Cooling simulation and model training method, device, equipment, medium and program product

Abstract

The invention provides a cooling simulation and model training method and device, equipment, a medium and a program product, and the method comprises the steps: obtaining a three-dimensional passenger compartment temperature model used for describing temperature field data in a passenger compartment, and a one-dimensional air conditioning system model used for describing the air outlet temperature of an air conditioning system; and performing order reduction processing on the three-dimensional passenger compartment temperature model based on the target neural network order reduction model to obtain a one-dimensional passenger compartment temperature model describing the temperature boundary of each cavity in the passenger compartment, and then simulating the cooling working condition based on the one-dimensional air conditioning system model and the one-dimensional passenger compartment temperature model to obtain a cooling simulation result. Thus, accurate temperature field data described by the three-dimensional passenger compartment temperature model can be added to the one-dimensional passenger compartment temperature model through the target neural network reduced-order model, the problem that the initial calculation boundary of the temperature field is inaccurate in the cooling simulation process is solved, and an accurate and reliable cooling simulation result is obtained.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a cooling simulation and model training method, device, equipment, medium and program product. Background Art

[0002] With the development of automobile electrification and people's increasing demand for automobile comfort, the role of air conditioning systems in automobiles is becoming more and more important. Among them, the most important function of the air conditioning system is to control the rapid cooling of the passenger compartment and automatically maintain it at an appropriate temperature to make the passengers feel comfortable. If the whole vehicle is exposed to the sun for a long time, the temperature in the passenger compartment will rise rapidly, and more and more models are using panoramic sunroofs, which aggravates the heat radiation and greenhouse effect of the passenger compartment.

[0003] In the existing technology, one-dimensional system simulation is usually used to analyze and predict the cooling conditions of the passenger compartment. The temperature change curve of the passenger compartment can be quickly obtained. By comparing it with the definition of the performance indicators of the whole vehicle, it can in turn guide the matching design of the air-conditioning system and better complete the selection of the compressor, evaporator, condenser and expansion valve.

[0004] After the vehicle is exposed to the sun, the temperature of different areas / cavities in the passenger compartment varies greatly. The dashboard can reach 70-80°C, and there is a large difference in temperature between the front and rear rows. However, in the prior art, when using a one-dimensional system to simulate the cooling of the passenger compartment, the calculation boundaries of each cavity in the entire passenger compartment are usually set to the same. Therefore, the simulation results of the cooling condition may have a large deviation and poor reliability. Summary of the invention

[0005] Based on the defects and shortcomings of the above-mentioned prior art, the present application proposes a cooling simulation and model training method, device, equipment, medium and program product, which can simulate the cooling condition of the one-dimensional passenger compartment temperature model obtained by reducing the order of the three-dimensional passenger compartment temperature model through the target neural network reduction model and the first air-conditioning system model to obtain accurate and reliable cooling simulation results, thereby avoiding the problem of inaccurate initial calculation boundaries of the temperature field during the cooling simulation process, resulting in poor accuracy and reliability of the cooling simulation results.

[0006] According to a first aspect of the present application, a cooling simulation method is provided, comprising:

[0007] Acquire a three-dimensional passenger compartment temperature model and a one-dimensional air conditioning system model, wherein the passenger compartment temperature model is used to describe temperature field data in the passenger compartment, and the one-dimensional air conditioning system model is used to describe an air outlet temperature of the air conditioning system;

[0008] performing order reduction processing on the three-dimensional passenger compartment temperature model based on the target neural network order reduction model to obtain a one-dimensional passenger compartment temperature model, wherein the one-dimensional passenger compartment temperature model is used to describe the temperature boundaries of each cavity in the passenger compartment, and each cavity is obtained by dividing the passenger compartment;

[0009] Based on the one-dimensional air-conditioning system model and the one-dimensional passenger compartment temperature model, a cooling condition is simulated to obtain a cooling simulation result.

[0010] According to a second aspect of an embodiment of the present application, a temperature reduction simulation device is provided, comprising:

[0011] an acquisition module, used to acquire a three-dimensional passenger compartment temperature model and a one-dimensional air conditioning system model, wherein the passenger compartment temperature model is used to describe the temperature field data in the passenger compartment, and the one-dimensional air conditioning system model is used to describe the air outlet temperature of the air conditioning system;

[0012] a model reduction module, used for reducing the order of the three-dimensional passenger compartment temperature model based on the target neural network reduction model to obtain a one-dimensional passenger compartment temperature model, wherein the one-dimensional passenger compartment temperature model is used to describe the temperature boundary of each cavity in the passenger compartment, wherein each cavity is obtained by dividing the passenger compartment;

[0013] The working condition simulation module is used to simulate the cooling working condition based on the one-dimensional air-conditioning system model and the one-dimensional passenger compartment temperature model to obtain a cooling simulation result.

[0014] According to a third aspect of the present application, a model training method is provided, comprising:

[0015] Acquire a historical three-dimensional passenger compartment temperature model, wherein the historical three-dimensional passenger compartment temperature model is used to describe historical temperature field data in the passenger compartment;

[0016] Training a preset neural network reduced-order model based on the historical three-dimensional passenger compartment temperature model to obtain the trained preset neural network reduced-order model;

[0017] If the mean square error of the trained preset neural network reduced-order model is less than a preset threshold, the trained preset neural network reduced-order model is determined as the target neural network reduced-order model.

[0018] According to a fourth aspect of the present application, a model training device is provided, comprising:

[0019] An acquisition module, used for acquiring a historical three-dimensional passenger compartment temperature model, wherein the historical three-dimensional passenger compartment temperature model is used for describing historical temperature field data in the passenger compartment;

[0020] A training module, used for training a preset neural network reduced-order model based on the historical three-dimensional passenger compartment temperature model to obtain the trained preset neural network reduced-order model;

[0021] The determination module is used to determine the preset neural network reduced-order model after training as the target neural network reduced-order model if the mean square error of the preset neural network reduced-order model after training is less than a preset threshold.

[0022] According to a fifth aspect of an embodiment of the present application, there is provided an electronic device, including a memory and a processor;

[0023] The memory is connected to the processor and is used to store programs;

[0024] The processor is used to implement the cooling simulation method as described in the first aspect or the model training method as described in the third aspect by running the program in the memory.

[0025] According to a sixth aspect of an embodiment of the present application, a storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the cooling simulation method as described in the first aspect or the model training method as described in the third aspect is implemented.

[0026] According to the seventh aspect of the embodiments of the present application, a computer program product is provided, wherein when the computer program instructions are executed by a processor, the processor implements the cooling simulation method as described in the first aspect or the model training method as described in the third aspect.

[0027] In the above-mentioned cooling simulation and model training method, device, equipment, medium and program product, a three-dimensional passenger compartment temperature model for describing the temperature field data in the passenger compartment and a one-dimensional air conditioning system model for describing the air outlet temperature of the air conditioning system can be obtained, and the three-dimensional passenger compartment temperature model can be reduced based on the target neural network reduction model to obtain a one-dimensional passenger compartment temperature model describing the temperature boundaries of each cavity in the passenger compartment. After that, based on the one-dimensional air conditioning system model and the one-dimensional passenger compartment temperature model, the cooling condition is simulated to obtain the cooling simulation result. In this way, the accurate temperature field data described by the three-dimensional passenger compartment temperature model can be added to the one-dimensional passenger compartment temperature model through the target neural network reduction model, so as to solve the problem of inaccurate initial calculation boundary of the temperature field during the cooling simulation process and obtain accurate and reliable cooling simulation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0029] Figure 1 A schematic diagram of a flow chart of a cooling simulation method provided in an embodiment of the present application;

[0030] Figure 2 A schematic diagram of a cavity provided in an embodiment of the present application;

[0031] Figure 3 A schematic diagram of a hot dip working condition provided in an embodiment of the present application;

[0032] Figure 4 A schematic diagram of a cavity division proposed in an embodiment of the present application;

[0033] Figure 5 A schematic diagram of a cooling simulation process proposed in an embodiment of the present application;

[0034] Figure 6 A flowchart of a model training method proposed in an embodiment of the present application;

[0035] Figure 7 A schematic diagram of the structure of a preset neural network reduction model proposed in an embodiment of the present application;

[0036] Figure 8 A schematic diagram of a cooling simulation and model training process proposed in an embodiment of the present application;

[0037] Fig. 9 A schematic diagram of the structure of a cooling simulation device proposed in an embodiment of the present application;

[0038] Fig.10 A schematic diagram of the structure of a model training device proposed in an embodiment of the present application;

[0039] Fig.11 A schematic diagram of the structure of an electronic device proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0041] Overview

[0042] As described in the background technology, in the prior art, one-dimensional system simulation is usually used to analyze and predict the cooling conditions of the passenger compartment, which can quickly obtain the temperature change curve of the passenger compartment. By comparing it with the definition of the vehicle performance index, it can in turn guide the matching design of the air-conditioning system and better complete the selection of the compressor, evaporator, condenser, and expansion valve. Because the temperature of different areas / cavities in the passenger compartment varies greatly after the vehicle is exposed to the sun, the dashboard can reach 70-80°C, and there is a large difference in temperature between the front and rear rows. However, in the prior art, when a one-dimensional system is used to simulate the cooling of the passenger compartment, the calculation boundaries of each cavity in the entire passenger compartment are usually set to the same. Therefore, the simulation results of the cooling condition may have large deviations and poor reliability.

[0043] On this basis, the inventors found through further research that the three-dimensional cabin temperature model used to describe the temperature field data in the cabin and the one-dimensional air conditioning system model used to describe the air outlet temperature of the air conditioning system can be obtained, and the three-dimensional cabin temperature model can be reduced based on the target neural network reduction model to obtain a one-dimensional cabin temperature model that describes the temperature boundaries of each cavity in the cabin. After that, the cooling condition can be simulated based on the one-dimensional air conditioning system model and the one-dimensional cabin temperature model to obtain the cooling simulation result. In this way, the accurate temperature field data described by the three-dimensional cabin temperature model can be added to the one-dimensional cabin temperature model through the target neural network reduction model, so as to solve the problem of inaccurate initial calculation boundary of the temperature field during the cooling simulation process and obtain accurate and reliable cooling simulation results.

[0044] Based on the above concept, an embodiment of the present specification provides a cooling simulation and model training method, which will be exemplarily described below in conjunction with the accompanying drawings.

[0045] Exemplary Methods

[0046] See also Figure 1 In an exemplary embodiment, a cooling simulation method is provided, which is applied to any electronic device, and the electronic device can obtain a three-dimensional passenger compartment temperature model and a one-dimensional air conditioning system model, call a target neural network reduced-order model, and perform a working condition simulation. Figure 1 As shown, the cooling simulation method includes steps S101-S103:

[0047] S101: Obtain a three-dimensional passenger cabin temperature model and a one-dimensional air conditioning system model.

[0048] Among them, the passenger compartment temperature model is used to describe the temperature field data in the passenger compartment, and the one-dimensional air-conditioning system model is used to describe the air outlet temperature of the air-conditioning system.

[0049] S102: Performing order reduction processing on the three-dimensional passenger compartment temperature model based on the target neural network order reduction model to obtain a one-dimensional passenger compartment temperature model.

[0050] Among them, the one-dimensional passenger compartment temperature model is used to describe the temperature boundaries of each cavity in the passenger compartment.

[0051] Specifically, the temperature in each cavity is the same as the temperature of its temperature boundary.

[0052] In addition, each cavity is obtained by dividing the passenger compartment, is a part of the passenger compartment, and together constitutes the passenger compartment.

[0053] More specifically, each cavity is divided according to the geometric shape and size of the passenger compartment.

[0054] For example, the passenger compartment is divided into cavities, and the obtained cavity division can be as follows: Figure 2 As shown. Among them, α is the angle between the front windshield of the vehicle and the horizontal plane where the vehicle chassis is located, β is the angle between the side glass of the vehicle and the vertical line perpendicular to the horizontal plane where the vehicle chassis is located, and γ is the angle between the rear windshield of the vehicle and the horizontal plane where the vehicle chassis is located. ah is used to characterize the size of each cavity.

[0055] S103: Based on the one-dimensional air conditioning system model and the one-dimensional passenger compartment temperature model, a cooling condition is simulated to obtain a cooling simulation result.

[0056] The cooling simulation results can be represented by the cooling curves of each cavity in the passenger compartment as the temperature changes.

[0057] After obtaining the cooling simulation results, the cooling simulation results can be displayed on the display interface or output to other devices for display, so that relevant personnel can understand the cooling performance of the current air-conditioning system and facilitate the selection of the air-conditioning system.

[0058] In this embodiment, the precise temperature field data described by the three-dimensional passenger compartment temperature model is added to the one-dimensional passenger compartment temperature model through the target neural network reduced-order model, so as to solve the problem of inaccurate initial calculation boundary of the temperature field during the cooling simulation process and obtain accurate and reliable cooling simulation results.

[0059] In order to ensure the accuracy of the three-dimensional passenger compartment temperature model, in some embodiments, the passenger compartment under heat soak conditions is analyzed based on computational fluid dynamics (CFD) to obtain a three-dimensional passenger compartment temperature model.

[0060] Specifically, CFD calculations can be performed based on information such as solar radiation, thermal radiation, heat conduction, and thermal convection to obtain the temperature field data of various positions in the passenger compartment after the vehicle is heat soaked in a high-temperature environment, and a three-dimensional passenger compartment temperature model can be built based on the calculated temperature field data.

[0061] For example, the vehicle may be in a Figure 3 In the heat soak condition shown, the front of the vehicle faces the sun, and the sun can directly shine on the front windshield of the vehicle. At this time, the temperature distribution in the passenger compartment is uneven, and the temperature in the front direction is higher than other positions in the passenger compartment.

[0062] For example, Figure 4 It is a three-dimensional illustration of the cavity division of the passenger compartment, which is obtained by dividing the passenger compartment according to a preset cube.

[0063] In this embodiment, due to the high complexity of CFD modeling, when performing CFD calculations, the passenger compartment is first meshed. The number of meshes in the passenger compartment can reach millions or even tens of millions, and the dimension of the temperature flow field solution is several times the grid dimension. Based on CFD, the passenger compartment under heat soak conditions is analyzed and modeled to obtain an accurate and reliable three-dimensional passenger compartment temperature model.

[0064] Due to different parking positions of the vehicle, the temperature of the passenger compartment may be different in different areas. In order to improve the accuracy and reliability of the cooling simulation results, in some embodiments, the target neural network reduced-order model is also used to divide the passenger compartment into cavities. At this time, when the three-dimensional passenger compartment temperature model is reduced based on the target neural network reduced-order model to obtain a one-dimensional passenger compartment temperature model, the three-dimensional passenger compartment temperature model is input into the target neural network reduced-order model to obtain multiple cavities of the passenger compartment and a one-dimensional passenger compartment temperature model.

[0065] Specifically, the three-dimensional passenger compartment temperature model is input into the target neural network reduced-order model to obtain multiple cavities of the passenger compartment, and the three-dimensional passenger compartment temperature model is reduced to a one-dimensional passenger compartment temperature model based on the cavities.

[0066] Exemplarily, the divided cavity may include the space where components in the passenger compartment are located, such as the interior floor, door interior, roof, front seats, rear seats, transmission case, windows (including front windshield, front side windows, rear side windows and rear window).

[0067] In this way, a reasonable cavity division can be carried out based on the actual temperature field in the actual passenger compartment, thereby obtaining a more reliable one-dimensional passenger compartment temperature model with reference significance.

[0068] In some embodiments, the cooling condition is simulated based on the one-dimensional air-conditioning system model and the one-dimensional passenger compartment temperature model. When the cooling simulation result is obtained, the attribute information of each cavity in the one-dimensional passenger compartment temperature model is first obtained, including the surface area, volume, material information, etc. Then, the one-dimensional air-conditioning system model, the attribute information of each cavity and the one-dimensional passenger compartment temperature model are integrated to obtain a one-dimensional cooling simulation model. Finally, based on the one-dimensional cooling simulation model, the cooling condition is simulated to obtain the cooling simulation result.

[0069] More specifically, the material information also includes the properties of the structural materials of each layer (such as thermal conductivity, density, specific heat capacity, etc.).

[0070] In this embodiment, since these properties are crucial for calculating heat conduction, heat radiation and temperature distribution in the passenger compartment, and affect the specific cooling conditions of each cavity in the passenger compartment, when determining the one-dimensional cooling simulation model, the attribute information of each cavity, the one-dimensional air-conditioning system model and the one-dimensional passenger compartment temperature model are integrated to obtain a one-dimensional cooling simulation model that can accurately simulate the cooling conditions.

[0071] For example, the cooling simulation process can be as follows: Figure 5 As shown, based on the neural network model, i.e., the above-mentioned target reduced-order neural network model, the three-dimensional passenger compartment temperature model under the heat soak condition is reduced to obtain a one-dimensional passenger compartment temperature model. The temperature of each cavity in the one-dimensional passenger compartment temperature model is used as the temperature boundary of the cavity to complete the calculation boundary setting, and the attributes of each cavity are defined. The simulation condition is determined to be a cooling condition. The one-dimensional passenger compartment temperature model and the one-dimensional air-conditioning system model are combined to simulate the cooling condition and obtain the cooling simulation result.

[0072] See also Figure 6 In an exemplary embodiment, a model training method is provided, which is applied to any electronic device, and the electronic device can obtain a historical three-dimensional passenger compartment temperature model, and train a preset model based on the historical three-dimensional passenger compartment temperature model to obtain a target neural network reduced-order model. Figure 6 As shown, the model training method includes steps S601-S603:

[0073] S601: Obtain a historical three-dimensional passenger compartment temperature model.

[0074] Among them, the historical three-dimensional passenger compartment temperature model is used to describe the historical temperature field data in the passenger compartment.

[0075] Similarly, the historical three-dimensional passenger compartment temperature model can be obtained by performing CFD calculations on the passenger compartment under historical heat soak conditions.

[0076] S602: Training a preset neural network reduced-order model based on a historical three-dimensional passenger compartment temperature model to obtain a trained preset neural network reduced-order model.

[0077] Specifically, a historical three-dimensional passenger compartment temperature model and a corresponding historical one-dimensional passenger compartment temperature model are used as training samples to perform model training on a preset neural network reduced-order model to obtain a trained preset neural network reduced-order model.

[0078] S603: If the mean square error of the trained preset neural network reduced-order model is less than a preset threshold, the trained preset neural network reduced-order model is determined as the target neural network reduced-order model.

[0079] Correspondingly, if the mean square error of the trained preset neural network reduced-order model is greater than or equal to the preset threshold, step S602 is continued to be executed to perform model training until the mean square error of the trained preset neural network reduced-order model is less than the preset threshold.

[0080] The mean square error is determined based on the test data.

[0081] For each test data, the three-dimensional passenger compartment temperature model in the test data is input into the trained preset neural network reduced-order model to obtain a predicted one-dimensional passenger compartment temperature model. The predicted one-dimensional passenger compartment is compared with the corresponding one-dimensional passenger compartment temperature model in the test data to determine the average difference in temperature of each cavity corresponding to the test data. Based on the average difference corresponding to all test data, the mean square error is calculated.

[0082] The test data include other historical three-dimensional passenger compartment temperature models and corresponding one-dimensional passenger compartment temperature models other than the above training data.

[0083] Exemplarily, the structure of the preset neural network reduction model can be as follows: Figure 7 As shown, it includes input layer, hidden layer and output layer.

[0084] Exemplarily, the temperature field data described by the historical three-dimensional passenger compartment temperature model calculated by CFD is used as input, including light intensity, radiation coefficient, HVAC air volume, convection heat transfer coefficient, humidity, and ambient temperature. The average temperature of each cavity after heat soaking in the passenger compartment is used as output. The preset neural network reduced-order model is trained until the mean square error of the trained preset neural network reduced-order model is less than a preset threshold, thereby obtaining a target neural network model.

[0085] In this embodiment, the preset neural network reduced order model is trained based on the historical three-dimensional passenger compartment temperature model until the mean square error of the trained preset neural network reduced order model is less than a preset threshold value, and then the trained preset neural network reduced order model is determined as the target neural network reduced order model. In this way, the precise temperature field data described by the three-dimensional passenger compartment temperature model is added to the one-dimensional passenger compartment temperature model through the target neural network reduced order model, thereby solving the problem of inaccurate initial calculation boundary of the temperature field during the cooling simulation process and obtaining accurate and reliable cooling simulation results.

[0086] For example, the process of cooling simulation and model training can be as follows: Figure 8 As shown, a passenger compartment heat soak CFD simulation is performed, that is, the historical temperature field data of the passenger compartment is calculated, and based on the data, the average temperature of each cavity in the passenger compartment is determined, and the average temperature is used as a one-dimensional passenger compartment temperature model. After that, a preset neural network reduced-order model is trained until the mean square error of the trained preset neural network reduced-order model meets the condition, that is, it is less than a preset threshold, and the target neural network reduced-order model is output, otherwise, the model training continues.

[0087] Afterwards, the three-dimensional passenger compartment temperature model is reduced in order based on the target neural network reduced-order model to obtain a one-dimensional passenger compartment temperature model. Combined with the one-dimensional air-conditioning system model, a one-dimensional cooling simulation model is generated after simulation condition setting, property definition and calculation boundary setting. The cooling condition simulation calculation is then performed to obtain the cooling simulation results.

[0088] In order to ensure the reliability of the target neural network model and ensure that the one-dimensional passenger compartment temperature distribution can be determined more accurately through the target neural network model, when training the model, the historical three-dimensional passenger compartment temperature model, the passenger compartment cavity division, and the corresponding historical one-dimensional passenger compartment temperature model are used as training samples to train the preset neural network reduced-order model to obtain the trained preset neural network reduced-order model. At this time, the target preset neural network reduced-order model finally obtained can be used for the passenger compartment cavity division and the three-dimensional passenger compartment temperature model reduction. Through the target neural network reduced-order model, a reasonable cavity division can be performed based on the actual temperature field in the actual passenger compartment, thereby obtaining a more reliable one-dimensional passenger compartment temperature model with reference significance.

[0089] Exemplary Devices

[0090] like Fig. 9 As shown, an embodiment of the present application further provides a cooling simulation device, including an acquisition module 901 , a model reduction module 902 , and a working condition simulation module 903 .

[0091] in,

[0092] An acquisition module 901 is used to acquire a three-dimensional passenger compartment temperature model and a one-dimensional air conditioning system model, wherein the passenger compartment temperature model is used to describe the temperature field data in the passenger compartment, and the one-dimensional air conditioning system model is used to describe the air outlet temperature of the air conditioning system;

[0093] A model reduction module 902 is used to reduce the order of the three-dimensional passenger compartment temperature model based on the target neural network reduction model to obtain a one-dimensional passenger compartment temperature model, wherein the one-dimensional passenger compartment temperature model is used to describe the temperature boundary of each cavity in the passenger compartment, and each cavity is obtained by dividing the passenger compartment;

[0094] The operating condition simulation module 903 is used to simulate the cooling operating condition based on the one-dimensional air-conditioning system model and the one-dimensional passenger compartment temperature model to obtain a cooling simulation result.

[0095] The cooling simulation device provided in this embodiment belongs to the same application concept as the cooling simulation method provided in the above embodiments of this application, and can execute the cooling simulation method provided in any of the above embodiments of this application, and has the corresponding functional modules and beneficial effects of executing the method. For technical details not fully described in this embodiment, please refer to the specific processing content of the cooling simulation method provided in the above embodiments of this application, and will not be repeated here.

[0096] The functions implemented by the above acquisition module 901, model reduction module 902 and working condition simulation module 903 can be implemented in the form of software called by the same or different processors, respectively, and the embodiments of the present application are not limited thereto.

[0097] like Fig.10 As shown, an embodiment of the present application also provides a model training device, including an acquisition module 1001, a training module 1002 and a determination module 1003.

[0098] in,

[0099] An acquisition module 1001 is used to acquire a historical three-dimensional passenger compartment temperature model, where the historical three-dimensional passenger compartment temperature model is used to describe historical temperature field data in the passenger compartment;

[0100] A training module 1002 is used to train a preset neural network reduced-order model based on the historical three-dimensional passenger compartment temperature model to obtain the trained preset neural network reduced-order model;

[0101] The determination module 1003 is used to determine the trained preset neural network reduced order model as the target neural network reduced order model if the mean square error of the trained preset neural network reduced order model is less than a preset threshold.

[0102] The model training device provided in this embodiment is used to train the target neural network reduction model used in the cooling simulation method provided in the above embodiment of this application. It belongs to the same application concept as the cooling simulation method provided in the above embodiment, and can execute the model training method provided in any of the above embodiments of this application, and has the corresponding functional modules and beneficial effects of executing the method. For the technical details not described in detail in this embodiment, please refer to the specific processing content of the model training method provided in the above embodiment of this application, which will not be repeated here.

[0103] The functions implemented by the above acquisition module 1001, training module 1002 and determination module 1003 can be implemented in the form of software called by the same or different processors, and the embodiments of the present application are not limited thereto.

[0104] Exemplary Electronic Devices

[0105] Another embodiment of the present application also provides an electronic device, see Fig.11 As shown, the electronic device includes: a memory 1100 and a processor 1110 .

[0106] The memory 1100 is connected to the processor 1110 and is used to store programs;

[0107] The processor 1110 is used to implement the cooling simulation or model training method disclosed in any of the above embodiments by running the program stored in the memory 1100.

[0108] Specifically, the electronic device may further include: a bus, a communication interface 1120 , an input device 1130 and an output device 1140 .

[0109] The processor 1110, the memory 1100, the communication interface 1120, the input device 1130 and the output device 1140 are connected to each other via a bus.

[0110] A bus may include a pathway that transfers information between components of a computer system.

[0111] The processor 1110 may be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0112] The processor 1110 may include a main processor, and may also include a baseband chip, a modem, and the like.

[0113] The memory 1100 stores a program for executing the technical solution of the present application, and may also store an operating system and other key services. Specifically, the program may include a program code, and the program code includes a computer operation instruction. More specifically, the memory 1100 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk storage, a flash, and the like.

[0114] The input device 1130 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor.

[0115] Output device 1140 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0116] The communication interface 1120 may include any transceiver or the like to communicate with other devices or communication networks, such as Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc.

[0117] The processor 1110 executes the program stored in the memory 1100 and calls other devices, which can be used to implement each step of any cooling simulation or model training method provided in the above embodiments of the present application.

[0118] Those skilled in the art will understand that Fig.11 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0119] An embodiment of the present application also proposes a chip, which includes a processor and a data interface. The processor reads and runs the program stored in the memory through the data interface to execute the cooling simulation or model training method introduced in any of the above embodiments. The specific processing process and its beneficial effects can be found in the introduction to the embodiments of the cooling simulation or model training method.

[0120] In addition to the above-mentioned methods and devices, an embodiment of the present application proposes a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the cooling simulation or model training method according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0121] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0122] In addition, an embodiment of the present application further proposes a storage medium on which a computer program is stored, and the computer program is executed by a processor to execute the steps of the cooling simulation method according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0123] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details disclosed above are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0124] The block diagrams of the devices, apparatuses, equipment, and systems involved in the present invention are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The word "such as" used here refers to the phrase "such as but not limited to", and can be used interchangeably with it.

[0125] It should also be noted that in the device, apparatus and method of the present invention, each component or each step can be decomposed and / or reassembled, and such decomposition and / or reassembly should be regarded as an equivalent solution of the present invention.

[0126] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present invention. Therefore, the present invention is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0127] It should be understood that the qualifiers "first", "second", "third", "fourth", "fifth" and "sixth" used in the description of the embodiments of the present invention are only used to more clearly explain the technical solutions and cannot be used to limit the scope of protection of the present invention.

[0128] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present invention to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A cooling simulation method, characterized in that: The method comprises: Acquire a three-dimensional passenger compartment temperature model and a one-dimensional air conditioning system model, wherein the passenger compartment temperature model is used to describe temperature field data in the passenger compartment, and the one-dimensional air conditioning system model is used to describe an air outlet temperature of the air conditioning system; performing order reduction processing on the three-dimensional passenger compartment temperature model based on the target neural network order reduction model to obtain a one-dimensional passenger compartment temperature model, wherein the one-dimensional passenger compartment temperature model is used to describe the temperature boundaries of each cavity in the passenger compartment, and each cavity is obtained by dividing the passenger compartment; Based on the one-dimensional air-conditioning system model and the one-dimensional passenger compartment temperature model, a cooling condition is simulated to obtain a cooling simulation result.

2. The cooling simulation method according to claim 1, characterized in that: The obtaining of the three-dimensional passenger compartment temperature model comprises: Based on computational fluid dynamics (CFD), the passenger compartment under heat soak condition is analyzed to obtain the three-dimensional passenger compartment temperature model.

3. The cooling simulation method according to claim 1, characterized in that: The three-dimensional passenger compartment temperature model is reduced in order based on the target neural network reduced order model to obtain a one-dimensional passenger compartment temperature model, including: The three-dimensional passenger compartment temperature model is input into the target neural network reduced-order model to obtain a plurality of cavities of the passenger compartment, and the one-dimensional passenger compartment temperature model is obtained based on the plurality of cavities.

4. The cooling simulation method according to claim 1, characterized in that: The step of simulating a cooling condition based on the one-dimensional air conditioning system model and the one-dimensional passenger compartment temperature model to obtain a cooling simulation result includes: Acquire attribute information of each cavity in the one-dimensional cabin temperature model, wherein the attribute information includes surface area, volume, and material information; Integrating the one-dimensional air conditioning system model, the attribute information of each cavity, and the one-dimensional passenger compartment temperature model to obtain a one-dimensional cooling simulation model; Based on the one-dimensional cooling simulation model, the cooling condition is simulated to obtain the cooling simulation result.

5. A model training method, characterized in that: The method comprises: Acquire a historical three-dimensional passenger compartment temperature model, wherein the historical three-dimensional passenger compartment temperature model is used to describe historical temperature field data in the passenger compartment; Training a preset neural network reduced-order model based on the historical three-dimensional passenger compartment temperature model to obtain the trained preset neural network reduced-order model; If the mean square error of the trained preset neural network reduced-order model is less than a preset threshold, the trained preset neural network reduced-order model is determined as the target neural network reduced-order model.

6. A cooling simulation device, characterized in that: The device comprises: an acquisition module, used to acquire a three-dimensional passenger compartment temperature model and a one-dimensional air conditioning system model, wherein the passenger compartment temperature model is used to describe the temperature field data in the passenger compartment, and the one-dimensional air conditioning system model is used to describe the air outlet temperature of the air conditioning system; a model reduction module, used for reducing the order of the three-dimensional passenger compartment temperature model based on the target neural network reduction model to obtain a one-dimensional passenger compartment temperature model, wherein the one-dimensional passenger compartment temperature model is used to describe the temperature boundary of each cavity in the passenger compartment, wherein each cavity is obtained by dividing the passenger compartment; The working condition simulation module is used to simulate the cooling working condition based on the one-dimensional air-conditioning system model and the one-dimensional passenger compartment temperature model to obtain a cooling simulation result.

7. A model training device, characterized in that: The device comprises: An acquisition module, used for acquiring a historical three-dimensional passenger compartment temperature model, wherein the historical three-dimensional passenger compartment temperature model is used for describing historical temperature field data in the passenger compartment; A training module, used for training a preset neural network reduced-order model based on the historical three-dimensional passenger compartment temperature model to obtain the trained preset neural network reduced-order model; The determination module is used to determine the preset neural network reduced-order model after training as the target neural network reduced-order model if the mean square error of the preset neural network reduced-order model after training is less than a preset threshold.

8. An electronic device, characterized in that: including memory and processor; The memory is connected to the processor and is used to store programs; The processor is used to implement the cooling simulation method as described in any one of claims 1 to 4 or the model training method as described in claim 5 by running the program in the memory.

9. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the cooling simulation method according to any one of claims 1 to 4 or the model training method according to claim 5 is implemented.

10. A computer program product, characterized in that It includes computer program instructions, which, when executed by a processor, enable the processor to implement the cooling simulation method as described in any one of claims 1 to 4 or the model training method as described in claim 5.

Images