Control method and apparatus for thermal management system in vehicle, and vehicle

Abstract

A control method for a thermal management system in a vehicle, and a computer-readable storage medium, a control apparatus and a vehicle. The control method comprises: acquiring a plurality of control parameter groups, and a real-time operating condition of a vehicle at the current moment; on the basis of the real-time operating condition and the plurality of control parameter groups, predicting a plurality of target predicted values of the vehicle in a prediction time domain following the current moment, wherein each target predicted value is used for representing the energy consumption of a thermal management system of the vehicle under a corresponding control parameter group, and whether the temperature rise of a battery in the vehicle meets a temperature rise requirement; and in the prediction time domain, controlling the thermal management system on the basis of a control parameter group corresponding to the minimum target predicted value among the plurality of target predicted values, such that the energy consumption of the thermal management system in the prediction time domain is the minimum, and the temperature rise of the battery meets the temperature rise requirement. Thus, it is ensured that the energy consumption of the thermal management system in the prediction time domain is the minimum, and the temperature rise of the battery meets the temperature rise requirement.

Description

Control methods and devices for thermal management systems in vehicles, vehicles

[0001] Related applications

[0002] This invention claims priority to Chinese invention patent with patent application number 202411093978.7, application date August 9, 2024, entitled "Control method and device for thermal management system in vehicle, vehicle". Technical Field

[0003] This invention relates to the field of vehicle technology, and in particular to a control method and device for a thermal management system in a vehicle, and a vehicle thereof. Background Technology

[0004] In low-temperature environments, the thermal management system in a vehicle typically needs to heat the battery to extend its driving range. However, the energy consumption of the thermal management system can be high during the battery heating process. Summary of the Invention

[0005] This invention aims to at least partially solve one of the technical problems in related technologies. Therefore, a first objective of this invention is to provide a control method for a thermal management system in a vehicle that minimizes the energy consumption of the thermal management system within the prediction time domain while ensuring that the battery temperature rise meets the required temperature rise.

[0006] On the one hand, a control method for a thermal management system in a vehicle is provided, the method comprising:

[0007] Acquire multiple control parameter groups, as well as the vehicle's real-time operating status at the current moment;

[0008] Based on real-time operating conditions and multiple control parameter sets, multiple target prediction values ​​of the vehicle in the prediction time domain after the current moment are predicted. Each target prediction value is used to characterize the energy consumption of the vehicle's thermal management system under a corresponding control parameter set, and whether the temperature rise of the battery in the vehicle meets the temperature rise requirements.

[0009] Within the prediction time domain, the thermal management system is controlled based on the control parameter set corresponding to the smallest target prediction value among multiple target prediction values, so as to minimize the energy consumption of the thermal management system within the prediction time domain and ensure that the temperature rise of the battery meets the temperature rise requirements.

[0010] In some embodiments of the present invention, based on real-time operating conditions and multiple control parameter sets, multiple target predicted values ​​of the vehicle in the prediction time domain after the current moment are predicted, including:

[0011] For each set of control parameters, predict the first energy consumption of the thermal management system in the prediction time domain based on the set of control parameters.

[0012] The temperature rise demand evaluation value is used for characterizing whether the temperature rise of the battery meets the temperature rise demand;

[0013] The target prediction value is determined based on the first energy consumption prediction value and the temperature rise demand evaluation value.

[0014] The target prediction value is positively correlated with the first energy consumption prediction value and the temperature rise demand evaluation value.

[0015] In some embodiments of the present application, the prediction time domain includes a plurality of prediction time points, and each control parameter group includes control parameters at each prediction time point. The first energy consumption prediction value of the thermal management system in the prediction time domain is predicted based on the control parameter group, including:

[0016] For each prediction time point, the instantaneous energy consumption prediction value of the thermal management system at the prediction time point is predicted based on the control parameters at the prediction time point.

[0017] The first energy consumption prediction value of the thermal management system in the prediction time domain is predicted based on the sum of the plurality of instantaneous energy consumption prediction values.

[0018] In some embodiments of the present application, the instantaneous energy consumption prediction value of the thermal management system at the prediction time point is predicted based on the control parameters at the prediction time point, including:

[0019] The state parameters of the thermal management system under the control parameters are predicted based on the control parameters at the prediction time point.

[0020] The instantaneous energy consumption prediction value of the thermal management system at the prediction time point is predicted based on the control parameters and the state parameters.

[0021] In some embodiments of the present application, the thermal management system includes at least one of the following heat exchange subsystems: an electric drive heat exchange subsystem, an air conditioning subsystem and a battery heat exchange subsystem.

[0022] The state parameters are used to reflect the running state of the running components in the heat exchange subsystem.

[0023] The control parameters are used to adjust the running state of the running components.

[0024] In some embodiments of the present application, in the case where the thermal management system includes the electric drive heat exchange subsystem, the state parameters include at least one of the power of the pump, the ambient temperature, the fluid temperature, the temperature of the electric control and the temperature of the motor; and the control parameters include the torque of the motor, the rotating speed of the pump and the rotating speed of the fan.

[0025] In the case where the thermal management system comprises an air conditioning subsystem, the state parameters comprise at least one of an inlet pressure of the compressor, an outlet pressure of the compressor, a temperature of the heat exchanger, a vehicle speed, an ambient temperature, a temperature of the passenger compartment, an outlet temperature of the evaporator, and an outlet temperature of the condenser; and the control parameters comprise a rotating speed of the compressor and an opening degree of the first valve.

[0026] In the case where the thermal management system comprises a battery heat exchange subsystem, the state parameters comprise at least one of a vehicle speed, an ambient temperature, a temperature of the battery, an inlet heat exchange working medium temperature of the battery, an outlet refrigerant temperature of the battery, and a heat exchange power of the battery heat exchanger; and the control parameters comprise an opening degree of the second valve.

[0027] In some embodiments of the present application, based on the real-time working condition and the control parameter group, a temperature rise demand evaluation value of the battery in a prediction time domain is predicted, comprising:

[0028] predicting a battery demand temperature of the battery in the prediction time domain based on the real-time working condition and the control parameter group;

[0029] predicting a battery prediction temperature of the battery in the prediction time domain based on the control parameter group;

[0030] predicting a temperature rise demand evaluation value of the battery in the prediction time domain based on the battery demand temperature and the battery prediction temperature.

[0031] In some embodiments of the present application, in the case where the battery prediction temperature is greater than or equal to the battery demand temperature, the temperature rise demand evaluation value is a preset value;

[0032] In the case where the battery prediction temperature is less than the battery demand temperature, the temperature rise demand evaluation value is determined based on a product of a square value of a target difference value and a weight coefficient;

[0033] wherein the target difference value is a difference between the battery demand temperature and the battery prediction temperature, and the preset value is less than the product.

[0034] In some embodiments of the present application, the prediction time domain comprises a plurality of prediction time points, and each control parameter group comprises control parameters at each prediction time point; predicting the battery prediction temperature of the battery in the prediction time domain based on the control parameter group, comprising:

[0035] inputting the control parameters of a target prediction time point in the plurality of prediction time points into a digital twin model of the thermal management system to obtain the battery prediction temperature of the battery in the prediction time domain;

[0036] wherein the target prediction time point is before a last prediction time point in the plurality of prediction time points and adjacent to the last prediction time point.

[0037] In some embodiments of the present application, predicting the battery demand temperature of the battery in the prediction time domain based on the real-time working condition and the control parameter group, comprising:

[0038] determining the vehicle demand power of the vehicle in the prediction time domain based on the real-time working condition;

[0039] predicting the predicted SOC value of the battery in the prediction time domain based on the real-time working condition, the control parameter group and the actual SOC value of the battery at the current time;

[0040] predicting the battery demand temperature of the battery in the prediction time domain based on the vehicle demand power and the predicted SOC value.

[0041] In some embodiments of the present application, the determination of the vehicle demand power of the vehicle in the prediction time domain based on the real-time working condition comprises:

[0042] predicting the target working condition of the vehicle in the prediction time domain based on the real-time working condition;

[0043] determining the vehicle demand power of the vehicle based on the target working condition.

[0044] In some embodiments of the present application, the determination of the vehicle demand power of the vehicle based on the target working condition comprises:

[0045] determining the calibration power corresponding to the target working condition from the correspondence between the working condition and the power;

[0046] determining the vehicle demand power of the vehicle based on the calibration power.

[0047] In some embodiments of the present application, the determination of the vehicle demand power of the vehicle based on the calibration power comprises:

[0048] determining the vehicle demand power of the vehicle based on the sum of the calibration power and the preset power.

[0049] In some embodiments of the present application, the prediction of the predicted SOC value of the battery in the prediction time domain based on the real-time working condition, the control parameter group and the actual SOC value of the battery at the current time comprises:

[0050] predicting a second energy consumption prediction value of the vehicle in the prediction time domain based on the real-time working condition and the control parameter group;

[0051] determining the predicted SOC value of the battery in the prediction time domain based on the difference between the actual SOC value and the target ratio value;

[0052] The target ratio value is the ratio of the second energy consumption prediction value to the rated total energy of the battery.

[0053] In some embodiments of the present application, the prediction of the second energy consumption prediction value of the vehicle in the prediction time domain based on the real-time working condition and the control parameter group comprises:

[0054] predict a third energy consumption prediction value of the electric drive system of the vehicle in the prediction time domain based on the real-time working condition;

[0055] determine a second energy consumption prediction value of the vehicle in the prediction time domain based on a sum of the first energy consumption prediction value and the third energy consumption prediction value.

[0056] In another aspect, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the control method of the thermal management system in the vehicle.

[0057] In yet another aspect, a control device of a thermal management system in a vehicle is provided, and the device comprises:

[0058] an acquisition module configured to acquire a plurality of control parameter groups and a real-time working condition of the vehicle at a current time;

[0059] a prediction module configured to predict a plurality of target prediction values of the vehicle in a prediction time domain after the current time according to the real-time working condition and the plurality of control parameter groups, each target prediction value being used to represent whether an energy consumption of the thermal management system and a temperature rise of a battery in the vehicle satisfy a temperature rise requirement under a corresponding one of the control parameter groups;

[0060] a control module configured to control the thermal management system according to a control parameter group corresponding to a smallest target prediction value in the plurality of target prediction values in the prediction time domain, so as to make the energy consumption of the thermal management system in the prediction time domain be the lowest and the temperature rise of the battery satisfy the temperature rise requirement.

[0061] In still another aspect, a vehicle is provided, and the vehicle comprises the control device of the thermal management system in the vehicle.

[0062] In summary, the embodiments of the present application provide a control method and device of a thermal management system in a vehicle and the vehicle, and in the method, after a controller acquires a plurality of control parameter groups and a real-time working condition of the vehicle at a current time, the controller can predict a plurality of target prediction values of the vehicle in a prediction time domain after the current time according to the real-time working condition and the plurality of control parameter groups, each target prediction value being used to represent whether an energy consumption of the thermal management system and a temperature rise of a battery in the vehicle satisfy a temperature rise requirement under a corresponding one of the control parameter groups. Since the thermal management system is controlled according to a control parameter group corresponding to a smallest target prediction value in the plurality of target prediction values in the prediction time domain, the energy consumption of the thermal management system in the prediction time domain can be made the lowest and the temperature rise of the battery can satisfy the temperature rise requirement, thereby ensuring the energy consumption of the thermal management system in the prediction time domain to be the lowest under the condition that the battery has a long battery life.

[0063] Additional aspects and advantages of the present application will be given in part in the following description, become apparent from the following description, or be understood by practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0064] Fig. 1 is a flow chart of a control method of a thermal management system in a vehicle according to an embodiment of the present application;

[0065] Fig. 2 is a flow chart of a control method of a thermal management system in a vehicle according to another embodiment of the present application;

[0066] Fig. 3 is a schematic diagram of a digital twin model of a thermal management system according to an embodiment of the present application;

[0067] Fig. 4 is a schematic diagram of a working condition prediction model according to an embodiment of the present application;

[0068] Fig. 5 is a schematic diagram of the relationship between the whole vehicle demand power, the predicted battery SOC value and the battery target temperature according to an embodiment of the present application;

[0069] Fig. 6 is a schematic diagram of a structure of a thermal management system according to an embodiment of the present application;

[0070] Fig. 7 is a block diagram of a control device of a thermal management system in a vehicle according to an embodiment of the present application;

[0071] Fig. 8 is a block diagram of a structure of a vehicle according to an embodiment of the present application. DETAILED DESCRIPTION

[0072] Embodiments of the present application are described in detail below with reference to the accompanying drawings, in which like or similar elements or elements having the same or similar functions are denoted by the same reference numerals throughout the drawings. The embodiments described below by reference to the accompanying drawings are exemplary and are intended to explain the present application, and should not be understood as limiting the present application.

[0073] The control method and device of a thermal management system in a vehicle and the vehicle according to an embodiment of the present application are described below with reference to the accompanying drawings.

[0074] Fig. 1 is a flow chart of a control method of a thermal management system in a vehicle according to an embodiment of the present application, which is applied to a controller in a vehicle, as shown in Fig. 1, the method comprises the following steps:

[0075] S10, obtaining a plurality of control parameter groups and a real-time working condition of the vehicle at the current time.

[0076] The controller can obtain a plurality of control parameter groups and a real-time working condition of the vehicle at the current time.

[0077] S20, predicting a plurality of target prediction values in a prediction time domain after the current time of the vehicle according to the real-time working condition and the plurality of control parameter groups.

[0078] After obtaining the plurality of control parameter groups and the real-time working condition of the vehicle at the current time, the controller can predict, according to the real-time working condition and the plurality of control parameter groups, a plurality of target prediction values of the vehicle in a prediction time domain after the current time, wherein each target prediction value is used to represent whether the temperature rise of the battery in the vehicle and the energy consumption of the thermal management system of the vehicle under a corresponding one of the control parameter groups meet the temperature rise requirement.

[0079] S30, in the prediction time domain, the thermal management system is controlled according to the control parameter group corresponding to the smallest target prediction value in the plurality of target prediction values, so that the energy consumption of the thermal management system in the prediction time domain is the lowest, and the temperature rise of the battery meets the temperature rise requirement.

[0080] After the controller predicts, according to the real-time working condition and the plurality of control parameter groups, the plurality of target prediction values of the vehicle in the prediction time domain after the current time, the controller can control, in the prediction time domain, the thermal management system according to the control parameter group corresponding to the smallest target prediction value in the plurality of target prediction values, so that the energy consumption of the thermal management system in the prediction time domain is the lowest, and the temperature rise of the battery meets the temperature rise requirement.

[0081] In summary, the embodiment of the present application provides a control method of a thermal management system in a vehicle. After obtaining the plurality of control parameter groups and the real-time working condition of the vehicle at the current time, the controller can predict, according to the real-time working condition and the plurality of control parameter groups, a plurality of target prediction values of the vehicle in a prediction time domain after the current time, wherein each target prediction value is used to represent whether the temperature rise of the battery in the vehicle and the energy consumption of the thermal management system of the vehicle under a corresponding one of the control parameter groups meet the temperature rise requirement. Since the thermal management system is controlled according to the control parameter group corresponding to the smallest target prediction value in the plurality of target prediction values in the prediction time domain, the energy consumption of the thermal management system in the prediction time domain can be the lowest, and the temperature rise of the battery meets the temperature rise requirement, thereby ensuring that the energy consumption of the thermal management system in the prediction time domain is the lowest under the condition that the battery has a long endurance time.

[0082] In some embodiments of the present application, the real-time working condition can be represented by the running parameters of the vehicle at the current time. Optionally, the running parameters representing the real-time working condition can include: an average driving speed p1, a maximum driving speed p2, a standard deviation of the speed p3, a percentage of the speed in a speed range of 0-30 kilometers per hour (km / h) p4, a percentage of the speed in a speed range of 30-70 km / h p5, a percentage of the average driving speed p1 in a speed range of 70-120 km / h p6, a percentage of the speed greater than 120 km / h p7, an average acceleration p8, a maximum acceleration p9, a standard deviation of the acceleration p 10at least one of: a percentage p of accelerations located in an acceleration range 0-1.0 meter per second squared (m / s 2 ) per second squared (m / s 11 ) per second squared (m / s 2 ) per second squared (m / s 12 ) per second squared (m / s 2 ) per second squared (m / s 13 ) per second squared (m / s 14 ) per second squared (m / s 15 ) per second squared (m / s 16 .

[0083] wherein the percentage of vehicle speeds located in the vehicle speed range refers to a ratio of a first number to a total number of a plurality of historical time points in a historical period. The first number is a number of vehicle speeds of the vehicle located in the vehicle speed range at the plurality of historical time points, and the historical period is a period located before the current time point. The vehicle speed at each historical time point refers to an instantaneous speed of the vehicle at the historical time point. The percentage of accelerations located in the acceleration range refers to a ratio of a second number to the total number. The second number is a number of accelerations of the vehicle located in the acceleration range at the plurality of historical time points.

[0084] In some embodiments of the present application, as shown in FIG. 2, the controller can predict a plurality of target prediction values of the vehicle in a prediction time domain after the current time point according to the real-time working condition and a plurality of control parameter groups, which can comprise the following steps:

[0085] S201, for each control parameter group, predicting a first energy consumption prediction value of the thermal management system in the prediction time domain based on the control parameter group.

[0086] For each control parameter group, the controller can predict a first energy consumption prediction value of the thermal management system in the prediction time domain based on the control parameter group, and the first energy consumption prediction value is used to represent the energy consumption of the thermal management system under the control parameter group. The thermal management system can comprise at least one of the following heat exchange subsystems: an electric drive heat exchange subsystem, an air conditioning subsystem, and a battery heat exchange subsystem.

[0087] S202, predicting a temperature rise demand evaluation value of the battery in the prediction time domain based on the real-time working condition and the control parameter group.

[0088] For each control parameter group, after the controller predicts a first energy consumption prediction value of the thermal management system in the prediction time domain based on the control parameter group, the controller can predict a temperature rise demand evaluation value of the battery in the prediction time domain based on the real-time working condition and the control parameter group, and the temperature rise demand evaluation value is used to represent whether the temperature rise of the battery meets the temperature rise demand.

[0089] S203, determining a target prediction value based on the first energy consumption prediction value and the temperature rise demand evaluation value.

[0090] The controller can determine a target prediction value based on the first energy consumption prediction value and the temperature rise demand evaluation value after predicting the temperature rise demand evaluation value of the battery in the prediction time domain based on the real-time working condition and the control parameter group. The target prediction value is positively correlated with both the first energy consumption prediction value and the temperature rise demand evaluation value.

[0091] Optionally, the controller can determine the sum of the first energy consumption prediction value M and the temperature rise demand evaluation value h as the target prediction value. The target prediction value J can satisfy: J=M+h.

[0092] In some embodiments of the present application, when the prediction time domain is long, the prediction time domain can include a plurality of prediction time points, and the time interval between any two adjacent prediction time points in the plurality of prediction time points can be a preset time length, which can be pre-stored in the controller. For example, the preset time length can be 10 minutes. Each control parameter group can include control parameters at each prediction time point in the plurality of prediction time points, and the control parameters included in any two control parameter groups in the plurality of control parameter groups have different values. The controller can predict the first energy consumption prediction value of the thermal management system in the prediction time domain based on the control parameter group, which can include the following steps:

[0093] S2011、For each prediction time point, predict the state parameter of the thermal management system under the control parameter of the prediction time point.

[0094] For each prediction time point, the controller can predict the state parameter of the thermal management system under the control parameter based on the control parameter of the prediction time point. The state parameter can be used to reflect at least the running state of the running component in the heat exchange subsystem, and the control parameter can be used to adjust the running state of the running component.

[0095] The controller can input the control parameter of the prediction time point into the state prediction model of the thermal management system to obtain the state parameter of the thermal management system under the control parameter.

[0096] Optionally, when the thermal management system includes an electric drive heat exchange subsystem, the state parameter can include at least one of the power of the pump, the ambient temperature, the fluid temperature, the temperature of the electric control, and the temperature of the motor, and the control parameter can include the torque of the motor, the rotating speed of the pump, and the rotating speed of the fan. The running component in the electric drive heat exchange subsystem can include at least one of the pump, the electric control, and the motor. The pump can include an oil pump and a water pump.

[0097] In the case that the thermal management system comprises an air conditioning subsystem, the state parameters can comprise at least one of an inlet pressure of the compressor, an outlet pressure of the compressor, a temperature of the heat exchanger, a vehicle speed, an ambient temperature, a temperature of the passenger cabin, an outlet temperature of the evaporator, and an outlet temperature of the condenser, and the control parameters can comprise a rotating speed of the compressor and an opening degree of the first valve. Optionally, the control parameters can further comprise a fan gear and an internal-external circulation ratio. The operating components in the air conditioning subsystem can comprise at least one of the heat exchanger, the compressor, the evaporator, and the condenser. The temperature of the heat exchanger can be a temperature of the cooling liquid in the plate heat exchanger. The condenser can comprise an internal condenser and an external condenser.

[0098] In the case that the thermal management system comprises a battery heat exchange subsystem, the state parameters can comprise at least one of a vehicle speed, an ambient temperature, a temperature of the battery, an inlet heat exchange medium temperature of the battery, an outlet heat exchange medium temperature of the battery, and a heat exchange power of the battery heat exchanger, and the control parameters can comprise an opening degree of the second valve. The operating components in the battery heat exchange subsystem can comprise at least one of the battery and the battery heat exchanger, and the battery heat exchanger can be a battery direct cooling plate. The heat exchange medium temperature can be a refrigerant temperature.

[0099] In the embodiments of the present application, the prediction time t, the state parameters x(t) at the prediction time t, and the control parameters u(t) at the prediction time t can satisfy the following conditions respectively:

[0100] wherein x min (t) represents a lower limit value of the first numerical range in which the state parameters at the prediction time t are located, x max (t) represents an upper limit value of the first numerical range in which the state parameters of the vehicle at the prediction time t are located, u min (t) represents a lower limit value of the second numerical range in which the control parameters of the vehicle at the prediction time t are located, u max (t) represents an upper limit value of the second numerical range in which the control parameters at the prediction time t are located, τ is a starting time of the prediction time domain, and t p is a terminal time of the prediction time domain, i.e., the last time of the prediction time domain.

[0101] It should be noted that in the case that the state parameters and the control parameters are both multiple, the first numerical ranges in which different state parameters are located can be the same or different. For example, the first numerical range in which the inlet pressure of the compressor is located can be the same as the first numerical range in which the outlet pressure of the compressor is located. The first numerical range in which the vehicle speed is located can be different from the first numerical range in which the ambient temperature is located. The second numerical ranges in which different control parameters are located can be the same or different. For example, the second numerical range in which the rotating speed of the compressor is located can be different from the second numerical range in which the opening degree of the first valve is located.

[0102] In the embodiment of the present application, at the prediction time, the electric control predicted temperature, the motor predicted temperature, the passenger cabin predicted temperature and the battery predicted temperature are all within the corresponding temperature ranges, and the temperature ranges corresponding to the electric control predicted temperature, the motor predicted temperature, the passenger cabin predicted temperature and the battery predicted temperature can be the same or different.

[0103] Optionally, the controller can input the control parameters and the state parameters at the previous prediction time of the prediction time into the digital twin model of the thermal management system to obtain the electric control predicted temperature, the motor predicted temperature, the passenger cabin predicted temperature and the battery predicted temperature at the prediction time. The controller can pre-store the digital twin model, and the digital twin model can be a neural network model.

[0104] Referring to FIG. 3, the digital twin model of the thermal management system can include a first input layer P1, a first hidden layer e1x, a second hidden layer f2x and a first output layer S1. The control parameters and the state parameters of the thermal management system at the prediction time are g, assuming that g is 9, then the controller can input the first parameter q1 to the ninth parameter q9 into the first input layer P1, and after the processing of the first hidden layer e1x and the second hidden layer f2x, finally output the electric control predicted temperature T C and the motor predicted temperature T m , the passenger cabin predicted temperature (not shown in FIG. 3) and the battery predicted temperature (not shown in FIG. 3) through the first output layer S1.

[0105] The first hidden layer e1x can include neurons e 11 to neurons e 1k , a total of k neurons. The second hidden layer f2x can include neurons e 21 to neurons e 2k , a total of k neurons. g is a positive integer equal to the total number of state parameters and control parameters, and k is a positive integer less than g.

[0106] In the embodiment of the present application, the digital twin model of the thermal management system can include the digital twin models of each heat exchange subsystem, and a mathematical model for connecting the digital twin models of different heat exchange subsystems. The mathematical model is used to describe the physical relationship between different heat subsystems, and to simulate the heat flow and energy conversion between different heat exchange subsystems.

[0107] S2012, based on the control parameters and the state parameters, predicting the instantaneous energy consumption prediction value of the thermal management system at the prediction time.

[0108] For each prediction time, after the controller predicts the state parameters of the thermal management system under the control parameters based on the control parameters at the prediction time, the controller can predict the instantaneous energy consumption prediction value of the thermal management system at the prediction time based on the control parameters and the state parameters.

[0109] The controller can input the control parameter and the state parameter into the first energy consumption prediction function (or the first energy consumption prediction model) to obtain an instantaneous energy consumption prediction value of the thermal management system at the prediction time. The controller can pre-store the first energy consumption prediction function (or the first energy consumption prediction model). The first energy consumption prediction function (or the first energy consumption prediction model) is trained by using a plurality of first sample data. Each first sample data can include a sample control parameter, a sample state parameter corresponding to the sample control parameter, and a sample instantaneous energy consumption prediction value of a sample thermal management system.

[0110] S2013, predicting a first energy consumption prediction value of the thermal management system in the prediction time domain based on the sum of the plurality of instantaneous energy consumption prediction values.

[0111] After the controller predicts the instantaneous energy consumption prediction value of the thermal management system at the prediction time based on the control parameter and the state parameter, the controller can predict the first energy consumption prediction value of the thermal management system in the prediction time domain based on the sum of the plurality of instantaneous energy consumption prediction values.

[0112] Optionally, the controller can determine the sum of the plurality of instantaneous energy consumption prediction values and a preset coefficient as the first energy consumption prediction value of the thermal management system in the prediction time domain. The preset coefficient can be pre-stored in the controller.

[0113] Alternatively, the controller can determine the sum of the plurality of instantaneous energy consumption prediction values as the first energy consumption prediction value of the thermal management system in the prediction time domain. The first energy consumption prediction value M can satisfy:

[0114] Wherein, L(x(t), u(t)) represents the instantaneous energy consumption prediction value of the thermal management system at the prediction time t, and L represents the first energy consumption prediction function (or the first energy consumption prediction model).

[0115] In some embodiments of the present application, the controller predicts the temperature rise demand evaluation value of the battery in the prediction time domain based on the real-time working condition and the control parameter group, which can include the following steps:

[0116] S2021, predicting a battery demand temperature of the battery in the prediction time domain based on the real-time working condition and the control parameter group.

[0117] The controller can predict a battery demand temperature of the battery in the prediction time domain based on the real-time working condition and the control parameter group. The battery demand temperature is a demand temperature of the battery at the last prediction time in the prediction time domain.

[0118] S2022, predicting a battery prediction temperature of the battery in the prediction time domain based on the control parameter group.

[0119] After the controller predicts the battery's required temperature in the prediction time domain based on real-time operating conditions and control parameter sets, it can predict the battery's predicted temperature in the prediction time domain based on the control parameter sets.

[0120] The controller can input the control parameters for a target prediction time from multiple prediction times into the digital twin model of the thermal management system to obtain the battery's predicted temperature in the prediction time domain. The target prediction time is the prediction time preceding and adjacent to the last prediction time among the multiple prediction times. The battery's predicted temperature in the prediction time domain is the same as the battery's predicted temperature at the last prediction time.

[0121] Optionally, the controller can input the control parameters and state parameters of the target prediction time from multiple prediction times into the digital twin model of the thermal management system to obtain the predicted battery temperature in the prediction time domain.

[0122] S2023. Based on the battery demand temperature and the battery prediction temperature, predict the temperature rise demand assessment value of the battery in the prediction time domain.

[0123] After the controller predicts the battery temperature in the prediction time domain based on the control parameter set, it can predict the battery temperature rise requirement assessment value in the prediction time domain based on the battery demand temperature and the battery prediction temperature.

[0124] Optionally, if the predicted battery temperature is greater than or equal to the required battery temperature, the temperature rise requirement assessment value can be a preset value. If the predicted battery temperature is less than the required battery temperature, the temperature rise requirement assessment value is determined based on the product of the square of the target difference and a weighting coefficient. The target difference can be the difference between the required battery temperature and the predicted battery temperature, and this preset value is less than the product. This preset value can be pre-stored in the controller; for example, this preset value can be 0.

[0125] When the temperature rise requirement assessment value is a preset value, the temperature rise requirement assessment value indicates that the temperature rise of the battery meets the temperature rise requirement. When the temperature rise requirement assessment value is a product, the temperature rise requirement assessment value indicates that the temperature rise of the battery does not meet the temperature rise requirement.

[0126] The target difference ΔT can satisfy:

[0127] Among them, T b (t p ) represents the last prediction time t of the battery in the prediction time domain. p The required temperature of the battery, This indicates that the battery is at the last predicted time t. p Predicted battery temperature at that time.

[0128] The temperature rise requirement assessment value h can satisfy:

[0129] wherein, δ is a weight coefficient, δ is greater than 0, T0 is a preset value, and the controller can pre-store the weight coefficient δ.

[0130] In some embodiments of the present application, the controller can predict the battery demand temperature of the battery in the prediction time domain based on the real-time working condition and the control parameter group, which can include the following steps:

[0131] SA1, determining the vehicle demand power of the vehicle in the prediction time domain based on the real-time working condition.

[0132] The controller can determine the vehicle demand power of the vehicle in the prediction time domain based on the real-time working condition.

[0133] Optionally, the controller can predict the target working condition of the vehicle in the prediction time domain based on the real-time working condition, determine the calibration power corresponding to the target working condition from the corresponding relationship between the working condition and the power, and then determine the vehicle demand power of the vehicle based on the calibration power.

[0134] Optionally, the controller can determine the vehicle demand power of the vehicle based on the sum of the calibration power and the preset power. The vehicle demand power P1 can satisfy: P1 = P0 + ΔP

[0135] wherein, P0 is the calibration power, ΔP is the preset power, the controller can pre-store the corresponding relationship between the working condition and the power, and the preset power.

[0136] In the embodiments of the present application, by increasing the preset power on the basis of the calibration power, the vehicle demand power is determined, which can ensure the high power demand of the vehicle when overtaking or climbing.

[0137] The controller can input the real-time working condition at the current time into the working condition prediction model, so as to obtain the target working condition output by the working condition prediction model. The target working condition can be represented by the running parameters of the vehicle in the prediction time domain, which are the same as the running parameters representing the real-time working condition, but the values of the running parameters are different from those of the running parameters representing the real-time working condition. The working condition prediction model can be a neural network model, and the working condition prediction model can be a double-hidden layer neural network model. Referring to FIG. 4, the working condition prediction model can include a second input layer P2, a third hidden layer d1x, a fourth hidden layer d2x, and a second output layer S2.

[0138] Suppose that the running parameters used to represent the real-time working condition include a first running parameter p1 to a sixteenth running parameter p 16 , the controller can input the running parameters used to represent the real-time working condition into the second input layer P2, process through the third hidden layer d1x and the fourth hidden layer d2x, and finally output the first running parameter S1 to the sixteenth running parameter S representing the target working condition through the second output layer S2.16 The third hidden layer d1x can include neurons d 11 to neurons d 1m The fourth hidden layer d2x can include neurons d 21 to neurons d 2m The fourth hidden layer d2x can include neurons d 10 max In the embodiment of the present application, the target working condition of the vehicle in the prediction time domain is determined quickly and accurately by inputting the real-time working condition into the working condition prediction model to obtain the target working condition output by the working condition prediction model, so that the delay can be effectively reduced.

[0001] SA2, based on the real-time working condition, the control parameter set and the actual SOC value of the battery at the current time, predicts the predicted SOC value of the battery in the prediction time domain.

[0002] After the controller determines the whole vehicle demand power of the vehicle in the prediction time domain based on the real-time working condition, the controller can predict the predicted SOC value of the battery in the prediction time domain based on the real-time working condition, the control parameter set and the actual SOC value of the battery at the current time. Optionally, the controller can predict the third energy consumption prediction value of the electric drive system of the vehicle in the prediction time domain based on the real-time working condition, determine the second energy consumption prediction value of the vehicle in the prediction time domain based on the sum of the first energy consumption prediction value and the third energy consumption prediction value, and determine the predicted SOC value of the battery in the prediction time domain based on the difference between the target ratio and the actual SOC value. The target ratio can be the ratio of the second energy consumption prediction value to the rated total energy of the battery.

[0003] After the controller predicts the target working condition of the vehicle in the prediction time domain based on the real-time working condition, the controller can predict the third energy consumption prediction value of the electric drive system in the prediction time domain based on the target working condition. Optionally, the controller can input the target working condition into the second energy consumption prediction model (or the second energy consumption prediction function) of the electric drive system to obtain the third energy consumption prediction value output by the second energy consumption prediction model (or the second energy consumption prediction function).

[0004] The second energy consumption prediction function (or the second energy consumption prediction model) is trained by using a plurality of second sample data, and each second sample data can include a sample working condition and a sample energy consumption value of a sample electric drive system. The controller can determine the sum of the first energy consumption prediction value and the third energy consumption prediction value as the second energy consumption prediction value of the vehicle in the prediction time domain. The second energy consumption prediction value N can satisfy:

[0005]

[0006] Q represents the second energy consumption prediction value.

[0007] The rated total energy Q0 of the battery can satisfy: Q0=C0×U0

[0148] The rated capacity C0 of the battery and the rated voltage U0 of the battery can be pre-stored by the controller.

[0149] The target ratio V can satisfy:

[0150] The predicted SOC value SO of the battery in the prediction time domain can satisfy:

[0151] The actual SOC value is SOC0.

[0152] SA3, based on the vehicle demand power and the predicted SOC value, predicts the battery demand temperature of the battery in the prediction time domain.

[0153] After the controller predicts the predicted SOC value of the battery in the prediction time domain based on the real-time working condition, the control parameter group and the actual SOC value of the battery at the current time, the controller can predict the battery demand temperature of the battery in the prediction time domain based on the vehicle demand power and the predicted SOC value.

[0154] Optionally, the controller can determine the corresponding relationship between the SOC value and the temperature corresponding to the vehicle demand power, and then determine the battery demand temperature corresponding to the predicted SOC value based on the corresponding relationship between the SOC value and the temperature.

[0155] Assuming that the vehicle demand power is P', FIG. 5 is a curve diagram of the corresponding relationship between the SOC value and the temperature in the case where the vehicle demand power is P' according to an embodiment of the present application. Referring to FIG. 5, the vertical axis is the SOC value and the horizontal axis is the temperature T. As can be seen from FIG. 5, if the predicted SOC value is SOC', the battery demand temperature is T'.

[0156] In some embodiments of the present application, in the case where the prediction time domain is short, each control parameter group can include a control parameter, the control parameter can be multiple, and the values of the control parameters included in any two control parameter groups are different. The controller can input the control parameter and the state parameter corresponding to the control parameter into the first energy consumption prediction model function or the second energy consumption prediction model to obtain the first energy consumption prediction value.

[0157] In addition, the controller can input the control parameter and the state parameter into the digital twin model of the thermal management system to obtain the predicted battery temperature of the battery in the prediction time domain.

[0158] In the embodiment of the present application, with reference to FIG. 6, the heat management system can include: a plate heat exchanger 20, a compressor 31, an inner condenser 32, a battery direct cooling plate 33, a first expansion valve 34, an outer condenser 35, a first electromagnetic valve 36a, a second electromagnetic valve 36b, a third electromagnetic valve 36c, a fourth electromagnetic valve 36d, a fifth electromagnetic valve 36e, a sixth electromagnetic valve 36f, a first check valve 37a, a second check valve 37b, a third check valve 37c, a fourth check valve 37d, a fifth check valve 37e, a gas-liquid separator 38, a second expansion valve 39, a three-way valve 40, a motor electric control radiator 41, a power assembly 42, a water pump 43, a water temperature sensor 44, a fan 45, a PTC electric heater 46, a third expansion valve 47, an evaporator 48, a fourth expansion valve 49, a first pressure sensor PT1, a second pressure sensor PT2, a third pressure sensor PT3, and a fourth pressure sensor PT4.

[0159] The power assembly 42 can include a motor, an electric drive, and an oil pump. The first electromagnetic valve 36a is connected to the inner condenser 32 and one end of the second electromagnetic valve 36b, respectively. The other end of the second electromagnetic valve 36b is connected to one end of the outer condenser 35.

[0160] The first check valve 37a is connected to the other end of the outer condenser 35 and one end of the second check valve 37b, respectively. The other end of the second check valve 37b is connected to the battery direct cooling plate 33 through the second expansion valve 39.

[0161] The third electromagnetic valve 36c is connected to the first expansion valve 34 and one end of the third check valve 37c, respectively. The gas-liquid separator 38 is connected to the other end of the third check valve 37c and an inlet of the compressor 31, respectively.

[0162] The heat exchanger 20 is connected to a first end a of the three-way valve 40 and one end of the water temperature sensor 44, respectively.

[0163] A second end b of the three-way valve 40 is connected to one end of the power assembly 42. The motor electric control radiator 41 is connected to a third end c of the three-way valve 40 and one end of the power assembly 42, respectively. The water pump 43 is connected to the other end of the power assembly 42 and the other end of the water temperature sensor 44, respectively. The fan 45 is connected to the motor electric control radiator 41.

[0164] The first electromagnetic valve 36a is connected to the inner condenser 32 and one end of the fourth electromagnetic valve 36d, respectively. The other end of the fourth electromagnetic valve 36d is connected to a refrigerant side of the heat exchanger 20. One end of the second check valve 37b is also connected to the refrigerant side of the heat exchanger 20.

[0165] One end of the second pressure sensor PT2 is connected to an outlet of the compressor 31. The other end of the second pressure sensor PT2 is connected to the inner condenser 32. The PTC electric heater 46 is arranged on the inner condenser.

[0166] The third expansion valve 47 is connected in parallel with the inner condenser 32, one end of the fifth electromagnetic valve 36e is connected with the other end of the second pressure sensor PT2, and the other end of the fifth electromagnetic valve 36e is connected with the battery direct cooling plate 33 through the first expansion valve 34.

[0167] The third pressure sensor PT3 is connected between the battery direct cooling plate 33 and the second expansion valve 39, and the fourth one-way valve 37d is connected between the second expansion valve 39 and the fourth electromagnetic valve 36d.

[0168] The fourth pressure sensor PT4 is connected with the gas-liquid separator 38 and one end of the fifth one-way valve 37e respectively, the other end of the fifth one-way valve 37e is connected with one end of the evaporator 48, and the other end of the evaporator 48 is connected with one end of the fourth expansion valve 49.

[0169] The other end of the fourth expansion valve 49 is connected with one end of the second one-way valve 37b, and the sixth electromagnetic valve 36f is connected with one end of the fifth one-way valve 37e and the other end of the fourth expansion valve 49 respectively.

[0170] In the embodiment of the present application, the air conditioning subsystem can include the plate heat exchanger 20, the compressor 31, the inner condenser 32, the outer condenser 35, the first electromagnetic valve 36a, the second electromagnetic valve 36b, the fourth electromagnetic valve 36d, the sixth electromagnetic valve 36f, the first one-way valve 37a, the third one-way valve 37c, the fifth one-way valve 37e, the gas-liquid separator 38, the PTC electric heater 46, the third expansion valve 47, the evaporator 48, the fourth expansion valve 49, the second pressure sensor PT2, and the fourth pressure sensor PT4. The first valve can include the first electromagnetic valve 36a, the second electromagnetic valve 36b, the fourth electromagnetic valve 36d, the sixth electromagnetic valve 36f, the first one-way valve 37a, the third one-way valve 37c, the fifth one-way valve 37e, the third expansion valve 47, and the fourth expansion valve 49.

[0171] The electric drive heat exchange subsystem can include the three-way valve 40, the motor electric control radiator 41, the power assembly 42, the water pump 43, the water temperature sensor 44, and the fan 45.

[0172] The battery heat exchange subsystem can include the battery direct cooling plate 33, the first expansion valve 34, the third electromagnetic valve 36c, the fifth electromagnetic valve 36e, the second one-way valve 37b, the fourth one-way valve 37d, the second expansion valve 39, the first pressure sensor PT1, and the third pressure sensor PT3. The second valve can include the first expansion valve 34, the third electromagnetic valve 36c, the fifth electromagnetic valve 36e, the second one-way valve 37b, the fourth one-way valve 37d, and the second expansion valve 39.

[0173] In some embodiments of the present application, the controller can pre-store a plurality of control parameter groups. Alternatively, the controller can determine the plurality of control parameter groups and the control parameter group corresponding to the minimum target prediction value in the plurality of target prediction values by using a genetic algorithm. Optionally, the controller can determine the plurality of control parameter groups and the control parameter group corresponding to the minimum target prediction value by using a genetic algorithm, and the method can comprise the following steps:

[0174] S401, obtaining an initial population.

[0175] The controller can obtain an initial population, which comprises U initial control parameter groups, each of which is an individual in the initial population. Each initial control parameter group can comprise control parameters at each prediction time, and each control parameter at each prediction time can be multiple. Any two initial control parameter groups can comprise control parameters with different values.

[0176] In embodiments of the present application, for each control parameter in the plurality of control parameters at each prediction time, the controller can pre-store a plurality of values of the control parameter. The controller can randomly select a value of the control parameter from the plurality of values of the control parameter as the value of the control parameter, thereby generating an initial control parameter group.

[0177] Optionally, the controller can use a fixed-length binary symbol string to represent an individual. For example, the fixed length can be 10. Assuming that the initial control parameter group only comprises the compressor speed r, in the case of a fixed length of 10, the compressor speed r can have 2 10 different encodings, each of which corresponds to a number, which can be the decimal value corresponding to the encoding. The correspondence between the value of the compressor speed r, the encoding and the number can be seen in Table 1, wherein, r max represents the maximum value of the compressor speed.

[0178] Table 1

[0179] S402, repeatedly executing an iteration process until a termination condition is met. The iteration process can comprise:

[0180] S4021, for each target control parameter group in the target population, determining a fitness value based on the real-time working condition and the target control parameter group.

[0181] In the case of first executing step 4021, the target population is the initial population, and the target control parameter group is the initial control parameter group. In the case of non-first execution of step 4021, the target population is the target population updated in step 4022, and the target control parameter group is the target control parameter group in the target population updated in step 4022.

[0182] The controller can determine a target prediction value based on the real-time working condition and the target control parameter group, and determine the opposite number of the target prediction value as the fitness value. That is, the fitness value E satisfies: E = -J

[0183] S4022, updating the target population based on the plurality of fitness values.

[0184] The controller can update the target population based on the plurality of fitness values.

[0185] Optionally, the controller can select Y target control parameter groups from the plurality of target control parameter groups in the target population as Y parent individuals based on the plurality of fitness values by using a roulette selection, tournament selection, proportional selection or the like algorithm, and perform a crossover operation on the Y parent individuals to generate R new control parameters as R child individuals. Then, the R child individuals can be subjected to mutation processing according to a preset probability, and the individuals in the target population are updated to the R child individuals. Y is a positive integer less than or equal to the total number of the plurality of target control parameter groups, and R is a positive integer less than or equal to Y.

[0186] S403, in the case where the end condition is met, the target control parameter group corresponding to the maximum fitness value in the target population is taken as the control parameter group corresponding to the minimum target prediction value.

[0187] Since the fitness value is the opposite number of the target prediction value, the controller can take the target control parameter group corresponding to the maximum fitness value in the target population as the control parameter group corresponding to the minimum target prediction value in the case where it is detected that the end condition is met.

[0188] The plurality of control parameter groups employed in the embodiments of the present application can include all control parameter groups in the plurality of initial populations and all control parameter groups in the target populations. The control parameters included in any two control parameter groups determined by using the genetic algorithm are different in value.

[0189] In summary, the embodiment of the present application provides a control method of a thermal management system in a vehicle. After obtaining a plurality of control parameter groups and a real-time working condition of the vehicle at a current time, the controller can predict a plurality of target prediction values of the vehicle in a prediction time domain after the current time according to the real-time working condition and the plurality of control parameter groups. Each target prediction value is used to represent whether the temperature rise of the battery in the vehicle meets the temperature rise demand and the energy consumption of the thermal management system under a corresponding one of the control parameter groups. The thermal management system is controlled according to the control parameter group corresponding to the smallest target prediction value in the plurality of target prediction values in the prediction time domain. Therefore, the energy consumption of the thermal management system in the prediction time domain can be guaranteed to be the lowest, and the temperature rise of the battery meets the temperature rise demand. In this way, the energy consumption of the thermal management system in the prediction time domain is guaranteed to be the lowest under the condition that the endurance time of the battery is guaranteed.

[0190] Further, the present application also provides a computer readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the control method of the thermal management system in the vehicle according to any one of the above embodiments is implemented.

[0191] Fig. 7 is a block diagram of a control device of a thermal management system in a vehicle according to an embodiment of the present application. As shown in Fig. 7, the control device 100 of the thermal management system in the vehicle comprises:

[0192] The obtaining module 601 is configured to obtain a plurality of control parameter groups and a real-time working condition of the vehicle at a current time.

[0193] The prediction module 602 is configured to predict a plurality of target prediction values of the vehicle in a prediction time domain after the current time according to the real-time working condition and the plurality of control parameter groups. Each target prediction value is used to represent whether the temperature rise of the battery in the vehicle meets the temperature rise demand and the energy consumption of the thermal management system under a corresponding one of the control parameter groups.

[0194] The control module 603 is configured to control the thermal management system according to the control parameter group corresponding to the smallest target prediction value in the plurality of target prediction values in the prediction time domain, so that the energy consumption of the thermal management system in the prediction time domain is guaranteed to be the lowest, and the temperature rise of the battery meets the temperature rise demand.

[0195] Optionally, the prediction module 602 is configured to:

[0196] For each control parameter group, a first energy consumption prediction value of the thermal management system in the prediction time domain is predicted based on the control parameter group.

[0197] A temperature rise demand evaluation value of the battery in the prediction time domain is predicted based on the real-time working condition and the control parameter group. The temperature rise demand evaluation value is used to represent whether the temperature rise of the battery meets the temperature rise demand.

[0198] determine a target prediction value based on the first energy consumption prediction value and the temperature rise demand evaluation value;

[0199] The target prediction value is positively correlated with both the first energy consumption prediction value and the temperature rise demand evaluation value.

[0200] Optionally, the prediction time domain includes multiple prediction time points, and each control parameter group includes control parameters at each prediction time point; the prediction module 602 is configured to:

[0201] For each prediction time point, predict an instantaneous energy consumption prediction value of the thermal management system at the prediction time point based on the control parameters at the prediction time point;

[0202] Based on the sum of the multiple instantaneous energy consumption prediction values, predict a first energy consumption prediction value of the thermal management system in the prediction time domain.

[0203] Optionally, the prediction module 602 is configured to:

[0204] Based on the control parameters at the prediction time point, predict a state parameter of the thermal management system under the control parameters;

[0205] Based on the control parameters and the state parameter, predict an instantaneous energy consumption prediction value of the thermal management system at the prediction time point.

[0206] Optionally, the thermal management system includes at least one of the following heat exchange subsystems: an electric drive heat exchange subsystem, an air conditioning subsystem, and a battery heat exchange subsystem;

[0207] The state parameter is used to reflect the operating state of the operating component in the heat exchange subsystem;

[0208] The control parameter is used to adjust the operating state of the operating component.

[0209] In some embodiments of the present application, in the case where the thermal management system includes the electric drive heat exchange subsystem, the state parameter includes at least one of the power of the pump, the ambient temperature, the fluid temperature, the temperature of the electric control, and the temperature of the motor; and the control parameter includes the torque of the motor, the rotating speed of the pump, and the rotating speed of the fan;

[0210] In the case where the thermal management system includes the air conditioning subsystem, the state parameter includes at least one of the inlet pressure of the compressor, the outlet pressure of the compressor, the temperature of the heat exchanger, the vehicle speed, the ambient temperature, the temperature of the passenger compartment, the outlet temperature of the evaporator, and the outlet temperature of the condenser; and the control parameter includes the rotating speed of the compressor and the opening degree of the first valve;

[0211] In the case where the thermal management system includes the battery heat exchange subsystem, the state parameter includes at least one of the vehicle speed, the ambient temperature, the temperature of the battery, the inlet heat exchange working medium temperature of the battery, the outlet refrigerant temperature of the battery, and the heat exchange power of the battery heat exchanger; and the control parameter includes the opening degree of the second valve.

[0212] Optionally, the prediction module 602 is configured to:

[0213] predict a battery demand temperature of the battery in the prediction time domain based on the real-time working condition and the control parameter set;

[0214] predict a battery prediction temperature of the battery in the prediction time domain based on the control parameter set;

[0215] predict a temperature rise demand evaluation value of the battery in the prediction time domain based on the battery demand temperature and the battery prediction temperature.

[0216] Optionally, the prediction module 602 is configured to

[0217] in a case where the battery prediction temperature is greater than or equal to the battery demand temperature, the temperature rise demand evaluation value is a preset value;

[0218] in a case where the battery prediction temperature is less than the battery demand temperature, the temperature rise demand evaluation value is determined based on a product of a square value of a target difference value and a weight coefficient;

[0219] wherein the target difference value is a difference between the battery demand temperature and the battery prediction temperature, and the preset value is less than the product.

[0220] Optionally, the prediction time domain includes a plurality of prediction time points, and each control parameter set includes control parameters at each prediction time point; the prediction module 602 is configured to:

[0221] input the control parameters at a target prediction time point in the plurality of prediction time points into a digital twin model of the thermal management system to obtain the battery prediction temperature of the battery in the prediction time domain;

[0222] wherein the target prediction time point is a last prediction time point before the plurality of prediction time points and adjacent prediction time points.

[0223] Optionally, the prediction module 602 is configured to:

[0224] determine a vehicle demand power of the vehicle in the prediction time domain based on the real-time working condition;

[0225] predict a prediction SOC value of the battery in the prediction time domain based on the real-time working condition, the control parameter set, and an actual SOC value of the battery at a current time point;

[0226] predict the battery demand temperature of the battery in the prediction time domain based on the vehicle demand power and the prediction SOC value.

[0227] Optionally, the prediction module 602 is configured to:

[0228] predict a target working condition of the vehicle in the prediction time domain based on the real-time working condition;

[0229] Determine the whole vehicle demand power of the vehicle based on the target working condition.

[0230] Optionally, the prediction module 602 is configured to:

[0231] Determine the calibration power corresponding to the target working condition from the corresponding relationship between working conditions and power;

[0232] Determine the whole vehicle demand power of the vehicle based on the calibration power.

[0233] Optionally, the prediction module 602 is configured to:

[0234] Determine the whole vehicle demand power of the vehicle based on the sum of the calibration power and the preset power.

[0235] Optionally, the prediction module 602 is configured to:

[0236] Predict a second energy consumption prediction value of the vehicle in a prediction time domain based on the real-time working condition and the control parameter group;

[0237] Determine a predicted SOC value of the battery in the prediction time domain based on the difference between the actual SOC value and the target ratio.

[0238] The target ratio is the ratio of the second energy consumption prediction value to the rated total energy of the battery.

[0239] Optionally, the prediction module 602 is configured to:

[0240] Predict a third energy consumption prediction value of the electric drive system of the vehicle in the prediction time domain based on the real-time working condition;

[0241] Determine the second energy consumption prediction value of the vehicle in the prediction time domain based on the sum of the first energy consumption prediction value and the third energy consumption prediction value.

[0242] In summary, the embodiment of the present application provides a control device of a thermal management system in a vehicle. After obtaining a plurality of control parameter groups and a real-time working condition of the vehicle at the current time, the control device of the thermal management system can predict a plurality of target prediction values of the vehicle in a prediction time domain after the current time according to the real-time working condition and the plurality of control parameter groups. Each target prediction value is used to represent whether the energy consumption of the thermal management system and the temperature rise of the battery in the vehicle meet the temperature rise demand under a corresponding control parameter group of the thermal management system. Since the thermal management system is controlled according to the control parameter group corresponding to the smallest target prediction value in the plurality of target prediction values in the prediction time domain, the energy consumption of the thermal management system in the prediction time domain can be guaranteed to be the lowest, and the temperature rise of the battery meets the temperature rise demand, thereby ensuring that the energy consumption of the thermal management system in the prediction time domain is the lowest under the condition that the battery endurance time is guaranteed.

[0243] Fig. 8 is a structural block diagram of a vehicle in an embodiment of the present application, as shown in Fig. 8, the vehicle 200 includes the control device 100 of the thermal management system in the vehicle in the above-described embodiment.

[0244] In addition, other configurations and functions of the vehicle in the embodiment of the present application are known to those skilled in the art, and to reduce redundancy, they are not described here.

[0245] It should be noted that the logic and / or steps represented in flow diagrams or otherwise described herein, for example, can be considered as a list of executable instructions for implementing logic functions, and can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor- based system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions, or a combination of these. For the purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection having one or more wires (electrical apparatus), a portable computer diskette (magnetic apparatus), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber (optical apparatus), and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium can even be paper or another suitable medium upon which the program is printed, because the program can be electronically captured, for example, by optically scanning the paper or other suitable medium, then electronically converted into a form that is suitable for use by the instruction execution system, apparatus, or device, and then stored in the computer memory.

[0246] It should be understood that various parts of the present application can be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, a plurality of steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and as in another embodiment, it can be implemented using any or a combination of the following technologies, which are well known in the art: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0247] In the description of the present application, the description of the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the description of the present application, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0248] In the description of the present application, it should be understood that the orientation or positional relationship indicated by the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like are based on the orientation or positional relationship shown in the drawings, and are only for the purpose of facilitating the description of the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation of the present application.

[0249] In addition, the terms "first", "second", etc. used in the embodiments of the present application are only for the purpose of description, and cannot be understood as indicating or implying relative importance, or implicitly indicating the number of technical features referred to in the embodiments. Therefore, the features defined with the terms "first", "second" and the like in the embodiments of the present application can be explicitly or implicitly indicated to include at least one of the features in the embodiments. In the description of the present application, the meaning of the word "plurality" is at least two or two or more, such as two, three, four, etc., unless otherwise specifically limited in the embodiments.

[0250] In the present application, unless otherwise specifically defined or limited in the embodiments, the terms "mounting", "connecting", "connecting" and "fixing" and the like appearing in the embodiments should be understood in a broad sense, for example, the connection can be a fixed connection, or a detachable connection, or integrated, which can be understood, or can be a mechanical connection, an electrical connection, etc. Of course, it can also be directly connected, or indirectly connected through an intermediate medium, or it can be the internal communication of two elements, or the interaction relationship between two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific implementation situation.

[0251] In the present application, unless otherwise explicitly specified and limited, a first feature is "on" or "under" a second feature can mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, the first feature is "over", "above" and "on top of" the second feature can mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is horizontally higher than the second feature. The first feature is "under", "below" and "underneath" the second feature can mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is horizontally lower than the second feature.

[0252] Although the embodiments of the present application have been shown and described above, it is to be understood that the above-described embodiments are exemplary only, and are not to be construed as limiting the present application, and that changes, modifications, substitutions and variations can be made thereto by those skilled in the art without departing from the scope of the present application.

Claims

1. A control method of a thermal management system in a vehicle, characterized by, The method comprises: obtaining a plurality of control parameter groups and a real-time working condition of the vehicle at a current time; predicting, according to the real-time working condition and the plurality of control parameter groups, a plurality of target prediction values of the vehicle in a prediction time domain after the current time, each of the target prediction values being used to represent whether the temperature rise of a battery in the vehicle and the energy consumption of a thermal management system of the vehicle under a corresponding one of the control parameter groups meet a temperature rise requirement; controlling, in the prediction time domain, the thermal management system according to the control parameter group corresponding to the smallest target prediction value among the plurality of target prediction values, so as to make the energy consumption of the thermal management system in the prediction time domain the lowest and the temperature rise of the battery meet the temperature rise requirement.

2. The method of claim 1, wherein, The method comprises: for each of the control parameter groups, predicting a first energy consumption prediction value of the thermal management system in the prediction time domain based on the control parameter group; predicting, based on the real-time working condition and the control parameter group, a temperature rise requirement evaluation value of the battery in the prediction time domain, the temperature rise requirement evaluation value being used to represent whether the temperature rise of the battery meets the temperature rise requirement; determining the target prediction value based on the first energy consumption prediction value and the temperature rise requirement evaluation value; wherein the target prediction value is positively correlated with the first energy consumption prediction value and the temperature rise requirement evaluation value.

3. The method of claim 2, wherein, The prediction time domain comprises a plurality of prediction times, and each of the control parameter groups comprises control parameters of each of the prediction times. The method comprises: for each of the prediction times, predicting an instantaneous energy consumption prediction value of the thermal management system at the prediction time based on the control parameters of the prediction time; predicting the first energy consumption prediction value of the thermal management system in the prediction time domain based on a sum of the plurality of instantaneous energy consumption prediction values.

4. The method of claim 3, wherein, The method comprises: predicting a state parameter of the thermal management system under the control parameters based on the control parameters of the prediction time; predicting the instantaneous energy consumption prediction value of the thermal management system at the prediction time based on the control parameters and the state parameter.

5. The method of claim 4, wherein, The thermal management system comprises at least one of the following heat exchange subsystems: an electric drive heat exchange subsystem, an air conditioning subsystem and a battery heat exchange subsystem; the state parameter is used to reflect an operating state of an operating component in the heat exchange subsystem; the control parameter is used to adjust the operating state of the operating component.

6. The method of claim 5, wherein, in the case where the thermal management system comprises the electric drive heat exchange subsystem, the state parameter comprises at least one of a power of a pump, an ambient temperature, a fluid temperature, a temperature of an electric control and a temperature of an electric machine; and the control parameter comprises a torque of the electric machine, a rotating speed of the pump and a rotating speed of a fan. ​ In the case that the thermal management system comprises the air conditioning subsystem, the state parameters comprise at least one of an inlet pressure of the compressor, an outlet pressure of the compressor, a temperature of a heat exchanger, a vehicle speed, an ambient temperature, a temperature of a passenger cabin, an outlet temperature of an evaporator, and an outlet temperature of a condenser; and the control parameters comprise a rotating speed of the compressor and an opening degree of a first valve. In the case that the thermal management system comprises the battery heat exchange subsystem, the state parameters comprise at least one of the vehicle speed, the ambient temperature, a temperature of the battery, an inlet heat exchange working medium temperature of the battery, an outlet refrigerant temperature of the battery, and a heat exchange power of a battery heat exchanger; and the control parameters comprise an opening degree of a second valve.

7. The method according to any one of claims 2 to 6, characterized in that, Based on the real-time working condition and the control parameter group, a temperature rise demand evaluation value of the battery in the prediction time domain is predicted, comprising: predicting a battery demand temperature of the battery in the prediction time domain based on the real-time working condition and the control parameter group; predicting a battery predicted temperature of the battery in the prediction time domain based on the control parameter group; predicting a temperature rise demand evaluation value of the battery in the prediction time domain based on the battery demand temperature and the battery predicted temperature.

8. The method of claim 7, wherein, in the case that the battery predicted temperature is greater than or equal to the battery demand temperature, the temperature rise demand evaluation value is a preset value; in the case that the battery predicted temperature is less than the battery demand temperature, the temperature rise demand evaluation value is determined based on a product of a square value of a target difference value and a weight coefficient; wherein the target difference value is a difference between the battery demand temperature and the battery predicted temperature, and the preset value is less than the product.

9. The method of claim 7, wherein, The prediction time domain comprises a plurality of prediction time points, and each control parameter group comprises control parameters at each prediction time point. The battery predicted temperature of the battery in the prediction time domain is predicted based on the control parameter group, comprising: inputting the control parameters of a target prediction time point in the plurality of prediction time points into a digital twin model of the thermal management system to obtain the battery predicted temperature of the battery in the prediction time domain; wherein the target prediction time point is before the last prediction time point in the plurality of prediction time points and adjacent to a prediction time point.

10. The method of claim 7, wherein, The battery demand temperature of the battery in the prediction time domain is predicted based on the real-time working condition and the control parameter group, comprising: determining a whole vehicle demand power of the vehicle in the prediction time domain based on the real-time working condition; predicting a predicted SOC value of the battery in the prediction time domain based on the real-time working condition, the control parameter group, and an actual SOC value of the battery at the current time point; predicting the battery demand temperature of the battery in the prediction time domain based on the whole vehicle demand power and the predicted SOC value.

11. The method of claim 10, wherein, The whole vehicle demand power of the vehicle in the prediction time domain is determined based on the real-time working condition, comprising: predicting a target working condition of the vehicle in the prediction time domain based on the real-time working condition; determining the whole vehicle demand power of the vehicle based on the target working condition.

12. The method of claim 11, wherein, The determining of the whole-vehicle demand power of the vehicle based on the target working condition comprises: determining a calibration power corresponding to the target working condition from a corresponding relationship between working conditions and powers; and determining the whole-vehicle demand power of the vehicle based on the calibration power.

13. The method of claim 12, wherein, The determining of the whole-vehicle demand power of the vehicle based on the calibration power comprises: determining the whole-vehicle demand power of the vehicle based on a sum of the calibration power and a preset power.

14. The method of claim 10, wherein, The predicting of the predicted SOC value of the battery in the prediction time domain based on the real-time working condition, the control parameter group and the actual SOC value of the battery at the current time comprises: predicting a second energy consumption prediction value of the vehicle in the prediction time domain based on the real-time working condition and the control parameter group; determining the predicted SOC value of the battery in the prediction time domain based on a difference between the actual SOC value and a target ratio value; wherein the target ratio value is a ratio of the second energy consumption prediction value to a rated total energy of the battery.

15. The method of claim 14, wherein, The predicting of the second energy consumption prediction value of the vehicle in the prediction time domain based on the real-time working condition and the control parameter group comprises: predicting a third energy consumption prediction value of an electric drive system of the vehicle in the prediction time domain based on the real-time working condition; determining the second energy consumption prediction value of the vehicle in the prediction time domain based on a sum of the first energy consumption prediction value and the third energy consumption prediction value.

16. A computer-readable storage medium, characterized in that, A computer program is stored on the computer readable medium, and the program is executed by a processor to implement the control method of the vehicle thermal management system according to any one of claims 1 to 15.

17. A control device of a thermal management system in a vehicle, characterized by The apparatus comprises: an acquisition module configured to acquire a plurality of control parameter groups and a real-time working condition of the vehicle at a current time; a prediction module configured to predict a plurality of target prediction values of the vehicle in a prediction time domain after the current time according to the real-time working condition and the plurality of control parameter groups, each of the target prediction values being used to represent an energy consumption of a thermal management system of the vehicle under a corresponding one of the control parameter groups and whether a temperature rise of a battery of the vehicle meets a temperature rise demand; a control module configured to control the thermal management system according to a control parameter group corresponding to a smallest one of the target prediction values in the prediction time domain, so as to make the energy consumption of the thermal management system in the prediction time domain be the lowest and the temperature rise of the battery meet the temperature rise demand.

18. A vehicle characterized by comprising: The control apparatus of the vehicle thermal management system according to claim 17. The control apparatus of the vehicle thermal management system according to claim 17.

Images