Battery thermal management optimal control method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a battery thermal management optimal control method and device, electronic equipment and a storage medium, and relates to the technical field of battery system thermal management. The method comprises the following steps: judging whether any water inlet flow has a water inlet temperature interval meeting a constraint condition or not by utilizing a pre-trained proxy model; and if yes, performing iterative optimization by using a dichotomy to obtain optimal control parameters of the water inlet flow and the water inlet temperature. According to the method, the water inlet flow and the water inlet temperature of the battery heat management system can be optimally controlled, so that energy consumption is reduced, the cruising ability is improved, and the problems that according to an existing method, unreasonable water inlet flow and water inlet temperature combination is used, unnecessary waste of energy consumption of the whole vehicle is caused, and then the cruising ability of the electric vehicle is not improved easily are solved.

Description

Technical Field

[0001] The present application relates to the technical field of battery system thermal management, and in particular to a battery thermal management optimal control method, device, electronic device and storage medium. Background Art

[0002] Reducing energy consumption is an important aspect of improving the endurance of electric vehicles. The energy consumption of existing electric vehicles under various operating conditions is directly related to the battery thermal management system, and the effective operation of the battery thermal management system is regulated by the water inlet flow and water inlet temperature of the liquid cooling system. The existing battery thermal management system adjusts the water inlet flow and water inlet temperature so that the monitored physical quantities of the liquid-cooled battery system under various operating conditions (such as heating time and maximum temperature difference of the battery cell under low-temperature heating conditions) meet the target requirements. However, an unreasonable combination of water inlet flow and water inlet temperature will cause unnecessary waste of energy consumption of the entire vehicle, which is not conducive to improving the endurance of electric vehicles. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a battery thermal management optimal control method, device, electronic device and storage medium, which can optimally control the water inlet flow and water inlet temperature of the battery thermal management system to reduce energy consumption and improve endurance. It solves the problem that the existing method uses an unreasonable combination of water inlet flow and water inlet temperature, which causes unnecessary waste of energy consumption of the entire vehicle, and is not conducive to improving the endurance of the electric vehicle.

[0004] The present application provides a battery thermal management optimal control method, the method comprising:

[0005] Use the pre-trained proxy model to determine whether there is a water inlet temperature range that meets the constraint conditions for any water inlet flow rate;

[0006] If it exists, the binary search method is used to iterate and optimize to obtain the optimal control parameters of the water inlet flow rate and water inlet temperature;

[0007] The proxy model is trained by using the water inlet flow rate and water inlet temperature of the cooling system as input parameters and the battery physical quantities corresponding to the constraint conditions as output parameters.

[0008] In the above implementation process, the proxy model is used to obtain the optimal control parameters corresponding to the water inlet flow rate and the water inlet temperature, so that the battery system is thermally managed based on the optimal control parameters. While meeting the thermal management requirements, energy consumption can be reduced and the endurance can be improved. This solves the problem that the existing method uses an unreasonable combination of water inlet flow rate and water inlet temperature, which causes unnecessary waste of energy consumption of the entire vehicle, and is not conducive to improving the endurance of electric vehicles.

[0009] Furthermore, the obtaining of optimal control parameters of the water inlet flow rate and the water inlet temperature corresponding to the current working condition based on the battery heating time curve and the maximum temperature difference curve between the battery cells includes:

[0010] Determine the water flow range of the cooling system based on the current operating conditions and water pump power;

[0011] Based on the maximum water inlet flow rate in the water inlet flow rate interval, using the proxy model to determine whether there is a first water inlet temperature interval that meets the constraint condition;

[0012] Based on the minimum water inlet flow rate in the water inlet flow rate interval, using the proxy model to determine whether there is a second water inlet temperature interval that meets the constraint condition;

[0013] If the first water inlet temperature interval exists and the second water inlet temperature interval does not exist, the binary search method is used to iteratively search for the optimal control parameters of the water inlet flow rate and the water inlet temperature;

[0014] The constraints are expressed as follows: the battery heating time and the maximum temperature difference between the cells are lower than the preset values ​​respectively.

[0015] In the above implementation process, when the water inlet flow rate is the maximum value and the minimum value respectively, the proxy model can be used to determine whether the water inlet temperature range exists. If the first water inlet temperature range exists and the second water inlet temperature range does not exist, the dichotomy method can be used to optimize the first water inlet temperature range to obtain the corresponding optimal control parameters of the water inlet flow rate and the water inlet temperature.

[0016] Furthermore, if the first water inlet temperature interval exists and the second water inlet temperature interval does not exist, iterative optimization is performed using a binary search method to obtain optimal control parameters of the water inlet flow rate and the water inlet temperature, including:

[0017] If the first water inlet temperature interval exists and the second water inlet temperature interval does not exist, calculate the larger water inlet flow rate:

[0018] Q1=(Qmax+Qmin) / 2;

[0019] Among them, Q max Indicates the maximum water flow rate, Q min Indicates the minimum value of water inflow;

[0020] Taking the larger water inlet flow rate as the input of the proxy model, calculating whether a third water inlet temperature range that satisfies the constraint condition exists;

[0021] If the third water inlet temperature range exists, determine whether the cutoff condition for terminating the optimization is met:

[0022] Q i -Q i+1 <D;

[0023] Among them, Q i represents the previous larger inflow rate that meets the conditions, Q i+1 Indicates the current maximum water inflow, and D indicates the preset value;

[0024] If satisfied, the optimization is terminated, and the current larger water inlet flow rate is taken as the optimal value of the water inlet flow rate, and the lower limit of the water inlet temperature corresponding to the optimal value of the water inlet flow rate is taken as the optimal value of the water inlet temperature;

[0025] If not satisfied, update the larger water inflow:

[0026] Q=(Q i+1 +Qmin) / 2;

[0027] The updated larger water inlet flow rate is reused as the input of the proxy model to calculate whether a water inlet temperature range that satisfies the constraint condition exists.

[0028] In the above implementation process, an iterative optimization process using the binary search method is given to obtain the optimal value of the water inlet flow rate and the corresponding optimal value of the water inlet temperature.

[0029] Furthermore, the method further comprises:

[0030] If the third water inlet temperature range does not exist, the larger water inlet flow rate is updated:

[0031] Q=(Q i +Q i+1 ) / 2;

[0032] The updated larger water inlet flow rate is reused as the input of the proxy model to calculate whether a water inlet temperature range that satisfies the constraint condition exists.

[0033] In the above implementation process, if the third water inlet temperature interval does not exist, because the second water inlet temperature interval corresponding to the minimum water inlet flow rate does not exist at this time, the water inlet flow rate can be increased to make it close to the maximum water inlet flow rate to find the existing water inlet temperature interval.

[0034] Furthermore, the method further comprises:

[0035] If the second water inlet temperature interval exists, the minimum water inlet flow rate is used as the optimal water inlet flow rate, and the lower limit of the water inlet temperature corresponding to the optimal water inlet flow rate is used as the optimal water inlet temperature.

[0036] In the above implementation process, if the second water inlet temperature range exists, the minimum water inlet flow rate is the optimal value. At this time, the water pump requires the minimum power, so it is also the most energy-efficient.

[0037] Furthermore, the method further comprises:

[0038] If neither the first water inlet temperature interval nor the second water inlet temperature interval exists, then there is no optimal value of the water inlet flow rate and the optimal value of the water inlet temperature.

[0039] In the above implementation process, if the water inlet temperature intervals corresponding to the maximum and minimum water inlet temperature do not exist, it means that there is no optimal value.

[0040] Furthermore, before the step of obtaining, under any operating condition, a battery heating time curve corresponding to different water inlet flow rates that vary with the water inlet temperature, and a maximum temperature difference curve between battery cells corresponding to different water inlet flow rates that vary with the water inlet temperature using a pre-trained proxy model, the method further includes:

[0041] Generate training data using the calibrated three-dimensional CAE model of the battery system, and divide the training data into a training set and a validation set, wherein the training data includes different battery states of charge, battery aging states, charge and discharge rates, ambient temperatures, battery external heat exchange coefficients, water inlet flow rates of the cooling system, and battery heating times and maximum temperature differences between cells under water inlet temperatures;

[0042] The training set is input into the proxy model for training, and the validation set is used for validation.

[0043] In the above implementation process, the calibrated three-dimensional CAE model of the battery system is used to generate training data to train the proxy model, and the trained proxy model is obtained to obtain the corresponding water inlet temperature range based on the water inlet flow rate and constraint conditions.

[0044] The present application also provides a battery thermal management optimal control device, the device comprising:

[0045] The water inlet temperature interval judgment module is used to use the pre-trained proxy model to determine whether there is a water inlet temperature interval that meets the constraint conditions for any water inlet flow rate;

[0046] The optimization module is used to iteratively optimize the water inlet flow rate and water inlet temperature by using the binary search method if there is a water inlet temperature range;

[0047] The proxy model is trained by using the water inlet flow rate and water inlet temperature of the cooling system as input parameters and the battery physical quantities corresponding to the constraint conditions as output parameters.

[0048] In the above implementation process, the proxy model can be used to calculate whether there is a reasonable water inlet temperature range for a certain water inlet flow rate of the liquid cooling system, and the combination of water inlet flow rate and water inlet temperature with the lowest energy consumption can be found through binary search iteration, thereby saving energy and improving the vehicle's endurance.

[0049] An embodiment of the present application also provides an electronic device, which includes a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the above-mentioned battery thermal management optimal control method.

[0050] An embodiment of the present application further provides a readable storage medium, wherein the readable storage medium stores computer program instructions, and when the computer program instructions are read and executed by a processor, the above-mentioned battery thermal management optimal control method is executed. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 A flowchart of a battery thermal management optimal control method provided in an embodiment of the present application;

[0053] Figure 2 A schematic diagram of the relationship between the entropy thermal coefficient and the battery state of charge SOC provided in an embodiment of the present application;

[0054] Figure 3 A flowchart of initial input and optimal determination of water inlet flow rate and water inlet temperature provided in an embodiment of the present application;

[0055] Figure 4 A flowchart for obtaining optimal control parameters of water inlet flow rate and water inlet temperature corresponding to the current working conditions provided in an embodiment of the present application;

[0056] Figure 5 A schematic diagram of a battery heating time curve corresponding to different water inlet flow rates as the water inlet temperature changes and a maximum temperature difference curve between battery cells corresponding to different water inlet flow rates as the water inlet temperature changes provided in an embodiment of the present application;

[0057] Figure 6 A flowchart of iteratively updating and performing a dichotomy to find the optimal values ​​of the inlet water temperature and the inlet water flow rate provided in an embodiment of the present application;

[0058] Figure 7 A flowchart for the specific implementation of the battery thermal management optimal control method provided in the embodiment of the present application;

[0059] Figure 8 A training flow chart of the proxy model provided in the embodiment of the present application;

[0060] Fig. 9A flowchart for establishing and verifying a three-dimensional CAE model of a battery system provided in an embodiment of the present application;

[0061] Fig.10 A schematic diagram of a three-dimensional CAE model of a battery system provided in an embodiment of the present application;

[0062] Fig.11 A schematic diagram of accuracy verification of a three-dimensional CAE model of a battery system provided in an embodiment of the present application;

[0063] Fig.12 A flow chart of agent model training and verification provided in an embodiment of the present application;

[0064] Fig.13 A schematic diagram of DNN neural network modeling provided in an embodiment of the present application;

[0065] Fig.14 A flow chart of proxy model operation, cloud-based intensive training and OTA upgrade provided in the embodiment of the present application;

[0066] Fig.15 A structural block diagram of a battery thermal management optimal control device provided in an embodiment of the present application;

[0067] Fig.16 A structural block diagram of another battery thermal management optimal control device provided in an embodiment of the present application.

[0068] icon:

[0069] 100 - water inlet temperature interval judgment module; 200 - optimization module; 110 - water inlet flow interval determination module; 120 - first water inlet temperature interval judgment module; 130 - second water inlet temperature interval judgment module; 140 - first optimization module; 150 - second optimization module; 160 - third optimization module; 300 - model training module. DETAILED DESCRIPTION

[0070] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0071] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0072] Example 1

[0073] Please see Figure 1 , Figure 1A flow chart of a battery thermal management optimal control method provided for an embodiment of the present application. The water inlet flow rate and water inlet temperature required for the battery physical quantities (such as the heating time and the maximum temperature difference of the battery cell under low-temperature heating conditions) under various operating conditions to meet the target requirements (such as the constraints described below) are an interval range, that is, as long as the water inlet flow rate and the water inlet temperature are within the corresponding interval range, they can meet the thermal management requirements of the battery, but within the interval range, different water inlet flow rates and water inlet temperatures consume different amounts of energy. For example, if both the maximum and minimum water inlet flow rates can meet the thermal management requirements, but the water pump power required for the minimum water inlet flow rate is also the smallest, so the least energy can be consumed. Compared with other water inlet flow rates within the interval range, unnecessary energy waste can be reduced. At this time, the minimum water inlet flow rate is the optimal value sought by this application.

[0074] However, in actual applications, the optimal value of the inlet flow rate is often a value between the maximum inlet flow rate and the minimum inlet flow rate, rather than the minimum inlet flow rate. In this case, the optimal value of the inlet flow rate can be obtained by binary search.

[0075] Therefore, by obtaining the optimal control parameters of the water inlet flow rate and water inlet temperature in the interval range, the thermal management system can achieve the target requirements based on the minimum energy consumption, achieve the purpose of saving energy, and thus improve the endurance.

[0076] The method specifically comprises the following steps:

[0077] Step S100: using a pre-trained proxy model to determine whether any water inlet flow rate has a water inlet temperature range that satisfies the constraint condition;

[0078] Step S200: If it exists, iterative optimization is performed using the binary search method to obtain the optimal control parameters of the water inlet flow rate and water inlet temperature;

[0079] The proxy model is trained by using the water inlet flow and water inlet temperature of the cooling system as input parameters and the battery physical quantities corresponding to the constraints as output parameters.

[0080] As one of the implementation methods, for example, under low-temperature heating conditions, the battery physical quantity may be the heating time and the maximum temperature difference between the cells. A pre-trained proxy model is used to obtain a battery heating time curve corresponding to different water inlet flow rates that vary with the water inlet temperature, and a maximum temperature difference curve between the cells corresponding to different water inlet flow rates that vary with the water inlet temperature, wherein the input parameters of the training proxy model include but are not limited to the water inlet flow rate and water inlet temperature of the cooling system, and the battery heating time and the maximum temperature difference between the cells can be used as an output parameter.

[0081] The proxy model that can be used in the present application obtains the battery heating time curve corresponding to different water inlet flow rates that change with the water inlet temperature, as well as the maximum temperature difference curve between battery cells corresponding to different water inlet flow rates that change with the water inlet temperature. By inputting a certain water inlet flow rate into the proxy model, it can be determined whether there is a reasonable water inlet temperature range that satisfies the battery heating time and the maximum temperature difference of the battery cell. If so, the optimal value of the water inlet flow rate that satisfies the water inlet temperature range can be obtained through iterative optimization using binary search based on the water inlet flow rate, and then the corresponding optimal value of the water inlet temperature can be obtained based on the optimal water inlet flow rate.

[0082] Example 2

[0083] The embodiment of the present application provides a battery thermal management optimal control method. Based on Example 1, as one of the implementation methods, the input parameters of the training agent model also include battery state of charge, battery aging state, charge and discharge rate, ambient temperature, and battery external heat exchange coefficient.

[0084] The trained proxy model can be embedded in the control software of the BMS (Battery Management System). Under specific operating conditions, the battery system parameters such as battery state of charge, battery aging state, charge and discharge rate, ambient temperature, and battery external heat exchange coefficient are all non-adjustable parameters, while the water flow rate and water temperature of the cooling system are adjustable parameters, as follows:

[0085] When the battery system is in working state, if there is current flowing through the circuit, each battery cell will generate heat. The heat generation power q is determined by the Bernadi model, and the expression is as follows:

[0086]

[0087] Where I represents the charge and discharge current, R is the internal resistance of the battery, and T is the battery temperature. It is the entropy thermal coefficient. In the battery system, the current I is related to the charging rate C and can be read in real time from the BMS system; the temperature T can be collected in real time through the battery NTC sensor; the internal resistance R is the inherent physical property of the battery. Usually, the quantitative relationship between the battery internal resistance and the temperature T, the battery state of charge and the aging state SOH has been calibrated when the battery is offline. When the value is actually called, it is read in the form of a real-time table lookup; the entropy thermal coefficient The battery is obtained through OCV test when it leaves the factory, usually in The relational expression of Figure 2 The figure shows the relationship between the entropy thermal coefficient and the battery state of charge SOC. When reading the entropy thermal coefficient, it is usually read in the form of a table lookup.

[0088] In addition to the heat generation power, the ambient temperature is determined by the environment in which the battery system is located, and real-time data can be measured by arranging temperature sensors. The external heat transfer coefficient represents the heat transfer capacity and is an inherent physical property of the material.

[0089] Taking low-temperature heating conditions as an example, the battery system is evaluated from the perspective of heat generation and heat exchange. Under low-temperature heating conditions, the independent control parameters mainly include seven factors. Specifically, the heating time Δt and the maximum temperature difference between the cells ΔT max Mainly related to battery charging state SOC, battery aging state SOH, charging rate C, ambient temperature T amb , battery external heat transfer coefficient h, cooling system water flow Q fiow and water inlet temperature T inlet Related, that is:

[0090]

[0091] Among them, the first two variables SOC and SOH are related to the usage status of the battery itself, C and T amb It is related to the working condition of the battery, h is related to the external heat exchange factor of the battery, and the water flow rate Q of the cooling system fiow and water inlet temperature T inlet Related to the battery cooling system. The first five factors are related to the battery status or usage environment and are generally not controlled by the battery thermal management strategy. The last two factors are related to the cooling system and are controlled by the battery thermal management strategy.

[0092] Since the water inflow and water temperature are controlled by the battery BMS system, and the cooling system water inflow and water temperature have a greater impact on the battery temperature distribution. Therefore, the battery BMS system controls the cooling system water inflow and water temperature to make the cell heating time Δt and the single cell maximum temperature T max The maximum temperature difference between the single battery and the max Satisfy certain pre-set safety standards.

[0093] Taking the low temperature heating condition of the battery system as an example, its safety standard is the monitored battery physical quantity, namely the heating time Δt and the maximum temperature difference ΔT between the cells. max They are lower than a preset value respectively, and the expressions are as follows:

[0094]

[0095] Where, ΔT max =MAX{|T i -T j |},(i,j∈N), where N is the total number of cells in the battery system.

[0096] As one of the implementation methods, if the current working condition is the low temperature heating mode, when the battery system is in the low temperature heating condition, its battery thermal management control strategy is to adjust the cooling system water flow and water temperature to meet the control conditions of heating time and maximum temperature difference of the battery cell (the above expression), regardless of whether the selected water flow and water temperature can represent the minimum energy consumption of the system. In other words, the existing BMS control system cannot seek the optimal control parameters of water temperature and water flow.

[0097] Therefore, when performing thermal management on the battery, the present application can achieve optimal control of the water inlet flow rate and water inlet temperature through the proxy model, so that when the control conditions of the heating time and the maximum temperature difference of the battery cell are met, the required water inlet flow rate and water inlet temperature are the lowest energy consumption, thereby achieving the purpose of saving energy.

[0098] In the process of optimizing the inlet flow rate and inlet water temperature, the maximum and minimum inlet flow rates can be obtained based on the upper and lower limits of the water pump power. If the minimum inlet flow rate exists in an inlet water temperature interval that meets the constraints, then the minimum inlet flow rate is the optimal inlet flow rate, because at this time, the pumping flow of the water pump is the smallest and the energy is the most energy-efficient. Therefore, the optimization process can be divided into three cases: initially, the maximum inlet flow rate input has a corresponding inlet water temperature interval and the minimum inlet flow rate does not exist. In this case, it is necessary to continue iterative optimization; the minimum inlet flow rate has a corresponding inlet water temperature interval; and the maximum and minimum inlet flow rates do not have corresponding inlet water temperature intervals. Please refer to Figure 3 , Figure 3 This is the initial input and optimal judgment flow chart of the inlet water flow rate and inlet water temperature.

[0099] For the first case: see Figure 4 , Figure 4 A flowchart of obtaining the optimal control parameters of the inlet water flow rate and the inlet water temperature corresponding to the current working conditions provided in the embodiment of the present application. Based on embodiment 1, the flowchart specifically includes the following steps:

[0100] Step S210: determining the water inlet flow range of the cooling system based on the current working condition and the water pump power;

[0101] Step S220: Based on the maximum water inlet flow rate in the water inlet flow rate interval, using the proxy model to determine whether there is a first water inlet temperature interval that meets the constraint condition;

[0102] Step S230: Based on the minimum water inlet flow rate in the water inlet flow rate interval, using the proxy model to determine whether there is a second water inlet temperature interval that meets the constraint condition;

[0103] Step S240: if the first water inlet temperature interval exists and the second water inlet temperature interval does not exist, iterative optimization is performed using a binary search method to obtain optimal control parameters of the water inlet flow rate and the water inlet temperature;

[0104] The constraints are expressed as follows: the battery heating time and the maximum temperature difference between the cells are lower than the preset values ​​respectively.

[0105] For example, under low-temperature heating conditions (ambient temperature such as -15°C), the water inlet flow range of the cooling system is determined based on the water pump power, where the maximum water inlet flow is the liquid cooling flow rate that can be driven by the maximum power of the water pump; conversely, the minimum water inlet flow is the liquid cooling flow rate that can be driven by the minimum power of the water pump. For example, the water inlet flow is affected by the water pump power, and the flow range is between [6,14] L / min; similarly, the water inlet temperature is affected by the PTC heating power, and the water temperature can reach a temperature range of [24,56]°C.

[0106] For the determination of whether the first water inlet temperature range exists, for example, please refer to Figure 5 , Figure 5 The figure is a schematic diagram of the battery heating time curve corresponding to different water inlet flow rates and the maximum temperature difference curve between battery cells corresponding to different water inlet flow rates. Specifically, when different water inlet flow rates and water inlet temperatures are input into the proxy model, the battery heating time and maximum temperature difference curve between battery cells are generated.

[0107] For example, when the maximum water flow rate is 14L / min, the critical point for the heating time to satisfy Δt≤50min is Figure 5 A1 in the figure means that the water inlet temperature is greater than the water inlet temperature corresponding to A1 (about 36.5℃) to meet the heating time requirement. On the other hand, the maximum temperature difference ΔT max The critical point of ≤6℃ is A2, that is, the water inlet temperature must be lower than the water inlet temperature corresponding to point A2 (about 45.5℃) to meet the maximum temperature difference requirement. Figure 5 It can be found that under the condition of 14L / min water inlet flow rate, the water inlet temperature needs to be set within the temperature range [36.5,45.5]℃ corresponding to A1 and A2 to simultaneously meet the heating time Δt≤50min and the maximum temperature difference ΔT max ≤6℃ thermal management requirement. Therefore, there is a first water inlet temperature range of [36.5,45.5]℃.

[0108] For example, when the water flow rate adopts the minimum water flow rate of 6L / min, the critical point for the heating time to meet Δt≤50min is on D1 ( Figure 5 ), that is, the water inlet temperature must be greater than the water inlet temperature corresponding to point D1 (about 42.5℃) to meet the heating time requirement; on the other hand, the maximum temperature difference ΔTmax The critical point of ≤6℃ is D2( Figure 5 ), that is, the water inlet temperature must be lower than the water inlet temperature corresponding to point D2 (about 37.5℃) to meet the maximum temperature difference requirement. Figure 5 It can be found that under the condition of 6L / min water inlet flow rate, the water inlet temperature must meet the conditions of >42.5℃ and <37.5℃ at the same time to meet the conditions of heating time Δt≤50min and maximum temperature difference ΔT max ≤6℃. Obviously, there is no reasonable range of water inlet temperature that satisfies both constraints under low temperature heating conditions, so there is no second water inlet temperature range.

[0109] At this time, the first water inlet temperature interval exists and the second water inlet temperature interval does not exist. It is necessary to use the binary search method to continue to optimize, so as to obtain the optimal value of the water inlet flow rate. The optimal value of the water inlet flow rate here refers to the minimum value of the water inlet flow rate that meets the existence condition of the first water inlet temperature interval, and then the corresponding optimal value of the water inlet temperature is obtained based on the optimal value of the water inlet flow rate.

[0110] Please see Figure 6 , Figure 6 The flowchart of performing the binary search for the optimal values ​​of the water inlet temperature and the water inlet flow rate for iterative update includes the following steps:

[0111] Step S241: If the first water inlet temperature interval exists and the second water inlet temperature interval does not exist, then calculate the larger water inlet flow rate:

[0112] Q1=(Qmax+Qmin) / 2;

[0113] Among them, Q max Indicates the maximum water flow rate, Q min Indicates the minimum value of water inflow;

[0114] Step S242: taking the larger water inlet flow rate as the input of the proxy model, and determining whether a third water inlet temperature range that satisfies the constraint condition exists;

[0115] Step S243: If the third water inlet temperature range exists, determine whether the cutoff condition for terminating the optimization is met:

[0116] Q i -Q i+1 <D;

[0117] Among them, Q i represents the previous larger inflow rate that meets the conditions, Q i+1 Indicates the current maximum water inflow, and D indicates the preset value;

[0118] Step S244: if the conditions are met, the optimization is terminated, and the current larger water inlet flow rate is taken as the optimal water inlet flow rate, and the lower limit of the water inlet temperature corresponding to the optimal water inlet flow rate is taken as the optimal water inlet temperature;

[0119] Step S245: If not satisfied, update the larger water inflow flow rate and execute step S242:

[0120] Q=(Q i+1 +Qmin) / 2;

[0121] The updated larger water inlet flow rate is reused as the input of the proxy model to calculate whether there is a water inlet temperature range that meets the constraints.

[0122] Step S246: If the third water inlet temperature range does not exist, the larger water inlet flow rate is updated, and step S242 is executed:

[0123] Q=(Q i +Q i+1 ) / 2;

[0124] The updated larger water inlet flow rate is reused as the input of the proxy model to calculate whether a water inlet temperature range that satisfies the constraint condition exists.

[0125] In the second case, the minimum water inlet flow rate has a corresponding water inlet temperature range:

[0126] If the second water inlet temperature range exists, the minimum water inlet flow rate is taken as the optimal water inlet flow rate, and the lower limit of the water inlet temperature corresponding to the optimal water inlet flow rate is taken as the optimal water inlet temperature.

[0127] If the second inlet water temperature range exists, that is, there is an inlet water temperature range with a minimum inlet water flow rate that meets the constraint conditions, and the minimum inlet water flow rate, that is, the power required by the water pump to pump the minimum inlet water flow rate is the smallest, because pumping a small flow rate is more energy-efficient. Therefore, at this time, regardless of whether the first inlet water temperature range exists, there is no need to continue to search for the optimal value, and the minimum inlet water flow rate can be used as the optimal inlet water flow rate.

[0128] In the third case, there is no corresponding water inlet temperature range for both the maximum and minimum water inlet flow rates:

[0129] If neither the first water inlet temperature interval nor the second water inlet temperature interval exists, then there is no optimal value of the water inlet flow rate and the optimal value of the water inlet temperature, and the optimization search can be terminated.

[0130] In summary, by deploying the agent model to the BMS system, it can be calculated in real time whether there is a reasonable water inlet temperature range for a certain water inlet flow rate in the cooling system. If there is a reasonable water inlet temperature range, the combination of water inlet flow rate and water inlet temperature with the lowest energy consumption can be found through iterative optimization using the binary search method, thereby improving the vehicle's endurance. After analysis and comparison, the use of this battery thermal management optimal control method under the CLTC endurance condition (China Light Vehicle Test Cycle) can improve the vehicle's endurance by more than 12%.

[0131] The method also includes using the calibrated three-dimensional CAE (Computer-aided engineering) model of the battery system to train the proxy model and conduct enhanced training and upgrading after it is put into use. Figure 7 , Figure 7 This is a specific implementation flow chart of the optimal control method for battery thermal management. Figure 8 , Figure 8 The training flow chart of the proxy model includes the following steps:

[0132] Step S310: Generate training data using the calibrated three-dimensional CAE model of the battery system, and divide the training data into a training set and a validation set, wherein the training data includes different battery states of charge, battery aging states, charge and discharge rates, ambient temperatures, battery external heat exchange coefficients, battery heating time at water inlet flow and water inlet temperature of the cooling system, and maximum temperature difference between cells;

[0133] Step S320: input the training set into the proxy model for training, and use the validation set for validation.

[0134] Please see Fig. 9 , Fig. 9 The following is a flow chart for establishing and verifying a three-dimensional CAE model of a battery system. First, the establishment and verification of a three-dimensional CAE model of a battery system specifically includes the following steps:

[0135] Step S311: obtaining a detailed digital model (CAD model) of the battery system, and performing geometric cleaning on the digital model of the battery system;

[0136] Step S312: Grid division, setting corresponding boundary conditions (such as ambient temperature, heat transfer coefficient, battery operating conditions, etc.), thermal resistance parameters, etc., and establishing the corresponding battery system simulation analysis CAE model, please refer to Fig.10 , Fig.10 It is a schematic diagram of the three-dimensional CAE model of the battery system, and outputs the temperature distribution and temperature rise curve of each cell in the battery system;

[0137] Step S313: Calibrate the battery system simulation analysis CAE model: After the battery system CAE model is established, the analysis results need to be compared with the temperature data collected in the test. Fig.11 , Fig.11 This is a schematic diagram of the accuracy verification of the three-dimensional CAE model of the battery system, which is used to verify the accuracy of the CAE analysis model. If the analysis results are too different from the test results, it is necessary to adjust the corresponding parameters of the model so that the accuracy of the analysis results can meet the requirements.

[0138] Step S314: The three-dimensional CAE model calibrated by the test results can be used to analyze the heating time and maximum temperature difference of the battery under different charging rates, different heat transfer coefficients, different ambient temperatures, different battery SOC states, different battery aging states SOH, different water inlet flow rates and different water inlet temperatures. Sufficient data is generated through the three-dimensional CAE model as a data set for subsequent training of the proxy model.

[0139] Please see Fig.12 , Fig.12 This is the flow chart for agent model training and verification, specifically:

[0140] Due to the long calculation time, the three-dimensional CAE model can only analyze a limited number of input parameters. The input parameters are usually analyzed by using a 3D battery thermal model to analyze the sensitivity of each input parameter to the results, and then different input levels are designed for different input parameters according to the sensitivity ranking. In the DOE test design, 4-5 input levels are generally selected for each parameter, but the input level of input parameters with high sensitivity can be appropriately increased, and the input level of input parameters with low sensitivity can be appropriately reduced. Run the 3D battery thermal model to analyze different test designs and generate result data, including the maximum temperature difference and heating time between single cells. The data generated by the 3D battery thermal model is divided into two categories, namely training set and validation set. The training set generally accounts for 80% of the result data and is mainly used to train the proxy model. The remaining result data is classified as a validation set, which is mainly used to verify the effectiveness of the proxy model.

[0141] For example, the proxy model can adopt an artificial neural network model, such as a deep neural network DNN, a convolutional neural network CNN, and a recurrent neural network RNN, etc. Here, DNN is taken as an example. Fig.13 , Fig.13 The following is a schematic diagram of DNN neural network modeling. The input parameters (x1, x2, x3, x4, x5, x6, x7) include battery state of charge, battery aging state SOH, charge and discharge rate, ambient temperature, battery external heat exchange coefficient, cooling system water flow rate and cooling system water temperature. The neural network model can use multiple hidden layers, and each layer uses multiple neurons. Fig.13The modeling process with two hidden layers and 14 neurons in each hidden layer is shown. Output parameters (y1, y2). For low temperature heating conditions, the output parameters are heating time and maximum temperature difference between cells.

[0142] For intensive training and upgrades after later commissioning, please refer to Fig.14 , Fig.14 This is a flowchart for proxy model operation, cloud-based intensive training, and OTA (Over-The-Air technology) upgrades. Specifically:

[0143] After the proxy model is deployed to the BMS control system, it can calculate the optimal water inlet flow and water inlet temperature of the liquid cooling system at any time according to the operating status and working conditions of the battery;

[0144] The NTC (Negative Temperature Coefficient) temperature sensor arranged on the battery system can collect the temperature data of the battery cell in real time. This data can be uploaded to the cloud and used as calibration and comparison data for the proxy model.

[0145] Data such as the water inlet flow rate of the liquid cooling system, the water inlet temperature control range, the current battery status SOC and SOH, the discharge rate, and the ambient temperature can all be uploaded to the cloud in real time. The cloud can further enhance the training of the proxy model based on the original training data and the newly uploaded data during operation.

[0146] The model after intensive training can output the predicted temperature of the NTC collection point and compare it with the measured temperature to further improve the model accuracy.

[0147] When the prediction results of the proxy model are compared with the test data and the accuracy meets the requirements, the proxy model deployed on the vehicle side can be upgraded regularly through OTA to ensure that the model becomes more accurate and up-to-date with frequent use.

[0148] In summary, the vehicle-side operating data can be uploaded to the cloud in real time, which can continuously strengthen the training model and thus improve the accuracy of the proxy model. The vehicle-side model upgraded through OTA can be used frequently and become more accurate with use.

[0149] Example 3

[0150] The present application embodiment provides a battery thermal management optimal control device, which is applied to the battery thermal management optimal control method described in Embodiments 1-2. Fig.15 , Fig.15 This is a structural block diagram of a battery thermal management optimal control device, which includes but is not limited to:

[0151] The water inlet temperature interval judgment module 100 is used to use a pre-trained proxy model to judge whether any water inlet flow rate has a water inlet temperature interval that meets the constraint conditions;

[0152] The optimization module 200 is used to perform iterative optimization using a binary search method to obtain optimal control parameters of the water inlet flow rate and the water inlet temperature if there is a water inlet temperature range;

[0153] The proxy model is trained by using the water inlet flow rate and water inlet temperature of the cooling system as input parameters and the battery physical quantities corresponding to the constraint conditions as output parameters.

[0154] Please see Fig.16 , Fig.16 It is a structural block diagram of another battery thermal management optimal control device, which specifically includes:

[0155] A water inlet flow interval determination module 110, configured to determine a water inlet flow interval of a cooling system based on current operating conditions and water pump power;

[0156] A first water inlet temperature interval determination module 120, configured to determine whether there is a first water inlet temperature interval that satisfies the constraint condition based on the maximum water inlet flow rate in the water inlet flow rate interval and using the proxy model;

[0157] A second water inlet temperature interval determination module 130, configured to determine whether there is a second water inlet temperature interval that satisfies the constraint condition by using the proxy model based on the minimum water inlet flow rate of the water inlet flow rate interval;

[0158] A first optimization module 140 is used to perform iterative optimization using a binary search method to obtain optimal control parameters of the water inlet flow rate and the water inlet temperature if the first water inlet temperature interval exists and the second water inlet temperature interval does not exist;

[0159] The constraints are expressed as follows: the battery heating time and the maximum temperature difference between the cells are lower than the preset values ​​respectively.

[0160] Specifically:

[0161] If the first water inlet temperature interval exists and the second water inlet temperature interval does not exist, calculate the larger water inlet flow rate:

[0162] Q1=(Qmax+Qmin) / 2;

[0163] Among them, Q max Indicates the maximum water flow rate, Q min Indicates the minimum value of water inflow;

[0164] Taking the larger water inlet flow rate as the input of the proxy model, calculating whether a third water inlet temperature range that satisfies the constraint condition exists;

[0165] If the third water inlet temperature range exists, determine whether the cutoff condition for terminating the optimization is met:

[0166] Q i -Q i+1 <D;

[0167] Among them, Q i represents the previous larger inflow rate that meets the conditions, Q i+1 Indicates the current maximum water inflow, and D indicates the preset value;

[0168] If satisfied, the optimization is terminated, and the current larger water inlet flow rate is taken as the optimal value of the water inlet flow rate, and the lower limit of the water inlet temperature corresponding to the optimal value of the water inlet flow rate is taken as the optimal value of the water inlet temperature;

[0169] If not satisfied, update the larger water inflow:

[0170] Q=(Q i+1 +Qmin) / 2;

[0171] The updated larger water inlet flow rate is reused as the input of the proxy model to calculate whether a water inlet temperature range that satisfies the constraint condition exists.

[0172] If the third water inlet temperature range does not exist, the larger water inlet flow rate is updated:

[0173] Q=(Q i +Q i+1 ) / 2;

[0174] The updated larger water inlet flow rate is reused as the input of the proxy model to calculate whether a water inlet temperature range that satisfies the constraint condition exists.

[0175] The second optimization module 150 is used to take the minimum inlet water flow rate as the optimal inlet water flow rate and the lower limit of the inlet water temperature corresponding to the optimal inlet water flow rate as the optimal inlet water temperature if the second inlet water temperature range exists.

[0176] The third optimization module 160 is used to determine that if neither the first water inlet temperature interval nor the second water inlet temperature interval exists, then there is no optimal value of the water inlet flow rate and the optimal value of the water inlet temperature.

[0177] The device also includes a model training module 300:

[0178] Generate training data using the calibrated three-dimensional CAE model of the battery system, and divide the training data into a training set and a validation set, wherein the training data includes a water inlet flow rate of the cooling system and a battery heating time at a water inlet temperature and a maximum temperature difference between battery cells;

[0179] The training set is input into the proxy model for training, and the validation set is used for validation.

[0180] The specific training process has been specifically described in the above embodiments and will not be repeated here.

[0181] An embodiment of the present application also provides an electronic device, which includes a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the above-mentioned battery thermal management optimal control method.

[0182] An embodiment of the present application further provides a readable storage medium, wherein the readable storage medium stores computer program instructions, and when the computer program instructions are read and executed by a processor, the above-mentioned battery thermal management optimal control method is executed.

[0183] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0184] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0185] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0186] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0187] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0188] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A battery thermal management optimal control method, characterized in that: The method comprises: Use the pre-trained proxy model to determine whether there is a water inlet temperature range that meets the constraint conditions for any water inlet flow rate; If it exists, the binary search method is used to iterate and optimize to obtain the optimal control parameters of the water inlet flow rate and water inlet temperature; The proxy model is trained by using the water inlet flow rate and water inlet temperature of the cooling system as input parameters and the battery physical quantities corresponding to the constraint conditions as output parameters.

2. The battery thermal management optimal control method according to claim 1, characterized in that: The method of using the pre-trained proxy model to determine whether any water inlet flow rate has a water inlet temperature range that satisfies the constraint condition includes: Determine the water flow range of the cooling system based on the current operating conditions and water pump power; Based on the maximum water inlet flow rate in the water inlet flow rate interval, using the proxy model to determine whether there is a first water inlet temperature interval that meets the constraint condition; Based on the minimum water inlet flow rate in the water inlet flow rate interval, using the proxy model to determine whether there is a second water inlet temperature interval that meets the constraint condition; If the first water inlet temperature interval exists and the second water inlet temperature interval does not exist, the binary search method is used to iteratively search for the optimal control parameters of the water inlet flow rate and the water inlet temperature; The constraints are expressed as follows: the battery heating time and the maximum temperature difference between the cells are lower than the preset values ​​respectively.

3. The battery thermal management optimal control method according to claim 2, characterized in that: If the first water inlet temperature interval exists and the second water inlet temperature interval does not exist, iterative optimization is performed using a binary search method to obtain optimal control parameters of the water inlet flow rate and the water inlet temperature, including: If the first water inlet temperature interval exists and the second water inlet temperature interval does not exist, calculate the larger water inlet flow rate: Q1=(Qmax+Qmin) / 2; Among them, Q max Indicates the maximum water flow rate, Q min Indicates the minimum value of water inflow; Taking the larger water inlet flow rate as the input of the proxy model, determining whether a third water inlet temperature range that satisfies the constraint condition exists; If the third water inlet temperature range exists, determine whether the cutoff condition for terminating the optimization is met: Q i -Q i+1 <D; Among them, Q i represents the previous larger inflow rate that meets the conditions, Q i+1 Indicates the current maximum water inflow, and D indicates the preset value; If satisfied, the optimization is terminated, and the current larger water inlet flow rate is taken as the optimal value of the water inlet flow rate, and the lower limit of the water inlet temperature corresponding to the optimal value of the water inlet flow rate is taken as the optimal value of the water inlet temperature; If not satisfied, update the larger water inflow: Q=(Q i+1 +Qmin) / 2; The updated larger water inlet flow rate is reused as the input of the proxy model to calculate whether a water inlet temperature range that satisfies the constraint condition exists.

4. The battery thermal management optimal control method according to claim 3, characterized in that: The method further comprises: If the third water inlet temperature range does not exist, the larger water inlet flow rate is updated: Q=(Q i +Q i+1 ) / 2; The updated larger water inlet flow rate is reused as the input of the proxy model to calculate whether a water inlet temperature range that satisfies the constraint condition exists.

5. The battery thermal management optimal control method according to claim 2, characterized in that: The method further comprises: If the second water inlet temperature interval exists, the minimum water inlet flow rate is used as the optimal water inlet flow rate, and the lower limit of the water inlet temperature corresponding to the optimal water inlet flow rate is used as the optimal water inlet temperature.

6. The battery thermal management optimal control method according to claim 2, characterized in that: The method further comprises: If neither the first water inlet temperature interval nor the second water inlet temperature interval exists, then there is no optimal value of the water inlet flow rate and the optimal value of the water inlet temperature.

7. The battery thermal management optimal control method according to claim 1, characterized in that: Before the step of using the pre-trained proxy model to determine whether any water inlet flow rate has a water inlet temperature range that satisfies the constraint condition, the method further includes: Generate training data using the calibrated three-dimensional CAE model of the battery system, and divide the training data into a training set and a validation set, wherein the training data includes a water inlet flow rate of the cooling system and a battery heating time at a water inlet temperature and a maximum temperature difference between battery cells; The training set is input into the proxy model for training, and the validation set is used for validation.

8. A battery thermal management optimal control device, characterized in that: The device comprises: The water inlet temperature interval judgment module is used to use the pre-trained proxy model to determine whether there is a water inlet temperature interval that meets the constraint conditions for any water inlet flow rate; The optimization module is used to iteratively optimize the water inlet flow rate and water inlet temperature by using the binary search method if there is a water inlet temperature range; The proxy model is trained by using the water inlet flow rate and water inlet temperature of the cooling system as input parameters and the battery physical quantities corresponding to the constraint conditions as output parameters.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the battery thermal management optimal control method according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores computer program instructions, and when the computer program instructions are read and executed by a processor, the battery thermal management optimal control method according to any one of claims 1 to 7 is executed.

Images