Parameter calibration method and device of thermal management system, vehicle and electronic equipment

Abstract

The invention discloses a parameter calibration method and device for a thermal management system, a vehicle and electronic equipment, and the method comprises the steps: obtaining a vehicle system state of a thermal management system simulation model, inputting the vehicle system state into a thermal management system control model, and inputting a control instruction outputted by the thermal management system control model into the thermal management system simulation model; determining at least two output targets of the thermal management system simulation model and corresponding loss functions, and determining a to-be-calibrated quantity in the thermal management system control model; and determining the to-be-calibrated quantity enabling the loss function to be optimal as a target calibration parameter. Compared with a calibration mode of a computer-aided calibration engineer, a mode of automatically calibrating the thermal management system is adopted, the problems that a mode of manually adjusting calibration parameters is poor in reusability and long in consumed time are solved, meanwhile, the basis of parameter calibration is quantified, and the calibration parameters are optimal.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle technology, and in particular to a parameter calibration method and device for a thermal management system, a vehicle, and an electronic device. Background Art

[0002] When calibrating parameters in a thermal management system, software engineers usually set initial parameters based on their own experience during the software development process. Calibration engineers then modify the initial parameters based on the performance of the vehicle during a large number of road tests and environmental chamber tests to obtain calibration parameters.

[0003] However, the above manual adjustment of calibration parameters relies on the experience of calibration engineers, it is difficult to quantify the calibration basis, the reusability is poor, and it takes a long time. In order to solve the problem of time-consuming manual labeling, the relevant technology adopts the method of computer-assisted calibration engineers to perform calibration. Although this method reduces the burden of calibration engineers, it still requires manual control of the computer to select a preset number of parameters for calibration. Therefore, this method cannot determine whether the calibration parameters are optimal. Summary of the invention

[0004] The present disclosure provides a parameter calibration method and device for a thermal management system, a vehicle and an electronic device. The main purpose is to solve the problem that the calibration method of computer-aided calibration engineers still requires manual control of the computer to select a preset number of parameters for calibration, and it is impossible to determine whether the calibration parameters are optimal.

[0005] According to a first aspect of the present disclosure, a parameter calibration method for a thermal management system is provided, comprising:

[0006] Acquire the vehicle system state of the thermal management system simulation model, input the vehicle system state into the thermal management system control model, and input the control instruction output by the thermal management system control model into the thermal management system simulation model, wherein the thermal management system simulation model is used to calculate the vehicle system state according to the environmental parameters of the vehicle and the control instruction, and the thermal management system control model is used to generate the control instruction according to the environmental parameters of the vehicle and the vehicle system state;

[0007] Determine at least two output targets and corresponding loss functions of the thermal management system simulation model, and determine the quantity to be calibrated in the thermal management system control model, wherein the vehicle system state output includes the at least two output targets, and the parameter value of each quantity to be calibrated will affect the value of the loss function;

[0008] The quantity to be calibrated that makes the loss function optimal is determined as the target calibration parameter.

[0009] Optionally, the at least two output targets include a passenger compartment temperature target, a battery temperature target, a thermal management system energy consumption target, and a system stability target;

[0010] The determining of at least two output targets of the thermal management system simulation model and corresponding loss functions includes:

[0011] defining a first loss function corresponding to the passenger compartment temperature target according to a square root of a quotient of a sum of squares of differences between a passenger compartment real-time temperature and a passenger compartment target temperature and a simulation time, wherein the simulation time is an execution time of the thermal management system simulation model;

[0012] A second loss function corresponding to the battery temperature target is defined according to the square root of the quotient of the penalty value exceeding the battery safety range and the simulation time, wherein the penalty value exceeding the battery safety range is a piecewise function based on the actual battery temperature and the battery safety range;

[0013] Defining a third loss function corresponding to the energy consumption target of the thermal management system according to the product of the sum of the energy consumption related parameters and the correlation coefficient;

[0014] According to the status information of the operating parameters of each component of the vehicle, a fourth loss function corresponding to the system stability target is defined.

[0015] Optionally, after determining at least two output targets of the thermal management system simulation model and corresponding loss functions, the method further includes:

[0016] Based on the preset weights corresponding to each loss function, the first loss function, the second loss function, the third loss function and the fourth loss function are linearly calculated to obtain the target loss function, and the linear calculation is the sum of the products of each loss function and the corresponding weight.

[0017] Optionally, determining the amount to be calibrated that optimizes the loss function as a target calibration parameter includes:

[0018] Call a preset algorithm to calculate the quantity to be calibrated that makes the loss function optimal, and determine the optimal quantity to be calibrated as the target calibration parameter, wherein the preset algorithm is at least one heuristic algorithm, which can iteratively calculate the target loss function based on the target loss function and the current calibration quantity to make it reach the optimal point, or reach a preset number of iterations.

[0019] Optionally, the calling of a preset particle swarm algorithm to calculate the amount to be calibrated that makes the loss function optimal, and determining the optimal amount to be calibrated as the target calibration parameter includes:

[0020] Calculate the objective function value corresponding to the objective loss function when the calibration quantities of the thermal management system simulation model are respectively the quantities to be calibrated;

[0021] The preset update algorithm is called to update the candidate calibration value until the objective function value corresponding to the candidate calibration value reaches a preset condition, and the candidate calibration value is determined as the target calibration parameter.

[0022] A parameter calibration device for a thermal management system, comprising:

[0023] An input unit, used to obtain a vehicle system state of a thermal management system simulation model, and input the vehicle system state into a thermal management system control model, and input a control instruction output by the thermal management system control model into the thermal management system simulation model, wherein the thermal management system simulation model is used to calculate the vehicle system state according to the environmental parameters of the vehicle and the control instruction, and the thermal management system control model is used to generate the control instruction according to the environmental parameters of the vehicle and the vehicle system state;

[0024] A first determining unit, used to determine at least two output targets of the thermal management system simulation model and corresponding loss functions;

[0025] A second determination unit is used to determine a quantity to be calibrated in the thermal management system control model, wherein the vehicle system state output includes the at least two output targets, and a parameter value of each quantity to be calibrated will affect a value of a loss function;

[0026] The third determining unit is used to determine the quantity to be calibrated that makes the loss function optimal as a target calibration parameter.

[0027] The at least two output targets of the thermal management system simulation model include a passenger compartment temperature target, a battery temperature target, a thermal management system energy consumption target, and a system stability target;

[0028] Optionally, the first determining unit includes:

[0029] a first definition module, configured to define a first loss function corresponding to the passenger compartment temperature target according to a square root of a quotient of a sum of squares of differences between a real-time passenger compartment temperature and a target passenger compartment temperature and a simulation time, wherein the simulation time is an execution time of the thermal management system simulation model;

[0030] A second definition module is used to define a second loss function corresponding to the battery temperature target according to the square root of the quotient of the penalty value exceeding the battery safety range and the simulation time, wherein the penalty value exceeding the battery safety range is a piecewise function based on the actual battery temperature and the battery safety range;

[0031] A third definition module, used to define a third loss function corresponding to the energy consumption target of the thermal management system according to the product of the sum of the energy consumption related parameters and the correlation coefficient;

[0032] The fourth definition module is used to define a fourth loss function corresponding to the system stability target according to the state information of the operating parameters of each component of the vehicle.

[0033] Optionally, the first determination unit is also used to perform linear calculations on the first loss function, the second loss function, the third loss function and the fourth loss function based on preset weights corresponding to each loss function to obtain a target loss function after the first determination unit determines at least two output targets and corresponding loss functions of the thermal management system simulation model, wherein the linear calculation is the sum of the products of each loss function and the corresponding weights.

[0034] Optionally, the third determination unit is further used to call a preset algorithm to calculate the quantity to be calibrated that makes the loss function optimal, and determine the optimal quantity to be calibrated as the target calibration parameter, wherein the preset algorithm is at least one heuristic algorithm, which can iteratively calculate the target loss function based on the target loss function and the current calibration quantity so that the target loss function reaches the optimal point, or reaches a preset number of iterations.

[0035] Optionally, the third determining unit includes:

[0036] A calculation module, used for calculating the objective function value corresponding to the objective loss function when the calibration quantities of the thermal management system simulation model are respectively the quantities to be calibrated;

[0037] An updating module, used to call a preset updating algorithm to update the candidate calibration value until the objective function value corresponding to the candidate calibration value meets a preset condition;

[0038] A determination module is used to determine the candidate calibration value as the target calibration parameter.

[0039] According to a third aspect of the present disclosure, a vehicle is provided, comprising a parameter calibration device for a thermal management system.

[0040] According to a fourth aspect of the present disclosure, there is provided an electronic device, including:

[0041] at least one processor; and

[0042] a memory communicatively connected to the at least one processor; wherein,

[0043] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0044] According to a fifth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described in the first aspect.

[0045] According to a sixth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0046] The parameter calibration method and device of the thermal management system provided by the present disclosure, the vehicle and the electronic device, obtain the vehicle system state of the thermal management system simulation model, input the vehicle system state into the thermal management system control model, input the control instruction output by the thermal management system control model into the thermal management system simulation model, wherein the thermal management system simulation model is used to calculate the vehicle system state according to the environmental parameters of the vehicle and the control instruction, and the thermal management system control model is used to generate the control instruction according to the environmental parameters of the vehicle and the vehicle system state; determine at least two output targets and corresponding loss functions of the thermal management system simulation model, and determine the quantity to be calibrated in the thermal management system control model, wherein the vehicle system state output includes the at least two output targets, and the parameter values ​​of each quantity to be calibrated will affect the value of the loss function; determine the quantity to be calibrated that makes the loss function optimal as the target calibration parameter. The present disclosure adopts the method of automatically calibrating the thermal management system. Compared with the method of calibration by computer-aided calibration engineers, while solving the problem of poor reusability and long time consumption of the method of manually adjusting the calibration parameters, it quantifies the basis of parameter calibration and makes the calibration parameters optimal.

[0047] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0049] Figure 1 A schematic flow chart of a parameter calibration method for a thermal management system provided by an embodiment of the present disclosure;

[0050] Figure 2 A flow chart of a method for defining a loss function provided in an embodiment of the present disclosure;

[0051] Figure 3 A flow chart of a method for determining target calibration parameters provided in an embodiment of the present disclosure;

[0052] Figure 4A schematic diagram of the structure of a parameter calibration device for a thermal management system provided in an embodiment of the present disclosure;

[0053] Figure 5 A schematic diagram of the structure of another parameter calibration device for a thermal management system provided by an embodiment of the present disclosure;

[0054] Figure 6 A schematic block diagram of an exemplary electronic device 500 provided for an embodiment of the present disclosure. DETAILED DESCRIPTION

[0055] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0056] The following describes a parameter calibration method and apparatus for a thermal management system, a vehicle, and an electronic device according to an embodiment of the present disclosure with reference to the accompanying drawings.

[0057] Figure 1 A schematic flow chart of a parameter calibration method for a thermal management system provided in an embodiment of the present disclosure.

[0058] like Figure 1 As shown, the method comprises the following steps:

[0059] Step 101, obtain the vehicle system state of the thermal management system simulation model, and input the vehicle system state into the thermal management system control model, and input the control instructions output by the thermal management system control model into the thermal management system simulation model, wherein the thermal management system simulation model is used to calculate the vehicle system state according to the environmental parameters of the vehicle and the control instructions, and the thermal management system control model is used to generate the control instructions according to the environmental parameters of the vehicle and the vehicle system state.

[0060] In order to realize the thermal management system control model to control the thermal management system simulation model to perform parameter calibration, the thermal management system simulation model feeds back the system state to the thermal management system control model, and uses the output of the thermal management system simulation model as the input of the thermal management system control model, and the output of the thermal management system control model as the input of the thermal management system simulation model, so that the thermal management system simulation model and the thermal management system control model form a logical closure to form a joint simulation model, wherein the output of the thermal management system simulation model is the vehicle system state calculated according to the vehicle environment parameters and control instructions, the output of the thermal management system control model is the control instruction generated according to the vehicle environment parameters and the vehicle system state, and the thermal management system control model contains modifiable calibration parameters. The thermal management system simulation model can receive the vehicle environment parameters and control instructions as input, and the environment parameters include but are not limited to the vehicle outside temperature, the initial vehicle interior temperature, the initial battery temperature, the vehicle outside humidity, the vehicle outside light, etc.; the control instruction is generated according to the system state fed back to the thermal management system control model by the thermal management system simulation model, as the output of the thermal management system control model. The thermal management system control model can receive the vehicle's environmental parameters and the vehicle system status as input. The vehicle's environmental parameters include but are not limited to the outside temperature, the initial inside temperature, the initial battery temperature, the outside humidity, the outside light, etc.; the vehicle system status includes but is not limited to the high and low pressures of the refrigerant system, the real-time inside temperature, the real-time battery temperature and the system energy consumption, etc.

[0061] In the embodiment of the present application, in order to obtain the vehicle system state as the input of the thermal management system control model, the thermal management system simulation model calculates the vehicle system state according to the vehicle ambient temperature and the control instruction. In order to obtain the control instruction as the input of the thermal management simulation model, the thermal management system control model generates the control instruction according to the vehicle ambient temperature and the vehicle system state.

[0062] Step 102: Determine at least two output targets of the thermal management system simulation model and corresponding loss functions.

[0063] In an embodiment of the present application, at least two output targets of the thermal management system simulation model include but are not limited to: a passenger compartment temperature target, a battery temperature target, a thermal management system energy consumption target, and a system stability target under specific operating conditions. The specific operating conditions are not limited to: cooling conditions, heating conditions, dehumidification conditions, etc.

[0064] In an embodiment of the present application, the loss function is defined according to the output target. In order to obtain different loss functions, at least two output targets can be selected for combination according to the requirements of different vehicle model projects. One output target corresponds to one loss function, that is, the number of output targets is the same as the number of loss functions.

[0065] Step 103 , determining the quantity to be calibrated in the thermal management system control model, wherein the vehicle system state output includes the at least two output targets, and the parameter value of each quantity to be calibrated will affect the value of the loss function.

[0066] After determining at least two output targets and corresponding loss functions of the thermal management system simulation model, the quantity to be calibrated in the thermal management system control model is determined according to the output targets and the corresponding loss functions, and then the quantity to be calibrated is calculated by a preset algorithm to determine the optimal calibration quantity in the thermal management system control model. Among them, the preset algorithm includes but is not limited to a heuristic algorithm, which is a search algorithm based on experience and rules. It evaluates each possible solution through a heuristic function and selects the solution that is most likely to lead to the optimal solution for expansion. Heuristic algorithms are usually used to solve NP-hard (Non-deterministic Polynomial Hard) problems, such as the traveling salesman problem and the knapsack problem. The advantage of the heuristic algorithm is that a better solution can be found in a shorter time, but the disadvantage is that it cannot guarantee the global optimal solution. Common heuristic algorithms include genetic algorithms, annealing algorithms, particle swarm algorithms, etc. In addition, the parameter values ​​of each quantity to be calibrated will affect the value of the corresponding loss function.

[0067] Step 104, determining the calibration amount that optimizes the loss function as the target calibration parameter.

[0068] In the embodiment of the present application, the loss function determined in step 102 is used as the fitness function of the heuristic algorithm. The heuristic algorithm described in the embodiment of the present invention can adopt but is not limited to common heuristic algorithms, such as particle swarm algorithm, genetic algorithm, annealing algorithm, etc. The heuristic algorithm can calculate the calibration parameters of the thermal management system control model of the next iteration according to the value of the loss function and the quantity to be calibrated in a certain iteration, until the quantity to be calibrated of the thermal management system control model can make the loss function reach the global optimal point (minimum value) or reach the specified number of iterations.

[0069] In order to update the modifiable calibration parameters contained in the thermal management system control model, the parameter value of the quantity to be calibrated that makes the loss function optimal is determined as the target calibration parameter. The loss function characterizes the achievement of the output target. The smaller the loss function value, the higher the target achievement. Therefore, the optimal calibration quantity of the loss function is the calibration quantity that minimizes the target loss function value. The parameter value of the calibration quantity that makes the loss function optimal is determined as the target calibration parameter and updated to the thermal management system control model.

[0070] The parameter calibration method of the thermal management system provided by the present disclosure obtains the vehicle system state of the thermal management system simulation model, and inputs the vehicle system state into the thermal management system control model, and inputs the control instruction output by the thermal management system control model into the thermal management system simulation model; the thermal management system simulation model is used to calculate the vehicle system state according to the environmental parameters of the vehicle and the control instruction, and the thermal management system control model is used to generate the control instruction according to the environmental parameters of the vehicle and the vehicle system state; at least two output targets and corresponding loss functions of the thermal management system simulation model are determined, and the quantity to be calibrated in the thermal management system control model is determined, wherein the vehicle system state output includes the at least two output targets, and the parameter value of each quantity to be calibrated will affect the value of the loss function; the quantity to be calibrated that makes the loss function optimal is determined as the target calibration parameter. The present disclosure adopts the method of automatically calibrating the thermal management system. Compared with the method of calibration by computer-aided calibration engineers, while solving the problem of poor reusability and long time consumption of the method of manually adjusting the calibration parameters, it quantifies the basis of parameter calibration and makes the calibration parameters optimal.

[0071] In some embodiments, at least two output targets of the thermal management system simulation model may include but are not limited to a passenger compartment temperature target, a battery temperature target, a thermal management system energy consumption target, and a system stability target.

[0072] In some embodiments, the at least two output targets and corresponding loss functions of the thermal management system simulation model can be determined by, but should not be limited to, the following method. Figure 2 , Figure 2 A flow chart of a method for defining a loss function provided in an embodiment of the present disclosure.

[0073] like Figure 2 As shown, the method comprises the following steps:

[0074] Step 201, defining a first loss function corresponding to the passenger compartment temperature target according to the square root of the quotient of the sum of the squares of the difference between the real-time passenger compartment temperature and the target passenger compartment temperature and the simulation time, wherein the simulation time is the execution time of the thermal management system simulation model.

[0075] Based on the passenger compartment temperature target, the first loss function is defined as the square root of the quotient of the sum of the squares of the difference between the real-time temperature of the passenger compartment and the target temperature of the passenger compartment and the simulation time. For a better understanding of the definition of the first loss function, please refer to formula (1).

[0076]

[0077] In formula (1), C cabin is the cabin temperature target, t cabin，i is the real-time temperature of the passenger compartment, t cabin，tgt is the target temperature of the passenger compartment, and T is the simulation time of the thermal management system simulation model. Based on the above formula (1), the first loss function corresponding to the target temperature of the passenger compartment is obtained.

[0078] Step 202, defining a second loss function corresponding to the battery temperature target according to the square root of the quotient of the penalty value exceeding the battery safety range and the simulation time, wherein the penalty value exceeding the battery safety range is a piecewise function based on the actual battery temperature and the battery safety range.

[0079] Based on the battery safety goal, the second loss function is defined as the square root of the sum of the penalty values ​​exceeding the battery safety range and the simulation time, wherein the penalty value exceeding the battery safety range is a piecewise function based on the actual battery temperature and the battery safety range. When the actual battery temperature exceeds or falls below the safety threshold, the value of the second loss function is maximum. When the actual battery temperature is within the battery safety range, the second loss function is a quadratic function, as shown in formula (2)(3), wherein formula 2 is the formula corresponding to defining the second loss function, and formula (3) is the penalty value exceeding the battery safety range.

[0080]

[0081]

[0082] Among them, C batt is the battery temperature target, f loss is the penalty value for exceeding the battery safety range, C batt，i is the actual battery temperature, t batt，tgt is the battery target temperature, Step 203: define a third loss function corresponding to the energy consumption target of the thermal management system according to the product of the sum of the energy consumption related parameters and the correlation coefficient.

[0083] The lower the energy consumption of the thermal management system, the more beneficial it is to the vehicle's endurance. Therefore, the third loss function defined based on the energy consumption target of the thermal management system is a function that is positively correlated with the energy consumption of the thermal management system, as shown in formula (4).

[0084] C power =a(P cmp +P fan +P pump +P blwr ) (4)

[0085] Among them, C power is the energy consumption target of the thermal management system, P cmp is the compressor power, P fan is the fan power, P pump is the pump power, P blwr is the blower power, and a is the correlation coefficient.

[0086] Step 204: Define a fourth loss function corresponding to the system stability target according to the status information of the operating parameters of each component of the vehicle.

[0087] For the thermal management system, stable operation of the system is very important to the vehicle performance and system life. Therefore, based on the stability target of the thermal management system, the fourth loss function is defined as a function related to the fluctuation of the operating parameters of each component, as shown in formula (5), where (Sp) represents the curve of the operating state of a component of the thermal management system changing with time, such as the compressor speed, and std() represents the standard deviation function. Therefore, the greater the fluctuation of the operating state of a component of the thermal management system, the lower the C stable The bigger.

[0088] C stable =∑std(Sp) (5)

[0089] Among them, C stable is the system stability target, (Sp) represents the curve of the operating status of a component of the thermal management system changing with time, such as the compressor speed, and std() represents the standard deviation function.

[0090] After determining at least two output targets and corresponding loss functions of the thermal management system simulation model, the first loss function, the second loss function, the third loss function and the fourth loss function are linearly calculated based on the preset weights corresponding to each loss function to obtain the target loss function.

[0091] The objective loss function calculation formula is shown in formula (6):

[0092] C=K1C Cabin +K2C batt +K3C power +K4Cstable (6)

[0093] Among them, C represents the target loss function, K1, K2, K3, K4 are the weights of each sub-item loss function, C Cabin is the cabin temperature target, C batt is the battery temperature target, C power is the energy consumption target of the thermal management system, C stable For the purpose of system stability, individual weight values ​​can be appropriately increased or decreased according to the project focus.

[0094] In some embodiments, in order to determine the quantity to be calibrated that makes the loss function optimal as the target calibration parameter, the following methods may be used but are not limited to: calling a preset algorithm to calculate the quantity to be calibrated that makes the loss function optimal, and determining the optimal quantity to be calibrated as the target calibration parameter. The preset algorithm may use but is not limited to a heuristic algorithm.

[0095] The calling of the preset algorithm to calculate the quantity to be calibrated that makes the loss function optimal, and determining the optimal quantity to be calibrated as the target calibration parameter can be implemented by but not limited to the following methods. Taking the particle swarm algorithm as an example, the particle swarm algorithm is a heuristic algorithm. Please refer to Figure 3 , Figure 3 A flow chart of a method for determining target calibration parameters provided in an embodiment of the present disclosure.

[0096] like Figure 3 As shown, the method comprises the following steps:

[0097] Step 301 , calculating the objective function value corresponding to the objective loss function when the calibration quantities of the thermal management system simulation model are respectively the quantities to be calibrated.

[0098] In the embodiment of the present application, the quantities to be calibrated in the thermal management control model are determined, and all the quantities to be calibrated are combined into a vector Cali. Randomly initialize m candidate calibration quantities and their initial speeds (initial change directions), Cali1, Cali2...Cali m 、V1,V2…V m Entering the iteration process, the one-dimensional simulation model of the thermal management system is calculated when the calibration quantities are equal to Cali1, Cali2…Cali m The objective function value at .

[0099] Step 302: Call a preset update algorithm to update the candidate calibration value until the objective function value corresponding to the candidate calibration value meets a preset condition.

[0100] In some embodiments, in order to find a candidate calibration value Cali that can minimize the objective function among the current candidate calibration values, gbest, and the calibration value Cali that each candidate calibration value can minimize the objective function in each previous iteration i，pbest , call the preset update algorithm and update the candidate calibration quantity according to formula (7),

[0101] Cali i =Cali i +αV i +r1(Cali gbest -Cali i )+r2(Cali i，pbest -Cali i ) (7)

[0102] In the formula, Cali i is the i-th calibration value among the m candidate calibration values, V i For Cali i The corresponding initial velocity, Cali gbest is the candidate calibration value that can minimize the objective function among the current candidate calibration values. i，pbest For each candidate calibration, the calibration value that can minimize the objective function in each previous iteration is used. r1 and r2 are random numbers between (0, 1). α is the initial velocity, which can be reduced as the number of iterations increases.

[0103] Iterate and update multiple times until the candidate calibration value Cali that can minimize the objective function is found among the current candidate calibration values. gbest The corresponding objective function value reaches the expected range or the number of iterations reaches the target number of iterations.

[0104] Step 303: determine the candidate calibration value as the target calibration parameter.

[0105] When the objective function value corresponding to the candidate calibration value that can minimize the objective function among the candidate calibration quantities reaches the expected range or the number of iterations reaches the target number of iterations, the candidate calibration value is the optimal calibration value, and the candidate calibration value is determined as the target calibration parameter.

[0106] The above formula is not intended to limit the updating of the target calibration parameters to be achieved only through the above formula, and other methods are not limited in the embodiments of the present application.

[0107] In summary, the embodiments of the present disclosure can achieve the following effects:

[0108] 1. Construct a thermal management system simulation model and a thermal management system control model, establish an objective function for automated calibration based on the passenger compartment temperature target, battery temperature target, thermal management system energy consumption target, and system stability target, and quantify the basis for calibration parameter correction.

[0109] 2. Using the preset update algorithm, search for the calibration parameter combination that can achieve the optimal objective function.

[0110] Corresponding to the above-mentioned parameter calibration method of the thermal management system, the present invention also proposes a parameter calibration device for the thermal management system. Since the device embodiment of the present invention corresponds to the above-mentioned method embodiment, the details not disclosed in the device embodiment can be referred to the above-mentioned method embodiment, and will not be repeated in the present invention.

[0111] Figure 4 A schematic diagram of a parameter calibration device for a thermal management system provided by an embodiment of the present disclosure is shown in FIG. Figure 4 As shown, including:

[0112] An input unit 41 is used to obtain a vehicle system state of a thermal management system simulation model, and input the vehicle system state into a thermal management system control model, and input a control instruction output by the thermal management system control model into the thermal management system simulation model, wherein the thermal management system simulation model is used to calculate the vehicle system state according to the environmental parameters of the vehicle and the control instruction, and the thermal management system control model is used to generate the control instruction according to the environmental parameters of the vehicle and the vehicle system state;

[0113] A first determination unit 42, configured to determine at least two output targets of the thermal management system simulation model and corresponding loss functions;

[0114] A second determination unit 43 is used to determine the quantity to be calibrated in the thermal management system control model, wherein the vehicle system state output includes the at least two output targets, and the parameter value of each quantity to be calibrated will affect the value of the loss function;

[0115] The third determining unit 44 is used to determine the quantity to be calibrated that makes the loss function optimal as a target calibration parameter.

[0116] The parameter calibration device of the thermal management system provided by the present disclosure obtains the vehicle system state of the thermal management system simulation model, and inputs the vehicle system state into the thermal management system control model, and inputs the control instruction output by the thermal management system control model into the thermal management system simulation model, wherein the thermal management system simulation model is used to calculate the vehicle system state according to the environmental parameters of the vehicle and the control instruction, and the thermal management system control model is used to generate the control instruction according to the environmental parameters of the vehicle and the vehicle system state; determines at least two output targets and corresponding loss functions of the thermal management system simulation model, and determines the quantity to be calibrated in the thermal management system control model, wherein the vehicle system state output includes the at least two output targets, and the parameter values ​​of each quantity to be calibrated will affect the value of the loss function; the quantity to be calibrated that makes the loss function optimal is determined as the target calibration parameter. The present disclosure adopts an automated calibration method for the thermal management system. Compared with the calibration method performed by computer-aided calibration engineers, while solving the problem of poor reusability and long time consumption of the manual adjustment of calibration parameters, it quantifies the basis for parameter calibration and optimizes the calibration parameters.

[0117] Furthermore, the at least two output targets include a passenger compartment temperature target, a battery temperature target, a thermal management system energy consumption target, and a system stability target.

[0118] Furthermore, in a possible implementation of this embodiment, as Figure 5 As shown, the first determining unit 42 includes:

[0119] A first definition module 421, configured to define a first loss function corresponding to the passenger compartment temperature target according to a square root of a quotient of a sum of squares of differences between a real-time passenger compartment temperature and a target passenger compartment temperature and a simulation time, wherein the simulation time is an execution time of the thermal management system simulation model;

[0120] A second definition module 422, configured to define a second loss function corresponding to the battery temperature target according to a square root of a quotient of a penalty value exceeding a battery safety range and a simulation time, wherein the penalty value exceeding a battery safety range is a piecewise function based on an actual battery temperature and a battery safety range;

[0121] A third definition module 423, used to define a third loss function corresponding to the energy consumption target of the thermal management system according to the sum of the energy consumption related parameters and the product of the correlation coefficient;

[0122] The fourth definition module 424 is used to define a fourth loss function corresponding to the system stability target according to the state information of the operating parameters of each component of the vehicle.

[0123] Furthermore, the first determination unit 42 is also used to perform linear calculations on the first loss function, the second loss function, the third loss function and the fourth loss function based on preset weights corresponding to each loss function to obtain a target loss function after the first determination unit determines at least two output targets and corresponding loss functions of the thermal management system simulation model, and the linear calculation is the sum of the products of each loss function and the corresponding weights.

[0124] Furthermore, the third determination unit 44 is also used to call a preset algorithm to calculate the quantity to be calibrated that makes the loss function optimal, and determine the optimal quantity to be calibrated as the target calibration parameter, wherein the preset algorithm is at least one heuristic algorithm, which can iteratively calculate the target loss function based on the target loss function and the current calibration quantity so that the target loss function reaches the optimal point, or reaches a preset number of iterations.

[0125] Further, the third determining unit 44 includes:

[0126] A calculation module 441 is used to calculate the objective function value corresponding to the objective loss function when the calibration quantities of the thermal management system simulation model are respectively the quantities to be calibrated;

[0127] An updating module 442 is used to call a preset updating algorithm to update the candidate calibration value until the objective function value corresponding to the candidate calibration value meets a preset condition;

[0128] The determination module 443 is used to determine the candidate calibration value as the target calibration parameter.

[0129] It should be noted that the above explanation of the method embodiment is also applicable to the device of this embodiment, and the principle is the same, which is not limited in this embodiment.

[0130] According to an embodiment of the present disclosure, the present disclosure also provides a vehicle, an electronic device, a readable storage medium, and a computer program product.

[0131] Figure 6 A schematic block diagram of an example electronic device 500 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0132] like Figure 6 As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 502 or a computer program loaded from a storage unit 508 into a RAM (Random Access Memory) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An I / O (Input / Output) interface 505 is also connected to the bus 504.

[0133] A number of components in the device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0134] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as a method for parameter calibration of a thermal management system. For example, in some embodiments, the method for parameter calibration of a thermal management system may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to execute the aforementioned parameter calibration method of the thermal management system in any other appropriate manner (for example, by means of firmware).

[0135] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SOCs (System On Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor that may be a dedicated or general-purpose programmable processor that may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0136] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0137] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include electrical connections based on one or more lines, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0138] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0139] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.

[0140] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs that run on the corresponding computers and have a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server for a distributed system, or a server combined with a blockchain.

[0141] It should be noted that artificial intelligence is a discipline that studies how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0142] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0143] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A parameter calibration method for a thermal management system, characterized in that: include: Acquire the vehicle system state of the thermal management system simulation model, input the vehicle system state into the thermal management system control model, and input the control instruction output by the thermal management system control model into the thermal management system simulation model, wherein the thermal management system simulation model is used to calculate the vehicle system state according to the environmental parameters of the vehicle and the control instruction, and the thermal management system control model is used to generate the control instruction according to the environmental parameters of the vehicle and the vehicle system state; Determine at least two output targets and corresponding loss functions of the thermal management system simulation model, and determine the quantity to be calibrated in the thermal management system control model, wherein the vehicle system state output includes the at least two output targets, and the parameter value of each quantity to be calibrated will affect the value of the loss function; The quantity to be calibrated that makes the loss function optimal is determined as the target calibration parameter.

2. The method according to claim 1, characterized in that The at least two output targets include a passenger compartment temperature target, a battery temperature target, a thermal management system energy consumption target, and a system stability target; The determining of at least two output targets of the thermal management system simulation model and corresponding loss functions includes: defining a first loss function corresponding to the passenger compartment temperature target according to a square root of a quotient of a sum of squares of differences between a passenger compartment real-time temperature and a passenger compartment target temperature and a simulation time, wherein the simulation time is an execution time of the thermal management system simulation model; Define a second loss function corresponding to the battery temperature target according to the square root of the quotient of the sum of the penalty values ​​exceeding the battery safety range and the simulation time, wherein the penalty value exceeding the battery safety range is a piecewise function based on the actual battery temperature and the battery safety range; Defining a third loss function corresponding to the energy consumption target of the thermal management system according to the product of the sum of the energy consumption related parameters and the correlation coefficient; According to the status information of the operating parameters of each component of the vehicle, a fourth loss function corresponding to the system stability target is defined.

3. The method according to claim 2, characterized in that After determining at least two output targets of the thermal management system simulation model and corresponding loss functions, the method further includes: Based on the preset weights corresponding to each loss function, the first loss function, the second loss function, the third loss function and the fourth loss function are linearly calculated to obtain the target loss function, and the linear calculation is the sum of the products of each loss function and the corresponding weight.

4. The method according to claim 3, characterized in that The amount to be calibrated that will make the loss function optimal, determined as the target calibration parameter, includes: Call a preset algorithm to calculate the quantity to be calibrated that makes the loss function optimal, and determine the optimal quantity to be calibrated as the target calibration parameter, wherein the preset algorithm is at least one heuristic algorithm, which can iteratively calculate the target loss function based on the target loss function and the current calibration quantity to make it reach the optimal point, or reach a preset number of iterations.

5. The method according to claim 4, characterized in that The calling of a preset algorithm to calculate the quantity to be calibrated that makes the loss function optimal, and determining the optimal quantity to be calibrated as the target calibration parameter comprises: Calculate the objective function value corresponding to the objective loss function when the calibration quantities of the thermal management system simulation model are respectively the quantities to be calibrated; The preset update algorithm is called to update the candidate calibration value until the objective function value corresponding to the candidate calibration value reaches a preset condition, and the candidate calibration value is determined as the target calibration parameter.

6. A parameter calibration device for a thermal management system, characterized in that: include: An input unit, used to obtain a vehicle system state of a thermal management system simulation model, and input the vehicle system state into a thermal management system control model, and input a control instruction output by the thermal management system control model into the thermal management system simulation model, wherein the thermal management system simulation model is used to calculate the vehicle system state according to the environmental parameters of the vehicle and the control instruction, and the thermal management system control model is used to generate the control instruction according to the environmental parameters of the vehicle and the vehicle system state; A first determining unit, used to determine at least two output targets of the thermal management system simulation model and corresponding loss functions; A second determination unit is used to determine a quantity to be calibrated in the thermal management system control model, wherein the vehicle system state output includes the at least two output targets, and a parameter value of each quantity to be calibrated will affect a value of a loss function; The third determining unit is used to determine the quantity to be calibrated that makes the loss function optimal as a target calibration parameter.

7. A vehicle, characterized in that: The vehicle comprises the parameter calibration device of the thermal management system as claimed in claim 6.

8. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.

10. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images