Air conditioner calibration method and device, storage medium, vehicle and chip

Abstract

The invention relates to the technical field of air conditioners, in particular to an air conditioner calibration method and device, a storage medium, a vehicle and a chip. The air conditioner calibration method comprises the steps that current operation parameters of an air conditioner are obtained; the current operation parameters are input into a transient temperature prediction model, a plurality of predicted transient temperatures output by the transient temperature prediction model according to the current operation parameters in a target time period are obtained, and the transient temperature prediction model is constructed based on a solid heat conduction rule; and according to the multiple predicted transient temperatures, predicted steady-state temperatures are obtained, and according to the predicted steady-state temperatures, operation parameters of the air conditioner are calibrated.

Description

Technical Field

[0001] The present disclosure relates to the technical field of air conditioning, and in particular to an air conditioning calibration method, device, storage medium, vehicle and chip. Background Art

[0002] While the vehicle is driving, external conditions, such as temperature, vehicle speed and sunlight radiation, are constantly changing. In order to ensure the comfort of the occupants in the vehicle, the air volume and temperature of the air conditioner must be continuously adjusted so that the steady-state temperature in the vehicle meets the comfort needs of the occupants.

[0003] In related technologies, calibration is mainly performed manually by calibration engineers based on their experience. The entire process is extremely time-consuming and involves a massive amount of data, which makes the calibration cost high. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present disclosure provides an air conditioning calibration method, device, storage medium, vehicle and chip.

[0005] According to a first aspect of an embodiment of the present disclosure, there is provided an air conditioner calibration method, comprising:

[0006] Get the current operating parameters of the air conditioner;

[0007] Inputting the current operating parameters into a transient temperature prediction model to obtain a plurality of predicted transient temperatures output by the transient temperature prediction model according to the current operating parameters within a target time period, wherein the transient temperature prediction model is constructed based on the solid thermal conductivity law;

[0008] A predicted steady-state temperature is obtained according to the multiple predicted transient temperatures, and an operating parameter of the air conditioner is calibrated according to the predicted steady-state temperature.

[0009] Optionally, obtaining a predicted steady-state temperature according to the plurality of predicted transient temperatures, and calibrating an operating parameter of the air conditioner according to the predicted steady-state temperature, comprises:

[0010] Calculating an average value of a plurality of the predicted transient temperatures, and using the average value as the predicted steady-state temperature;

[0011] Substituting the predicted steady-state temperature and the actual steady-state temperature into a first loss function, iteratively solving the first loss function through a gradient descent algorithm to obtain a first loss value, and determining a first gradient value corresponding to the current operating parameter, the first loss value being the minimum value of the first loss function;

[0012] Subtracting the current operating parameter from the first gradient value to obtain a first difference;

[0013] Multiplying the first difference by the learning rate of the transient temperature prediction model to obtain a target operating parameter;

[0014] The current operating parameters of the air conditioner are calibrated according to the target operating parameters.

[0015] Optionally, the training process of the transient temperature prediction model includes:

[0016] Substituting the predicted transient temperature and the actual transient temperature of the target position at the same time into a second loss function, iteratively solving the second loss function through a gradient descent algorithm to obtain a second loss value, and determining a second gradient value corresponding to an initial hyperparameter in the transient temperature prediction model, wherein the second loss value is less than a loss threshold;

[0017] Subtracting the initial hyperparameter from the second gradient value corresponding to the initial hyperparameter to obtain a second difference;

[0018] Multiplying the second difference by the learning rate of the transient temperature prediction model to obtain an optimized target hyperparameter;

[0019] The initial hyperparameters in the transient temperature prediction model are updated to the target hyperparameters.

[0020] Optionally, the air conditioner is provided on a vehicle, and the transient temperature prediction model includes an in-vehicle average temperature prediction model and a target position temperature prediction model;

[0021] The vehicle interior average temperature prediction model is used to predict the vehicle interior average temperature according to the input current operating parameter output;

[0022] The target position temperature prediction model is used to output the predicted transient temperature of the target position according to the input predicted average temperature inside the vehicle.

[0023] Optionally, the construction of the vehicle interior average temperature prediction model includes:

[0024] Determining heat energy output by an air conditioner of the vehicle, heat energy of a first environment inside the vehicle, heat energy of a human body of an occupant of the vehicle, and heat energy of a second environment outside the vehicle;

[0025] Obtaining the total energy of the gas inside the vehicle according to the heat energy output by the air conditioner, the first environment heat energy, the human body heat energy and the second environment heat energy;

[0026] The total energy of the gas in the vehicle is taken as an independent variable, and the average temperature in the vehicle is taken as a dependent variable, a variation function is constructed so that the independent variable is positively correlated with the dependent variable, and a prediction model for the average temperature in the vehicle is obtained.

[0027] Optionally, the determining the heat energy output by the air conditioner of the vehicle, the first environment heat energy inside the vehicle, the body heat energy of the occupants inside the vehicle, and the second environment heat energy outside the vehicle includes:

[0028] Obtaining the vehicle speed, the average wind speed of each air outlet of the air conditioner, the total air volume, the internal ambient temperature of the vehicle, the body temperature of the occupants in the vehicle, and the external ambient temperature of the vehicle;

[0029] Obtaining the heat energy output by the air conditioner according to the average temperature in the vehicle, the vehicle speed, the average wind speed and the total air volume;

[0030] Obtaining the first ambient heat energy according to the average temperature inside the vehicle, the vehicle speed, and the internal ambient temperature;

[0031] According to the external environment temperature, obtaining the second environment heat energy;

[0032] The human body thermal energy is obtained according to the average temperature in the vehicle and the human body temperature.

[0033] Optionally, the construction of the target location temperature prediction model includes:

[0034] For a direct blowing key point of the air conditioner whose target position is a direct blowing key point, determining a first target air outlet of the air conditioner corresponding to the direct blowing key point, determining a distance from the first target air outlet to the direct blowing key point, a wind speed, an air volume, a cross-sectional area, and a first wind temperature of the first target air outlet, and determining a movement time of gas from the first target air outlet to the direct blowing key point according to the distance, the wind speed, the air volume, and the cross-sectional area;

[0035] Obtaining a loss temperature from the first target air outlet to a direct blowing key point according to the movement time, the vehicle speed, and the first wind temperature, and constructing a direct blowing key point temperature function according to the first wind temperature and the loss temperature;

[0036] For a non-direct blowing key point of the air conditioner whose target position is the non-direct blowing key point, determine the second target air outlet of the air conditioner corresponding to the non-direct blowing key point, and obtain the second wind temperature of the second target air outlet, and construct a non-direct blowing key point temperature function based on the second wind temperature and the predicted average temperature in the vehicle.

[0037] According to a second aspect of an embodiment of the present disclosure, there is provided an air conditioner calibration device, comprising:

[0038] An acquisition module, configured to acquire current operating parameters of the air conditioner;

[0039] A prediction module is configured to input the current operating parameters into a transient temperature prediction model to obtain a plurality of predicted transient temperatures output by the transient temperature prediction model according to the current operating parameters within a target time period, wherein the transient temperature prediction model is constructed based on a solid thermal conductivity law;

[0040] The calibration module is configured to obtain a predicted steady-state temperature according to the plurality of predicted transient temperatures, and to calibrate the operating parameters of the air conditioner according to the predicted steady-state temperature.

[0041] According to a third aspect of an embodiment of the present disclosure, another air conditioner calibration device is provided, comprising:

[0042] a first processor;

[0043] a first memory for storing first processor executable instructions;

[0044] Wherein, the first processor is configured as follows:

[0045] Get the current operating parameters of the air conditioner;

[0046] Inputting the current operating parameters into a transient temperature prediction model to obtain a plurality of predicted transient temperatures output by the transient temperature prediction model according to the current operating parameters within a target time period, wherein the transient temperature prediction model is constructed based on the solid thermal conductivity law;

[0047] A predicted steady-state temperature is obtained according to the multiple predicted transient temperatures, and an operating parameter of the air conditioner is calibrated according to the predicted steady-state temperature.

[0048] According to a fourth aspect of an embodiment of the present disclosure, a vehicle is provided, comprising an air conditioner and the air conditioner calibration device described in the third aspect.

[0049] According to a fifth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the air conditioner calibration method provided in the first aspect of the present disclosure are implemented.

[0050] According to a sixth aspect of an embodiment of the present disclosure, a chip is provided, comprising a second processor and an interface; the second processor is used to read instructions to execute the steps of the vehicle calibration method provided in the first aspect.

[0051] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: the present disclosure constructs a transient temperature prediction model based on the solid thermal conductivity law, and the transient temperature prediction model can obtain multiple predicted transient temperatures within a target time period based on a small number of current operating parameters, obtain predicted steady-state temperatures based on multiple predicted transient temperatures, and calibrate the operating parameters of the air conditioner based on the predicted steady-state temperatures. The accuracy of the air conditioner calibration results is improved, and the entire process does not require manual calibration, shortening the calibration time and reducing the calibration cost.

[0052] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0054] Figure 1 The figure is a flow chart of an air conditioner calibration method according to an exemplary embodiment.

[0055] Figure 2 is another flow chart of an air conditioner calibration method according to an exemplary embodiment.

[0056] Figure 3 is another flow chart of an air conditioner calibration method according to an exemplary embodiment.

[0057] Figure 4 is another flow chart of an air conditioner calibration method according to an exemplary embodiment.

[0058] Figure 5 is a schematic diagram of output of a transient temperature prediction model according to an exemplary embodiment.

[0059] Figure 6 is another flow chart of an air conditioner calibration method according to an exemplary embodiment.

[0060] Figure 7 The figure is a schematic diagram of an air conditioner operating state after calibration according to an air conditioner calibration method according to an exemplary embodiment.

[0061] Figure 8 is another schematic diagram of an air conditioner operating state after calibration according to an air conditioner calibration method according to an exemplary embodiment.

[0062] Fig. 9 The figure is a block diagram of an air conditioner calibration device according to an exemplary embodiment.

[0063] Fig.10is another block diagram of an air conditioner calibration device according to an exemplary embodiment.

[0064] Fig.11 is a block diagram of a vehicle according to an exemplary embodiment. DETAILED DESCRIPTION

[0065] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0066] It should be noted that all data acquisition actions in the present disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the data is located, and with the authorization given by the owner of the corresponding device.

[0067] Figure 1 is a flow chart of an air conditioner calibration method according to an exemplary embodiment. The method can be applied to air conditioners of different models in different places, vehicles equipped with air conditioners, and control equipment in high-temperature working conditions, such as boiler scenarios, aircraft engine temperature detection scenarios, or temperature detection scenarios in high-pressure gas turbines, etc. Figure 1 As shown, taking the air conditioning calibration method used for the air conditioning on a vehicle as an example, the air conditioning calibration method may include the following steps:

[0068] In step S11, the current operating parameters of the air conditioner are obtained.

[0069] Among them, the current operating parameters include the current wind temperature and current wind volume of the air conditioner.

[0070] In step S12, the current operating parameters are input into the transient temperature prediction model to obtain a plurality of predicted transient temperatures output by the transient temperature prediction model according to the current operating parameters within the target time period, and the transient temperature prediction model is constructed based on the solid thermal conductivity law.

[0071] Among them, the target time period can be preset according to the time required for the temperature in the car to reach a steady state after starting the air conditioner. In this disclosure, the target time period is taken as 1 hour.

[0072] In step S13, a predicted steady-state temperature is obtained according to a plurality of predicted transient temperatures, and the operating parameters of the air conditioner are calibrated according to the predicted steady-state temperature.

[0073] Among them, according to the transient law, the predicted steady-state temperature is determined by a transient temperature prediction model, and the operating parameters of the air conditioner are calibrated according to the predicted steady-state temperature.

[0074] In the present invention, a plurality of predicted transient temperatures within a target time period are output based on the current wind temperature and the current air volume of the air conditioner based on a transient temperature prediction model, and a predicted steady-state temperature is obtained based on the plurality of predicted transient temperatures, thereby calibrating the operating parameters of the air conditioner according to the predicted steady-state temperature. The entire process involves fewer operating parameters of the air conditioner and does not require manual calibration, thus shortening the calibration time and reducing the calibration cost. In addition, the calibration results are not affected by human factors and are reliable.

[0075] In order to facilitate those skilled in the art to better understand the air conditioner calibration method provided by the present disclosure, the relevant steps of the above-mentioned air conditioner calibration method are described in detail with examples below.

[0076] In one possible embodiment, see Figure 2 In step S13, a predicted steady-state temperature is obtained according to a plurality of predicted transient temperatures, and the operating parameters of the air conditioner are calibrated according to the predicted steady-state temperature, which may include the following steps:

[0077] In step S21, an average value of a plurality of predicted transient temperatures is calculated, and the average value is used as the predicted steady-state temperature.

[0078] Among them, according to the transient law, the predicted steady-state temperature is determined taking into account the time and temperature difference, which ensures the accuracy and reliability of the calibration results.

[0079] For example, the transient temperature prediction model outputs a predicted transient temperature per second. When the target time period is 1 hour, the average value of 60 predicted transient temperatures is calculated and used as the predicted steady-state temperature.

[0080] In step S22, the predicted steady-state temperature and the actual steady-state temperature are substituted into the first loss function, the first loss function is iteratively solved by the gradient descent algorithm to obtain the first loss value, and the first gradient value corresponding to the current operating parameters is determined. The first loss value is the minimum value of the first loss function.

[0081] The formula of the first loss function is: MES = 1 / n·∑(x i -x` i ), MES represents the first loss value, n represents the number of samples, x i Characterizes the true steady-state temperature, x` i Characterize the predicted steady-state temperature.

[0082] For example, the minimum loss value loss between the predicted steady-state temperature and the actual steady-state temperature is calculated by a gradient descent algorithm, and a first gradient value of the current wind temperature and the current wind volume of the air conditioner corresponding to the minimum loss value is determined.

[0083] In step S23, the current operating parameter is subtracted from the first gradient value to obtain a first difference.

[0084] For example, the current wind temperature is subtracted from the first gradient value corresponding to the current wind temperature to obtain a first difference value corresponding to the current wind temperature; the current wind volume is subtracted from the first gradient value corresponding to the current wind volume to obtain a first difference value corresponding to the current wind volume.

[0085] In step S24, the first difference is multiplied by the learning rate of the transient temperature prediction model to obtain the target operating parameters.

[0086] The learning rate is a configurable hyperparameter of the transient temperature prediction model, which has a small positive value, usually in the range between 0.0 and 1.0, and the present disclosure does not limit this.

[0087] For example, the first difference corresponding to the current wind temperature is multiplied by the learning rate of the transient temperature prediction model to obtain the target wind temperature; the first difference corresponding to the current wind volume is multiplied by the learning rate of the transient temperature prediction model to obtain the target wind volume.

[0088] In step S25, the current operating parameters of the air conditioner are calibrated according to the target operating parameters.

[0089] For example, the current air volume of the air conditioner is adjusted to the target air volume, and the current air temperature of the air conditioner is adjusted to the target air temperature, so as to achieve calibration of the current operating parameters of the air conditioner.

[0090] The present invention obtains the minimum loss value between the predicted steady-state temperature and the actual steady-state temperature through a gradient descent algorithm, thereby determining the first gradient value of the current operating parameter of the air conditioner, optimizing the current operating parameter according to the first gradient value, obtaining the target operating parameter, and calibrating the current operating parameter of the air conditioner according to the target operating parameter. The current operating parameter can be calibrated with a small amount of data, and the air conditioner can be calibrated, thereby reducing the calibration cost.

[0091] In one possible embodiment, see Figure 3 , the training process of the transient temperature prediction model can include:

[0092] In step S31, the predicted transient temperature and the actual transient temperature of the target position at the same time are substituted into the second loss function, the second loss function is iteratively solved by the gradient descent algorithm to obtain the second loss value, and the second gradient value of the initial hyperparameter in the corresponding transient temperature prediction model is determined, and the second loss value is less than the damage threshold.

[0093] The loss threshold may be preset according to the accuracy requirement of the calibration result. In the embodiment of the present disclosure, the loss threshold is set to 1.5.

[0094] The initial hyperparameters in the transient temperature prediction model include initial weight parameters of various parameters in the temperature prediction model during the calculation process.

[0095] The formula of the second loss function is: MES`=1 / n·∑(y i -y` i ), MES` represents the second loss value, n represents the number of samples, y i Characterizes the true transient temperature, y` i Characterize and predict transient temperatures.

[0096] For example, a second loss value less than 1.5 between the actual transient temperature and the predicted transient temperature is calculated by a gradient descent algorithm, and a gradient value of an initial hyperparameter in the transient temperature prediction model corresponding to the second loss value is determined.

[0097] In step S32, the initial hyperparameter is subtracted from the second gradient value corresponding to the initial hyperparameter to obtain a second difference.

[0098] In step S33, the second difference is multiplied by the learning rate of the transient temperature prediction model to obtain the optimized target hyperparameter.

[0099] The learning rate is a configurable hyperparameter of the transient temperature prediction model, which has a small positive value, usually in the range between 0.0 and 1.0, and the present disclosure does not limit this.

[0100] In step S34, the initial hyperparameters in the transient temperature prediction model are updated to target hyperparameters.

[0101] The present invention obtains the loss value of the predicted transient temperature and the real transient temperature through the gradient descent algorithm, thereby determining the second gradient value of the initial parameter of the transient temperature prediction model, optimizing the initial hyperparameter according to the second gradient value, obtaining the target hyperparameter, and updating the initial hyperparameter in the transient temperature prediction model to the target hyperparameter, thereby optimizing the transient temperature prediction model. The transient temperature prediction model can be optimized with a small amount of data, ensuring the reliability and accuracy of the output result of the transient temperature prediction model.

[0102] In a possible embodiment, the air conditioner is installed in the vehicle, and the transient temperature prediction model includes an in-vehicle average temperature prediction model and a target location temperature prediction model.

[0103] The average temperature prediction model inside the vehicle is used to predict the average temperature inside the vehicle according to the input current operating parameters.

[0104] Among them, considering that the air pressure and volume inside the car are constant, the gas energy inside the car is only affected by the average temperature inside the car. Therefore, a prediction model for the average temperature inside the car is constructed based on the laws of solid thermal conductivity and the physical laws of thermal energy.

[0105] The target location temperature prediction model is used to output the predicted transient temperature of the target location according to the input predicted average temperature inside the vehicle.

[0106] The target positions include two types of direct blowing key points and non-direct blowing key points of the air outlet of the air conditioner. For different categories, the calculation principles of the target position temperature prediction model are completely different.

[0107] In a possible embodiment, the construction of the vehicle interior average temperature prediction model may include the following steps:

[0108] The air conditioner output heat energy of the vehicle, the first environment heat energy inside the vehicle, the body heat energy of the vehicle occupant, and the second environment heat energy outside the vehicle are determined.

[0109] Among them, the total energy of the gas in the car is affected by the heat energy output by the air conditioner in the car ΔQ 空调 , the first ambient heat energy ΔQ inside the vehicle 内环境 , the body heat energy of the passengers in the car ΔQ 人体 and the second ambient heat energy ΔQ outside the vehicle 外环境 The second ambient heat energy outside the vehicle may change due to the influence of the solar thermal energy.

[0110] The total energy of the gas inside the vehicle is obtained according to the heat energy output by the air conditioner, the first environment heat energy, the human body heat energy and the second environment heat energy.

[0111] Among them, the total energy of the gas in the car ΔQ 车 =ΔQ 空调 +ΔQ 内环境 +ΔQ 人体 +ΔQ 外环境 .

[0112] Taking the total energy of the gas in the car as the independent variable and the average temperature in the car as the dependent variable, a change function that makes the independent variable positively correlated with the dependent variable is constructed to obtain the average temperature prediction model in the car.

[0113] Wherein, the change function includes:

[0114] T 车内平均 =ΔQ 车 / λ1=(ΔQ 空调 +ΔQ 内环境 +ΔQ 人体 +ΔQ 外环境 ) / λ1;

[0115] T 车内平均Represents the average temperature inside the car, ΔQ 车 represents the total energy of the gas in the car, λ1 represents the first weight parameter, ΔQ 空调 Characterizes the heat output of air conditioning, ΔQ 内环境 Characterizes the first ambient thermal energy, ΔQ 人体 Characterizes human body heat energy, ΔQ 外环境 Characterizes the thermal energy of the second environment.

[0116] In a possible embodiment, determining the heat energy output by the air conditioner of the vehicle, the first environment heat energy inside the vehicle, the body heat energy of the occupants inside the vehicle, and the second environment heat energy outside the vehicle may include the following steps:

[0117] The vehicle speed, the average wind speed of each air outlet of the air conditioner, the total air volume, the internal ambient temperature of the vehicle, the body temperature of the occupants in the vehicle, and the external ambient temperature of the vehicle are obtained.

[0118] The heat energy output by the air conditioner is obtained based on the average temperature in the car, vehicle speed, average wind speed and total air volume.

[0119] Among them, the average temperature inside the car T 车内平均 , vehicle speed V 车 , average wind speed T 出风平均 And the total air volume VOL 总风 Substituting into the first solid thermal conductivity function, the air conditioning output energy is obtained.

[0120] The first solid thermal conductivity function includes:

[0121] ΔQ 空调 ={λ2-λ3·[sigmoid(λ4·V 车 )-0.5]}·(T 出风平均 -T 车内平均 )·VOL 总风 Δt;

[0122] ΔQ 空调 represents the air conditioner output energy, λ2 represents the second weight parameter, λ3 represents the third weight parameter, λ4 represents the fourth weight parameter, V 车 represents the vehicle speed, sigmoid() represents the activation function, which is used to map the variable to between 0 and 1, T 出风平均 Represents the average wind speed, VOL 总风 represents the total air volume, and Δt represents the target time.

[0123] The first ambient heat energy is obtained according to the average temperature in the vehicle, the vehicle speed, and the internal ambient temperature.

[0124] The average temperature inside the vehicle, the vehicle speed, and the internal ambient temperature are substituted into the second solid thermal conductivity function to obtain the first ambient thermal energy.

[0125] The second solid thermal conductivity function includes:

[0126] ΔQ 内环境 ={λ5+λ6·[sigmoid(λ7·V 车 )-0.5]}·(T 环境 -T 车内平均 )·Δt;

[0127] ΔQ 内环境 represents the first environmental heat energy, λ5 represents the fifth weight parameter, λ6 represents the sixth weight parameter, λ7 represents the seventh weight parameter, V 车 represents the vehicle speed, sigmoid() represents the activation function, which is used to map the variable to between 0 and 1, T 环境 represents the internal ambient temperature, and Δt represents the target time.

[0128] According to the external environment temperature, the second environment heat energy is obtained.

[0129] The external environment temperature is substituted into the first physical function to obtain the second environment heat energy. The first physical function includes: ΔQ 外环境 =λ8·P 阳光 Δt;

[0130] ΔQ 外环境 represents the second environment heat energy, λ8 represents the eighth weight parameter, P 阳光 represents the external environment temperature, and Δt represents the target time.

[0131] The human body heat energy is obtained based on the average temperature in the car and the human body temperature.

[0132] The average temperature inside the car is substituted into the second physical function to obtain the human body heat energy. The second physical function includes: ΔQ 人体 =λ9·(T 人体 -T 车内平均 )·Δt;

[0133] ΔQ 人体 represents the heat energy of human body, λ9 represents the ninth weight parameter, T 人体 represents the human body temperature, and Δt represents the target time.

[0134] For example, the first solid thermal conductivity function, the second solid thermal conductivity function, the first physical function, and the second physical function are substituted into the variation function to obtain:

[0135] T 车内平均 =ΔQ 车 / λ1

[0136] ={{λ2-λ3·[sigmoid(λ4·V 车 )-0.5]}·(T出风平均 -T 车内平均 )·VOL 总风 ·Δt+{λ5+λ6·[sigmoid(λ7·V 车 )-0.5]}·(T 环境 -T 车内平均 )·Δt+λ9·(T 人体 -T 车内平均 )·Δt+λ8·P 阳光 ·Δt)} / λ1.

[0137] The present invention replaces the complex gas thermal conductivity law with the solid thermal conductivity law, so as to efficiently and accurately obtain the vehicle's air-conditioning output heat energy, the first environment heat energy inside the vehicle, the body heat energy of the vehicle's passengers, and the second environment heat energy outside the vehicle that affect the total energy of the gas in the vehicle.

[0138] In a possible embodiment, the construction of the target location temperature prediction model may include the following steps:

[0139] For the direct blowing key point of the air conditioner whose target position is determined, the first target air outlet of the air conditioner corresponding to the direct blowing key point is determined, the distance from the first target air outlet to the direct blowing key point, the wind speed, air volume, cross-sectional area and the first wind temperature of the first target air outlet are determined, and the movement time of the gas from the first target air outlet to the direct blowing key point is determined based on the distance, wind speed, air volume and cross-sectional area.

[0140] The distance from the first target air outlet to the direct blowing key point and the wind speed of the first target air outlet are substituted into the distance calculation function to obtain the movement time from the first target air outlet to the direct blowing key point.

[0141] Among them, the distance calculation function includes:

[0142]

[0143] L represents the distance from the first target air outlet to the direct blowing key point, V 风 Characterizes the wind speed at the first target outlet, dV 风 / dt=-λ 10 t, VOL represents the air volume, S 出风口 Characterizes the cross-sectional area.

[0144] The loss temperature from the first target air outlet to the direct blowing key point is obtained according to the movement time, the vehicle speed and the first wind temperature, and the direct blowing key point temperature function is constructed according to the first wind temperature and the loss temperature.

[0145] The temperature loss function includes:

[0146] ΔQ 损失1 ={λ11+ λ 12 ·[sigmoid(λ 13 ·V 车 )-0.5]}·(T 风温1 -T 车内平均 )·Δt 风 ;

[0147] ΔQ 损失1 Represents the sum of the temperature loss from the first target outlet to the direct blowing key point during the movement time, λ 11 Characterizes the eleventh weight parameter, λ 12 represents the twelfth weight parameter, sigmoid() represents the activation function, which is used to map the variable to between 0 and 1, and λ 13 Characterize the thirteenth weight parameter, V 车 Represents vehicle speed, T 风温1 Characterizes the first wind temperature, Δt 风 Represents movement time.

[0148] Among them, because each moment in the movement time corresponds to a loss temperature, the movement time corresponds to multiple loss temperatures. The direct blowing key point temperature is the difference between the air temperature at the air outlet of the air conditioner during the movement time and the sum of all loss temperatures during the movement time.

[0149] Among them, the direct blowing key point temperature function includes: ΔQ 直吹关键点 =T 风温 -ΔQ 损失 .

[0150] For a non-direct blowing key point of the air conditioner whose target position is the non-direct blowing key point, the second target air outlet of the air conditioner corresponding to the non-direct blowing key point is determined, and the second wind temperature of the second target air outlet is obtained. The temperature function of the non-direct blowing key point is constructed according to the second wind temperature and the predicted average temperature in the vehicle.

[0151] Wherein, the non-direct blowing key point temperature function includes: ΔQ 损失2 =(T 风温2 -T 车内平均 ) / 2;

[0152] Q 损失2 Characterizes the loss temperature from the second target outlet to the non-direct blowing key point, T 风温2 Characterizes the second wind temperature.

[0153] The present invention constructs different target position temperature prediction models for different target positions, taking into account the temperature difference between direct blowing key points and non-direct blowing key points, thereby ensuring the reliability and stability of the prediction results.

[0154] The hyperparameters of the transient temperature prediction model in the present disclosure include the first weight parameter λ1 to the thirteenth weight parameter λ 13.

[0155] For example, see Figure 4 The transient temperature prediction model can predict the temperature of the key point of direct blowing by the following steps:

[0156] In step S41, the initial temperature of the direct blowing key point is determined.

[0157] Among them, the initial temperature is the temperature of the direct blowing key point when the air conditioner is just started, which can be collected by a sensor set at the direct blowing key point.

[0158] In step S42, the current temperature of the direct blowing key point is obtained.

[0159] In step S43, the current temperature and external conditions are input into the transient temperature prediction model.

[0160] Among them, the external conditions include the heat energy output by the vehicle's air conditioner, the first environmental heat energy inside the vehicle, the body heat energy of the vehicle's occupants, the second environmental heat energy outside the vehicle, and the current operating parameters of the air conditioner.

[0161] In step S44, the predicted temperature of the direct blowing key point output by the transient temperature prediction model according to the external conditions and the current temperature is obtained.

[0162] In step S45, the temperature difference between the current temperature and the predicted temperature of the direct blowing key point is determined.

[0163] In step S46, it is determined whether the temperature difference is less than the temperature difference threshold. If the temperature difference is less than the temperature difference threshold, step S47 is executed; if the temperature difference is not less than the temperature difference threshold, step S48 is executed.

[0164] In step S47, the target temperature of the direct blowing key point is obtained.

[0165] In step S48, the predicted temperature is used as the new current temperature, and the process returns to step S42.

[0166] In the process of steps S41 to S48, the temperature of the direct blowing key point is controlled by the outside temperature and the air-conditioning output. After turning on the air-conditioning, it takes a certain amount of time for the temperature inside the car to reach a steady state from the ambient temperature. During this time period, the transient temperature prediction model can output the predicted temperature for each moment in the time period.

[0167] For example, see Figure 5 When the air conditioner is just started, the initial temperature of the direct blowing key point is greatly different from the air temperature of the air conditioner, but slightly different from the outside temperature. As time goes by, the current temperature of the direct blowing key point is gradually smaller than the air temperature of the air conditioner, but slightly different from the outside temperature, until the temperature difference between the predicted temperature and the current temperature is less than the temperature threshold.

[0168] For example, see Figure 6 The process of predicting the temperature of a target position in a vehicle using a transient temperature prediction model may include the following steps:

[0169] In step S61, the air temperature and air volume of each air outlet of the air conditioner are determined.

[0170] In step S62, the heat energy output by the air conditioner is determined according to the wind temperature and wind volume of each air outlet.

[0171] In step S63, the total energy of the gas inside the vehicle is determined according to the heat energy output by the air conditioner, the environmental energy inside the vehicle, and the environmental energy outside the vehicle.

[0172] In step S64, the average temperature inside the vehicle is obtained according to the total energy of the gas inside the vehicle. When the target position is a direct blowing key point, step S65 is executed; when the target position is a non-direct blowing key point, step S67 is executed.

[0173] In step S65, the movement time of the gas from the first target air outlet to the direct blowing key point is determined, and the loss temperature is obtained according to the wind temperature, the air volume and the average temperature inside the vehicle.

[0174] In step S66, the direct blowing key point temperature is obtained according to the movement time and the loss temperature.

[0175] In step S67, the air temperature of the second target air outlet is determined.

[0176] In step S68, the non-direct blowing key point temperature is obtained according to the wind temperature and the average temperature in the vehicle.

[0177] Through steps S61 to S68, the following can be obtained: Figure 7 , Figure 8 The simulation result sample shown. The present disclosure can make predictions based on 10% of the current operating parameters, and the prediction results meet the prediction accuracy requirements for 86% of the working conditions, and can achieve a 100% satisfaction rate for the working conditions in the simulation data, thereby reducing the air conditioning calibration cost by 90%.

[0178] Based on the same inventive concept, the present disclosure also provides an air conditioning calibration device. Fig. 9 is a block diagram of an air conditioner calibration device according to an exemplary embodiment. Fig. 9 The air conditioning calibration device 900 includes an acquisition module 901 , a prediction module 902 and a calibration module 903 .

[0179] The acquisition module 901 is configured to acquire the current operating parameters of the air conditioner.

[0180] The prediction module 902 is configured to input the current operating parameters into the transient temperature prediction model to obtain multiple predicted transient temperatures output by the transient temperature prediction model according to the current operating parameters within the target time period. The transient temperature prediction model is constructed based on the solid thermal conductivity law.

[0181] The calibration module 903 is configured to obtain a predicted steady-state temperature according to a plurality of predicted transient temperatures, and calibrate the operating parameters of the air conditioner according to the predicted steady-state temperature.

[0182] In the present invention, a plurality of predicted transient temperatures within a target time period are output based on the current wind temperature and the current air volume of the air conditioner based on a transient temperature prediction model, and a predicted steady-state temperature is obtained based on the plurality of predicted transient temperatures, thereby calibrating the operating parameters of the air conditioner according to the predicted steady-state temperature. The entire process involves fewer operating parameters of the air conditioner and does not require manual calibration, thus shortening the calibration time and reducing the calibration cost. In addition, the calibration results are not affected by human factors and are reliable.

[0183] Further, the calibration module 903 is configured to calculate an average value of a plurality of predicted transient temperatures and use the average value as the predicted steady-state temperature;

[0184] Substituting the predicted steady-state temperature and the actual steady-state temperature into the first loss function, iteratively solving the first loss function through the gradient descent algorithm to obtain a first loss value, and determining a first gradient value corresponding to the current operating parameter, the first loss value being the minimum value of the first loss function;

[0185] Subtracting the current operating parameter from the first gradient value to obtain a first difference;

[0186] Multiplying the first difference by a learning rate of a transient temperature prediction model to obtain a target operating parameter;

[0187] The current operating parameters of the air conditioner are calibrated according to the target operating parameters.

[0188] Furthermore, the air conditioner calibration device 900 also includes a training module, which is configured to:

[0189] Substituting the predicted transient temperature and the actual transient temperature of the target position at the same time into the second loss function, iteratively solving the second loss function through the gradient descent algorithm to obtain a second loss value, and determining a second gradient value of the initial hyperparameter in the corresponding transient temperature prediction model, the second loss value is less than the loss threshold;

[0190] Subtracting the initial hyperparameter from the second gradient value corresponding to the initial hyperparameter to obtain a second difference;

[0191] Multiplying the second difference by the learning rate of the transient temperature prediction model to obtain an optimized target hyperparameter;

[0192] Update the initial hyperparameters in the transient temperature prediction model to the target hyperparameters.

[0193] Furthermore, the air conditioner is installed in the vehicle, and the transient temperature prediction model includes an average temperature prediction model in the vehicle and a target location temperature prediction model;

[0194] The average temperature prediction model inside the vehicle is used to predict the average temperature inside the vehicle according to the input current operating parameters output;

[0195] The target location temperature prediction model is used to output the predicted transient temperature of the target location according to the input predicted average temperature inside the vehicle.

[0196] Further, the air conditioning calibration device 900 further includes a construction module, which is configured to determine the air conditioning output heat energy of the vehicle, the first environment heat energy inside the vehicle, the body heat energy of the vehicle occupant, and the second environment heat energy outside the vehicle;

[0197] Obtaining the total energy of the gas inside the vehicle according to the heat energy output by the air conditioner, the first environment heat energy, the human body heat energy and the second environment heat energy;

[0198] Taking the total energy of the gas in the car as the independent variable and the average temperature in the car as the dependent variable, a change function that makes the independent variable positively correlated with the dependent variable is constructed to obtain the average temperature prediction model in the car.

[0199] Further, the building module is configured to obtain the vehicle speed, the average wind speed of each air outlet of the air conditioner, the total air volume, the internal ambient temperature of the vehicle, the body temperature of the occupants in the vehicle, and the external ambient temperature of the vehicle;

[0200] According to the average temperature in the car, the vehicle speed, the average wind speed and the total air volume, the heat energy output by the air conditioner is obtained;

[0201] The first environment heat energy is obtained according to the average temperature inside the vehicle, the vehicle speed, and the internal environment temperature;

[0202] According to the external environment temperature, the second environment heat energy is obtained;

[0203] The human body heat energy is obtained based on the average temperature in the car and the human body temperature.

[0204] Further, the construction module is configured to determine, for a target position being a direct blowing key point of an air conditioner, a first target air outlet of the air conditioner corresponding to the direct blowing key point, determine a distance from the first target air outlet to the direct blowing key point, a wind speed, an air volume, a cross-sectional area, and a first wind temperature of the first target air outlet, and determine a movement time of the gas from the first target air outlet to the direct blowing key point according to the distance, the wind speed, the air volume, and the cross-sectional area;

[0205] According to the movement time, the vehicle speed and the first wind temperature, the loss temperature from the first target air outlet to the direct blowing key point is obtained, and the direct blowing key point temperature function is constructed according to the first wind temperature and the loss temperature;

[0206] For a non-direct blowing key point of the air conditioner whose target position is the non-direct blowing key point, the second target air outlet of the air conditioner corresponding to the non-direct blowing key point is determined, and the second wind temperature of the second target air outlet is obtained. The temperature function of the non-direct blowing key point is constructed according to the second wind temperature and the predicted average temperature in the vehicle.

[0207] Regarding the air conditioning calibration device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0208] The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon, and the program instructions, when executed by a processor, implement the steps of the air conditioner calibration method provided by the present disclosure.

[0209] Based on the same inventive concept, the present disclosure provides another air conditioner calibration device, comprising:

[0210] a first processor;

[0211] a first memory for storing first processor executable instructions;

[0212] Wherein, the first processor is configured as:

[0213] Get the current operating parameters of the air conditioner;

[0214] Inputting the current operating parameters into the transient temperature prediction model, obtaining a plurality of predicted transient temperatures output by the transient temperature prediction model according to the current operating parameters within the target time period, wherein the transient temperature prediction model is constructed based on the solid thermal conductivity law;

[0215] A predicted steady-state temperature is obtained according to a plurality of predicted transient temperatures, and operating parameters of the air conditioner are calibrated according to the predicted steady-state temperature.

[0216] In the present invention, a plurality of predicted transient temperatures within a target time period are output based on the current wind temperature and the current air volume of the air conditioner based on a transient temperature prediction model, and a predicted steady-state temperature is obtained based on the plurality of predicted transient temperatures, thereby calibrating the operating parameters of the air conditioner according to the predicted steady-state temperature. The entire process involves fewer operating parameters of the air conditioner and does not require manual calibration, thus shortening the calibration time and reducing the calibration cost. In addition, the calibration results are not affected by human factors and are reliable.

[0217] Fig.101 is a block diagram of an air conditioner calibration device 1000 according to an exemplary embodiment. For example, the air conditioner calibration device 1000 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a tablet device, a personal digital assistant, and the like.

[0218] Reference Fig.10 The air conditioning calibration device 1000 may include one or more of the following components: a processing component 1002 , a first memory 1004 , a power component 1006 , a multimedia component 10010 , an audio component 1010 , an input / output interface 1012 , a sensor component 1014 , and a communication component 1016 .

[0219] The processing component 1002 generally controls the overall operation of the air conditioning calibration device 1000, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 1002 may include one or more first processors 1020 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 1002 may include one or more modules to facilitate the interaction between the processing component 1002 and other components. For example, the processing component 1002 may include a multimedia module to facilitate the interaction between the multimedia component 1008 and the processing component 1002.

[0220] The first memory 1004 is configured to store various types of data to support the operation of the air conditioner calibration device 1000. Examples of such data include instructions for any application or method operating on the air conditioner calibration device 1000, current operating parameters of the air conditioner, predicted transient temperature, and predicted steady-state temperature, etc. The first memory 1004 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0221] The power supply component 1006 provides power to various components of the air conditioning calibration device 1000. The power supply component 1006 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the air conditioning calibration device 1000.

[0222] The multimedia component 1008 includes a screen that provides an output interface between the air conditioning calibration device 1000 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 1008 includes a front camera and / or a rear camera. When the air conditioning calibration device 1000 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0223] The audio component 1010 is configured to output and / or input audio signals. For example, the audio component 1010 includes a microphone (MIC), and when the air conditioning calibration device 1000 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the first memory 1004 or sent via the communication component 1016. In some embodiments, the audio component 1010 also includes a speaker for outputting audio signals.

[0224] The input / output interface 1012 provides an interface between the processing component 1002 and the peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0225] The sensor assembly 1014 includes one or more sensors for providing various aspects of status evaluation for the air conditioning calibration device 1000. For example, the sensor assembly 1014 can detect the open / closed state of the air conditioning calibration device 1000, the relative positioning of the components, such as the display and keypad of the air conditioning calibration device 1000, and the sensor assembly 1014 can also detect the position change of the air conditioning calibration device 1000 or a component of the air conditioning calibration device 1000, the presence or absence of contact between the user and the air conditioning calibration device 1000, the orientation or acceleration / deceleration of the air conditioning calibration device 1000, and the temperature change of the air conditioning calibration device 1000. The sensor assembly 1014 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 1014 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1014 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0226] The communication component 1016 is configured to facilitate wired or wireless communication between the air conditioning calibration device 1000 and other devices. The air conditioning calibration device 1000 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 1016 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1016 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0227] In an exemplary embodiment, the air conditioner calibration device 1000 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned air conditioner calibration method.

[0228] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a first memory 1004 including instructions, and the instructions can be executed by a first processor 1020 of the air conditioner calibration device 1000 to complete the air conditioner calibration method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0229] In addition to being an independent electronic device, the air conditioning calibration device 1000 can also be a part of an independent electronic device. For example, in one embodiment, the device can be an integrated circuit (IC) or a chip, wherein the integrated circuit can be an IC or a collection of multiple ICs; the chip can include but is not limited to the following types: GPU (Graphics Processing Unit), CPU (Central Processing Unit), FPGA (Field Programmable Gate Array), DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), SOC (System on Chip, SoC), etc. The above-mentioned integrated circuit or chip can be used to execute executable instructions (or codes) to implement the above-mentioned air conditioning method. The executable instructions can be stored in the integrated circuit or chip, or can be obtained from other devices or equipment, such as the integrated circuit or chip including a processor, a memory, and an interface for communicating with other devices. The executable instruction can be stored in the second memory, and when the executable instruction is executed by the processor, the above-mentioned air conditioner calibration method is implemented; alternatively, the integrated circuit or chip can receive the executable instruction through the interface and transmit it to the processor for execution, so as to implement the above-mentioned air conditioner calibration method.

[0230] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program that can be executed by a programmable device. The computer program has a code portion for executing the above-mentioned air conditioning calibration method when executed by the programmable device.

[0231] Based on the same inventive concept, the present disclosure also provides a vehicle, including an air conditioner and the above-mentioned air conditioner calibration device 1000.

[0232] The present invention obtains the loss value of the predicted transient temperature and the real transient temperature through the gradient descent algorithm, thereby determining the second gradient value of the initial parameter of the transient temperature prediction model, optimizing the initial hyperparameter according to the second gradient value, obtaining the target hyperparameter, and updating the initial hyperparameter in the transient temperature prediction model to the target hyperparameter, thereby optimizing the transient temperature prediction model. The transient temperature prediction model can be optimized with a small amount of data, ensuring the reliability and accuracy of the output result of the transient temperature prediction model.

[0233] Fig.111 is a block diagram of a vehicle 1100 according to an exemplary embodiment. For example, the vehicle 1100 may be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicles. The vehicle 1100 may be an autonomous vehicle or a semi-autonomous vehicle.

[0234] Reference Fig.11 , the vehicle 1100 may include various subsystems, such as an infotainment system 1110, a perception system 1120, a decision control system 1130, a drive system 1140, and a computing platform 1150. The vehicle 1100 may also include more or fewer subsystems, and each subsystem may include multiple components. In addition, each subsystem and each component of the vehicle 1100 may be interconnected by wire or wireless means.

[0235] In some embodiments, the infotainment system 1110 may include a communication system, an entertainment system, and a navigation system, etc.

[0236] The perception system 1120 may include several sensors for sensing information about the environment around the vehicle 1100. For example, the perception system 1120 may include a global positioning system (the global positioning system may be a GPS system, or a Beidou system or other positioning systems), an inertial measurement unit (IMU), a laser radar, a millimeter wave radar, an ultrasonic radar, and a camera.

[0237] The decision control system 1130 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0238] The drive system 1140 may include components that provide powered motion for the vehicle 1100. In one embodiment, the drive system 1140 may include an engine, an energy source, a transmission system, and wheels. The engine may be one or a combination of an internal combustion engine, an electric motor, and an air compression engine. The engine is capable of converting energy provided by the energy source into mechanical energy.

[0239] Some or all functions of the vehicle 1100 are controlled by a computing platform 1150. The computing platform 1150 may include at least one third processor 1151 and a third memory 1152, and the third processor 1151 may execute instructions 1153 stored in the third memory 1152.

[0240] The third processor 1151 may be any conventional processor, such as a commercially available CPU. The processor may also include a graphics processor (Graphic Process Unit, GPU), a field programmable gate array (Field Programmable Gate Array, FPGA), a system on chip (System on Chip, SOC), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC) or a combination thereof.

[0241] The third memory 1152 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0242] In addition to the instructions 1153 , the third memory 1152 may also store data, such as road maps, route information, and data such as the location, direction, and speed of the vehicle. The data stored in the third memory 1152 may be used by the computing platform 1150 .

[0243] In the embodiment of the present disclosure, the third processor 1151 may execute instruction 1153 to complete all or part of the steps of the above-mentioned time synchronization method.

[0244] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the present disclosure. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0245] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An air conditioning calibration method, characterized in that: include: Get the current operating parameters of the air conditioner; Inputting the current operating parameters into a transient temperature prediction model to obtain a plurality of predicted transient temperatures output by the transient temperature prediction model according to the current operating parameters within a target time period, wherein the transient temperature prediction model is constructed based on the solid thermal conductivity law; A predicted steady-state temperature is obtained according to the multiple predicted transient temperatures, and an operating parameter of the air conditioner is calibrated according to the predicted steady-state temperature.

2. The air conditioning calibration method according to claim 1, characterized in that: The step of obtaining a predicted steady-state temperature according to the plurality of predicted transient temperatures, and calibrating an operating parameter of the air conditioner according to the predicted steady-state temperature, comprises: Calculating an average value of a plurality of the predicted transient temperatures, and using the average value as the predicted steady-state temperature; Substituting the predicted steady-state temperature and the actual steady-state temperature into a first loss function, iteratively solving the first loss function through a gradient descent algorithm to obtain a first loss value, and determining a first gradient value corresponding to the current operating parameter, the first loss value being a minimum value of the first loss function; Subtracting the current operating parameter from the first gradient value to obtain a first difference; Multiplying the first difference by the learning rate of the transient temperature prediction model to obtain a target operating parameter; The current operating parameters of the air conditioner are calibrated according to the target operating parameters.

3. The air conditioning calibration method according to claim 1, characterized in that: The training process of the transient temperature prediction model includes: Substituting the predicted transient temperature and the actual transient temperature of the target position at the same time into a second loss function, iteratively solving the second loss function through a gradient descent algorithm to obtain a second loss value, and determining a second gradient value corresponding to an initial hyperparameter in the transient temperature prediction model, wherein the second loss value is less than a loss threshold; Subtracting the initial hyperparameter from the second gradient value corresponding to the initial hyperparameter to obtain a second difference; Multiplying the second difference by the learning rate of the transient temperature prediction model to obtain an optimized target hyperparameter; The initial hyperparameters in the transient temperature prediction model are updated to the target hyperparameters.

4. The air conditioning calibration method according to any one of claims 1 to 3, characterized in that: The air conditioner is arranged on the vehicle, and the transient temperature prediction model includes an in-vehicle average temperature prediction model and a target position temperature prediction model; The vehicle interior average temperature prediction model is used to predict the vehicle interior average temperature according to the input current operating parameter output; The target position temperature prediction model is used to output the predicted transient temperature of the target position according to the input predicted average temperature inside the vehicle.

5. The air conditioning calibration method according to claim 4, characterized in that: The construction of the vehicle interior average temperature prediction model includes: Determining heat energy output by an air conditioner of the vehicle, heat energy of a first environment inside the vehicle, heat energy of a human body of an occupant of the vehicle, and heat energy of a second environment outside the vehicle; Obtaining the total energy of the gas inside the vehicle according to the heat energy output by the air conditioner, the first environment heat energy, the human body heat energy and the second environment heat energy; The total energy of the gas in the vehicle is taken as an independent variable, and the average temperature in the vehicle is taken as a dependent variable, a variation function is constructed so that the independent variable is positively correlated with the dependent variable, and a prediction model for the average temperature in the vehicle is obtained.

6. The air conditioning calibration method according to claim 5, characterized in that: The determining of the heat energy output by the air conditioner of the vehicle, the first environment heat energy inside the vehicle, the body heat energy of the occupant inside the vehicle, and the second environment heat energy outside the vehicle includes: Obtaining the vehicle speed, the average wind speed of each air outlet of the air conditioner, the total air volume, the internal ambient temperature of the vehicle, the body temperature of the occupants in the vehicle, and the external ambient temperature of the vehicle; Obtaining the heat energy output by the air conditioner according to the average temperature in the vehicle, the vehicle speed, the average wind speed and the total air volume; Obtaining the first ambient heat energy according to the average temperature inside the vehicle, the vehicle speed, and the internal ambient temperature; According to the external environment temperature, obtaining the second environment heat energy; The human body thermal energy is obtained according to the average temperature in the vehicle and the human body temperature.

7. The air conditioning calibration method according to claim 6, characterized in that: The construction of the target location temperature prediction model includes: For a direct blowing key point of the air conditioner whose target position is a direct blowing key point, determining a first target air outlet of the air conditioner corresponding to the direct blowing key point, determining a distance from the first target air outlet to the direct blowing key point, a wind speed, an air volume, a cross-sectional area, and a first wind temperature of the first target air outlet, and determining a movement time of gas from the first target air outlet to the direct blowing key point according to the distance, the wind speed, the air volume, and the cross-sectional area; Obtaining a loss temperature from the first target air outlet to a direct blowing key point according to the movement time, the vehicle speed, and the first wind temperature, and constructing a direct blowing key point temperature function according to the first wind temperature and the loss temperature; For a non-direct blowing key point of the air conditioner whose target position is the non-direct blowing key point, determine the second target air outlet of the air conditioner corresponding to the non-direct blowing key point, and obtain the second wind temperature of the second target air outlet, and construct a non-direct blowing key point temperature function based on the second wind temperature and the predicted average temperature in the vehicle.

8. An air conditioning calibration device, characterized in that: include: An acquisition module, configured to acquire current operating parameters of the air conditioner; A prediction module is configured to input the current operating parameters into a transient temperature prediction model to obtain a plurality of predicted transient temperatures output by the transient temperature prediction model according to the current operating parameters within a target time period, wherein the transient temperature prediction model is constructed based on a solid thermal conductivity law; The calibration module is configured to obtain a predicted steady-state temperature according to the plurality of predicted transient temperatures, and to calibrate the operating parameters of the air conditioner according to the predicted steady-state temperature.

9. An air conditioning calibration device, characterized in that: include: a first processor; a first memory for storing first processor executable instructions; Wherein, the first processor is configured as follows: Get the current operating parameters of the air conditioner; Inputting the current operating parameters into a transient temperature prediction model to obtain a plurality of predicted transient temperatures output by the transient temperature prediction model according to the current operating parameters within a target time period, wherein the transient temperature prediction model is constructed based on the solid thermal conductivity law; A predicted steady-state temperature is obtained according to the multiple predicted transient temperatures, and an operating parameter of the air conditioner is calibrated according to the predicted steady-state temperature.

10. A vehicle, characterized in that: The vehicle includes an air conditioner and the air conditioner calibration device according to claim 9.

11. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

12. A chip, characterized in that: The method comprises a second processor and an interface; the second processor is used to read instructions to execute the method according to any one of claims 1 to 7.

Images