Vehicle-mounted air conditioner control method and device, vehicle and storage medium

Abstract

The invention relates to a vehicle-mounted air conditioner control method and device, a vehicle and a storage medium in the technical field of vehicle thermal management. The method comprises the steps that target information of the vehicle at the current moment and setting information of each air outlet of a vehicle-mounted air conditioner are obtained; the setting information corresponding to the current moment and the target information are input into a vehicle-mounted air conditioner model, and the predicted passenger compartment temperature corresponding to the current moment output by the vehicle-mounted air conditioner model is obtained; and under the condition that the predicted passenger compartment temperature does not meet the passenger compartment temperature condition, setting information of an air outlet of the vehicle-mounted air conditioner is adjusted, model parameters of the vehicle-mounted air conditioner model are updated through back propagation, and the updated vehicle-mounted air conditioner model is obtained. The real physical law can be more approached in the vehicle temperature change process from the transient state to the steady state, and therefore the accuracy of temperature adjustment of the passenger compartment of the vehicle is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle thermal management technology, and in particular to a vehicle air conditioning control method, device, vehicle and storage medium. Background Art

[0002] The comfort of the passenger compartment temperature is one of the important factors that affect the user experience of a car. In relevant scenarios, the passenger compartment temperature is predicted through simulation analysis, and the outlet temperature and air volume of the vehicle air conditioner are adjusted to optimize the temperature distribution in the passenger compartment and improve the comfort and satisfaction of passengers. However, the prediction of the passenger compartment temperature by simulation software or by establishing a heat balance equation only considers the ideal situation. There is a large difference between the predicted passenger compartment temperature and the actual passenger compartment temperature, resulting in low accuracy in the adjustment of the passenger compartment temperature. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the present disclosure provides a vehicle air conditioning control method, device, vehicle and storage medium.

[0004] According to a first aspect of an embodiment of the present disclosure, there is provided a vehicle air conditioning control method, comprising:

[0005] Obtain the target information of the vehicle at the current moment and the setting information of each air outlet of the vehicle air conditioner;

[0006] Inputting the setting information and the target information corresponding to the current moment into the vehicle air conditioning model, so that the vehicle air conditioning model outputs the predicted passenger compartment temperature corresponding to the current moment;

[0007] When the predicted passenger compartment temperature does not meet the passenger compartment temperature condition, the setting information of the air outlet of the vehicle air conditioner is adjusted and the model parameters of the vehicle air conditioner model are updated by back propagation to obtain an updated vehicle air conditioner model.

[0008] Optionally, the model parameters include heat exchange learning parameters, heat radiation learning parameters and influence weight parameters of each of the air outlets, and the vehicle air conditioning model determines the predicted passenger compartment temperature in the following manner:

[0009] Determining the heat exchange temperature of each of the air outlets according to the heat exchange learning parameter, the setting information of each of the air outlets at the current moment, and the ambient temperature, vehicle speed, and historical predicted passenger compartment temperature in the target information;

[0010] Determine the thermal radiation temperature of each of the air outlets according to the thermal radiation information corresponding to each of the air outlets in the target information, the thermal radiation information corresponding to the previous N moments, and the thermal radiation learning parameter;

[0011] Determining the predicted temperature at the current moment according to the influence weight parameter of each air outlet, the heat radiation temperature corresponding to the air outlet, and the heat exchange temperature;

[0012] The predicted passenger compartment temperature corresponding to the previous N moments and the average value of the predicted temperature at the current moment are calculated to obtain the predicted passenger compartment temperature corresponding to the current moment.

[0013] Optionally, the heat exchange learning parameters include internal heat exchange learning parameters and external heat exchange learning parameters, and determining the heat exchange temperature of each air outlet according to the heat exchange learning parameters, setting information of each air outlet at a current moment, and the ambient temperature, vehicle speed, and historical predicted passenger compartment temperature in the target information includes:

[0014] Determine the influence value of the activation function according to the vehicle speed at the current moment and the historical vehicle speeds at N moments before the current moment;

[0015] Determining the internal heat exchange temperature of each of the air outlets according to the setting information of each of the air outlets at the current moment, the influence value, and the historical predicted passenger compartment temperature in the target information;

[0016] Determine the external heat exchange temperature of each of the air outlets according to the setting information of each of the air outlets at the current moment, the impact value and the ambient temperature in the target information;

[0017] The heat exchange temperature of each of the air outlets is determined according to the internal heat exchange learning parameter, the external heat exchange learning parameter, the internal heat exchange temperature of each of the air outlets, and the external heat exchange temperature.

[0018] Optionally, determining the internal heat exchange temperature of each of the air outlets according to the setting information of each of the air outlets at the current moment, the influence value, and the historical predicted passenger compartment temperature in the target information includes:

[0019] Determine the temperature change of each of the air outlets according to the air outlet temperature in the setting information of each of the air outlets at the current moment and the historical predicted passenger compartment temperature at the previous N moments in the target information;

[0020] Determining the internal heat exchange parameters of each of the air outlets according to the temperature change of each of the air outlets and the air volume of the air outlet corresponding to the air outlet in the setting information;

[0021] The internal heat exchange temperature of each air outlet is determined according to the influence value and the internal heat exchange parameter of each air outlet.

[0022] Optionally, determining the external heat exchange temperature of each of the air outlets according to the setting information of each of the air outlets at the current moment, the impact value, and the ambient temperature in the target information includes:

[0023] Determine the temperature difference of each of the air outlets according to the air outlet temperature in the setting information of each of the air outlets at the current moment and the ambient temperature in the target information;

[0024] Determining the external heat exchange parameters of each of the air outlets according to the temperature difference of each of the air outlets and the air volume of the air outlet corresponding to the air outlet in the setting information;

[0025] The external heat exchange temperature of each air outlet is determined according to the influence value and the external heat exchange parameter of each air outlet.

[0026] Optionally, determining the heat exchange temperature of each air outlet according to the internal heat exchange learning parameter, the external heat exchange learning parameter, the internal heat exchange temperature of each air outlet, and the external heat exchange temperature includes:

[0027] Calculating the product of the internal heat exchange learning parameter and the internal heat exchange temperature of each of the air outlets to obtain a first temperature parameter, and calculating the product of the external heat exchange learning parameter and the external heat exchange temperature of each of the air outlets to obtain a second temperature parameter;

[0028] The sum of the first temperature parameter of each air outlet and the corresponding second temperature parameter is determined as the heat exchange temperature corresponding to each air outlet.

[0029] Optionally, the thermal radiation information includes thermal radiation information of multiple directions, and each direction of the vehicle is correspondingly provided with a thermal radiation learning parameter in the vehicle air conditioning model;

[0030] The determining the thermal radiation temperature of each of the air outlets according to the thermal radiation information corresponding to each of the air outlets in the target information, the thermal radiation information corresponding to the previous N moments, and the thermal radiation learning parameter includes:

[0031] Determine the cumulative radiation temperature of the position according to the thermal radiation information of the position corresponding to each of the air outlets in the target information and the thermal radiation information of the position corresponding to the previous N moments;

[0032] The thermal radiation temperature of each of the air outlets is determined according to the cumulative radiation temperature and the thermal radiation learning parameter corresponding to the orientation.

[0033] Optionally, determining the predicted temperature at the current moment according to the influence weight parameter of each air outlet, the heat radiation temperature corresponding to the air outlet, and the heat exchange temperature includes:

[0034] Determining the thermal parameter temperature of each of the air outlets according to the heat radiation temperature and the heat exchange temperature of each of the air outlets;

[0035] The predicted temperature of each air outlet is determined according to the thermal parameter temperature of each air outlet and the influence weight parameter corresponding to the air outlet.

[0036] According to a second aspect of an embodiment of the present disclosure, there is provided a vehicle air conditioning control device, comprising:

[0037] An acquisition module is configured to acquire target information of the vehicle at a current moment and setting information of each air outlet of the vehicle air conditioner;

[0038] an input module configured to input the setting information and the target information corresponding to the current moment into the vehicle air conditioning model, and obtain a predicted passenger compartment temperature corresponding to the current moment output by the vehicle air conditioning model;

[0039] The adjustment and update module is configured to adjust the setting information of the air outlet of the vehicle air conditioner and back-propagate to update the model parameters of the vehicle air conditioner model when the predicted passenger compartment temperature does not meet the passenger compartment temperature condition, so as to obtain an updated vehicle air conditioner model.

[0040] Optionally, the model parameters include heat exchange learning parameters, heat radiation learning parameters and influence weight parameters of each of the air outlets, and the input module is configured to enable the vehicle air conditioning model to determine the predicted passenger compartment temperature in the following manner:

[0041] Determining the heat exchange temperature of each of the air outlets according to the heat exchange learning parameter, the setting information of each of the air outlets at the current moment, and the ambient temperature, vehicle speed, and historical predicted passenger compartment temperature in the target information;

[0042] Determine the thermal radiation temperature of each of the air outlets according to the thermal radiation information corresponding to each of the air outlets in the target information, the thermal radiation information corresponding to the previous N moments, and the thermal radiation learning parameter;

[0043] Determining the predicted temperature at the current moment according to the influence weight parameter of each air outlet, the heat radiation temperature corresponding to the air outlet, and the heat exchange temperature;

[0044] The predicted passenger compartment temperature corresponding to the previous N moments and the average value of the predicted temperature at the current moment are calculated to obtain the predicted passenger compartment temperature corresponding to the current moment.

[0045] Optionally, the heat exchange learning parameters include internal heat exchange learning parameters and external heat exchange learning parameters, and the input module is configured to enable the vehicle air conditioning model to determine the heat exchange temperature in the following manner, including:

[0046] Determine the influence value of the activation function according to the vehicle speed at the current moment and the historical vehicle speeds at N moments before the current moment;

[0047] Determining the internal heat exchange temperature of each of the air outlets according to the setting information of each of the air outlets at the current moment, the influence value, and the historical predicted passenger compartment temperature in the target information;

[0048] Determine the external heat exchange temperature of each of the air outlets according to the setting information of each of the air outlets at the current moment, the impact value and the ambient temperature in the target information;

[0049] The heat exchange temperature of each of the air outlets is determined according to the internal heat exchange learning parameter, the external heat exchange learning parameter, the internal heat exchange temperature of each of the air outlets, and the external heat exchange temperature.

[0050] Optionally, the input module is configured to enable the vehicle air conditioning model to determine the internal heat exchange temperature in the following manner, including:

[0051] Determine the temperature change of each of the air outlets according to the air outlet temperature in the setting information of each of the air outlets at the current moment and the historical predicted passenger compartment temperature at the previous N moments in the target information;

[0052] Determining the internal heat exchange parameters of each of the air outlets according to the temperature change of each of the air outlets and the air volume of the air outlet corresponding to the air outlet in the setting information;

[0053] The internal heat exchange temperature of each air outlet is determined according to the influence value and the internal heat exchange parameter of each air outlet.

[0054] Optionally, the input module is configured to enable the vehicle air conditioning model to determine the external heat exchange temperature in the following manner, including:

[0055] Determine the temperature difference of each of the air outlets according to the air outlet temperature in the setting information of each of the air outlets at the current moment and the ambient temperature in the target information;

[0056] Determining the external heat exchange parameters of each of the air outlets according to the temperature difference of each of the air outlets and the air volume of the air outlet corresponding to the air outlet in the setting information;

[0057] The external heat exchange temperature of each air outlet is determined according to the influence value and the external heat exchange parameter of each air outlet.

[0058] Optionally, the input module is configured to enable the vehicle air conditioning model to determine the heat exchange temperature in the following manner, including:

[0059] Calculating the product of the internal heat exchange learning parameter and the internal heat exchange temperature of each of the air outlets to obtain a first temperature parameter, and calculating the product of the external heat exchange learning parameter and the external heat exchange temperature of each of the air outlets to obtain a second temperature parameter;

[0060] The sum of the first temperature parameter of each air outlet and the corresponding second temperature parameter is determined as the heat exchange temperature corresponding to each air outlet.

[0061] Optionally, the thermal radiation information includes thermal radiation information of multiple directions, and each direction of the vehicle is correspondingly provided with a thermal radiation learning parameter in the vehicle air conditioning model;

[0062] The input module is configured to enable the vehicle air conditioning model to determine the heat radiation temperature in the following manner, including:

[0063] Determine the cumulative radiation temperature of the position according to the thermal radiation information of the position corresponding to each of the air outlets in the target information and the thermal radiation information of the position corresponding to the previous N moments;

[0064] The thermal radiation temperature of each of the air outlets is determined according to the cumulative radiation temperature and the thermal radiation learning parameter corresponding to the orientation.

[0065] Optionally, the input module is configured to enable the vehicle air conditioning model to determine the predicted temperature in the following manner, including:

[0066] Determining the thermal parameter temperature of each of the air outlets according to the heat radiation temperature and the heat exchange temperature of each of the air outlets;

[0067] The predicted temperature of each air outlet is determined according to the thermal parameter temperature of each air outlet and the influence weight parameter corresponding to the air outlet.

[0068] According to a third aspect of an embodiment of the present disclosure, a vehicle is provided, comprising:

[0069] processor;

[0070] a memory for storing processor-executable instructions;

[0071] The processor is configured to execute the executable instructions stored in the memory to implement any method described in the first aspect.

[0072] According to a fourth aspect of an embodiment of the present disclosure, there is provided a computer-readable storage medium on which computer program instructions are stored, and when the program instructions are executed by a processor, the steps of any one of the methods described in the first aspect are implemented.

[0073] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:

[0074] Obtain the target information of the vehicle at the current moment and the setting information of each air outlet of the vehicle air conditioner; input the setting information and the target information corresponding to the current moment into the vehicle air conditioner model to obtain the predicted passenger compartment temperature corresponding to the current moment output by the vehicle air conditioner model; if the predicted passenger compartment temperature does not meet the passenger compartment temperature condition, adjust the setting information of the air outlet of the vehicle air conditioner and back-propagate to update the model parameters of the vehicle air conditioner model to obtain the updated vehicle air conditioner model. The real physical law can be more closely approached in the process of vehicle temperature change from transient to steady state, thereby improving the accuracy of passenger compartment temperature adjustment of the vehicle.

[0075] 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

[0076] 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.

[0077] Figure 1 The figure is a flow chart of a vehicle air conditioning control method according to an exemplary embodiment.

[0078] Figure 2 It is a block diagram of a vehicle air conditioning model according to an exemplary embodiment.

[0079] Figure 3 The present invention is a temporal residual network architecture of a vehicle air conditioning model according to an exemplary embodiment.

[0080] Figure 4 The present invention is a flow chart of a method for determining a predicted passenger compartment temperature using a vehicle air conditioning model according to an exemplary embodiment.

[0081] Figure 5 An implementation according to an exemplary embodiment is shown Figure 4 Flowchart of step S41 in FIG.

[0082] Figure 6 An implementation according to an exemplary embodiment is shown Figure 5 Flowchart of step S412 in FIG.

[0083] Figure 7 An implementation according to an exemplary embodiment is shown Figure 5 Flowchart of step S413 in FIG.

[0084] Figure 8An implementation according to an exemplary embodiment is shown Figure 4 Flowchart of step S42 in FIG.

[0085] Fig. 9 An implementation according to an exemplary embodiment is shown Figure 4 Flowchart of step S43 in FIG.

[0086] Fig.10 The figure is a block diagram of a vehicle air conditioning control device according to an exemplary embodiment.

[0087] Fig.11 It is a schematic diagram of a functional block diagram of a vehicle according to an exemplary embodiment. DETAILED DESCRIPTION

[0088] 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.

[0089] It should be noted that all actions of acquiring signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located, and with the authorization given by the owner of the corresponding device.

[0090] Before introducing the vehicle air conditioning control method, device, vehicle and storage medium provided by the present disclosure, the defects of predicting the passenger compartment temperature through simulation software are introduced. First, there is a large gap between simulation and real scenes. Simulation software relies on many body material parameters, such as thermal conductivity, thickness, absorptivity, transmittance and reflectivity of vehicle passenger compartment components. The calculation complexity is high, and there is a large difference between the predicted passenger compartment temperature and the actual passenger compartment temperature, resulting in low accuracy of passenger compartment temperature adjustment. In addition, in related scenarios, during the automobile R&D stage, air conditioning data is very small and involves a large number of working conditions, making it difficult to model the changing law of transient passenger compartment temperature with a small amount of data.

[0091] Therefore, an embodiment of the present disclosure provides a vehicle air conditioning control method, which aims to reduce the difference between the predicted passenger compartment temperature and the actual passenger compartment temperature, thereby improving the accuracy of passenger compartment temperature adjustment.

[0092] Further, Figure 1 is a flow chart of a vehicle air conditioning control method according to an exemplary embodiment, the method is applied to a vehicle air conditioning controller or a vehicle cabin domain controller, such as Figure 1As shown, the method may include the following steps.

[0093] In step S11, the target information of the vehicle at the current moment and the setting information of each air outlet of the vehicle air conditioner are obtained.

[0094] In the disclosed embodiment, the vehicle is equipped with a vehicle air conditioner, which is usually connected to a plurality of air outlets through an air duct, for example, corresponding to the seats of the vehicle, each seat is correspondingly arranged with at least one air outlet. The air outlet can be understood as an air outlet through which the vehicle air conditioner provides cold air, warm air, or natural air to the passenger compartment.

[0095] It is understandable that each air outlet is independently equipped with an adjustment device, which can be used to adjust the air volume and air temperature of the corresponding air outlet, wherein the air volume is the size of the wind provided to the passenger compartment. For example, the adjustment device can usually be set to multiple gears, each gear corresponding to a different size of air volume, and the air temperature is the temperature of the air blown out from the air outlet. Therefore, the setting information may include adjusting the air volume and air temperature of the corresponding air outlet.

[0096] Among them, the driver and passengers can manually adjust the air volume and air temperature through the adjustment device. In the automatic mode, the car air conditioner can also automatically adjust the air volume and air temperature of each air outlet through the adjustment device.

[0097] Among them, the total air volume can be allocated according to the air conditioning blowing modes, such as blowing on the face, blowing on the feet, blowing on the window, three blowing and other air conditioning blowing modes, so that the air volume of each air outlet can be obtained.

[0098] Among them, the target information refers to the numerical value of the preset specified parameters at the current moment. For example, the preset specified parameters include ambient temperature, then the target information refers to the numerical value of the ambient temperature at the current moment. For another example, the preset specified parameters include vehicle speed, then the target information refers to the numerical value of the vehicle speed at the current moment. It can be understood that the target information can include the numerical values ​​of the preset specified parameters in multiple dimensions. For example, ambient temperature is one dimension, vehicle speed is one dimension, passenger compartment temperature is one dimension, ambient humidity is one dimension, and thermal radiation and ultraviolet rays are one dimension.

[0099] In step S12, the setting information and the target information corresponding to the current moment are input into the vehicle air-conditioning model, and the predicted passenger compartment temperature corresponding to the current moment output by the vehicle air-conditioning model is obtained.

[0100] Among them, the vehicle air-conditioning model can be constructed based on the time series residual network. The time series residual refers to the residual between the predicted passenger compartment temperature and the actual passenger compartment temperature at each moment, so that the parameters in the time series residual network can be adjusted according to the residual, that is, the model parameters of the vehicle air-conditioning model can be adjusted according to the residual.

[0101] See also Figure 2 As shown is a block diagram of the vehicle air-conditioning model in the embodiment of the present disclosure. A residual module is deployed for each air outlet in the vehicle air-conditioning model. The residual module can convert the setting information corresponding to the air outlet into a feature vector under the action of network parameters, and further combine the feature vector with the target information to obtain the predicted temperature corresponding to the air outlet, and then use the predicted temperature of each air outlet as input to the Multi-Layer Perception (MLP). The MLP fuses the predicted temperatures of multiple air outlets, and then obtains the predicted passenger compartment temperature corresponding to the current moment based on the fused temperature and target information. For example, at the Nth moment, the setting information of air outlet 1, air outlet 2 and air outlet 3 is obtained, and the setting information is converted through the network parameters of the residual module respectively to obtain the feature vector corresponding to the setting information of air outlet 1, the feature vector corresponding to the setting information of air outlet 2 and the feature vector corresponding to the setting information of air outlet 3. Then, according to the thermal radiation information corresponding to air outlet 1 and the feature vector corresponding to the setting information of air outlet 1, the predicted temperature corresponding to air outlet 1 is obtained, according to the thermal radiation information corresponding to air outlet 2 and the feature vector corresponding to the setting information of air outlet 2, the predicted temperature corresponding to air outlet 2 is obtained, according to the thermal radiation information corresponding to air outlet 3 and the feature vector corresponding to the setting information of air outlet 3, the predicted temperature corresponding to air outlet 3 is obtained, and then the predicted temperature corresponding to air outlet 1, the predicted temperature corresponding to air outlet 2 and the predicted temperature corresponding to air outlet 3 are input into the MLP, and then the predicted passenger compartment temperature at the N+1th moment is obtained according to the temperature fused by the MLP and the average of the predicted passenger compartment temperatures at the previous N moments.

[0102] Further, see Figure 3 The architecture of the time series residual network shown in the figure inputs the predicted cabin temperature of the previous N moments, the setting information of each air outlet, and the external conditions at the 0th moment, wherein the external conditions may include thermal radiation information, humidity information, temperature information, etc. After the above information passes through the residual network, the predicted cabin temperature at the 0th moment is output. Further, the predicted cabin temperature of the previous N moments, the setting information of each air outlet, and the external conditions are input at the 1st moment, wherein the predicted cabin temperature of the previous N moments here includes the predicted cabin temperature of the 0th moment, and after the above information passes through the residual network, the predicted cabin temperature of the 1st moment is output; and so on, the predicted cabin temperature of the previous N moments, the setting information of each air outlet, and the external conditions are input at the Nth moment, and similarly, the predicted cabin temperature of the previous N moments here includes the predicted cabin temperature of the N-1th moment, and after the above information passes through the residual network, the predicted cabin temperature of the Nth moment is output. Wherein, Figure 3 The residual network in is composed of Figure 3It is composed of the residual modules corresponding to each air outlet.

[0103] In the disclosed embodiment, a relatively sparse network is used to replace the fully connected network, and only the variables that generate heat exchange with each other have network connections, thereby reducing the solution space and reducing the structure and computational complexity of the vehicle air conditioning model. As a result, the vehicle air conditioning model can quickly output the predicted passenger compartment temperature corresponding to the current moment, improving the timeliness of adjusting the passenger compartment temperature.

[0104] In step S13, when the predicted passenger compartment temperature does not meet the passenger compartment temperature condition, the setting information of the air outlet of the vehicle air conditioner is adjusted and the model parameters of the vehicle air conditioner model are updated by back propagation to obtain an updated vehicle air conditioner model.

[0105] In the disclosed embodiment, the passenger compartment temperature condition may be to predict whether the passenger compartment temperature is within a preset range of a preset comfort temperature. For example, the preset comfort temperature may be 26 degrees Celsius, and the preset range is ±0.5 degrees Celsius, that is, the passenger compartment temperature condition is to predict whether the passenger compartment temperature is between 25.5 degrees Celsius and 26.5 degrees Celsius. Furthermore, in the case where the predicted passenger compartment temperature satisfies the passenger compartment temperature condition, step S11 of the present application is re-executed to directly enter the passenger compartment temperature prediction at the next moment. That is, in the case where the predicted passenger compartment temperature is between 25.5 degrees Celsius and 26.5 degrees Celsius, step S11 of the present application is re-executed to directly enter the passenger compartment temperature prediction at the next moment.

[0106] When it is predicted that the passenger compartment temperature is not between 25.5 degrees Celsius and 26.5 degrees Celsius, the setting information of the air outlet of the vehicle air conditioner is adjusted and the model parameters of the vehicle air conditioner model are updated by back propagation to obtain an updated vehicle air conditioner model.

[0107] In the disclosed embodiment, the error is obtained by calculating the difference between the predicted passenger compartment temperature and the preset comfort temperature, and then the loss is obtained according to the error. The model parameters of the vehicle air conditioning model are updated by back propagating the parameter gradient through the loss. The back propagation of the present application adopts the technical principle of the prior art without making any improvements, so it will not be described in detail. By updating the model parameters of the vehicle air conditioning model by predicting the passenger compartment temperature each time, the defects of less data and involving a large number of working conditions can be overcome in the vehicle development stage.

[0108] The above technical solution obtains the target information of the vehicle at the current moment and the setting information of each air outlet of the vehicle air conditioner; inputs the setting information and the target information corresponding to the current moment into the vehicle air conditioner model, and obtains the predicted passenger compartment temperature corresponding to the current moment output by the vehicle air conditioner model; when the predicted passenger compartment temperature does not meet the passenger compartment temperature condition, adjusts the setting information of the air outlet of the vehicle air conditioner and back-propagates and updates the model parameters of the vehicle air conditioner model, and obtains the updated vehicle air conditioner model. It can be closer to the real physical law in the process of vehicle temperature change from transient to steady state, thereby improving the accuracy of the vehicle's passenger compartment temperature adjustment.

[0109] Optionally, the model parameters include heat exchange learning parameters, heat radiation learning parameters and influence weight parameters of each of the air outlets, see Figure 4 As shown, the vehicle air conditioning model determines the predicted passenger compartment temperature in the following manner:

[0110] In step S41, the heat exchange temperature of each air outlet is determined according to the heat exchange learning parameter, the setting information of each air outlet at the current moment, and the ambient temperature, vehicle speed and historical predicted passenger compartment temperature in the target information.

[0111] Among them, heat exchange refers to the heat exchange between the passenger compartment of the vehicle and the external environment, and the heat exchange learning parameter can be understood as the model learning parameter of the vehicle air conditioning model when the passenger compartment and the external environment perform heat exchange under different external environments. For example, the first heat exchange learning parameter corresponding to the heat exchange between the front windshield of the passenger compartment and the external environment, and the second heat exchange learning parameter corresponding to the heat exchange between the right side glass of the passenger compartment and the external environment, the third heat exchange learning parameter corresponding to the heat exchange between the left side glass of the passenger compartment and the external environment, and the fourth heat exchange learning parameter corresponding to the heat exchange between the roof of the passenger compartment and the external environment.

[0112] In step S42, the thermal radiation temperature of each of the air outlets is determined according to the thermal radiation information corresponding to each of the air outlets in the target information, the thermal radiation information corresponding to the previous N moments, and the thermal radiation learning parameter.

[0113] The thermal radiation information refers to the influence of solar radiation on the temperature of the passenger compartment of the vehicle. However, the thermal radiation information received is different due to the different orientations of the air outlets to the sun and the distances from the external environment. For example, the thermal radiation information may include the thermal radiation on the left side of the vehicle and the thermal radiation on the right side of the vehicle.

[0114] Among them, thermal radiation will cause the temperature of the vehicle glass and interior lights to change. The impact of thermal radiation is not short-term, but continuous. Therefore, when calculating the thermal radiation temperature at the current moment, it is necessary to introduce the thermal radiation information corresponding to the previous N moments. This will improve the accuracy of calculating the thermal radiation temperature.

[0115] In step S43, the predicted temperature at the current moment is determined according to the influence weight parameter of each air outlet, the heat radiation temperature corresponding to the air outlet, and the heat exchange temperature.

[0116] Among them, the influence weight parameters of each air outlet are configured in the residual module of the residual network, and each air outlet can determine the influence on the temperature of the entire passenger compartment through the influence weight parameters.

[0117] In step S44, the average value of the predicted passenger compartment temperature corresponding to the previous N moments and the predicted temperature at the current moment is calculated to obtain the predicted passenger compartment temperature corresponding to the current moment.

[0118] In the disclosed embodiment, the external conditions at the current moment, the sliding average of the external conditions at the previous N moments, and the sliding average of the predicted passenger compartment temperature at the previous N moments are used as inputs to output the predicted passenger compartment temperature at the current moment. For the initial moment, only the passenger compartment temperature at the current moment and the external conditions are used as inputs. Among them, the external conditions can be understood as environmental information such as ambient temperature, ambient humidity, and thermal radiation.

[0119] In some embodiments of the present disclosure, the predicted passenger compartment temperature corresponding to the current moment may be calculated by the following formula:

[0120]

[0121] in, is the sum of the predicted cabin temperatures corresponding to the previous N moments, Y i is the predicted temperature at the current moment, Y (N+1)i is the predicted cabin temperature corresponding to the current moment.

[0122] It can be explained that in the present disclosure, back propagation updates the model parameters of the vehicle air-conditioning model, namely, updates the heat exchange learning parameters, the heat radiation learning parameters and the influence weight parameters of each air outlet.

[0123] In the presence of multiple factors, the passenger compartment temperature is not only affected by internal equipment such as the outlet position, outlet temperature and outlet air volume, but also by external conditions such as ambient temperature, thermal radiation and vehicle speed, which causes heat exchange between the air inside the passenger compartment and the external environment, thereby changing the passenger compartment temperature. Therefore, the introduction of heat exchange learning parameters and thermal radiation learning parameters can improve the accuracy of the vehicle air conditioning model in predicting the passenger compartment temperature.

[0124] Taking into account the hysteresis and persistence of some factors on the temperature of the passenger compartment, the external conditions of the previous N moments are introduced and the passenger compartment temperature is predicted through a sliding window at each moment, which is very robust to noise and avoids the accumulation of errors caused by excessive deviations in some transient predictions.

[0125] Optionally, the heat exchange learning parameters include internal heat exchange learning parameters and external heat exchange learning parameters, see Figure 5 As shown, in step S41, the heat exchange temperature of each air outlet is determined according to the heat exchange learning parameter, the setting information of each air outlet at the current moment, and the ambient temperature, vehicle speed and historical predicted passenger compartment temperature in the target information, including:

[0126] In step S411, the influence value of the activation function is determined according to the vehicle speed at the current moment and the historical vehicle speeds at N moments before the current moment.

[0127] In the embodiment of the present disclosure, the activation function is a sigmoid function, wherein the mean value v of the historical vehicle speed at the previous N moments is calculated last , add the average value v of the historical speed of the previous N moments to the current speed v last , that is, sigmoid(v+v last ).

[0128] In step S412, the internal heat exchange temperature of each of the air outlets is determined according to the setting information of each of the air outlets at the current moment, the influence value, and the historical predicted passenger compartment temperature in the target information.

[0129] The setting information may include the air volume and air temperature of the air outlet.

[0130] Among them, the average of the historical predicted passenger compartment temperatures at the previous N moments before the current moment can be obtained based on the historical predicted passenger compartment temperature in the target information. For example, when predicting the internal heat exchange temperature at the N+1th moment, the average of the historical predicted passenger compartment temperatures at the previous N moments can be calculated.

[0131] In some embodiments, the internal heat exchange temperature of each air outlet can be determined by the following formula:

[0132]

[0133] in, is the internal heat exchange temperature of the i-th air outlet at the N+1th time, T windi is the outlet temperature of the ith outlet at the Nth moment, is the average value of the historical predicted cabin temperature at the previous N moments, Tvoli is the air volume of the i-th air outlet at the N-th moment.

[0134] In step S413, the external heat exchange temperature of each of the air outlets is determined according to the setting information of each of the air outlets at the current moment, the impact value, and the ambient temperature in the target information.

[0135] In some embodiments, the internal heat exchange temperature of each air outlet can be determined by the following formula:

[0136]

[0137] in, is the external heat exchange temperature of the i-th air outlet at the N+1th time, T windi is the outlet temperature of the ith outlet at the Nth moment, T env is the ambient temperature at the N+1th moment.

[0138] In step S414, the heat exchange temperature of each of the air outlets is determined according to the internal heat exchange learning parameter, the external heat exchange learning parameter, the internal heat exchange temperature of each of the air outlets, and the external heat exchange temperature.

[0139] Optionally, in this step, determining the heat exchange temperature of each air outlet according to the internal heat exchange learning parameter, the external heat exchange learning parameter, the internal heat exchange temperature of each air outlet, and the external heat exchange temperature includes:

[0140] The product of the internal heat exchange learning parameter and the internal heat exchange temperature of each of the air outlets is calculated to obtain a first temperature parameter, and the product of the external heat exchange learning parameter and the external heat exchange temperature of each of the air outlets is calculated to obtain a second temperature parameter.

[0141] The sum of the first temperature parameter of each air outlet and the corresponding second temperature parameter is determined as the heat exchange temperature corresponding to each air outlet.

[0142] The heat exchange temperature of each air outlet is determined by the following formula:

[0143]

[0144] Among them, y i is the heat exchange temperature of the i-th air outlet, W in is the internal heat exchange learning parameter, W out Learn parameters for external heat exchange.

[0145] In order to appropriately suppress the influence of air volume and vehicle speed and prevent the vehicle air conditioning model from only learning the influence of these two factors, the square root operation and sigmoid activation function are used to model the influence of air volume and vehicle speed. In addition, in order to integrate the two features, the internal heat exchange learning parameters and the external heat exchange learning parameters are introduced to automatically learn the influence of the two types of features on the current passenger compartment temperature.

[0146] The change of passenger compartment temperature is a very complex process. At every moment, the passenger compartment will exchange heat with the outside world. For example, the vehicle speed is not fixed, but will change dynamically over time, and there will be a certain lag and continuity. For example, when the vehicle speed increases rapidly, the heat exchange with the outside world increases, but the increase will not immediately affect the vehicle temperature, but will affect the temperature change of the vehicle for several seconds or even tens of seconds. Therefore, introducing the vehicle speed of the previous N moments as an influence can improve the accuracy of the heat exchange temperature calculation.

[0147] Alternatively, see Figure 6 As shown, in step S412, the internal heat exchange temperature of each of the air outlets is determined according to the setting information of each of the air outlets at the current moment, the influence value, and the historical predicted passenger compartment temperature in the target information, including:

[0148] In step S4121, the temperature change of each air outlet is determined based on the air outlet temperature in the setting information of each air outlet at the current moment and the historical predicted passenger compartment temperature at the previous N moments in the target information.

[0149] In the disclosed embodiment, the temperature difference between the air outlet temperature in the setting information of each air outlet at the current moment and the historical predicted passenger compartment temperature at the previous N moments in the target information is calculated to determine the temperature change of each air outlet.

[0150] In step S4122, the internal heat exchange parameters of each of the air outlets are determined according to the temperature change of each of the air outlets and the air volume of the air outlet corresponding to the air outlet in the setting information.

[0151] In the disclosed embodiment, the product of the temperature change of each air outlet and the air volume of the corresponding air outlet in the setting information is calculated to obtain the internal heat exchange parameters of each air outlet.

[0152] In step S4123, the internal heat exchange temperature of each of the air outlets is determined according to the influence value and the internal heat exchange parameter of each of the air outlets.

[0153] In some embodiments of the present disclosure, the internal heat exchange temperature of each air outlet can be obtained by calculating the difference between the internal heat exchange parameter of each air outlet and the influence value.

[0154] Alternatively, see Figure 7 As shown, in step S413, determining the external heat exchange temperature of each of the air outlets according to the setting information of each of the air outlets at the current moment, the impact value and the ambient temperature in the target information includes:

[0155] In step S4131, the temperature difference of each of the air outlets is determined according to the air outlet temperature in the setting information of each of the air outlets at the current moment and the ambient temperature in the target information.

[0156] It is understandable that the temperature difference here is the temperature difference between the air outlet temperature and the ambient temperature, that is, the difference between the air outlet temperature of each air outlet and the ambient temperature in the target information is calculated to obtain the temperature difference of each air outlet.

[0157] In step S4132, the external heat exchange parameters of each of the air outlets are determined according to the temperature difference of each of the air outlets and the air volume of the air outlet corresponding to the air outlet in the setting information.

[0158] In the disclosed embodiment, the product of the temperature difference of each air outlet and the air volume of the corresponding air outlet in the setting information is calculated to obtain the external heat exchange parameters of each air outlet.

[0159] In step S4133, the external heat exchange temperature of each of the air outlets is determined according to the influence value and the external heat exchange parameters of each of the air outlets.

[0160] In some embodiments of the present disclosure, the external heat exchange temperature of each air outlet can be obtained by calculating the difference between the external heat exchange parameter of each air outlet and the influence value.

[0161] Optionally, the thermal radiation information includes thermal radiation information of multiple directions, and a thermal radiation learning parameter is correspondingly set for each direction of the vehicle in the vehicle air-conditioning model.

[0162] Since the air outlets of the vehicle are located at different positions in the vehicle, the air outlets are subject to different heat radiation in different directions. Therefore, the corresponding heat radiation learning parameters of each air outlet in the vehicle air conditioning model are different in different directions. For example, the air outlet near the right A-pillar on the co-pilot side is subject to greater environmental heat radiation from the right side of the vehicle and the front windshield, so the heat radiation information on the right and front is greater, and the corresponding heat radiation learning parameters are more affected. The environmental heat radiation from the roof is smaller, so the heat radiation information on the top is smaller, and the corresponding heat radiation learning parameters are less affected. The environmental heat radiation from the left side of the vehicle and the rear windshield can be ignored, and the heat radiation learning parameters can be configured. Similarly, the air outlet near the left A-pillar on the driver's side is subject to greater environmental heat radiation from the left side of the vehicle and the front windshield, so the heat radiation information on the left and front is larger, and the corresponding heat radiation learning parameters are more affected. The environmental heat radiation from the roof is smaller, so the heat radiation information on the top is smaller, and the corresponding heat radiation learning parameters are less affected. The environmental heat radiation from the right side of the vehicle and the rear windshield can be ignored, and the heat radiation learning parameters can be configured.

[0163] See also Figure 8 As shown, in step S42, determining the thermal radiation temperature of each air outlet according to the thermal radiation information corresponding to each air outlet in the target information, the thermal radiation information corresponding to the previous N moments, and the thermal radiation learning parameter includes:

[0164] In step S421, the cumulative radiation temperature of the direction is determined according to the thermal radiation information of the direction corresponding to each of the air outlets in the target information and the thermal radiation information of the direction corresponding to the previous N moments.

[0165] In the embodiment of the present disclosure, the mean value of the thermal radiation at each direction in the previous N moments is calculated, and then the mean value of the thermal radiation at the direction and the sum of the thermal radiation at the current moment are calculated to obtain the thermal radiation value of the direction, and then combined with the thermal radiation activation function, the thermal radiation value of the direction is substituted into the thermal radiation activation function to obtain the cumulative radiation temperature of the direction. The thermal radiation activation function can also be constructed based on sigmoid.

[0166] In step S422, the thermal radiation temperature of each of the air outlets is determined according to the cumulative radiation temperature and the thermal radiation learning parameter corresponding to the orientation.

[0167] In the disclosed embodiment, the product of the cumulative radiation temperature and the thermal radiation learning parameter corresponding to the orientation is calculated, and then the sum of the products of each orientation is calculated to obtain the thermal radiation temperature of each air outlet.

[0168] Taking the thermal radiation information from the left and right directions as an example, the cumulative thermal radiation temperature of the air outlet can be calculated using the following formula:

[0169]

[0170] Among them, y Ti is the cumulative thermal radiation temperature of the i-th air outlet, w li is the thermal radiation learning parameter on the left side of the i-th air outlet, w ri is the thermal radiation learning parameter to the right of the i-th air outlet, s li is the thermal radiation information on the left side of the i-th air outlet at the current moment, s ri is the thermal radiation information on the right side of the i-th air outlet at the current moment, is the average value of the thermal radiation on the left side of the i-th air outlet N moments before, is the average value of the thermal radiation on the right side of the i-th air outlet N moments before.

[0171] Here, the thermal radiation learning parameters in the left and right directions are used as an example for explanation. In specific implementation, the thermal radiation temperature of each air outlet can also be obtained based on the thermal radiation learning parameters in the front, rear, left, right and top directions.

[0172] Alternatively, see Fig. 9 As shown, in step S43, the predicted temperature at the current moment is determined according to the influence weight parameter of each air outlet, the heat radiation temperature corresponding to the air outlet, and the heat exchange temperature, including:

[0173] In step S431, the thermal parameter temperature of each of the air outlets is determined according to the heat radiation temperature and the heat exchange temperature of each of the air outlets.

[0174] In the disclosed embodiment, the sum of the heat radiation temperature of the air outlet and the heat exchange temperature of the corresponding air outlet is calculated to obtain the thermal parameter temperature of the air outlet.

[0175] In step S432, the predicted temperature at the current moment is determined according to the thermal parameter temperature of each of the air outlets and the influence weight parameter corresponding to the air outlet.

[0176] In some embodiments of the present disclosure, the predicted temperature at the current moment may be calculated by the following formula:

[0177]

[0178] Among them, Y i is the predicted temperature at the current moment, w i is the influence weight parameter of the i-th air outlet, y i is the thermal parameter temperature of the i-th air outlet, and k is the total number of air outlets of the vehicle.

[0179] The present disclosure establishes a vehicle air conditioning model, and can adjust the temperature of the passenger compartment from transient to steady state according to the change of the temperature of the passenger compartment with time and external conditions and other factors, and fit the relationship between various factors and the temperature of the passenger compartment through network parameters, so as to approach the real physical law. In addition, only a small amount of training data is needed to be applied to most working conditions, and can be applied to aspects such as passenger compartment temperature field estimation, energy consumption estimation, and system-side control design, which has guiding significance for the design of automobile air conditioning. It can avoid the problem that in the relevant scenarios, during the research and development stage of automobile air conditioning, it is necessary to repeatedly test on the car to verify whether the effect of the entire link from the system end to the passenger compartment meets the expectations, and each item needs to be repeatedly tested on the car, which is time-consuming and labor-intensive. Greatly reduce the cost of research and development and improve efficiency. For example: According to the model, the temperature of each position in the passenger compartment can be calculated. If the difference between the main and co-driver or the front and rear rows is too large, it means that there is a problem with the system strategy of a certain air outlet, and the problem can be quickly located and repaired. It can also solve the overshoot problem in heating / cooling.

[0180] The present disclosure also provides a vehicle air conditioning control device. Fig.10 As shown, including:

[0181] The acquisition module 110 is configured to acquire the target information of the vehicle at the current moment and the setting information of each air outlet of the vehicle air conditioner;

[0182] The input module 120 is configured to input the setting information and the target information corresponding to the current moment into the vehicle air conditioning model, and obtain the predicted passenger compartment temperature corresponding to the current moment output by the vehicle air conditioning model;

[0183] The adjustment and update module 130 is configured to adjust the setting information of the air outlet of the vehicle air conditioner and back-propagate to update the model parameters of the vehicle air conditioner model when the predicted passenger compartment temperature does not meet the passenger compartment temperature condition, so as to obtain an updated vehicle air conditioner model.

[0184] Optionally, the model parameters include heat exchange learning parameters, heat radiation learning parameters and influence weight parameters of each of the air outlets, and the input module 120 is configured to enable the vehicle air conditioning model to determine the predicted passenger compartment temperature in the following manner:

[0185] Determining the heat exchange temperature of each of the air outlets according to the heat exchange learning parameter, the setting information of each of the air outlets at the current moment, and the ambient temperature, vehicle speed, and historical predicted passenger compartment temperature in the target information;

[0186] Determine the thermal radiation temperature of each of the air outlets according to the thermal radiation information corresponding to each of the air outlets in the target information, the thermal radiation information corresponding to the previous N moments, and the thermal radiation learning parameter;

[0187] Determining the predicted temperature at the current moment according to the influence weight parameter of each air outlet, the heat radiation temperature corresponding to the air outlet, and the heat exchange temperature;

[0188] The predicted passenger compartment temperature corresponding to the previous N moments and the average value of the predicted temperature at the current moment are calculated to obtain the predicted passenger compartment temperature corresponding to the current moment.

[0189] Optionally, the heat exchange learning parameters include internal heat exchange learning parameters and external heat exchange learning parameters, and the input module 120 is configured to enable the vehicle air conditioning model to determine the heat exchange temperature in the following manner, including:

[0190] Determine the influence value of the activation function according to the vehicle speed at the current moment and the historical vehicle speeds at N moments before the current moment;

[0191] Determining the internal heat exchange temperature of each of the air outlets according to the setting information of each of the air outlets at the current moment, the influence value, and the historical predicted passenger compartment temperature in the target information;

[0192] Determine the external heat exchange temperature of each of the air outlets according to the setting information of each of the air outlets at the current moment, the impact value and the ambient temperature in the target information;

[0193] The heat exchange temperature of each of the air outlets is determined according to the internal heat exchange learning parameter, the external heat exchange learning parameter, the internal heat exchange temperature of each of the air outlets, and the external heat exchange temperature.

[0194] Optionally, the input module 120 is configured to enable the vehicle air conditioning model to determine the internal heat exchange temperature in the following manner, including:

[0195] Determine the temperature change of each of the air outlets according to the air outlet temperature in the setting information of each of the air outlets at the current moment and the historical predicted passenger compartment temperature at the previous N moments in the target information;

[0196] Determining the internal heat exchange parameters of each of the air outlets according to the temperature change of each of the air outlets and the air volume of the air outlet corresponding to the air outlet in the setting information;

[0197] The internal heat exchange temperature of each air outlet is determined according to the influence value and the internal heat exchange parameter of each air outlet.

[0198] Optionally, the input module 120 is configured to enable the vehicle air conditioning model to determine the external heat exchange temperature in the following manner, including:

[0199] Determine the temperature difference of each of the air outlets according to the air outlet temperature in the setting information of each of the air outlets at the current moment and the ambient temperature in the target information;

[0200] Determining the external heat exchange parameters of each of the air outlets according to the temperature difference of each of the air outlets and the air volume of the air outlet corresponding to the air outlet in the setting information;

[0201] The external heat exchange temperature of each air outlet is determined according to the influence value and the external heat exchange parameter of each air outlet.

[0202] Optionally, the input module 120 is configured to enable the vehicle air conditioning model to determine the heat exchange temperature in the following manner, including:

[0203] Calculating the product of the internal heat exchange learning parameter and the internal heat exchange temperature of each of the air outlets to obtain a first temperature parameter, and calculating the product of the external heat exchange learning parameter and the external heat exchange temperature of each of the air outlets to obtain a second temperature parameter;

[0204] The sum of the first temperature parameter of each air outlet and the corresponding second temperature parameter is determined as the heat exchange temperature corresponding to each air outlet.

[0205] Optionally, the thermal radiation information includes thermal radiation information of multiple directions, and each direction of the vehicle is correspondingly provided with a thermal radiation learning parameter in the vehicle air conditioning model;

[0206] The input module 120 is configured to enable the vehicle air conditioning model to determine the heat radiation temperature in the following manner, including:

[0207] Determine the cumulative radiation temperature of the position according to the thermal radiation information of the position corresponding to each of the air outlets in the target information and the thermal radiation information of the position corresponding to the previous N moments;

[0208] The thermal radiation temperature of each of the air outlets is determined according to the cumulative radiation temperature and the thermal radiation learning parameter corresponding to the orientation.

[0209] Optionally, the input module 120 is configured to enable the vehicle air conditioning model to determine the predicted temperature in the following manner, including:

[0210] Determining the thermal parameter temperature of each of the air outlets according to the heat radiation temperature and the heat exchange temperature of each of the air outlets;

[0211] The predicted temperature of each air outlet is determined according to the thermal parameter temperature of each air outlet and the influence weight parameter corresponding to the air outlet.

[0212] Regarding the 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.

[0213] The present disclosure also provides a vehicle, including:

[0214] processor;

[0215] a memory for storing processor-executable instructions;

[0216] The processor is configured to execute the executable instructions stored in the memory to implement the method described in any one of the aforementioned embodiments.

[0217] The embodiments of the present disclosure further provide a computer-readable storage medium having computer program instructions stored thereon, which implement the steps of the method described in any one of the aforementioned embodiments when the program instructions are executed by a processor.

[0218] Fig.11 6 is a block diagram of a vehicle 600 according to an exemplary embodiment. For example, the vehicle 600 may be a hybrid vehicle, a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other types of vehicles. The vehicle 600 may be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

[0219] Reference Fig.11 , the vehicle 600 may include various subsystems, such as an infotainment system 610, a perception system 620, a decision control system 630, a drive system 640, and a computing platform 650. Among them, the vehicle 600 may also include more or fewer subsystems, such as a vehicle air conditioner, and each subsystem may include multiple components. For example, a vehicle air conditioner may include an operation panel, multiple air outlets, a condenser, a compressor, an evaporator, and pipes and circuits connecting the various components. In addition, each subsystem and each component of the vehicle 600 can be interconnected by wire or wireless means.

[0220] In some embodiments, the infotainment system 610 may include a communication system, an entertainment system, and a navigation system, among others.

[0221] The perception system 620 may include several sensors for sensing information about the environment around the vehicle 600. For example, the perception system 620 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.

[0222] The decision control system 630 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0223] The drive system 640 may include components that provide powered motion for the vehicle 600. In one embodiment, the drive system 640 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.

[0224] Some or all functions of the vehicle 600 are controlled by a computing platform 650. The computing platform 650 may include at least one processor 651 and a memory 652, and the processor 651 may execute instructions 653 stored in the memory 652.

[0225] The processor 651 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.

[0226] The memory 652 may be implemented by any type of volatile or nonvolatile 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.

[0227] In addition to the instructions 653 , the memory 652 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 memory 652 may be used by the computing platform 650 .

[0228] In the embodiment of the present disclosure, the processor 651 can execute instruction 653 to complete all or part of the steps of the above-mentioned vehicle air conditioning control method.

[0229] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the present disclosure. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification 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.

[0230] 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. A vehicle air conditioning control method, characterized in that: include: Obtain the target information of the vehicle at the current moment and the setting information of each air outlet of the vehicle air conditioner; Inputting the setting information and the target information corresponding to the current moment into the vehicle air conditioning model, and obtaining the predicted passenger compartment temperature corresponding to the current moment output by the vehicle air conditioning model; When the predicted passenger compartment temperature does not meet the passenger compartment temperature condition, the setting information of the air outlet of the vehicle air conditioner is adjusted and the model parameters of the vehicle air conditioner model are updated by back propagation to obtain an updated vehicle air conditioner model.

2. The method according to claim 1, characterized in that The model parameters include heat exchange learning parameters, heat radiation learning parameters and influence weight parameters of each of the air outlets. The vehicle air conditioning model determines the predicted passenger compartment temperature in the following manner: Determining the heat exchange temperature of each of the air outlets according to the heat exchange learning parameter, the setting information of each of the air outlets at the current moment, and the ambient temperature, vehicle speed, and historical predicted passenger compartment temperature in the target information; Determine the thermal radiation temperature of each of the air outlets according to the thermal radiation information corresponding to each of the air outlets in the target information, the thermal radiation information corresponding to the previous N moments, and the thermal radiation learning parameter; Determining the predicted temperature at the current moment according to the influence weight parameter of each air outlet, the heat radiation temperature corresponding to the air outlet, and the heat exchange temperature; The predicted passenger compartment temperature corresponding to the previous N moments and the average value of the predicted temperature at the current moment are calculated to obtain the predicted passenger compartment temperature corresponding to the current moment.

3. The method according to claim 2, characterized in that The heat exchange learning parameters include an internal heat exchange learning parameter and an external heat exchange learning parameter, and determining the heat exchange temperature of each of the air outlets according to the heat exchange learning parameters, setting information of each of the air outlets at a current moment, and the ambient temperature, vehicle speed, and historical predicted passenger compartment temperature in the target information includes: Determine the influence value of the activation function according to the vehicle speed at the current moment and the historical vehicle speeds at N moments before the current moment; Determining the internal heat exchange temperature of each of the air outlets according to the setting information of each of the air outlets at the current moment, the influence value, and the historical predicted passenger compartment temperature in the target information; Determine the external heat exchange temperature of each of the air outlets according to the setting information of each of the air outlets at the current moment, the impact value and the ambient temperature in the target information; The heat exchange temperature of each of the air outlets is determined according to the internal heat exchange learning parameter, the external heat exchange learning parameter, the internal heat exchange temperature of each of the air outlets, and the external heat exchange temperature.

4. The method according to claim 3, characterized in that The determining the internal heat exchange temperature of each of the air outlets according to the setting information of each of the air outlets at the current moment, the influence value, and the historical predicted passenger compartment temperature in the target information includes: Determine the temperature change of each of the air outlets according to the air outlet temperature in the setting information of each of the air outlets at the current moment and the historical predicted passenger compartment temperature at the previous N moments in the target information; Determining the internal heat exchange parameters of each of the air outlets according to the temperature change of each of the air outlets and the air volume of the air outlet corresponding to the air outlet in the setting information; The internal heat exchange temperature of each air outlet is determined according to the influence value and the internal heat exchange parameter of each air outlet.

5. The method according to claim 3, characterized in that: The step of determining the external heat exchange temperature of each of the air outlets according to the setting information of each of the air outlets at the current moment, the impact value, and the ambient temperature in the target information includes: Determine the temperature difference of each of the air outlets according to the air outlet temperature in the setting information of each of the air outlets at the current moment and the ambient temperature in the target information; Determining the external heat exchange parameters of each of the air outlets according to the temperature difference of each of the air outlets and the air volume of the air outlet corresponding to the air outlet in the setting information; The external heat exchange temperature of each air outlet is determined according to the influence value and the external heat exchange parameter of each air outlet.

6. The method according to claim 3, characterized in that The step of determining the heat exchange temperature of each air outlet according to the internal heat exchange learning parameter, the external heat exchange learning parameter, the internal heat exchange temperature of each air outlet, and the external heat exchange temperature of each air outlet comprises: Calculating the product of the internal heat exchange learning parameter and the internal heat exchange temperature of each of the air outlets to obtain a first temperature parameter, and calculating the product of the external heat exchange learning parameter and the external heat exchange temperature of each of the air outlets to obtain a second temperature parameter; The sum of the first temperature parameter of each air outlet and the corresponding second temperature parameter is determined as the heat exchange temperature corresponding to each air outlet.

7. The method according to claim 2, characterized in that The thermal radiation information includes thermal radiation information of multiple directions, and each direction of the vehicle is correspondingly provided with a thermal radiation learning parameter in the vehicle air conditioning model; The determining the thermal radiation temperature of each of the air outlets according to the thermal radiation information corresponding to each of the air outlets in the target information, the thermal radiation information corresponding to the previous N moments, and the thermal radiation learning parameter includes: Determine the cumulative radiation temperature of the position according to the thermal radiation information of the position corresponding to each of the air outlets in the target information and the thermal radiation information of the position corresponding to the previous N moments; The thermal radiation temperature of each of the air outlets is determined according to the cumulative radiation temperature and the thermal radiation learning parameter corresponding to the orientation.

8. The method according to any one of claims 2 to 7, characterized in that: The step of determining the predicted temperature at the current moment according to the influence weight parameter of each air outlet, the heat radiation temperature corresponding to the air outlet, and the heat exchange temperature includes: Determining the thermal parameter temperature of each of the air outlets according to the heat radiation temperature and the heat exchange temperature of each of the air outlets; The predicted temperature of each air outlet is determined according to the thermal parameter temperature of each air outlet and the influence weight parameter corresponding to the air outlet.

9. A vehicle air conditioning control device, characterized in that: include: An acquisition module is configured to acquire target information of the vehicle at a current moment and setting information of each air outlet of the vehicle air conditioner; an input module configured to input the setting information and the target information corresponding to the current moment into the vehicle air conditioning model, and obtain a predicted passenger compartment temperature corresponding to the current moment output by the vehicle air conditioning model; The adjustment and update module is configured to adjust the setting information of the air outlet of the vehicle air conditioner and back-propagate to update the model parameters of the vehicle air conditioner model when the predicted passenger compartment temperature does not meet the passenger compartment temperature condition, so as to obtain an updated vehicle air conditioner model.

10. A vehicle, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to execute the executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.

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 8 are implemented.

Images