Vehicle energy management and heat management cooperative control method and system and vehicle

Abstract

The invention provides a cooperative control method and system for energy management and heat management of a vehicle and the vehicle. The vehicle includes a fuel cell and a power cell. The method comprises the steps that the current working condition of a vehicle is recognized; when it is recognized that the vehicle is in the short-term working condition, the vehicle is controlled according to a short-term working condition control mode, and the method comprises the steps that the vehicle speed change trend of the vehicle in the future preset duration is predicted; calculating the output power distribution of the fuel cell and the power cell in the future preset duration based on the vehicle speed change trend; based on the output power distribution of the fuel cell and the power cell, predicting the thermal load change trend of the vehicle in a future predetermined time period; and performing energy management control on the vehicle based on the output power distribution of the fuel cell and the power cell in the future predetermined time, and performing thermal management control on the vehicle based on the thermal load change trend in the future predetermined time.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method, system and vehicle for coordinated control of vehicle energy management and thermal management. Background Technology

[0002] Energy management in fuel cell vehicles ensures the vehicle's economy and durability; thermal management systems improve reliability and safety while ensuring all components operate within their optimal temperature ranges, further enhancing overall vehicle performance and economy. Current research primarily focuses on either individual fuel cell vehicle energy management or individual thermal management, lacking research on the coupling of energy and thermal management in fuel cell vehicles. Summary of the Invention

[0003] The purpose of this application is to provide a method, system, and vehicle for coordinated control of vehicle energy management and thermal management, which can perform coordinated control of vehicle energy management and thermal management to achieve better energy management and thermal management.

[0004] One aspect of this application provides a method, system, and vehicle for coordinated control of vehicle energy management and thermal management. The vehicle includes a fuel cell and a power battery. The method includes: identifying the current operating condition of the vehicle; when the vehicle is identified to be in a short-term operating condition, controlling the vehicle according to a short-term operating condition control mode, wherein the short-term operating condition is a continuous operating condition under a specific load, operating mode, or state for a predetermined short period of time, and controlling the vehicle according to the short-term operating condition control mode includes: predicting the vehicle speed change trend over a predetermined future period of time; calculating the output power distribution of the fuel cell and the power battery over the predetermined future period of time based on the speed change trend; predicting the thermal load change trend of the vehicle over the predetermined future period of time based on the output power distribution of the fuel cell and the power battery; performing energy management control on the vehicle based on the output power distribution of the fuel cell and the power battery over the predetermined future period of time, and performing thermal management control on the vehicle based on the thermal load change trend over the predetermined future period of time.

[0005] Furthermore, the method also includes: when the vehicle is detected to be entering a momentary operating condition, exiting the short-term operating condition control mode and adjusting the vehicle speed in real time.

[0006] Furthermore, the step of calculating the output power distribution of the fuel cell and the power battery within the predetermined future time period based on the vehicle speed change trend includes: performing vehicle speed planning based on the vehicle speed change trend to obtain a planned vehicle speed trajectory with optimal energy consumption; and calculating the output power distribution of the fuel cell and the power battery within the predetermined future time period based on the planned vehicle speed trajectory.

[0007] Furthermore, the step of planning vehicle speed based on the vehicle speed change trend to obtain the energy-optimal planned vehicle speed trajectory includes: constructing a state transition equation with the vehicle longitudinal force as the control variable and the vehicle speed as the state variable, wherein the vehicle longitudinal force includes the vehicle driving force and the vehicle braking force; discretizing the control variable and the state variable; and based on the vehicle speed change trend, with the goal of minimizing the total energy consumption during the driving process, using a dynamic programming algorithm and / or a forward enumeration method, traversing the value of the control variable corresponding to each discretized state variable during the state transition, to finally obtain the energy-optimal planned vehicle speed trajectory.

[0008] Furthermore, the calculation of the output power allocation of the fuel cell and the power battery within the predetermined future time period based on the planned vehicle speed trajectory includes: determining the energy demand trajectory based on the planned vehicle speed trajectory; establishing the total utility function of the power battery based on durability; establishing the total utility function of the fuel cell based on economy and durability; and obtaining the output power allocation of the fuel cell and the power battery within the predetermined future time period based on maximizing the total utility function of the power battery and the total utility function of the fuel cell and the energy demand trajectory.

[0009] Furthermore, the establishment of the total utility function of the power battery based on durability includes: establishing a utility function for the deviation between the output power and the average output power of the power battery; establishing a utility function for the power fluctuation of the power battery; and obtaining the total utility function of the power battery based on the weighted sum of the utility function for the deviation between the output power and the average output power and the utility function for the power fluctuation.

[0010] Furthermore, the establishment of the total utility function of the fuel cell based on economy and durability includes: establishing a utility function related to the economy of the fuel cell; establishing a utility function related to the durability of the fuel cell; and obtaining the total utility function of the fuel cell based on the weighted sum of the utility functions related to economy and durability.

[0011] Further, obtaining the output power allocation of the fuel cell and the power battery within the predetermined future time period based on maximizing the total utility function of the power battery and the total utility function of the fuel cell and the energy demand trajectory includes: transforming the bi-objective maximization function of the total utility function of the power battery and the total utility function of the fuel cell into a single-objective minimization function; solving the optimal solution of the single-objective minimization function under predetermined constraints to obtain the output power of the fuel cell and the power battery respectively, wherein the predetermined constraints include: each weight coefficient in the single-objective minimization function is in the range of 0 to 1, and the sum of the weight coefficients is equal to 1; the sum of the output power of the fuel cell and the power battery respectively satisfies the energy demand trajectory; and the output power of the fuel cell and the power battery is within their respective maximum ranges.

[0012] Furthermore, the step of predicting the heat load change trend of the vehicle within the predetermined future time period based on the output power distribution of the fuel cell and the power battery includes: constructing a dynamic heat load prediction model; and obtaining the heat load change trend of the vehicle within the predetermined future time period based on the dynamic heat load prediction model according to historical heat load data, meteorological characteristic data, the output power distribution of the fuel cell and the power battery within the predetermined future time period, and vehicle operating characteristics.

[0013] Furthermore, the thermal management control of the vehicle based on the heat load change trend within the predetermined future time period includes: controlling whether to trigger an advance regulation strategy based on the heat load change trend within the predetermined future time period, including: in the component cooling circuit, when it is predicted that the heat load of the component is in a continuous upward trend, increasing the speed of the cooling water pump and / or cooling fan in the cooling circuit in advance; when it is predicted that the heat load of the component is in a continuous downward trend, decreasing the speed of the cooling water pump and / or cooling fan in advance; in the waste heat utilization circuit, when it is predicted that the waste heat quality of the fuel cell is declining, turning on the heater in the power battery circuit in advance to heat the power battery, and simultaneously turning on the heater in the cabin heating circuit to ensure the cabin heating temperature; when it is predicted that the waste heat of the fuel cell continues to maintain a high quality, reducing or turning off the heater in the power battery circuit and the cabin heating circuit in advance.

[0014] Furthermore, the thermal management control of the vehicle based on the heat load change trend within the predetermined future time period includes: when the waste heat of the fuel cell is at a high grade, controlling the waste heat of the fuel cell to heat the circulating water of the cab heating circuit through a first heat exchanger; when the waste heat of the fuel cell is at a medium grade, controlling the waste heat of the fuel cell to preheat the power battery through a second heat exchanger; and when the waste heat of the fuel cell is at a low grade, controlling the waste heat of the fuel cell to preheat hydrogen through a third heat exchanger, wherein the fuel cell uses hydrogen as fuel, the waste heat temperature of the fuel cell at a high grade is greater than that of the fuel cell at a medium grade, and the waste heat temperature of the fuel cell at a medium grade is greater than that of the fuel cell at a low grade.

[0015] Furthermore, the thermal management control of the vehicle based on the thermal load change trend within the predetermined future time period includes: controlling whether to trigger a hysteresis compensation strategy based on the thermal load change trend and the current thermal load value, including: when the thermal load of the component is predicted to be in a stable trend, fine-tuning the speed of the cooling water pump and / or cooling fan in the cooling circuit based on the difference between the current thermal load value and the target value.

[0016] Another aspect of this application provides a coordinated control system for vehicle energy management and thermal management. The coordinated control system includes a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the steps of the coordinated control method for vehicle energy management and thermal management as described above.

[0017] Another aspect of this application provides a vehicle. The vehicle includes a coordinated control system for vehicle energy management and thermal management as described above.

[0018] The vehicle energy management and thermal management coordinated control method, system and vehicle of one or more embodiments of this application can obtain the vehicle speed change trend within a predetermined time period by predicting the vehicle speed when the vehicle is detected to be entering a short-term operating condition. In addition, the output power distribution and heat load change trend of the fuel cell and power battery of the vehicle within the predetermined time period can be obtained. In this way, the coordinated control of energy management and thermal management of the vehicle can be performed in advance, so that energy management and thermal management can be optimized. Attached Figure Description

[0019] Figure 1 This is a flowchart of a vehicle energy management and thermal management coordinated control method according to an embodiment of this application.

[0020] Figure 2 This is a schematic diagram of a distance-vehicle speed matrix according to an embodiment of this application.

[0021] Figure 3 This is a schematic diagram illustrating the state transition of vehicle speed according to an embodiment of this application.

[0022] Figure 4 This is a schematic diagram of a dynamic heat load prediction model based on the XGBoost algorithm according to an embodiment of this application.

[0023] Figure 5 This is a topology diagram of a vehicle thermal network according to an embodiment of this application.

[0024] Figure 6 This is a schematic diagram of advanced regulation according to one embodiment of this application.

[0025] Figure 7 This is a schematic diagram of hysteresis compensation according to one embodiment of this application.

[0026] Figure 8 This is a schematic block diagram of a vehicle energy management and thermal management coordinated control system according to an embodiment of this application. Detailed Implementation

[0027] 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 numerals 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 consistent with some aspects of this application as detailed in the appended claims.

[0028] The following detailed description, with reference to the accompanying drawings, outlines various embodiments of the vehicle energy management and thermal management coordinated control method, system, and vehicle of this application. Unless otherwise specified, the features of the following embodiments and implementations can be combined with each other.

[0029] This application provides a method for the coordinated control of vehicle energy management and thermal management. The vehicle is a fuel cell vehicle, which includes a fuel cell and a power battery. Figure 1 A flowchart illustrating a method for coordinated control of vehicle energy management and thermal management according to an embodiment of this application is provided. Figure 1 As shown, a method for coordinated control of vehicle energy management and thermal management according to an embodiment of this application may include steps S1 and S2.

[0030] In step S1, the current operating condition of the vehicle is identified.

[0031] In step S2, when the vehicle is identified as being in a short-term operating condition, the vehicle can be controlled according to the short-term operating condition control mode.

[0032] Short-term operating conditions refer to continuous operating conditions under a specific load, operating mode, or state for a predetermined period of time, which are different from instantaneous operating conditions and long-term operating conditions.

[0033] Step S2, which controls the vehicle according to the short-term operating condition control mode, may include steps S21 to S24.

[0034] In step S21, the trend of vehicle speed change over a predetermined period of time in the future is predicted.

[0035] Under short-term operating conditions, real-time map navigation, speed limits, and other information can be combined to predict the vehicle speed change trend within a predetermined time period (e.g., 30 seconds) using a Long Short-Term Memory (LSTM) artificial neural network algorithm, providing a basis for proactive regulation of energy management and thermal management.

[0036] In step S22, the output power distribution of the fuel cell and the power battery over a predetermined period of time in the future can be calculated based on the vehicle speed change trend.

[0037] In step S23, the trend of heat load change of the vehicle in the future within a predetermined period of time can be predicted based on the output power distribution of the fuel cell and the power battery.

[0038] In step S24, energy management control of the vehicle can be performed based on the output power distribution of the fuel cell and the power battery within a predetermined future time period, and thermal management control of the vehicle can be performed based on the heat load change trend within a predetermined future time period.

[0039] The vehicle energy management and thermal management coordinated control method of this application can obtain the vehicle speed change trend within a predetermined time period by predicting the vehicle speed when the vehicle enters a short-term operating condition. It can then obtain the output power distribution and thermal load change trend of the fuel cell and power battery within the predetermined time period. This allows for coordinated control of energy management and thermal management of the vehicle in advance, thereby achieving better energy management and thermal management.

[0040] In some embodiments, the coordinated control method for vehicle energy management and thermal management of this application may include step S3.

[0041] In step S3, when the vehicle is detected to be entering a momentary operating condition, the short-term operating condition control mode is exited and the vehicle speed is adjusted in real time.

[0042] This application can use the K-Means clustering algorithm to classify instantaneous operating conditions such as "high-speed overtaking, hill climbing, and emergency braking" in real time based on current vehicle information, so as to adjust the vehicle speed instantly.

[0043] This application can construct a multi-source data acquisition system integrating "real vehicle information + map data + big data": real-time acquisition of dynamic parameters such as vehicle speed and acceleration; access to information such as slope and speed limit from ADAS (Advanced Driver Assistance Systems) maps to establish a vehicle-specific operating condition perception database. Based on feature extraction results, a hierarchical perception system of "instantaneous operating condition classification - short-term operating condition prediction" is constructed.

[0044] In some embodiments, the calculation of the output power distribution of the fuel cell and the power battery over a predetermined period of time based on the vehicle speed change trend in step S22 may further include steps S221 and S222.

[0045] In step S221, vehicle speed planning is performed based on the vehicle speed change trend to obtain the energy-optimal planned vehicle speed trajectory.

[0046] The following will combine Figure 2 and Figure 3 This section will detail how to plan vehicle speed based on speed change trends to obtain the most energy-efficient planned speed trajectory.

[0047] The vehicle's maximum acceleration is obtained through testing or by considering factors such as the motor, vehicle weight, and maximum braking torque. a inc and maximum deceleration a dec Obtain the vehicle's maximum speed limit. V max (Unit: km / h).

[0048] Obtain the future booking distance using map and navigation information. s Road surface slope change information (unit: km) i Speed ​​limit information v lim Traffic congestion.

[0049] Distance s Divided into equal parts N Segments, each segment is △ s = s / N The maximum speed limit of the vehicle body. V max Divided into equal parts x Section, speed of each section is V max / x .

[0050] Calculate the initial velocity as V 0 for each segment △ sThe maximum change in vehicle speed and the maximum decrease in vehicle speed within the range. Specifically, the maximum increase in vehicle speed. Maximum reduction in vehicle speed .

[0051] This allows the formation of a distance-speed matrix. Figure 2 A schematic diagram of a distance-vehicle speed matrix according to an embodiment of this application is shown.

[0052] Calculate the predetermined distance based on the vehicle dynamics equations. s Internal vehicle driving energy consumption: First, calculate the vehicle driving force. F drv : F drv =F f +F w +F i +F a (1) in, F f For vehicle rolling resistance, F w For vehicle wind resistance, F i For vehicle slope resistance, F a This provides resistance to vehicle acceleration.

[0053] Then, based on the vehicle's driving force F drv Computation drives energy consumption E drv : E drv = ∫ F drv dt (2) Calculate the electric motor power of a vehicle that can recover energy F motbrk = f ( V,Brk The electric motor's power is usually the current vehicle speed. V and brake pedal opening Brk The function.

[0054] Then, the regenerative braking energy is calculated based on the vehicle's electric motor power and the energy recovery capacity. E brk : E brk= ∫| F motbrk | dt (3) Define state variables x ( k ) and control variables u ( k ).

[0055] Select vehicle longitudinal force F As a system control variable, the vehicle longitudinal force F Including vehicle driving force F drv and vehicle braking force F brk Vehicle braking force F brk Including brake pad braking force F mecbrk and electric motor power F motbrk Longitudinal force of the vehicle during driving. F=F drv longitudinal force of the vehicle during braking F=F brk speed V As system state variables, as shown below: x ( k )= V ( k (4) u ( k )= F ( k (5) The state transition equation is defined as follows: x ( k+ 1)= f ( x ( k ) ,u ( k ))(6) in, f Here is the state transition equation.

[0056] Construct the objective function as follows: (7) in, J This represents the total energy consumption during the driving process.

[0057] The parameter constraints are as follows: 0≤ V ≤ V max (8) 0 ≤ F drv ≤ F motmax (9) F motmin ≤ F motbrk ≤ 0 (10) SOC min ≤ SOC ≤ SOC max (11) in, V For vehicle speed, F motmin 、F motmax These represent the minimum braking force (negative value) and maximum driving force of the drive motor, respectively. SOC min , SOC max These are the lower and upper limits of the SOC (State of Charge) for power batteries, respectively.

[0058] Discretize the control variables and state variables.

[0059] Speed V and vehicle longitudinal force F The discrete state sequence and discrete control sequence are as follows: V =[0, 0 + x , 0 + 2 x , ..., V max (12) F =[ F motmin , F motmin + λ , F motmin +2 λ , ..., F motmax (13) in, x , λ These represent the discrete intervals of the state variables and the discrete intervals of the control variables, respectively.

[0060] Figure 3 A schematic diagram illustrating the state transition of vehicle speed according to an embodiment of this application is shown. Figure 3 As shown, with the first △ s、 Initial speed from V(0) changes to V Taking vehicle speed planning as an example (1), the vehicle speed changes from 00(0) to V (1) There are a total of x +1 option, which can be calculated based on maximum acceleration and maximum deceleration. .like V (1) If the change path does not exist beyond this range, then there is no need to calculate the energy change under this path. If V (1) If the range is not exceeded, calculate the change in driving force of the vehicle speed from 0(0) to V(1) (the acceleration is considered constant during the state transition), and then calculate the change from 00(0) in state 0 to state 1 according to formulas (1)(2)(3). V x (1) The energy change during the transfer is denoted as... E 0-x (1) and save, where 0- x This indicates that the vehicle speed changes from 0 to... x When the vehicle speed changes from state 0 V 2(0) to state 1 V x (1) During the transfer, the change in energy is recorded as follows: E 2-x (1).

[0061] 00(1) of state 1 to state 2 V x (2) During the transition, the method is the same as the transition from state 0 to state 1, and the energy change is recorded as follows: E 0-x (2), and so on.

[0062] Based on the trend of vehicle speed change, with the goal of minimizing the total energy consumption during the driving process, the dynamic programming algorithm and / or forward enumeration method are used to traverse the values ​​of the control variables corresponding to each discrete state variable during the state transition, so as to finally obtain the energy-optimal planned vehicle speed trajectory.

[0063] For example, taking the dynamic programming algorithm as an example, when at the th... N During the phase, first traverse from the first... N -1 stage transition to the next N Energy change corresponding to each state variable in a stage E With the first N -1 stage transition to the next N stage V 2( N For example, traversing the first... N -1 phase all transferred to the 1st phase N Possible stages and calculation of energy changes E ,like Figure 3As shown.

[0064] When in the first N Similarly, in stage -1, first traverse from the... N -2 phase transition to the next N- Energy change corresponding to each state variable in stage 1 E And save it.

[0065] When in the first k (1≤k≤ N -2) In stage 2, the same applies as in stage 3. N The method of stage -1 is used to perform reverse calculations until stage 1 is completed. At this point, the optimal control variables that determine the total energy consumption for all stages of the entire driving process can be obtained. F And the optimal planned vehicle speed trajectory.

[0066] After obtaining the planned vehicle speed trajectory with the optimal total energy consumption during the driving process, in step S222, the output power distribution of the fuel cell and power battery within a predetermined time period in the future can be calculated based on the planned vehicle speed trajectory.

[0067] This application enables the development of a predictive, hierarchical energy management strategy based on Model Predictive Control (MPC). The upper-layer algorithm references information from data acquisition and operational condition perception databases. If the vehicle is currently in a transient operational condition such as overtaking or climbing, it executes the current instantaneous speed request. If the vehicle is currently in a short-term operational condition, it executes the energy-optimal planned speed trajectory. Speed ​​control is primarily achieved through motor drive, braking force, or mechanical braking force. The upper-layer algorithm determines the planned speed trajectory, thus determining the energy demand trajectory. The lower-layer algorithm, based on the vehicle dynamics model and energy system model, considers component durability and overall vehicle economy, utilizing forward and / or inverse algorithms to plan the power allocation of energy components.

[0068] The following section will detail how to calculate the output power distribution of fuel cells and power batteries over a predetermined time period based on the planned vehicle speed trajectory.

[0069] In some embodiments, step S222, which calculates the output power distribution of the fuel cell and the power battery within a predetermined time period based on the planned vehicle speed trajectory, may further include steps S2221 to S2223.

[0070] In step S2221, the energy demand trajectory within the future predetermined time period can be determined based on the planned vehicle speed trajectory within the future predetermined time period.

[0071] In step S2222, the total utility function of the power battery is established based on durability; the total utility function of the fuel cell is established based on economy and durability.

[0072] When the output power of the power battery P bat Approaching the average output power of power batteries P ave Furthermore, the smaller the fluctuation in the power battery current, the lower the voltage degradation of each individual cell. Since the voltage of a single power battery cell can characterize its durability, we first establish the utility function of the deviation between the power battery's output power and its average output power, as well as the utility function of the power battery's power fluctuation. Then, we can obtain the total utility function of the power battery based on the weighted sum of the utility functions of the output power deviation and the power fluctuation.

[0073] The total utility function of a power battery based on durability can be expressed as follows: (14) (15) Fuel cells have a peak efficiency point; their economic efficiency is optimal when the fuel cell output power approaches this point. Furthermore, the smaller the variation in fuel cell output power, the lower its performance degradation and the higher its durability. Therefore, firstly, we establish utility functions related to the fuel cell's economic efficiency and durability. Then, based on the weighted sum of the economic and durability utility functions, we obtain the total utility function of the fuel cell.

[0074] The utility function of a fuel cell, considering both economic efficiency and durability, can be expressed as follows: (16) (17) The calculation method for the parameters in the utility function is shown in formula (5).

[0075] (18) in, U bat This is the total utility function of the power battery; U ave It is the utility function of the power battery that takes into account the deviation between the output power and the average output power; U dif It is the utility function of the power battery considering power fluctuations; ω ave , ω dif These are the weighting coefficients; P ave This represents the average output power of the power battery, measured in kW. P bat This represents the current output power of the power battery, in kW.P batl The power output of the battery in one second, in kW; P batmax This refers to the maximum output power of the power battery, measured in kW. U fc Let this be the total utility function of the fuel cell; U eco Let be the utility function related to the economics of fuel cells; U dua This is a utility function related to the durability of the fuel cell; ω eco , ω dua These are the weighting coefficients; P fcmax This represents the maximum output power of the fuel cell, measured in kW. P fctop This represents the output power corresponding to the highest efficiency of the fuel cell, in kW. P fc This represents the current output power of the fuel cell, in kW. P fcl This represents the output power of the fuel cell in one second, measured in kW. P difmax This represents the maximum variable load factor of the fuel cell, expressed in kW / s. a , b , c , d Used as constraints respectively U ave , U dif , U eco , U dua Greater than 0 and less than 1.

[0076] In step S2223, the output power distribution of the fuel cell and the power battery within a predetermined time period is obtained based on the maximization of the total utility function of the power battery and the total utility function of the fuel cell and the energy demand trajectory.

[0077] When the utility function is maximized, the economy and durability of the fuel cell, as well as the durability of the power battery, will be maximized. The form of maximizing the total utility function of the fuel cell and the power battery is shown below: (19) Since the solutions to the bi-objective maximization functions of the total utility function of the power battery and the total utility function of the fuel cell are not unique, it is ultimately difficult to solve for the output power of the fuel cell and the power battery. Therefore, in order to simplify the controller calculation process and obtain a unique solution, this application transforms the bi-objective maximization function into a single-objective minimization function, as shown below: (20) The single-objective minimization function must also satisfy the following predetermined constraints: the weight coefficients in the single-objective minimization function are in the range of 0 to 1, and the sum of the weight coefficients is 1; the sum of the output power of the fuel cell and the output power of the power battery satisfies the power demand given by the energy demand trajectory. P req The output power of the fuel cell and the power battery must be within their respective maximum ranges, as shown in the following formula: (twenty one) Formula (20) is essentially a quadratic equation with two unknowns, and it must also satisfy the constraints of Formula (21). The optimal solution to the single-objective minimization function in Formula (20) can be obtained by, for example, using the KKT (Karush-Kuhn-Tucker Conditions), thus ultimately yielding the output power of the fuel cell and the power battery. The KKT condition is a generalized Lagrange multiplier method that can transform a constrained optimization problem into an unconstrained optimization problem. Using the KKT condition, the equality and inequality constraints in Formula (21) and the single-objective minimization function in Formula (20) are combined into a new optimization function, the final form of which is shown below: (twenty two) in, L It is a Lagrange function; h It is a Lagrange multiplier.

[0078] make: (twenty three) (twenty four) (25) The extreme points can be obtained by solving equations (23) to (25) simultaneously, as shown below: (26) in, ω ave , ω dif , ω eco , ωdua The specific values ​​of the calibration data can be determined through offline calibration optimization.

[0079] In some embodiments, the prediction of the vehicle's heat load change trend over a predetermined period of time based on the output power distribution of the fuel cell and the power battery in step S23 may include steps S231 and S232.

[0080] In step S231, a dynamic prediction model for heat load is constructed.

[0081] For example, a dynamic prediction model of heat load can be built based on the XGBoost algorithm.

[0082] In step S232, based on historical heat load data, meteorological characteristic data, the output power distribution of fuel cells and power batteries within a predetermined future time period, and vehicle operating characteristics, the heat load change trend of the vehicle within a predetermined future time period is obtained based on the heat load dynamic prediction model.

[0083] Figure 4 A schematic diagram illustrating a dynamic heat load prediction model based on the XGBoost algorithm according to an embodiment of this application is shown. Figure 4 As shown, the dynamic heat load prediction model built based on the XGBoost algorithm includes a data input layer, a feature engineering layer, a model training layer, and a prediction output and evaluation layer. The output of each layer serves as the input for the next, collectively supporting accurate dynamic prediction of heat load. The data input layer receives historical heat load data (e.g., heat load data from the previous 0.1h / 0.5h), meteorological characteristic data (e.g., outdoor temperature / humidity / wind speed), and power distribution of energy components (i.e., fuel cells and power batteries) and vehicle operating characteristics (e.g., component temperature / power / vehicle speed) within a predetermined timeframe (e.g., 30s). The feature engineering layer is responsible for data cleaning (missing value imputation, outlier removal, etc.), feature construction, feature selection, and data preprocessing (feature standardization / normalization / feature encoding). The model training layer trains the prediction model based on the XGBoost algorithm, fitting the dynamic changes in heat load by integrating multiple decision trees. The prediction output and evaluation layer is used to output the short-term (e.g., 10s / 15s) heat load change trend and the long-term (e.g., 1min) heat load prediction results, and to evaluate the prediction performance of the dynamic heat load prediction model. Regression indicators (such as MAE (Mean Absolute Error), RMSE (Root Mean Squared Error), and MAPE (Mean Absolute Percentage Error)) are used to measure the error between the predicted value and the actual value, so as to verify whether the dynamic heat load prediction model meets the actual needs.

[0084] In some embodiments, step S24, which involves thermal management control of the vehicle based on the trend of heat load changes over a predetermined future period, may further include step S241.

[0085] In step S241, the decision to trigger the advance control strategy can be based on the trend of heat load changes within a predetermined time period in the future.

[0086] Figure 5 A topology diagram of the vehicle thermal network according to an embodiment of this application is disclosed. Combined with... Figure 5 As shown, the triggering of the proactive control strategy may include: in the component cooling circuit, when the heat load of the component is predicted to be on a continuous upward trend, the speed of the cooling water pumps 511, 512 and / or the cooling fan 501 in the cooling circuit is increased in advance; when the heat load of the component is predicted to be on a continuous downward trend, the speed of the cooling water pumps 511, 512 and / or the cooling fan 501 is reduced in advance; in the waste heat utilization circuit, when the waste heat quality of the fuel cell is predicted to decline, the heater in the power battery circuit (e.g., PTC heater 531) is turned on in advance to heat the power battery, ensuring that the power battery temperature remains within a suitable range, and the heater in the cab heating circuit (e.g., PTC heater 532) is turned on at the same time to ensure the cab heating temperature; when the waste heat of the fuel cell is predicted to remain at a high quality, the PTC heaters 531 and 532 in the power battery circuit and the cab heating circuit are reduced or turned off in advance, thereby reducing heating energy loss.

[0087] Figure 6 A schematic diagram illustrating one embodiment of the advance control of this application is shown. For example... Figure 6 As shown, at the current time k, the current system heat load status is collected. x ( k (such as fuel cell stack temperature) and current control inputs u ( k (e.g., the speed of cooling fan 501 and the speed of cooling water pumps 511 and 512, etc.), and input the heat load change data for a certain period of time in the prediction time domain with the corresponding reference target. R(k) (i.e., compared with pre-set thermal management targets) (such as the optimal operating temperature of the fuel cell stack), and the optimal control output for that time period in the prediction time domain is calculated by an optimization algorithm (such as Model Predictive Control, MPC). (For example, adjusting the coolant flow rate in advance by increasing the speed of cooling fan 501 and / or cooling water pumps 511 and 512, etc.), and outputting the optimal control within this time period. This process of prediction, calculation, and control is then repeated in the next time period, allowing for continuous and proactive regulation based on the future trend of heat load changes over a predetermined timeframe.

[0088] In some embodiments, step S24, which involves thermal management control of the vehicle based on the trend of heat load changes over a predetermined future period, may further include step S242.

[0089] In step S242, the hysteresis compensation strategy can be triggered based on the heat load change trend and the current heat load value.

[0090] The hysteresis compensation strategy includes: when the heat load of the component is predicted to be in a stable trend, the speed of the cooling water pumps 511, 512 and / or the cooling fan 501 in the cooling circuit can be finely adjusted based on the difference between the current heat load value and the target value.

[0091] Figure 7 A schematic diagram illustrating hysteresis compensation according to an embodiment of this application is shown. Figure 7 As shown, the disturbances in the system include measurable disturbances. d(k) and unpredictable disturbances w(k) Measurable disturbance d(k) For example, fuel cell power and vehicle speed (operating parameters that can be collected in advance and are directly related to changes in heat load); unmeasurable disturbances. w(k) Examples include sudden changes in ambient temperature and coolant leaks (interferences that cannot be accurately measured in advance). When a measurable disturbance is detected... d(k) The feedforward controller can calculate the advance control amount required to counteract the disturbance based on the thermal load model, and then directly add this control amount to the input control. u(k) In this way, the control input takes effect before the actual heat load increases (due to system lag), preventing the thermal state from deviating from the target. The system output will then be... y(k) System Status x(k) Feedback value and reference input R(k) Compare and output the deviation. e(k) The controller calculates additional control input based on the deviation e(k) and supplements it to the input control. u(k) In this process, closed-loop dynamic correction is used, taking into account unpredictable disturbances. w(k) Increased control margin to gradually eliminate deviations e(k) Ultimately, the system outputs... y(k) Approaching the reference target.

[0092] In some embodiments, step S24, which involves thermal management control of the vehicle based on the trend of heat load changes over a predetermined future period, may further include step S243.

[0093] In step S243, in conjunction with reference Figure 5As shown, when the waste heat from the fuel cell is at a high grade, it is controlled to heat the circulating water in the cab's heating circuit via the first heat exchanger 521; when the waste heat is at a medium grade, it is controlled to preheat the power battery via the second heat exchanger 522; and when the waste heat is at a low grade, it is controlled to preheat the hydrogen via a third heat exchanger (not shown) inside the fuel cell. The fuel cell uses hydrogen as fuel, and the waste heat temperature of the fuel cell at a high grade is higher than that of the fuel cell at a medium grade, and the waste heat temperature of the fuel cell at a medium grade is higher than that of the fuel cell at a low grade.

[0094] The collaborative control method for vehicle energy management and thermal management in this application can predict short-term vehicle speed change trends and further plan vehicle speed based on these trends to obtain the energy-optimal planned speed trajectory, thus providing a basis for energy management and thermal management. Regarding energy management, this application not only provides the current output power of the fuel cell and power battery but also predicts the output power distribution of the fuel cell and power battery in the short term, further providing a basis for thermal management solutions. Based on the output power distribution of the fuel cell and power battery in the short term, this application can further predict short-term heat load change trends and provide the optimal thermal management solution, proactively switching the fuel cell waste heat utilization path and / or adjusting the system's heat dissipation capacity, achieving collaborative control of vehicle energy management and thermal management, thereby optimizing vehicle energy management and thermal management.

[0095] This application also provides a coordinated control system for vehicle energy management and thermal management. Figure 8 A schematic block diagram of a vehicle energy management and thermal management coordinated control system 800 according to one embodiment of this application is shown. Figure 8 As shown, an embodiment of the vehicle energy management and thermal management coordinated control system 800 of this application includes a processor 801, an internal bus 802, a network interface 803, a memory 804, and a non-volatile memory 805, and may also include other hardware required for business operations. The processor 801 can read the corresponding computer program from the non-volatile memory 805 into the memory 804 and then run it to implement the steps of the vehicle energy management and thermal management coordinated control method as described above. Of course, in addition to the software implementation, this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0096] The vehicle energy management and thermal management coordinated control system 800 of this application can have similar beneficial technical effects to the vehicle energy management and thermal management coordinated control method described above, therefore, it will not be repeated here.

[0097] This application also provides a vehicle. The vehicle includes a vehicle energy management and thermal management coordinated control system 800 as described above.

[0098] The foregoing has provided a detailed description of the vehicle energy management and thermal management coordinated control method, system, and vehicle provided in the embodiments of this application. Specific examples have been used to illustrate the vehicle energy management and thermal management coordinated control method, system, and vehicle in the embodiments of this application. The descriptions of the embodiments above are only for helping to understand the core ideas of this application and are not intended to limit this application. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the spirit and principles of this application, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A method for coordinated control of vehicle energy management and thermal management, wherein the vehicle includes a fuel cell and a power battery, characterized in that: The method includes: Identify the vehicle's current operating condition; When the vehicle is detected to be in a short-term operating condition, the vehicle is controlled according to the short-term operating condition control mode. The short-term operating condition is a continuous operating condition that is in a specific load, operating mode, or state for a predetermined period of time. The control of the vehicle according to the short-term operating condition control mode includes: Predict the trend of vehicle speed changes over a predetermined period of time in the future; The output power distribution of the fuel cell and the power battery within the predetermined future time period is calculated based on the vehicle speed change trend. The heat load change trend of the vehicle in the future predetermined time period is predicted based on the output power distribution of the fuel cell and the power battery. The vehicle is energy managed and controlled based on the output power distribution of the fuel cell and the power battery within the predetermined future time period, and the vehicle is thermally managed and controlled based on the heat load change trend within the predetermined future time period.

2. The method as described in claim 1, characterized in that: The method further includes: When the system detects that the vehicle has entered a momentary operating condition, it exits the short-term operating condition control mode and adjusts the vehicle speed in real time.

3. The method as described in claim 1, characterized in that: The calculation of the output power distribution between the fuel cell and the power battery within the predetermined future time period based on the vehicle speed change trend includes: Based on the aforementioned vehicle speed change trend, vehicle speed planning is performed to obtain the energy-optimal planned vehicle speed trajectory. The output power distribution of the fuel cell and the power battery within the predetermined future time period is calculated based on the planned vehicle speed trajectory.

4. The method as described in claim 3, characterized in that: The process of planning vehicle speed based on the vehicle speed change trend to obtain the energy-optimal planned vehicle speed trajectory includes: Using the vehicle longitudinal force as the control variable and the vehicle speed as the state variable, a state transition equation is constructed. The vehicle longitudinal force includes the vehicle driving force and the vehicle braking force. Discretize the control variables and the state variables; Based on the vehicle speed change trend, with the goal of minimizing the total energy consumption during the driving process, the dynamic programming algorithm and / or forward enumeration method are used to traverse the values ​​of the control variables corresponding to each discrete state variable during state transitions, so as to finally obtain the energy-optimal planned vehicle speed trajectory.

5. The method as described in claim 3, characterized in that: The calculation of the output power distribution of the fuel cell and the power battery within the predetermined future time period based on the planned vehicle speed trajectory includes: The energy demand trajectory is determined based on the planned vehicle speed trajectory. Establish the total utility function of the power battery based on durability; The total utility function of fuel cells is established based on economic efficiency and durability. The output power distribution of the fuel cell and the power battery within the predetermined future time period is obtained by maximizing the total utility function of the power battery and the total utility function of the fuel cell, as well as the energy demand trajectory.

6. The method as described in claim 5, characterized in that: The overall utility function of the power battery based on durability includes: Establish a utility function for the deviation between the output power and the average output power of the power battery; Establish the utility function for the power fluctuation of the power battery; The total utility function of the power battery is obtained by weighting the utility function of the deviation between the output power and the average output power and the utility function of the power fluctuation.

7. The method as described in claim 5, characterized in that: The overall utility function for fuel cells, established based on economy and durability, includes: Establish the relevant economic utility function for the fuel cell; Establish a utility function related to the durability of the fuel cell; The total utility function of the fuel cell is obtained by weighting the utility function of economic efficiency and the utility function of durability.

8. The method as described in claim 5, characterized in that: The method of obtaining the output power distribution of the fuel cell and the power battery within the predetermined future time period based on maximizing the total utility function of the power battery and the total utility function of the fuel cell and the energy demand trajectory includes: The bi-objective maximization function of the total utility function of the power battery and the total utility function of the fuel cell is transformed into a single-objective minimization function; Under predetermined constraints, the optimal solution of the single-objective minimization function is obtained to determine the output power of the fuel cell and the power battery, respectively. The predetermined constraints include: each weight coefficient in the single-objective minimization function is in the range of 0 to 1, and the sum of the weight coefficients is equal to 1; the sum of the output power of the fuel cell and the power battery satisfies the energy demand trajectory; and the output power of the fuel cell and the power battery is within their respective maximum ranges.

9. The method as described in claim 1, characterized in that: The prediction of the vehicle's heat load change trend within the future predetermined time period based on the output power distribution of the fuel cell and the power battery includes: Construct a dynamic heat load prediction model; Based on historical heat load data, meteorological characteristic data, the output power distribution of the fuel cell and the power battery within the predetermined future time period, and vehicle operating characteristics, the heat load change trend of the vehicle within the predetermined future time period is obtained based on the heat load dynamic prediction model.

10. The method as described in claim 1, characterized in that: The thermal management control of the vehicle based on the heat load change trend within the predetermined future time period includes: Controlling whether to trigger an advance regulation strategy based on the heat load change trend within the predetermined future time period includes: In the component cooling circuit, when the heat load of the component is predicted to be on a continuous upward trend, the speed of the cooling water pump and / or cooling fan in the cooling circuit is increased in advance; when the heat load of the component is predicted to be on a continuous downward trend, the speed of the cooling water pump and / or cooling fan is reduced in advance. In the waste heat utilization circuit, when it is predicted that the waste heat quality of the fuel cell will decline, the heater in the power battery circuit will be turned on in advance to heat the power battery, and the heater in the cab heating circuit will be turned on at the same time to ensure the heating temperature of the cab; when it is predicted that the waste heat of the fuel cell will continue to maintain a high quality, the heater in the power battery circuit and the cab heating circuit will be reduced or turned off in advance.

11. The method as described in claim 1, characterized in that: The thermal management control of the vehicle based on the heat load change trend within the predetermined future time period includes: When the waste heat from the fuel cell is at a high level, the waste heat from the fuel cell is controlled to heat the circulating water in the cab heating circuit through the first heat exchanger. When the waste heat of the fuel cell is at a medium grade, the waste heat of the fuel cell is controlled to preheat the power battery through a second heat exchanger; When the waste heat of the fuel cell is at a low grade, the waste heat of the fuel cell is controlled to preheat hydrogen through a third heat exchanger. The fuel cell uses hydrogen as fuel. The waste heat temperature of the fuel cell at a high grade is higher than that of the fuel cell at a medium grade, and the waste heat temperature of the fuel cell at a medium grade is higher than that of the fuel cell at a low grade.

12. The method as described in claim 1, characterized in that: The thermal management control of the vehicle based on the heat load change trend within the predetermined future time period includes: Controlling whether to trigger a hysteresis compensation strategy based on the heat load change trend and the current heat load value includes: When the heat load of a component is predicted to be in a stable trend, the speed of the cooling water pump and / or cooling fan in the cooling circuit is finely adjusted based on the difference between the current heat load value and the target value.

13. A coordinated control system for vehicle energy management and thermal management, characterized in that: The system includes a memory, a processor, and a computer program stored in the memory, characterized in that the processor executes the computer program to implement the steps of the coordinated control method for vehicle energy management and thermal management as described in any one of claims 1 to 12.

14. A vehicle, characterized in that: This includes the coordinated control system for vehicle energy management and thermal management as described in claim 13.

Images