced order model as a simulation environment, applying an optimization algorithm to design an upper energy management strategy, and performing closed-loop verification and iterative optimization. The application can significantly improve the simulation credibility, optimize the energy management economy and durability, and accelerate the development process of fuel cell vehicles.

Description

Technical Field

[0001] This application relates to the field of new energy vehicle technology, and in particular to energy management modeling methods, devices, equipment and storage media for fuel cell vehicles. Background Technology

[0002] Fuel cell vehicles, with their advantages of high energy conversion efficiency, zero emissions, and long driving range, have become an important development direction in the field of clean transportation. A typical fuel cell vehicle power system usually includes components such as a fuel cell stack, on-board energy storage device, DC / DC converter, drive motor, vehicle transmission system, and control system.

[0003] Vehicle system modeling is a fundamental step in the development of fuel cell vehicles, widely used in simulation analysis, performance evaluation, and control strategy design and optimization. However, existing modeling methods still have the following shortcomings:

[0004] (1) The contradiction between model accuracy and computational efficiency. In order to reduce computational complexity, existing technologies often oversimplify fuel cell systems, ignoring key aspects such as internal electrochemical reactions, gas supply dynamics, and hydrothermal management processes. When driving conditions change drastically, the simulation error of such simplified models increases significantly, making it difficult to accurately reflect the actual output characteristics, degradation law, and impact on system life of the fuel cell.

[0005] (2) Decoupling modeling method between subsystems. Existing models usually model each power component independently and then connect them through fixed interfaces. This fails to fully describe the dynamic interaction and coupling effect between subsystems, making it difficult for the model to realistically reproduce the collaborative working characteristics of the whole vehicle system.

[0006] (3) The disconnect between energy management strategies and models. Traditional energy management strategies are mostly based on simplified or even static models, and fail to be optimized and verified in a high-fidelity dynamically coupled vehicle model. This results in performance degradation and insufficient system stability in practical applications.

[0007] (4) It is difficult to uniformly handle dynamic characteristics of multiple time dimensions. The internal reaction of fuel cells, gas pressure dynamics, thermal management process, energy storage system response and vehicle driving requirements have significantly different time constants. Existing models are difficult to take into account the dynamic processes of the above different time scales, and there is a lack of unified and efficient modeling and solution methods.

[0008] Therefore, how to construct a vehicle energy management model that can accurately describe the internal dynamics of fuel cells, precisely characterize the coupling relationships of subsystems, and support multi-time-dimensional collaborative simulation while ensuring computational efficiency has become a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0009] This application provides a fuel cell vehicle energy management modeling method, device, equipment, and storage medium, aiming to solve the problems of insufficient model accuracy, lack of dynamic coupling between subsystems, disconnect between energy management strategies and models, and difficulty in uniformly handling multi-time-dimensional dynamics in existing fuel cell vehicle modeling methods mentioned in the background. By constructing a multi-dimensional dynamic coupling model framework for forward simulation, integrating a high-fidelity quasi-two-dimensional dynamic model of the fuel cell with a dynamic model of the on-board energy storage system, dividing multiple time dimensions based on time constant differences and generating a reduced-order model using variable step-size collaborative simulation, and using this dynamic coupling model or reduced-order model as the simulation environment to apply optimization algorithms to design and perform closed-loop verification of the vehicle's energy management strategy, the application significantly improves the simulation accuracy of transient conditions, realistically reproduces the coupling characteristics of subsystems, uniformly handles multi-scale dynamic processes, and achieves efficient development and comprehensive performance optimization of energy management strategies while ensuring computational efficiency.

[0010] In a first aspect, this application provides a modeling method for energy management of fuel cell vehicles, the method comprising:

[0011] A multi-dimensional dynamic coupling model framework following forward simulation logic is constructed. The multi-dimensional dynamic coupling model framework includes a driver model, an upper-level vehicle energy management strategy module, and a lower-level component-level high-fidelity dynamic model set. Electrical coupling node equations and mechanical coupling node equations are established.

[0012] A high-fidelity quasi-two-dimensional dynamic model of a fuel cell system is established, which integrates at least an electrochemical sub-model, a mass transfer and flow field sub-model, a membrane water management sub-model, and a thermal management model.

[0013] A dynamic model of the vehicle-mounted energy storage system is established. The dynamic model of the vehicle-mounted energy storage system adopts an equivalent circuit model, whose parameters are functions of state of charge and temperature, and is connected to the vehicle's DC bus through a bidirectional DC / DC converter model.

[0014] Based on the difference in the dynamic characteristic time constant between the high-fidelity quasi-two-dimensional dynamic model of the fuel cell system and the dynamic model of the vehicle energy storage system, multiple time dimensions are divided, and a variable step-size collaborative simulation mechanism is used to solve the multi-dimensional dynamic coupling model framework, thereby generating a reduced-order model of the whole vehicle.

[0015] Using the multi-dimensional dynamic coupling model framework or the vehicle reduced-order model as the simulation environment or prediction model, an optimization algorithm is applied to design an upper-level vehicle energy management strategy, and closed-loop verification and iterative optimization are performed in the multi-dimensional dynamic coupling model framework.

[0016] In one possible design, the electrical coupling node equation is expressed as:

[0017] I fcdc+I batdc =I load ;

[0018] Among them, I fcdc I is the output current of the DC / DC converter on the fuel cell side. batdc I is the output current of the DC / DC converter on the energy storage system side. load This is the load current.

[0019] In one possible design, the electrochemical sub-model employs a semi-empirical voltage equation, in which the activation overpotential and ohmic overpotential parameters are dynamically related to the membrane water content and the stack temperature; the mass transfer and flow field sub-model uses a lumped parameter method to describe the dynamic changes in gas pressure and component concentration within the anode and cathode channels.

[0020] In one possible design, the high-fidelity quasi-two-dimensional dynamic model of the fuel cell system also includes a dynamic model of an air compressor, the power consumption of which is deducted from the net output power of the fuel cell stack as a load, and the air flow rate of which determines the cathode inlet pressure.

[0021] In one possible design, the on-board energy storage system corresponding to the dynamic model of the on-board energy storage system is a lithium-ion battery, and the equivalent circuit model is a second-order resistance-capacitor equivalent circuit model. The parameters of the second-order resistance-capacitor equivalent circuit model are identified through hybrid pulse power characteristic experiments and expressed as a two-dimensional lookup table function of state of charge and temperature.

[0022] In one possible design, the multiple time dimensions include:

[0023] Fast Dynamics: DC / DC Converter Switching Dynamics and Motor Current Loop;

[0024] Medium dynamics: gas pressure dynamics, circuit transient response, and drive torque response;

[0025] Slow dynamics: dynamics of fuel cell stack temperature and dynamics of membrane water content.

[0026] In one possible design, the reduced-order vehicle model is generated by extracting key dynamic characteristics from the input and output data of the multi-dimensional dynamically coupled model framework using neural networks, support vector machines, or state space identification methods.

[0027] Secondly, this application provides a fuel cell vehicle energy management modeling device, the device comprising:

[0028] The framework construction module is configured to build a multi-dimensional dynamic coupling model framework that follows forward simulation logic. The multi-dimensional dynamic coupling model framework includes a driver model, an upper-level vehicle energy management strategy module, and a lower-level component-level high-fidelity dynamic model set, and establishes electrical coupling node equations and mechanical coupling node equations.

[0029] The first model building module is configured to establish a high-fidelity quasi-two-dimensional dynamic model of the fuel cell system. The high-fidelity quasi-two-dimensional dynamic model of the fuel cell system integrates at least an electrochemical sub-model, a mass transfer and flow field sub-model, a membrane water management sub-model, and a thermal management model.

[0030] The second model building module is configured to establish a dynamic model of the vehicle-mounted energy storage system. The dynamic model of the vehicle-mounted energy storage system adopts an equivalent circuit model, whose parameters are functions of the state of charge and temperature, and is connected to the vehicle's DC bus through a bidirectional DC / DC converter model.

[0031] The time dimension partitioning module is configured to partition multiple time dimensions based on the difference in the dynamic characteristic time constants between the high-fidelity quasi-two-dimensional dynamic model of the fuel cell system and the dynamic model of the vehicle energy storage system, and to solve the multi-dimensional dynamic coupling model framework using a variable step-size collaborative simulation mechanism, thereby generating a reduced-order model of the whole vehicle.

[0032] The strategy optimization design module is configured to use the multi-dimensional dynamic coupling model framework or the vehicle reduced-order model as the simulation environment or prediction model, apply optimization algorithms to design the upper-level vehicle energy management strategy, and perform closed-loop verification and iterative optimization in the multi-dimensional dynamic coupling model framework.

[0033] Thirdly, embodiments of this application provide an electronic device, including: at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, causing the at least one processor to perform the fuel cell vehicle energy management modeling method as described in the first aspect and various possible designs of the first aspect.

[0034] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions. When a processor executes the computer-executable instructions, it implements the fuel cell vehicle energy management modeling method described in the first aspect and various possible designs of the first aspect.

[0035] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the fuel cell vehicle energy management modeling method described in the first aspect and various possible designs of the first aspect.

[0036] The fuel cell vehicle energy management modeling method, device, equipment, and storage medium provided in this application have at least the following beneficial effects:

[0037] 1) This application significantly improves the accuracy of vehicle simulation under transient conditions by constructing a high-fidelity quasi-two-dimensional dynamic model of a fuel cell system that integrates an electrochemical sub-model, a mass transfer and flow field sub-model, a membrane water management sub-model, and a thermal management sub-model, and by adopting an equivalent circuit model of the on-board energy storage system with parameters varying with state of charge and temperature.

[0038] 2) This application explicitly establishes electrical coupling node equations and mechanical coupling node equations in the multi-dimensional dynamic coupling model framework of forward simulation logic, which fully reproduces the dynamic interaction link between the fuel cell system, energy storage system and load, and improves the credibility of system stability analysis.

[0039] 3) Based on the difference in the dynamic characteristic time constants of fuel cell systems and energy storage systems, this application divides the system into fast dynamic, medium dynamic and slow dynamic, and uses a variable step size co-simulation mechanism for solving. It can simultaneously support the stability analysis corresponding to fast dynamic and the efficiency and life assessment corresponding to slow dynamic, and adapt to the design requirements of hierarchical control systems.

[0040] 4) This application uses a multi-dimensional dynamic coupling model framework as a high-fidelity simulation environment for offline optimization, and uses the resulting reduced-order vehicle model (obtained through neural networks, support vector machines or state space identification) for online control and hardware-in-the-loop testing, which shortens the development cycle of energy management strategies.

[0041] 5) When using model predictive control for energy management, this application takes minimizing the total hydrogen consumption in the prediction time domain as the optimization objective, and adds a fuel cell output power fluctuation penalty term to the objective function, which can smooth fuel cell power fluctuation while reducing the hydrogen consumption of the whole vehicle, thereby extending the service life of the fuel cell. Attached Figure Description

[0042] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0043] Figure 1 A flowchart illustrating a fuel cell vehicle energy management modeling method provided in this application embodiment;

[0044] Figure 2 This is a schematic diagram of the structure of the multi-dimensional dynamic coupling model framework provided in the embodiments of this application;

[0045] Figure 3This is a schematic diagram of the structure of a high-fidelity near-two-dimensional dynamic model of a fuel cell system provided in an embodiment of this application;

[0046] Figure 4 A schematic diagram of the multi-time-dimensional dynamic decoupling and co-simulation mechanism provided in the embodiments of this application;

[0047] Figure 5 A principle block diagram of energy management based on model predictive control using a dynamic coupling model, provided for embodiments of this application;

[0048] Figure 6 This is a structural diagram of a fuel cell vehicle energy management modeling device provided in an embodiment of this application.

[0049] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concepts of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation

[0050] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0051] The collection, storage, use, processing, transmission, provision, and disclosure of relevant data and information in the technical solution of this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0052] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, they do not mean that the applicant has used or necessarily used the solution.

[0053] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0054] This application provides a method for modeling energy management in fuel cell vehicles. Figure 1As shown, the fuel cell vehicle energy management modeling method includes the following steps S10~S50.

[0055] S10: Construct a multi-dimensional dynamic coupling model framework that follows forward simulation logic. The multi-dimensional dynamic coupling model framework includes a driver model, an upper-level vehicle energy management strategy module, and a lower-level component-level high-fidelity dynamic model set, and establishes electrical coupling node equations and mechanical coupling node equations.

[0056] Step S10 employs forward simulation logic, starting from the driver's operation command, sequentially passing through the vehicle controller and various component models, ultimately feeding back the vehicle speed to form a closed loop, realistically reflecting the signal transmission path of the actual vehicle. By explicitly establishing electrical and mechanical coupling node equations, subsystems such as the fuel cell system, energy storage system, and drive motor are dynamically coupled at the same node, avoiding coupling distortion caused by traditional backward simulation or fixed interface connections. The multi-dimensional dynamic coupling model framework constructed using step S10 can accurately reproduce the interactions between subsystems, especially during dynamic processes such as bus voltage fluctuations and power redistribution, improving the reliability of the vehicle system's stability analysis.

[0057] In one exemplary implementation, this multi-dimensional dynamic coupling model framework can be built in a MATLAB / Simulink simulation environment. The driver model calculates the drive torque request or braking torque request using a PID controller based on the difference between the target vehicle speed and the actual vehicle speed. The upper-level vehicle energy management strategy module is implemented in the form of a state machine or optimization algorithm, used to receive driver requirements and the states of various components, and output power allocation instructions for the fuel cell system and energy storage system. The lower-level component-level high-fidelity dynamic model set includes a fuel cell system model, a bidirectional DC / DC converter model, an energy storage system model, a drive motor model, a transmission system model, and a vehicle dynamics model. The electrical coupling node equations are specifically the DC bus current balance equations:

[0058] I fcdc +I batdc =I load ;

[0059] Among them, I fcdc I is the output current of the DC / DC converter on the fuel cell side. batdc I is the output current of the DC / DC converter on the energy storage system side. load The load current is the bus voltage, which is dynamically determined by the characteristics of all power sources and loads at this node.

[0060] The mechanical coupling node equation is, for example, the torque balance equation at the drive wheel, which transmits the motor output torque to the wheel through the transmission ratio and efficiency, and balances it with the driving resistance.

[0061] like Figure 2The diagram shows the structure of the multi-dimensional dynamic coupling model framework provided in this embodiment. This framework includes an input module, a core calculation module, and an output module. The input module comprises two sub-units: driver input and environment input. It is responsible for collecting driver operation commands and external environmental parameters, and sending all collected data to the core calculation module via a data transmission link. The core calculation module, as the computational core of the entire model framework, integrates a fuel cell system model, a powertrain system model, and a vehicle dynamics model. It can perform dynamic simulation calculations of each component of the vehicle's powertrain system based on the input data. The core calculation module and the output module interact via a bidirectional data transmission link. The simulation results output by the core calculation module are transmitted to the output module, which then generates vehicle state output and performance evaluation output. A bidirectional data transmission relationship also exists between the vehicle state output and the performance evaluation output. The analysis results of the performance evaluation output can be fed back to the vehicle state output, thereby enabling closed-loop optimization and parameter correction of the entire vehicle simulation process through the core calculation module.

[0062] S20: Establish a high-fidelity quasi-two-dimensional dynamic model of the fuel cell system. The high-fidelity quasi-two-dimensional dynamic model of the fuel cell system shall integrate at least the electrochemical sub-model, the mass transfer and flow field sub-model, the membrane water management sub-model, and the thermal management sub-model.

[0063] Step S20 overcomes the shortcomings of traditional zero-dimensional or one-dimensional models that oversimplify the internal processes of fuel cells by adopting a quasi-two-dimensional modeling method. Discretization is performed along the gas flow path and the membrane electrode thickness direction, while preserving the main physicochemical dynamics. Integrating multiple sub-models enables the description of the strong coupling relationships between voltage output, gas supply, water transfer, and thermal balance. Under drastic changes in driving conditions, this model can accurately predict the transient voltage response, net output power, and internal states of the fuel cell stack, such as membrane water content and temperature, thus providing reliable fuel cell performance boundaries and lifetime-related constraints for energy management strategies.

[0064] In one exemplary embodiment, a modified semi-empirical voltage equation is used to calculate the single-cell voltage, which includes open-circuit voltage, activation overpotential, ohmic overpotential, and concentration overpotential. The parameters in the activation and ohmic overpotentials are dynamically related to the membrane water content and stack temperature. The mass transfer and flow field sub-model employs a lumped parameter method to establish mass conservation equations for the anode hydrogen flow channel and the cathode air flow channel, respectively, dynamically calculating the partial and total pressures of hydrogen, oxygen, nitrogen, and water vapor. The membrane water management sub-model simulates the electroosmotic drag, reverse diffusion, and phase transition processes between the membrane and the flow channels, thereby calculating the membrane water content distribution. The thermal management sub-model establishes the stack's thermal balance equation, considering the heat of electrochemical reaction, ohmic heat, heat carried away by the coolant, and convective heat dissipation, dynamically updating the stack's average temperature. Furthermore, this fuel cell system model also includes a dynamic model of the air compressor, whose power consumption is subtracted from the fuel cell stack's gross power as an auxiliary load to obtain the net output power; the air compressor's mass flow rate determines the cathode inlet pressure, thus affecting the oxygen concentration on the cathode side.

[0065] like Figure 3 The diagram shows the structure of a high-fidelity quasi-two-dimensional dynamic model of a fuel cell system provided in this embodiment. This high-fidelity quasi-two-dimensional dynamic model adopts a three-layer modular architecture: an input layer, a core computation layer, and an output layer. The input layer receives the external boundary conditions and control input parameters required for the operation of the fuel cell system, specifically including three types of input quantities: gas flow rate, temperature, and pressure. All input parameters are synchronously transmitted to the core computation layer via a standardized data transmission link. The core computation layer is the computational center of the fuel cell model, integrating an electrochemical reaction model, a thermal management model, and a fluid dynamics model. Real-time data interaction and strong coupling computation are achieved between the three models, synchronously simulating the electrochemical reaction dynamics, heat generation and transfer balance process, and gas flow and mass transfer process inside the fuel cell. A bidirectional data transmission channel is established between the core computation layer and the output layer. The multiphysics simulation results output by the core computation layer are transmitted to the output layer, which generates three types of output results: voltage characteristics, power output, and efficiency analysis. Meanwhile, the efficiency analysis results inside the output layer can be fed back to the core computing layer to dynamically correct the calculation parameters of the electrochemical reaction model, thermal management model, and fluid dynamics model, thereby achieving online self-calibration and iterative improvement of simulation accuracy. This ensures that the simulation results of the fuel cell system under steady-state and transient conditions can accurately reflect the actual operating characteristics.

[0066] S30: Establish a dynamic model of the on-board energy storage system. The dynamic model of the on-board energy storage system adopts an equivalent circuit model, whose parameters are functions of state of charge and temperature, and is connected to the vehicle's DC bus through a bidirectional DC / DC converter model.

[0067] Step S30 uses an equivalent circuit model to achieve a balance between computational efficiency and accuracy, and represents key parameters as a two-dimensional function of state of charge and temperature to accommodate energy storage characteristics at different operating points and ambient temperatures. A bidirectional DC / DC converter model is connected to the DC bus, enabling the energy storage system to both discharge and recover regenerative energy. This accurately simulates the changes in terminal voltage, current, state of charge, and internal polarization effects of lithium-ion batteries during charging and discharging, providing real-time power capacity and status information of the energy storage system for energy management strategies.

[0068] In one exemplary implementation, the on-board energy storage system uses a lithium-ion battery and employs a second-order RC equivalent circuit model, consisting of an ohmic internal resistance and two parallel RC series networks, representing electrochemical polarization and concentration polarization, respectively. The open-circuit voltage, ohmic internal resistance, two polarization resistors, and two polarization capacitors are identified through hybrid pulse power characteristic experiments at different states of charge (SOC) and temperatures, and then established as two-dimensional lookup table functions for SOC and temperature. In the simulation, model parameters are obtained through real-time interpolation based on the current SOC and temperature, and then the battery terminal voltage and the maximum allowable charge / discharge power are calculated. The energy storage system is connected to the DC bus via a bidirectional DC / DC converter. This converter model includes voltage conversion ratio, switching losses, and conduction losses, and can control the output or input current of the energy storage system according to energy management strategy commands. The converter's dynamic response time constant is approximately in the microsecond range, falling into the fast dynamic range.

[0069] S40: Based on the difference in the time constant of the dynamic characteristics of the high-fidelity quasi-two-dimensional dynamic model of the fuel cell system and the dynamic model of the vehicle energy storage system, multiple time dimensions are divided, and a variable step size collaborative simulation mechanism is used to solve the multi-dimensional dynamic coupling model framework, thereby generating a reduced-order model of the whole vehicle.

[0070] Step S40 identifies the time constant differences of different physical processes in the system, divides the model into multiple time dimensions (fast, medium, and slow), and employs different solution step sizes and solvers for each dimension to improve overall simulation efficiency while ensuring numerical stability and accuracy. Through variable-step co-simulation, models in different dimensions exchange data at interface moments, thus achieving cross-scale coupling. Furthermore, key dynamic characteristics are extracted from the high-fidelity model using system identification methods to generate a reduced-order model, meeting the rapid computational needs of real-time control or hardware-in-the-loop testing. This approach preserves the accuracy of the high-fidelity model while significantly reducing the computational burden on online applications, achieving a balance between model accuracy and computational efficiency.

[0071] In one exemplary implementation, system dynamics are categorized into three types based on the magnitude of their time constants. Fast dynamics include the switching dynamics of the DC / DC converter and the current loop dynamics of the drive motor, with time constants typically in the range of microseconds to milliseconds. Medium dynamics include gas pressure dynamics, transient response of the DC bus circuit, and drive torque response, with time constants in the range of milliseconds to hundreds of milliseconds. Slow dynamics include stack temperature dynamics and membrane water content dynamics, with time constants in the range of seconds to minutes. In the co-simulation, a fixed small step size (e.g., 1 μs) is used for fast dynamics with the circuit simulation solver enabled; a variable step size (e.g., 1 ms) is used for medium dynamics; and a large step size (e.g., 0.1 s) is used for slow dynamics. At the end of each macro-time step, the models of each dimension exchange state variables such as voltage, current, temperature, and pressure through a coupling interface. After completing the multi-time-dimensional simulation of the high-fidelity model, input and output data of the model under typical driving conditions are collected. Inputs include vehicle speed, pedal opening, and power allocation commands of the energy management strategy; outputs include fuel cell net power, battery state of charge, and bus voltage. A low-order linear or nonlinear state-space model is trained or fitted using neural networks or state-space subspace identification methods to serve as a reduced-order model for the entire vehicle. This reduced-order model preserves the main mapping relationships for fast, medium, and slow dynamics, and its computational speed is more than an order of magnitude faster than that of the high-fidelity model.

[0072] like Figure 4 The diagram illustrates a multi-time-dimensional dynamic decoupling and co-simulation mechanism provided in this embodiment of the invention. This mechanism employs a hierarchical decoupling and co-solution architecture, dividing the vehicle's powertrain system into three independent levels—fast dynamic subsystem, medium dynamic subsystem, and slow dynamic subsystem—based on the time constant differences in its dynamic characteristics. Each subsystem outputs its corresponding time-dimensional operational status data, which is then uniformly transmitted to the variable-step-size co-simulation and data synchronization module. This module, acting as the core scheduling and data interaction unit, coordinates the solution step sizes of models across different time dimensions, completing the synchronization verification and interaction of cross-scale state data. The system delivers and outputs four types of application results: high-fidelity vehicle coupling and data synchronization, used to ensure the real-time transmission of data and the consistency of state parameters between subsystems of the high-fidelity vehicle model; high-fidelity vehicle coupling model, which can serve as a basic platform for high-precision iterative optimization of vehicle power performance simulation and energy management strategies under offline conditions; vehicle reduced-order model, which generates a high-fidelity model by system identification and extraction of core dynamic characteristics, significantly reducing computational complexity while retaining the main dynamic response characteristics of the system; and real-time simulation application, which can directly support hardware-in-the-loop testing and rapid prototype verification of the real vehicle controller, achieving seamless connection from offline simulation analysis to online control application.

[0073] S50: Using a multi-dimensional dynamic coupling model framework or a reduced-order vehicle model as the simulation environment or prediction model, apply optimization algorithms to design upper-level vehicle energy management strategies, and perform closed-loop verification and iterative optimization within the multi-dimensional dynamic coupling model framework.

[0074] Step S50 uses the high-fidelity multi-dimensional dynamic coupling model as the benchmark for offline optimization and verification, and the reduced-order model as the predictive model in online or real-time control. Optimization algorithms such as model predictive control are used to solve for the optimal power allocation sequence in the prediction time domain, and the first control variable is implemented. After one round of optimization, the obtained energy management strategy is embedded into the high-fidelity model framework for closed-loop simulation verification to evaluate its economic and durability performance under actual dynamic coupling conditions. If the effect does not meet expectations, the optimization algorithm parameters or weights are adjusted and iterated. This completely solves the problem of the disconnect between traditional energy management strategies and dynamic models, realizing an integrated closed-loop development process from strategy design, verification to optimization, significantly shortening the development cycle and improving the real-vehicle applicability of the strategy.

[0075] In one exemplary implementation, the optimization algorithm employs model predictive control. The reduced-order vehicle model generated in step S40 is used as the internal predictive model for model predictive control, with a prediction time domain of 10 s and a control time domain of 5 s. In each control cycle, the model predictive controller, based on the currently measured vehicle speed, battery state of charge, fuel cell state, etc., aims to minimize the total hydrogen consumption within the prediction time domain, and sets multiple constraints: the fuel cell power change rate does not exceed 5 kW per 10 ms, the energy storage system power does not exceed its maximum charge / discharge limit, the energy storage system state of charge is maintained between 0.3 and 0.9, and the DC bus voltage is maintained within 90% to 110% of the nominal value. A penalty term for fuel cell output power fluctuations is also added to the objective function, for example, by multiplying the square of the power change rate by a weighting coefficient, thereby reducing hydrogen consumption while suppressing fuel cell power fluctuations and extending stack life. Solving this constrained quadratic programming problem yields the optimal fuel cell power sequence, and the first value is output as an instruction to the lower-level component model. Subsequently, the model predictive control strategy is encapsulated into an upper-level vehicle energy management strategy module and embedded into the multi-dimensional dynamic coupling model framework constructed in step S10, replacing the original simple rule-based strategy. Closed-loop simulations are performed under typical driving conditions such as WLTC or CLTC-P, recording and analyzing indicators such as total hydrogen consumption, fuel cell power fluctuation amplitude, and battery state of charge trajectory. If hydrogen consumption or fluctuation amplitude does not meet expectations, the weighting coefficients or prediction time domain length in the model predictive control are adjusted, and the above closed-loop verification process is repeated until the design requirements are met. The final energy management strategy can be directly compiled into embedded code and applied to the actual vehicle controller.

[0076] like Figure 5The diagram shown illustrates the principle block diagram of energy management based on a dynamic coupling model using model predictive control, as provided in this embodiment of the invention. This control architecture for energy management based on a dynamic coupling model using model predictive control is divided into three sequentially connected and closed-loop interactive functional modules: a model base unit, a control calculation unit, and an execution output unit. The model base unit includes three sub-modules: a dynamic coupling model, system state estimation, and parameter identification. The dynamic coupling model outputs real-time operating data of the vehicle's powertrain system to the system state estimation module. The system state estimation module performs real-time estimation of key operating states of the vehicle based on the input data and transmits the estimation results to the parameter identification module. The parameter identification module dynamically corrects the model parameters according to changes in system state to ensure consistency between the dynamic coupling model and the actual system characteristics. The final output data of the model base unit is uniformly transmitted to the control calculation unit. The control calculation unit includes three sub-modules: model predictive control, rolling optimization, and feedback correction. The model predictive control module uses a reduced-order vehicle model as its internal prediction basis. The system generates a predictive control sequence based on the current state and future operating trends of the system and sends it to the rolling optimization module. The rolling optimization module solves for the optimal power allocation scheme that satisfies multiple constraints within the set prediction and control time domains. The feedback correction module receives the actual operation feedback data from the execution output unit and performs real-time compensation and correction on the calculation results of the rolling optimization to eliminate the impact of model errors and external disturbances on control accuracy. The optimal control command output by the control calculation unit is transmitted to the execution output unit, which includes three sub-modules: energy management, energy allocation strategy, and actuator control. The energy management module receives the control command and generates the overall target for the energy allocation of the entire vehicle. The energy allocation strategy module decomposes the overall target into specific power control commands for the fuel cell system and the energy storage system. The actuator control module drives each component to complete the corresponding actions according to the power commands. At the same time, the actuator control module feeds back the actual execution results to the energy management module, forming an energy management link from model calculation to control execution and then to feedback correction.

[0077] This application also provides a fuel cell vehicle energy management modeling device for implementing the methods described in any of the above embodiments, such as... Figure 6 As shown, the device includes:

[0078] The framework construction module 601 is configured to construct a multi-dimensional dynamic coupling model framework that follows forward simulation logic. The multi-dimensional dynamic coupling model framework includes a driver model, an upper-level vehicle energy management strategy module, and a lower-level component-level high-fidelity dynamic model set, and establishes electrical coupling node equations and mechanical coupling node equations.

[0079] The first model construction module 602 is configured to establish a high-fidelity quasi-two-dimensional dynamic model of a fuel cell system. The high-fidelity quasi-two-dimensional dynamic model of the fuel cell system integrates at least an electrochemical sub-model, a mass transfer and flow field sub-model, a membrane water management sub-model, and a thermal management model.

[0080] The second model construction module 603 is configured to establish a dynamic model of the vehicle-mounted energy storage system. The dynamic model of the vehicle-mounted energy storage system adopts an equivalent circuit model, whose parameters are functions of the state of charge and temperature, and is connected to the vehicle's DC bus through a bidirectional DC / DC converter model.

[0081] The time dimension partitioning module 604 is configured to partition multiple time dimensions based on the difference in dynamic characteristic time constants between the high-fidelity quasi-two-dimensional dynamic model of the fuel cell system and the dynamic model of the vehicle energy storage system, and to solve the multi-dimensional dynamic coupling model framework using a variable step size collaborative simulation mechanism, thereby generating a reduced-order model of the whole vehicle.

[0082] The strategy optimization design module 605 is configured to use the multi-dimensional dynamic coupling model framework or the vehicle reduced-order model as a simulation environment or prediction model, apply optimization algorithms to design upper-level vehicle energy management strategies, and perform closed-loop verification and iterative optimization in the multi-dimensional dynamic coupling model framework.

[0083] This application provides an electronic device. The electronic device may include a processor and a memory, wherein the processor and the memory can communicate; exemplarily, the processor and the memory communicate via a communication bus.

[0084] The processor executes computer execution instructions stored in memory, causing the processor to perform the scheme in the above embodiments. The processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0085] The communication bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The system bus can be divided into address bus, data bus, control bus, etc. Transceivers are used to enable communication between database access devices and other computers (e.g., clients, read-write libraries, and read-only libraries). Memory may include random access memory (RAM) and may also include non-volatile memory.

[0086] The electronic device provided in this application embodiment can be the terminal device described in the above embodiments.

[0087] This application also provides a computer-readable storage medium storing computer instructions. When the computer instructions are executed on a computer, the computer performs the technical solution of the fuel cell vehicle energy management modeling method described in the above embodiments.

[0088] This application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When the at least one processor executes the computer program, it can implement the technical solution of the fuel cell vehicle energy management modeling method in the above embodiments.

[0089] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0090] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to implement the solution of this embodiment according to actual needs.

[0091] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The unit composed of the above modules can be implemented in hardware or in the form of hardware plus software functional units.

[0092] The integrated modules described above, implemented as software functional modules, can be stored in a computer-readable storage medium. These software functional modules, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods of the various embodiments of this application.

[0093] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0094] The memory may include high-speed RAM, and may also include non-volatile storage (NVM), such as at least one disk storage device, and may also be a USB flash drive, external hard drive, read-only memory, disk or optical disc, etc.

[0095] Buses can be Industry Standard Architecture (ISA) buses, Peripheral Component Interconnect (PCI) buses, or Extended Industry Standard Architecture (EISA) buses, etc. Buses can be categorized into address buses, data buses, control buses, etc.

[0096] The aforementioned storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0097] An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Alternatively, the storage medium can be an integral part of the processor. The processor and storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and storage medium can exist as discrete components in an electronic control unit or main control device.

[0098] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A modeling method for energy management of fuel cell vehicles, characterized in that, The method includes: A multi-dimensional dynamic coupling model framework following forward simulation logic is constructed. The multi-dimensional dynamic coupling model framework includes a driver model, an upper-level vehicle energy management strategy module, and a lower-level component-level high-fidelity dynamic model set. Electrical coupling node equations and mechanical coupling node equations are established. A high-fidelity quasi-two-dimensional dynamic model of a fuel cell system is established, which integrates at least an electrochemical sub-model, a mass transfer and flow field sub-model, a membrane water management sub-model, and a thermal management model. A dynamic model of the vehicle-mounted energy storage system is established. The dynamic model of the vehicle-mounted energy storage system adopts an equivalent circuit model, whose parameters are functions of state of charge and temperature, and is connected to the vehicle's DC bus through a bidirectional DC / DC converter model. Based on the difference in the dynamic characteristic time constant between the high-fidelity quasi-two-dimensional dynamic model of the fuel cell system and the dynamic model of the vehicle energy storage system, multiple time dimensions are divided, and a variable step-size collaborative simulation mechanism is used to solve the multi-dimensional dynamic coupling model framework, thereby generating a reduced-order model of the whole vehicle. Using the multi-dimensional dynamic coupling model framework or the vehicle reduced-order model as the simulation environment or prediction model, an optimization algorithm is applied to design an upper-level vehicle energy management strategy, and closed-loop verification and iterative optimization are performed in the multi-dimensional dynamic coupling model framework.

2. The fuel cell vehicle energy management modeling method according to claim 1, characterized in that, The equation for the electrically coupled node is expressed as follows: I fcdc +I batdc =I load ; Among them, I fcdc I is the output current of the DC / DC converter on the fuel cell side. batdc I is the output current of the DC / DC converter on the energy storage system side. load This is the load current.

3. The fuel cell vehicle energy management modeling method according to claim 1, characterized in that, The electrochemical sub-model adopts a semi-empirical voltage equation, in which the activation overpotential and ohmic overpotential parameters are dynamically related to the membrane water content and the stack temperature; the mass transfer and flow field sub-model uses the lumped parameter method to describe the dynamic changes of gas pressure and component concentration in the anode and cathode channels.

4. The fuel cell vehicle energy management modeling method according to claim 1, characterized in that, The high-fidelity quasi-two-dimensional dynamic model of the fuel cell system also includes a dynamic model of an air compressor. The power consumption of the dynamic model of the air compressor is deducted from the net output power of the fuel cell stack as a load, and the air flow rate of the dynamic model of the air compressor determines the cathode inlet pressure.

5. The fuel cell vehicle energy management modeling method according to claim 1, characterized in that, The on-board energy storage system corresponding to the dynamic model of the vehicle energy storage system is a lithium-ion battery. The equivalent circuit model is a second-order resistance-capacitor equivalent circuit model. The parameters of the second-order resistance-capacitor equivalent circuit model are identified through hybrid pulse power characteristic experiments and expressed as a two-dimensional lookup table function of state of charge and temperature.

6. The fuel cell vehicle energy management modeling method according to claim 1, characterized in that, The multiple time dimensions include: Fast Dynamics: DC / DC Converter Switching Dynamics and Motor Current Loop; Medium dynamics: gas pressure dynamics, circuit transient response, and drive torque response; Slow dynamics: dynamics of fuel cell stack temperature and dynamics of membrane water content.

7. The fuel cell vehicle energy management modeling method according to claim 1, characterized in that, The vehicle reduced-order model is generated by extracting key dynamic characteristics from the input and output data of the multi-dimensional dynamic coupling model framework through neural networks, support vector machines, or state space identification methods.

8. A fuel cell vehicle energy management modeling device, characterized in that, The device includes: The framework construction module is configured to build a multi-dimensional dynamic coupling model framework that follows forward simulation logic. The multi-dimensional dynamic coupling model framework includes a driver model, an upper-level vehicle energy management strategy module, and a lower-level component-level high-fidelity dynamic model set, and establishes electrical coupling node equations and mechanical coupling node equations. The first model building module is configured to establish a high-fidelity quasi-two-dimensional dynamic model of the fuel cell system. The high-fidelity quasi-two-dimensional dynamic model of the fuel cell system integrates at least an electrochemical sub-model, a mass transfer and flow field sub-model, a membrane water management sub-model, and a thermal management model. The second model building module is configured to establish a dynamic model of the vehicle-mounted energy storage system. The dynamic model of the vehicle-mounted energy storage system adopts an equivalent circuit model, whose parameters are functions of the state of charge and temperature, and is connected to the vehicle's DC bus through a bidirectional DC / DC converter model. The time dimension partitioning module is configured to partition multiple time dimensions based on the difference in the dynamic characteristic time constants between the high-fidelity quasi-two-dimensional dynamic model of the fuel cell system and the dynamic model of the vehicle energy storage system, and to solve the multi-dimensional dynamic coupling model framework using a variable step-size collaborative simulation mechanism, thereby generating a reduced-order model of the whole vehicle. The strategy optimization design module is configured to use the multi-dimensional dynamic coupling model framework or the vehicle reduced-order model as the simulation environment or prediction model, apply optimization algorithms to design the upper-level vehicle energy management strategy, and perform closed-loop verification and iterative optimization in the multi-dimensional dynamic coupling model framework.

9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes the computer execution instructions stored in the memory to implement the fuel cell vehicle energy management modeling method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the fuel cell vehicle energy management modeling method as described in any one of claims 1-7.

Images