Performance evaluation model training method, performance prediction method and device for heat exchanger

Abstract

The present application provides a performance evaluation model training method, performance prediction method and device for a heat exchanger, including: constructing multiple performance evaluation samples; wherein the performance evaluation samples include: historical detection data of multiple heat exchangers, and historical standard heat dissipation obtained based on the historical detection data; using the historical detection data as the input of the performance evaluation model, and training the model parameters of the performance evaluation model according to the output results of the performance evaluation model based on the input historical detection data, and the historical standard heat dissipation obtained based on the historical detection data in the performance evaluation sample, until the loss of the performance evaluation model meets the preset conditions, and a performance evaluation model including the trained model parameters is obtained. The embodiment of the present application simplifies the performance evaluation model of the heat exchanger, and only needs to input fewer parameters to predict the performance parameters of the heat exchanger, thereby simplifying the prediction process and improving the efficiency of performance evaluation.

Description

Technical Field

[0001] The present application relates to the field of mechanical engineering technology, and in particular to a performance evaluation model training method, a performance prediction method and a device for a heat exchanger. Background Art

[0002] In the mechanical field, the heat exchanger, also known as the radiator, is mainly responsible for converting and dissipating the heat generated by the engine through the coolant. The specific working principle of the heat exchanger is: a high-temperature medium is introduced into the interior of the heat exchanger, and the low-temperature air is circulated to the fin position of the heat exchanger through the rotation of the fan, so that the low-temperature medium and the high-temperature air can be converted through heat exchange, thereby achieving the purpose of heat dissipation inside the machine.

[0003] In practice, it is usually necessary to select a heat exchanger with good heat dissipation performance to improve the specific operating efficiency of the engine. At present, the evaluation of the heat dissipation performance of the heat exchanger is often obtained through testing experiments. The testing process is complicated, consumes a lot of manpower and material resources, and the performance evaluation efficiency is low. Summary of the invention

[0004] In view of this, the purpose of the present application is to provide a performance evaluation model training method, a performance prediction method and a device for a heat exchanger. By simplifying the performance evaluation model of the heat exchanger, only fewer parameters need to be input to predict the performance parameters of the heat exchanger, thereby simplifying the prediction process and improving the performance evaluation efficiency.

[0005] The present application embodiment provides a performance evaluation model training method for a heat exchanger, the performance evaluation model training method comprising:

[0006] Constructing a plurality of performance evaluation samples; wherein the performance evaluation samples include: historical detection data of a plurality of heat exchangers, and historical standard heat dissipation obtained based on the historical detection data; wherein the historical detection data include the side lengths of the windward surfaces of the plurality of heat exchangers, and the medium flow and air flow rate passing through different heat exchangers;

[0007] The historical detection data is used as the input of a performance evaluation model, and the model parameters of the performance evaluation model are trained according to the output results of the performance evaluation model based on the input historical detection data and the historical standard heat dissipation obtained in the performance evaluation sample based on the historical detection data, until the loss of the performance evaluation model meets a preset condition, thereby obtaining a performance evaluation model including the trained model parameters.

[0008] In an optional implementation manner, when constructing the performance evaluation sample, it also includes:

[0009] The medium inlet temperature and the medium outlet temperature corresponding to each performance evaluation sample, and the air inlet temperature passing through the heat exchanger are obtained.

[0010] In an optional implementation manner, a method for obtaining a standard heat dissipation of the heat exchanger based on the detection data includes:

[0011] The standard heat dissipation is determined based on the medium inlet temperature, the air inlet temperature and the medium heat dissipation.

[0012] In an optional implementation manner, the method for determining the heat dissipation of the medium includes:

[0013] determining a medium temperature difference between the medium inlet temperature and the medium outlet temperature;

[0014] The medium heat dissipation amount is determined based on the medium temperature difference, the medium flow rate, and the specific heat capacity of the medium.

[0015] The present application provides a method for predicting the performance of a heat exchanger, the method comprising:

[0016] Acquire detection data; wherein the detection data includes the side length of the windward surface of the heat exchanger, and the medium flow rate and air flow rate passing through the heat exchanger;

[0017] The detection data is input into a trained performance evaluation model of the heat exchanger to obtain a performance prediction result of the heat exchanger; wherein the performance evaluation model is obtained based on the training method of the performance evaluation model of the heat exchanger described above.

[0018] In an optional implementation, the method further includes:

[0019] Based on the performance prediction result of the heat exchanger, the side length of the windward surface of the heat exchanger is adjusted.

[0020] The present application also provides a performance evaluation model training device for a heat exchanger, the device comprising:

[0021] A method for training a performance evaluation model of a heat exchanger, wherein the performance evaluation model training device comprises:

[0022] A construction module, used to construct a plurality of performance evaluation samples; wherein the performance evaluation samples include: historical detection data of a plurality of heat exchangers, and historical standard heat dissipation obtained based on the historical detection data; wherein the historical detection data include the side lengths of the windward surfaces of the plurality of heat exchangers, and the medium flow and air flow rate passing through different heat exchangers;

[0023] A training module is used to use the historical detection data as the input of a performance evaluation model, and train the model parameters of the performance evaluation model according to the output results of the performance evaluation model based on the input historical detection data and the historical standard heat dissipation obtained in the performance evaluation sample based on the historical detection data, until the loss of the performance evaluation model meets a preset condition, thereby obtaining a performance evaluation model including the trained model parameters.

[0024] In an optional implementation manner, the construction module is further used to:

[0025] The medium inlet temperature and the medium outlet temperature corresponding to each performance evaluation sample, and the air inlet temperature passing through the heat exchanger are obtained.

[0026] In an optional implementation manner, the construction module is specifically used for:

[0027] The standard heat dissipation is determined based on the medium inlet temperature, the air inlet temperature and the medium heat dissipation.

[0028] In an optional implementation manner, the construction module is specifically used for:

[0029] determining a medium temperature difference between the medium inlet temperature and the medium outlet temperature;

[0030] The medium heat dissipation amount is determined based on the medium temperature difference, the medium flow rate, and the specific heat capacity of the medium.

[0031] The embodiment of the present application also provides a performance prediction device for a heat exchanger, the performance prediction device comprising:

[0032] An acquisition module, used for acquiring detection data; wherein the detection data includes the side length of the windward surface of the heat exchanger, and the medium flow rate and air flow rate passing through the heat exchanger;

[0033] An input module is used to input the detection data into a trained performance evaluation model of the heat exchanger to obtain a performance prediction result of the heat exchanger; wherein the performance evaluation model is obtained based on the training method of the performance evaluation model of the heat exchanger described above.

[0034] In an optional implementation manner, the performance prediction device further includes:

[0035] The adjustment module is used to adjust the side length of the windward surface of the heat exchanger based on the performance prediction result of the heat exchanger.

[0036] An embodiment of the present application also provides a computer device, a processor, and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the processor is used to execute the machine-readable instructions stored in the memory. When the machine-readable instructions are executed by the processor, the steps in any one of the possible implementation modes described above are performed.

[0037] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the steps in any possible implementation manner described above are executed.

[0038] The embodiments of the present application provide a performance evaluation model training method, a performance prediction method and a device for a heat exchanger, comprising: constructing a plurality of performance evaluation samples; wherein the performance evaluation samples include: historical detection data of a plurality of heat exchangers, and historical standard heat dissipation obtained based on the historical detection data; wherein the historical detection data include the side length dimensions of the windward surfaces of a plurality of heat exchangers, and the medium flow rate and air flow rate through different heat exchangers; using the historical detection data as the input of the performance evaluation model, and training the model parameters of the performance evaluation model according to the output results of the performance evaluation model based on the input historical detection data, and the historical standard heat dissipation obtained based on the historical detection data in the performance evaluation sample, until the loss of the performance evaluation model meets the preset conditions, and a performance evaluation model including the trained model parameters is obtained. The embodiments of the present application simplify the performance evaluation model of the heat exchanger, and only a few parameters need to be input to predict the performance parameters of the heat exchanger, thereby simplifying the prediction process and improving the efficiency of performance evaluation.

[0039] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 A flow chart showing a method for training a performance evaluation model for a heat exchanger provided in an embodiment of the present application is shown;

[0042] Figure 2 A flow chart showing a method for predicting performance of a heat exchanger provided in an embodiment of the present application is shown;

[0043] Figure 3 A schematic structural diagram of a performance evaluation model training device for a heat exchanger provided in an embodiment of the present application is shown;

[0044] Figure 4 A schematic diagram showing the structure of a performance prediction device for a heat exchanger provided in an embodiment of the present application is shown;

[0045] Figure 5 A schematic diagram showing the structure of another device for predicting the performance of a heat exchanger provided in an embodiment of the present application is shown;

[0046] Figure 6 A schematic diagram of the structure of a computer device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0047] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0048] According to research, it is usually necessary to select a heat exchanger with good heat dissipation performance to improve the specific operating efficiency of the engine. At present, the evaluation of the heat dissipation performance of the heat exchanger is often obtained through testing experiments. The testing process is complicated, consumes a lot of manpower and material resources, and the performance evaluation efficiency is low.

[0049] Based on the above research, the embodiments of the present application provide a performance evaluation model training method, a performance prediction method and a device for a heat exchanger, including: constructing multiple performance evaluation samples; wherein the performance evaluation samples include: historical detection data of multiple heat exchangers, and historical standard heat dissipation obtained based on the historical detection data; wherein the historical detection data include the side length dimensions of the windward surfaces of multiple heat exchangers, and the medium flow rate and air flow rate through different heat exchangers; using the historical detection data as the input of the performance evaluation model, and training the model parameters of the performance evaluation model according to the output results of the performance evaluation model based on the input historical detection data, and the historical standard heat dissipation obtained based on the historical detection data in the performance evaluation sample, until the loss of the performance evaluation model meets the preset conditions, and a performance evaluation model including the trained model parameters is obtained. The embodiments of the present application simplify the performance evaluation model of the heat exchanger, and only need to input fewer parameters to predict the performance parameters of the heat exchanger, simplify the prediction process, and improve the efficiency of performance evaluation.

[0050] The defects existing in the above solutions are the results obtained by the inventor after practice and careful research. Therefore, the process of discovering the above problems and the solutions proposed by this application for the above problems below should be the contributions made by the inventor to this application during the application process.

[0051] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0052] To facilitate understanding of this embodiment, a performance evaluation model training method and a performance prediction method for a heat exchanger disclosed in the embodiment of the present application are first introduced in detail. The execution subject of the performance evaluation model training method and the performance prediction method for the heat exchanger provided in the embodiment of the present application is generally a computer device with a certain computing power, and the computer device includes, for example: a terminal device or a server or other processing device, and the terminal device can be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the performance evaluation model training method and the performance prediction method for the heat exchanger can be implemented by a processor calling a computer-readable instruction stored in a memory.

[0053] The performance evaluation model training method and performance prediction method of the heat exchanger provided in the embodiment of the present application are explained below by taking the execution subject as a terminal device as an example.

[0054] See also Figure 1 As shown, it is a flow chart of a performance evaluation model training method for a heat exchanger provided in an embodiment of the present application, and the performance evaluation model training method includes steps S101 to S102, wherein:

[0055] S101: construct multiple performance evaluation samples; wherein the performance evaluation samples include: historical detection data of multiple heat exchangers, and historical standard heat dissipation obtained based on the historical detection data; wherein the historical detection data includes the side lengths of the windward surfaces of multiple heat exchangers, and the medium flow and air flow rate passing through different heat exchangers;

[0056] S102: Using the historical detection data as the input of a performance evaluation model, and training the model parameters of the performance evaluation model according to the output result of the performance evaluation model based on the input historical detection data and the historical standard heat dissipation obtained in the performance evaluation sample based on the historical detection data, until the loss of the performance evaluation model meets a preset condition, thereby obtaining a performance evaluation model including the trained model parameters.

[0057] The embodiment of the present application constructs multiple performance evaluation samples; wherein the performance evaluation samples include: historical detection data of multiple heat exchangers, and historical standard heat dissipation obtained based on the historical detection data; wherein the historical detection data include the side length dimensions of the windward surfaces of multiple heat exchangers, and the medium flow rate and air flow rate through different heat exchangers; the historical detection data is used as the input of the performance evaluation model, and the model parameters of the performance evaluation model are trained according to the output results of the performance evaluation model based on the input historical detection data, and the historical standard heat dissipation obtained based on the historical detection data in the performance evaluation samples, until the loss of the performance evaluation model meets the preset conditions, thereby obtaining a performance evaluation model including the trained model parameters. The embodiment of the present application simplifies the performance evaluation model of the heat exchanger, and only needs to input fewer parameters to predict the performance parameters of the heat exchanger, thereby simplifying the prediction process and improving the efficiency of performance evaluation.

[0058] The above S101 to S102 are described in detail below.

[0059] 1. In the above S101, when training the performance evaluation model of the heat exchanger, it is first necessary to construct a plurality of performance evaluation samples.

[0060] The performance evaluation sample includes: historical detection data of multiple heat exchangers, and historical standard heat dissipation obtained based on the historical detection data; wherein the historical detection data includes the side length dimensions of the windward surfaces of multiple heat exchangers, and the medium flow rate and air flow rate passing through different heat exchangers.

[0061] At present, based on the structure of the heat exchanger, it is relatively easy to change the width and height of the windward surface of the heat exchanger, which is equivalent to only increasing the length or number of parts; it is more difficult to change the thickness of the windward surface, which is equivalent to redesigning the parts and redeveloping the mold. Based on the principle of heat exchange, when the internal structure of the heat exchanger is not changed (that is, the thickness and fin specifications remain unchanged), only the width and height of the windward surface are changed. The performance of the product after this change has certain comparability and continuity. Therefore, the parameters that affect the performance of the heat exchanger are analyzed and simplified, and finally a simplest model consisting of several input parameters can be obtained, which is of outstanding significance for optimizing the structure of the heat exchanger.

[0062] In one embodiment, when constructing the performance evaluation sample, it also includes:

[0063] The medium inlet temperature and the medium outlet temperature corresponding to each performance evaluation sample, and the air inlet temperature passing through the heat exchanger are obtained.

[0064] For example, when the heat exchanger is subjected to bench testing, some input quantities need to be given, including: structural parameters (width, height, thickness, fin specifications, cooling tube specifications), test conditions (medium flow rate, wind speed (affected by air flow rate and windward area), medium inlet temperature, air inlet temperature (i.e., ambient temperature). When a stable state is reached on the bench, the measured results include: the front and rear pressure drop of the product (i.e., external resistance / wind resistance), the internal pressure drop of the product (i.e., internal resistance / water resistance), the medium outlet temperature, and the air outlet temperature.

[0065] In one embodiment, the method for obtaining the standard heat dissipation of the heat exchanger based on the detection data includes:

[0066] The standard heat dissipation is determined based on the medium inlet temperature, the air inlet temperature and the medium heat dissipation.

[0067] Specifically, the standard heat dissipation is calculated by the following formula:

[0068]

[0069] Wherein, the method for determining the heat dissipation of the medium includes:

[0070] determining a medium temperature difference between the medium inlet temperature and the medium outlet temperature;

[0071] The medium heat dissipation amount is determined based on the medium temperature difference, the medium flow rate, and the specific heat capacity of the medium.

[0072] Specifically, the heat dissipation of the medium is calculated by the following formula:

[0073] Medium heat dissipation = medium flow rate × medium specific heat capacity × (medium inlet temperature - medium outlet temperature);

[0074] Heat absorbed by air = air flow rate × air specific heat capacity × (air outlet temperature - air inlet temperature).

[0075] Exemplarily, the heat exchanger is affected by the water side (i.e., medium) and the wind side (i.e., air) during the heat exchange process. Because there is a temperature difference between the medium temperature and the air temperature, heat energy can be transferred from the medium to the air. Moreover, the flow rate of the medium and the air affects the heat transferred by the two in unit time, i.e., the heat dissipation (or heat dissipation power). The heat absorbed by the wind side and the heat dissipated by the water side affect each other. Without considering other effects, theoretically, all the heat emitted by the water side will be absorbed and taken away by the air. However, in practice, considering the sensor position, thermal radiation, and other reasons, the heat dissipation on the water side is approximately equal to the heat absorbed on the wind side. When calculating the standard heat dissipation, the test standard of the heat exchanger takes the heat dissipation on the water side as the standard. Among them, according to the test standard, the "liquid temperature difference" (i.e., medium inlet temperature-air inlet temperature) must be 60°C, that is, when the inlet temperature (ambient temperature) is 25°C, the medium inlet temperature is 85°C. Therefore, for a specific heat exchanger, the standard heat dissipation is determined by two variables, the medium flow rate and the wind speed, and two fixed values, the water inlet temperature and the air inlet temperature, specified in the test standard.

[0076] 2. In the above S102, the historical detection data is used as the input of the performance evaluation model, and the model parameters of the performance evaluation model are trained according to the output result of the performance evaluation model based on the input historical detection data and the historical standard heat dissipation obtained in the performance evaluation sample based on the historical detection data, until the loss of the performance evaluation model meets the preset conditions, so as to obtain the performance evaluation model including the trained model parameters.

[0077] For example, when the internal structure of the heat exchanger is constant, that is, the core thickness is a fixed value, the specifications of the cooling tubes and fins remain unchanged, and a series of products are formed by changing the core width and core height, the performance data of this series of products have certain comparability and continuity. At this time, the standard heat dissipation of the series of products can be simplified into a model affected by four variables, that is, the input is width, height, medium flow, wind speed, and the output is the standard heat dissipation.

[0078] Exemplarily, the above-obtained performance evaluation model is modeled using machine learning software. A bench test is used to test multiple heat exchangers of the same structure, and raw data is measured. The relevant parameters and test results are imported into the software for training, and finally a trained model is obtained.

[0079] Among them, for heat exchangers, multiple heat exchangers with the same structure refer to the same cooling tube type (only the tube length can be changed) and the same heat dissipation belt type (only the heat dissipation belt length can be changed). Cooling tube length = heat dissipation belt length = core height of the product. By changing the number of cooling tubes and heat dissipation belts, the core width of the product can be changed. In this way, multiple products with different core heights and core widths can be obtained, that is, "the same structure", which can also be called the same series, which has the meaning of simplified input. Moreover, when the internal structure of the heat exchanger is constant, that is, the core thickness is a fixed value, the specifications of the cooling tube and the fin remain unchanged, a series of products is formed by changing the core width and core height. The performance data of this series of products has a certain degree of comparability and continuity, which is convenient for the model training process.

[0080] See also Figure 2 As shown, it is a flow chart of the performance prediction method of the heat exchanger provided in the embodiment of the present application, and the performance prediction method includes steps S201 to S202, wherein:

[0081] S201: Acquire detection data; wherein the detection data includes the side length of the windward surface of the heat exchanger, and the medium flow rate and air flow rate passing through the heat exchanger;

[0082] S202: Inputting the detection data into a trained performance evaluation model of the heat exchanger to obtain a performance prediction result of the heat exchanger; wherein the performance evaluation model is obtained based on the training method of the performance evaluation model of the heat exchanger described above.

[0083] The embodiment of the present application obtains detection data; wherein the detection data includes the side length of the windward surface of the heat exchanger, and the medium flow rate and air flow rate passing through the heat exchanger; the detection data is input into a trained performance evaluation model of the heat exchanger to obtain a performance prediction result of the heat exchanger; wherein the performance evaluation model is obtained based on the training method of the performance evaluation model of the heat exchanger described above. The embodiment of the present application only needs to input fewer parameters to predict the performance parameters of the heat exchanger, simplifying the prediction process and improving the efficiency of performance evaluation.

[0084] The above S201 to S202 are described in detail below.

[0085] 1. In the above S201, a bench test may be used to obtain the test data.

[0086] The detection data includes the side length of the windward surface of the heat exchanger, and the medium flow rate and air flow rate passing through the heat exchanger.

[0087] Exemplarily, the air flow rate=air volume flow / positive area.

[0088] 2. In the above S202, the detection data is input into the trained performance evaluation model of the heat exchanger to obtain the performance prediction result of the heat exchanger.

[0089] For example, a software interface (such as a web) can be established to provide an interface for inputting parameters. The performance prediction model obtained by the training method of the performance evaluation model of the heat exchanger described above is imported into the software, and the performance results are predicted based on the test data, and the prediction results are displayed.

[0090] In one embodiment, the method further includes: adjusting the side length of the windward surface of the heat exchanger based on the performance prediction result of the heat exchanger.

[0091] For example, there is a product in the design stage (a product with the same structure as the above product), but the width and height are different from the existing products, and the performance of the product (i.e., standard heat dissipation) is to be predicted. Using the trained model, the above test data are input, such as width (300mm), height (400mm), medium flow (100L / min), and wind speed (4m / s). The model predicts an output, i.e., the standard heat dissipation of the product (30kW). The design department can quickly review whether the design scheme meets customer needs at the stage without physical objects. This method is very user-friendly (product development personnel). Only a few parameters are input and the result is obtained by clicking a button. In addition, the error of the prediction result is related to the original data imported into the software training. The more data, the lower the error. The model after 1000-point data training has a prediction error between 0% and 12%. The more the parameters deviate from the training data, the higher the error. It is close to the accuracy of professional one-dimensional simulation software for analysis (such as KULI, etc.), but no professional training is required, and it is ready to use.

[0092] The embodiments of the present application can be applied to radiators, intercoolers, condensers, oil coolers, evaporators, battery coolers, motor coolers, and can be applied to refrigerators, air conditioners, and other fields in the automotive and home appliance industries.

[0093] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0094] Based on the same inventive concept, the embodiments of the present application also provide a performance evaluation model training device for a heat exchanger corresponding to the performance evaluation model training method for a heat exchanger, and a performance prediction device for a heat exchanger corresponding to the performance prediction method for a heat exchanger. Since the principle of solving the problem by the device in the embodiments of the present application is similar to the performance evaluation model training method for a heat exchanger and the performance prediction method for a heat exchanger in the embodiments of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0095] Reference Figure 3 As shown, Figure 3 This is a schematic diagram of the structure of a performance evaluation model training device for a heat exchanger provided in an embodiment of the present application. The performance evaluation model training device includes: a construction module 310 and a training module 320, wherein:

[0096] A construction module 310 is used to construct a plurality of performance evaluation samples; wherein the performance evaluation samples include: historical detection data of a plurality of heat exchangers, and historical standard heat dissipation obtained based on the historical detection data; wherein the historical detection data includes the side lengths of the windward surfaces of the plurality of heat exchangers, and the medium flow and air flow rate passing through different heat exchangers;

[0097] The training module 320 is used to use the historical detection data as the input of the performance evaluation model, and train the model parameters of the performance evaluation model according to the output results of the performance evaluation model based on the input historical detection data, and the historical standard heat dissipation obtained in the performance evaluation sample based on the historical detection data, until the loss of the performance evaluation model meets the preset conditions, thereby obtaining a performance evaluation model including the trained model parameters.

[0098] The embodiment of the present application constructs multiple performance evaluation samples; wherein the performance evaluation samples include: historical detection data of multiple heat exchangers, and historical standard heat dissipation obtained based on the historical detection data; wherein the historical detection data include the side length dimensions of the windward surfaces of multiple heat exchangers, and the medium flow rate and air flow rate through different heat exchangers; the historical detection data is used as the input of the performance evaluation model, and the model parameters of the performance evaluation model are trained according to the output results of the performance evaluation model based on the input historical detection data, and the historical standard heat dissipation obtained based on the historical detection data in the performance evaluation samples, until the loss of the performance evaluation model meets the preset conditions, thereby obtaining a performance evaluation model including the trained model parameters. The embodiment of the present application simplifies the performance evaluation model of the heat exchanger, and only needs to input fewer parameters to predict the performance parameters of the heat exchanger, thereby simplifying the prediction process and improving the efficiency of performance evaluation.

[0099] In an optional implementation manner, the construction module 310 is further used to:

[0100] The medium inlet temperature and the medium outlet temperature corresponding to each performance evaluation sample, and the air inlet temperature passing through the heat exchanger are obtained.

[0101] In an optional implementation manner, the construction module 310 is specifically used to:

[0102] The standard heat dissipation is determined based on the medium inlet temperature, the air inlet temperature and the medium heat dissipation.

[0103] In an optional implementation manner, the construction module 310 is specifically used to:

[0104] determining a medium temperature difference between the medium inlet temperature and the medium outlet temperature;

[0105] The medium heat dissipation amount is determined based on the medium temperature difference, the medium flow rate, and the specific heat capacity of the medium.

[0106] Reference Figure 4 , Figure 5 As shown, Figure 4 A schematic diagram of the structure of a performance prediction device for a heat exchanger provided in an embodiment of the present application. Figure 5 This is a schematic diagram of the structure of another heat exchanger performance prediction device provided in an embodiment of the present application. The heat exchanger performance prediction device includes: an acquisition module 410 and an input module 420, wherein:

[0107] The acquisition module 410 is used to acquire detection data; wherein the detection data includes the side length of the windward surface of the heat exchanger, and the medium flow rate and air flow rate passing through the heat exchanger;

[0108] The input module 420 is used to input the detection data into the trained performance evaluation model of the heat exchanger to obtain the performance prediction result of the heat exchanger; wherein the performance evaluation model is obtained based on the training method of the performance evaluation model of the heat exchanger described above.

[0109] The embodiment of the present application obtains detection data; wherein the detection data includes the side length of the windward surface of the heat exchanger, and the medium flow rate and air flow rate passing through the heat exchanger; the detection data is input into a trained performance evaluation model of the heat exchanger to obtain a performance prediction result of the heat exchanger; wherein the performance evaluation model is obtained based on the training method of the performance evaluation model of the heat exchanger described above. The embodiment of the present application only needs to input fewer parameters to predict the performance parameters of the heat exchanger, simplifying the prediction process and improving the efficiency of performance evaluation.

[0110] In an optional implementation, Figure 5 As shown, the performance prediction device also includes:

[0111] The adjustment module 430 is used to adjust the side length of the windward surface of the heat exchanger based on the performance prediction result of the heat exchanger.

[0112] The present application also provides a computer device, such as Figure 6 FIG. 1 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application, wherein the computer device 10 includes:

[0113] A processor 11 and a memory 12; the memory 12 stores machine-readable instructions executable by the processor 11. When the computer device 10 is running, the machine-readable instructions are executed by the processor 11 to implement the following steps:

[0114] Constructing a plurality of performance evaluation samples; wherein the performance evaluation samples include: historical detection data of a plurality of heat exchangers, and historical standard heat dissipation obtained based on the historical detection data; wherein the historical detection data include the side lengths of the windward surfaces of the plurality of heat exchangers, and the medium flow and air flow rate passing through different heat exchangers;

[0115] The historical detection data is used as the input of a performance evaluation model, and the model parameters of the performance evaluation model are trained according to the output results of the performance evaluation model based on the input historical detection data and the historical standard heat dissipation obtained in the performance evaluation sample based on the historical detection data, until the loss of the performance evaluation model meets a preset condition, thereby obtaining a performance evaluation model including the trained model parameters.

[0116] In an optional implementation manner, the instructions executed by the processor 11, when constructing the performance evaluation sample, further include:

[0117] The medium inlet temperature and the medium outlet temperature corresponding to each performance evaluation sample, and the air inlet temperature passing through the heat exchanger are obtained.

[0118] In an optional implementation, in the instructions executed by the processor 11, a method for obtaining a standard heat dissipation of the heat exchanger based on the detection data includes:

[0119] The standard heat dissipation is determined based on the medium inlet temperature, the air inlet temperature and the medium heat dissipation.

[0120] In an optional implementation manner, in the instruction executed by the processor 11, the method for determining the heat dissipation of the medium includes:

[0121] determining a medium temperature difference between the medium inlet temperature and the medium outlet temperature;

[0122] The medium heat dissipation amount is determined based on the medium temperature difference, the medium flow rate, and the specific heat capacity of the medium.

[0123] When the computer device 10 is running, the machine-readable instructions are also executed by the processor 11 to implement the following steps:

[0124] Acquire detection data; wherein the detection data includes the side length of the windward surface of the heat exchanger, and the medium flow rate and air flow rate passing through the heat exchanger;

[0125] The detection data is input into a trained performance evaluation model of the heat exchanger to obtain a performance prediction result of the heat exchanger; wherein the performance evaluation model is obtained based on the training method of the performance evaluation model of the heat exchanger described above.

[0126] In an optional implementation manner, the instructions executed by the processor 11 further include:

[0127] Based on the performance prediction result of the heat exchanger, the side length of the windward surface of the heat exchanger is adjusted.

[0128] The present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the heat exchanger performance evaluation model training method and performance prediction method described in the above method embodiment are executed. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0129] The computer program product of the performance evaluation model training method and the performance prediction method for the heat exchanger provided in the embodiments of the present application includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the steps of the performance evaluation model training method and the performance prediction method for the heat exchanger described in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0130] The present application also provides a computer program, which implements any one of the methods of the aforementioned embodiments when executed by a processor. The computer program product can be implemented in hardware, software, or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK), etc.

[0131] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0132] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0133] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0134] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application can essentially be embodied in the form of a software product, or in other words, the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0135] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for training a performance evaluation model for a heat exchanger, characterized in that: The performance evaluation model training method comprises: Constructing a plurality of performance evaluation samples; wherein the performance evaluation samples include: historical detection data of a plurality of heat exchangers, and historical standard heat dissipation obtained based on the historical detection data; wherein the historical detection data include the side lengths of the windward surfaces of the plurality of heat exchangers, and the medium flow and air flow rate passing through different heat exchangers; The historical detection data is used as the input of the performance evaluation model, and the model parameters of the performance evaluation model are trained according to the output results of the performance evaluation model based on the input historical detection data, and the historical standard heat dissipation obtained in the performance evaluation sample based on the historical detection data, so as to establish the correspondence between the side length of the windward surface of the heat exchanger, the medium flow rate through the heat exchanger, and the air flow rate and the standard heat dissipation; until the loss of the performance evaluation model meets the preset conditions, a performance evaluation model including the trained model parameters is obtained; wherein the performance evaluation model is used to output the performance prediction result of the heat exchanger based on the input side length of the windward surface of the heat exchanger, and the medium flow rate through the heat exchanger and the air flow rate; the performance prediction result is used to adjust the side length of the windward surface of the heat exchanger.

2. The performance evaluation model training method for a heat exchanger according to claim 1, characterized in that: When constructing the performance evaluation sample, it also includes: The medium inlet temperature and the medium outlet temperature corresponding to each performance evaluation sample, and the air inlet temperature passing through the heat exchanger are obtained.

3. The performance evaluation model training method for a heat exchanger according to claim 2, characterized in that: The method for obtaining the standard heat dissipation of the heat exchanger based on the detection data comprises: The standard heat dissipation is determined based on the medium inlet temperature, the air inlet temperature and the medium heat dissipation.

4. The performance evaluation model training method for a heat exchanger according to claim 3, characterized in that: The method for determining the heat dissipation of the medium comprises: determining a medium temperature difference between the medium inlet temperature and the medium outlet temperature; The medium heat dissipation amount is determined based on the medium temperature difference, the medium flow rate, and the specific heat capacity of the medium.

5. A method for predicting the performance of a heat exchanger, characterized in that: The performance prediction method comprises: Acquire detection data; wherein the detection data includes the side length of the windward surface of the heat exchanger, and the medium flow rate and air flow rate passing through the heat exchanger; The detection data is input into a trained performance evaluation model of the heat exchanger to obtain a performance prediction result of the heat exchanger; wherein the performance evaluation model is obtained based on the training method of the performance evaluation model of the heat exchanger according to any one of claims 1 to 4.

6. The performance prediction method of a heat exchanger according to claim 5, characterized in that: Also includes: Based on the performance prediction result of the heat exchanger, the side length of the windward surface of the heat exchanger is adjusted.

7. A performance evaluation model training device for a heat exchanger, characterized in that: The performance evaluation model training device comprises: A construction module, used to construct a plurality of performance evaluation samples; wherein the performance evaluation samples include: historical detection data of a plurality of heat exchangers, and historical standard heat dissipation obtained based on the historical detection data; wherein the historical detection data include the side lengths of the windward surfaces of the plurality of heat exchangers, and the medium flow and air flow rate passing through different heat exchangers; A training module is used to use the historical detection data as the input of a performance evaluation model, and train the model parameters of the performance evaluation model according to the output results of the performance evaluation model based on the input historical detection data, and the historical standard heat dissipation obtained in the performance evaluation sample based on the historical detection data, so as to establish a correspondence between the side length of the windward surface of the heat exchanger, the medium flow rate through the heat exchanger, and the air flow rate and the standard heat dissipation; until the loss of the performance evaluation model meets the preset conditions, a performance evaluation model including the trained model parameters is obtained; wherein the performance evaluation model is used to output the performance prediction result of the heat exchanger based on the input side length of the windward surface of the heat exchanger, and the medium flow rate through the heat exchanger and the air flow rate; the performance prediction result is used to adjust the side length of the windward surface of the heat exchanger.

8. A performance prediction device for a heat exchanger, characterized in that: The performance prediction device comprises: An acquisition module, used for acquiring detection data; wherein the detection data includes the side length of the windward surface of the heat exchanger, and the medium flow rate and air flow rate passing through the heat exchanger; An input module is used to input the detection data into a trained performance evaluation model of a heat exchanger to obtain a performance prediction result of the heat exchanger; wherein the performance evaluation model is obtained based on the training method of the performance evaluation model of the heat exchanger according to any one of claims 1 to 4.

9. A computer device, characterized in that: include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the processor is used to execute the machine-readable instructions stored in the memory. When the machine-readable instructions are executed by the processor, the processor executes the steps of the performance evaluation model training method for a heat exchanger as described in any one of claims 1 to 4, or the steps of the performance prediction method for a heat exchanger as described in any one of claims 5 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program. When the computer program is executed by a computer device, the computer device executes the steps of the performance evaluation model training method for the heat exchanger as described in any one of claims 1 to 4, or the steps of the performance prediction method for the heat exchanger as described in any one of claims 5 to 6.

Images