Air conditioning control method, device, vehicle and storage medium for pure electric vehicle

Abstract

The present application relates to the field of automobile air-conditioning control technology, and in particular to an air-conditioning control method, device, vehicle and storage medium for a pure electric vehicle. The method includes obtaining, in response to an automatic temperature adjustment mode of the vehicle air-conditioning system, information about the occupants in the vehicle's passenger compartment, information about the vehicle's vehicle body status and the air-conditioning setting temperature, etc., and determining a first heat load for heat exchange between the vehicle's passenger compartment and the outside environment based on vehicle speed information, external ambient temperature, passenger compartment temperature and vehicle body status information; determining a second heat load for heat absorption in the vehicle's passenger compartment based on vehicle paint information, light intensity and light projection area; determining a third heat load for heat generation in the vehicle's passenger compartment based on information about the occupants in the passenger compartment; and determining an electronic expansion valve opening signal and a compressor speed signal for controlling the temperature of the air-conditioning system in the passenger compartment based on the first heat load, the second heat load and the third heat load and based on a target neural network model. The method improves prediction accuracy and reduces energy consumption of the air-conditioning system.

Description

Technical Field

[0001] The present application relates to the technical field of automobile air-conditioning control, and in particular to an air-conditioning control method, device, vehicle and storage medium for a pure electric vehicle. Background Art

[0002] In the development of pure electric vehicles, the energy density of power batteries limits their range, which has always been a difficult problem that the industry urgently needs to solve. At present, the industry is using various innovative methods to improve the range of electric vehicles. For example, energy consumption control of air-conditioning systems has become an important research focus.

[0003] In related technologies, there is a method that processes information on environmental parameters inside and outside the vehicle (such as the vehicle's current location temperature, light intensity, and vehicle speed) to generate control information for adaptively adjusting the temperature of the vehicle's air conditioning. This method reduces the energy consumption of the air-conditioning system to a certain extent. However, some factors that have a greater impact on the temperature inside the vehicle are not taken into account, such as the opening and closing of windows, resulting in the subsequent prediction results having room for improvement in reducing the energy consumption of the air-conditioning system. At the same time, the PID independent control method used to generate feedback control signals for adjusting the temperature of the vehicle's air-conditioning system has a slower control rate and worse prediction accuracy. Summary of the Invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes an air conditioning control method, device, vehicle and storage medium for a pure electric vehicle.

[0005] In a first aspect, an embodiment of the present application provides an air conditioning control method for a pure electric vehicle, comprising:

[0006] In response to an automatic temperature adjustment mode of the air conditioning system of the target vehicle, obtaining current passenger compartment occupant information, vehicle speed information, vehicle body status information, vehicle paint information, light intensity, light projection area, external ambient temperature, passenger compartment temperature, and air conditioning setting temperature of the target vehicle;

[0007] determining a first heat load of heat exchange between the passenger compartment of the target vehicle and the external environment based on the vehicle speed information, the external environment temperature, the passenger compartment temperature, and the vehicle body state information;

[0008] determining a second heat load absorbed by a passenger compartment of the target vehicle based on the vehicle paint information, the light intensity, and the light projection area;

[0009] determining a third heat load generated by heat in the passenger compartment of the target vehicle based on the passenger compartment occupant information;

[0010] An electronic expansion valve opening signal and a compressor speed signal for controlling the temperature of the air conditioning system in the passenger compartment are determined according to the air conditioning set temperature, the first heat load, the second heat load, and the third heat load and based on a preset target CNN-GRU neural network model.

[0011] In some possible implementation examples, determining a first heat load of heat exchange between the passenger compartment of the target vehicle and the external environment based on the vehicle speed information, the external environment temperature, the passenger compartment temperature, and the vehicle body state information includes:

[0012] determining whether the vehicle speed information is zero;

[0013] If yes, determine the lifting and lowering opening information of each window and the opening and closing angle information of each door of the target vehicle according to the vehicle body state information;

[0014] If not, determining the airflow impact factor corresponding to the lift opening information of each window of the target vehicle and the current vehicle speed information;

[0015] Determining the effective area of ​​heat exchange between the current windows and doors of the target vehicle based on the lifting opening information and the opening and closing angle information;

[0016] A first heat load of heat exchange between the passenger compartment in the target vehicle and the external environment is determined based on the effective area, the external environment temperature, the passenger compartment temperature, and the airflow influencing factor.

[0017] In some possible implementation examples, determining a first heat load of heat exchange between the passenger compartment of the target vehicle and the external environment based on the effective area, the external environment temperature, the passenger compartment temperature, and the airflow influencing factor includes:

[0018] The calculation expression of the first heat load is:

[0019]

[0020] Where, and They represent the start and close time of the door opening, h represents the heat exchange coefficient, Indicates the effective area corresponding to the door opening and closing angle, and Respectively represent the start time and closing time of the window opening, Indicates the effective area corresponding to the window opening, Indicates the external ambient temperature, Indicates the passenger compartment temperature, represents the time step, Indicates the airflow impact factor.

[0021] In some possible implementation examples, determining the second heat load absorbed by the passenger compartment of the target vehicle based on the vehicle paint information, the light intensity, and the light projection area includes:

[0022] Determine the corresponding average RGB value according to the vehicle paint information;

[0023] The corresponding light absorption rate is determined according to the average RGB value and based on a preset light absorption linear regression model, wherein the light absorption linear regression model expression is:

[0024]

[0025] Where, represents the light absorption rate, 、 as well as Respectively represent the weight coefficient of each color component to the light absorption rate, 、 and Represent the red, green and blue components respectively, represents the bias term;

[0026] A second heat load absorbed by a passenger compartment of the target vehicle is determined according to the light absorption rate, the light intensity, and the light projection area.

[0027] In some possible implementation examples, determining the second heat load absorbed by the passenger compartment of the target vehicle according to the light absorption rate, the light intensity, and the light projection area includes:

[0028] The calculation expression of the second heat load is:

[0029]

[0030] Where, and They represent the start and end time of the vehicle body being illuminated. Indicates the light intensity outside the target vehicle, represents the vehicle body light projection area, represents the light absorption rate corresponding to the target vehicle paint, Indicates the time step.

[0031] In some possible implementation examples, in the step of determining the electronic expansion valve opening signal and the compressor speed signal for controlling the temperature of the air conditioning system in the passenger compartment based on the air conditioning set temperature, the first heat load, the second heat load, and the third heat load and based on a preset target CNN-GRU neural network model, creating the target CNN-GRU neural network model includes:

[0032] Obtaining an initial data sample of historical thermal load corresponding to a target vehicle model, and performing preprocessing and normalization on the initial data sample to obtain a target data sample;

[0033] Segmenting the target data sample based on a preset time window to obtain a sample subset, and dividing the sample subset into a training set and a validation set;

[0034] Creating an initial CNN-GRU neural network model, inputting the training set into the initial CNN-GRU neural network model, and outputting a predicted value;

[0035] The difference between the predicted value and the true value is determined based on a preset target loss function, and the trained initial CNN-GRU neural network model is verified based on the verification set to obtain the target CNN-GRU neural network model.

[0036] In some possible implementation examples, the creating an initial CNN-GRU neural network model, inputting the training set into the initial CNN-GRU neural network model, and outputting a predicted value includes:

[0037] The initial CNN-GRU neural network model includes a convolutional neural network module and a gated recurrent neural network module, wherein the convolutional neural network module includes at least two convolutional layers, a pooling layer, and a flattening layer for feature extraction and dimensionality reduction;

[0038] The gated recurrent neural network module includes at least one GRU layer, one dropout layer, and one fully connected layer for time series prediction and output;

[0039] In the convolutional neural network module, the two convolution layers include a first one-dimensional convolution layer and a second one-dimensional convolution layer, the first one-dimensional convolution layer includes 32 convolution kernels with a convolution kernel size of 3, the second one-dimensional convolution layer includes 62 convolution kernels with a convolution kernel size of 3, and the activation functions of the first one-dimensional convolution layer and the second one-dimensional convolution layer adopt the ReLU function;

[0040] The pooling layer is used to extract important features and suppress noise signals;

[0041] The flattening layer is used to process the data processed by the convolutional neural network module into a single dimension, so as to facilitate a smooth transition from the convolutional neural network module to the gated recurrent neural network module;

[0042] In the gated recurrent neural network module, based on the information passed from the previous moment Input information at the current moment A reset gate and an update gate are set, wherein the gated recurrent neural network module satisfies the following formula:

[0043]

[0044]

[0045]

[0046]

[0047] Where, To update the gate, To reset the gate, For candidate information, To transmit information to the next moment, is the sigmoid function, is the tanh function, 、 as well as They are the update gate, reset gate and weight matrix of candidate information respectively.

[0048] In a second aspect, an embodiment of the present application provides an air conditioning control device for a pure electric vehicle, comprising:

[0049] an acquisition module configured to acquire, in response to an automatic temperature adjustment mode of an air conditioning system of a target vehicle, current passenger compartment occupant information, vehicle speed information, vehicle body status information, vehicle paint information, light intensity, light projection area, external ambient temperature, passenger compartment temperature, and air conditioning set temperature of the target vehicle;

[0050] a first heat load determination module configured to determine a first heat load of heat exchange between the passenger compartment of the target vehicle and the external environment based on the vehicle speed information, the external environment temperature, the passenger compartment temperature, and the vehicle body state information;

[0051] a second heat load determination module configured to determine a second heat load absorbed by a passenger compartment of the target vehicle based on the vehicle paint information, the light intensity, and the light projection area;

[0052] a third heat load determination module configured to determine a third heat load generated by heat in the passenger compartment of the target vehicle based on the passenger compartment occupant information;

[0053] The data processing module is configured to determine an electronic expansion valve opening signal and a compressor speed signal for controlling the temperature of the air conditioning system in the passenger compartment based on the air conditioning set temperature, the first heat load, the second heat load, and the third heat load and based on a preset target CNN-GRU neural network model.

[0054] In a third aspect, an embodiment of the present application provides a vehicle, comprising:

[0055] processor;

[0056] a memory for storing instructions executable by the processor;

[0057] Wherein, the processor is configured to:

[0058] Implement the steps of the air conditioning control method for a pure electric vehicle described in any one of the embodiments of the first aspect above.

[0059] In a fourth aspect, an embodiment of the present application provides 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 a method for controlling the air conditioning of a pure electric vehicle described in any one of the embodiments of the first aspect are implemented.

[0060] Compared with the prior art, the technical solutions provided by the above embodiments of the present application have at least the following beneficial effects:

[0061] The air-conditioning control method of the pure electric vehicle of the present application responds to the automatic temperature adjustment mode of the target vehicle. By obtaining the current passenger cabin occupant information, vehicle speed information, vehicle body status information, vehicle paint information, light intensity, light projection area, external ambient temperature, passenger cabin temperature and air-conditioning setting temperature, when determining that the heat generated by external light on the target vehicle causes the temperature change in the passenger cabin, the light absorption linear regression model created fully considers the influence of the paint color on the light absorption rate, and can more accurately determine the temperature change in the passenger cabin caused by external light. By considering the window opening degree of the target vehicle and the influence of gas flow caused by different vehicle speeds on heat exchange when driving, and considering the possible influence of door opening when not driving, , thereby more accurately determining the temperature changes in the passenger compartment caused by heat exchange, and considering the occupant information and the temperature changes caused by different numbers of people in the passenger compartment. Finally, combined with the target CNN-GRU neural network model, a more accurate heat load input target CNN-GRU neural network model is obtained for prediction to output the electronic expansion valve opening signal and compressor speed signal used to control the temperature of the air-conditioning system in the passenger compartment, thereby realizing the precise temperature adjustment of the air-conditioning system in the passenger compartment, fully considering various influencing factors, improving the control accuracy and further reducing the energy consumption of the air-conditioning system. At the same time, the created target CNN-GRU neural network model has high calculation efficiency for time series data, making the prediction accuracy higher and generating feedback signals faster.

[0062] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0064] Figure 1 is a flow chart of an air conditioning control method for a pure electric vehicle provided in an embodiment of the present application;

[0065] Figure 2 1 is a training loss curve diagram of the iterative training process of the CNN-GRU neural network model provided in an embodiment of the present application;

[0066] Figure 3 is a comparison curve diagram of the predicted value and the actual value of the opening degree of the electronic expansion valve of the passenger compartment air conditioner provided in an embodiment of the present application;

[0067] Figure 4is a comparison curve diagram of the predicted value and the actual value of the compressor speed provided in an embodiment of the present application;

[0068] Figure 5 is a comparison chart of compressor control results obtained by the conventional method provided in the embodiment of the present application and the method of the present application;

[0069] Figure 6 is a block diagram of an air conditioning control device for a pure electric vehicle provided in accordance with an embodiment of the present application;

[0070] Figure 7 It is a block diagram of a vehicle provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0071] The embodiments of the present application are described in detail below. The embodiments described with reference to the accompanying drawings are exemplary. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0072] It should be noted that, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" as used herein includes any and all combinations of one or more of the relevant listed items.

[0073] See also Figure 1 This embodiment provides an air conditioning control method for a pure electric vehicle, including:

[0074] Step S100: In response to the automatic temperature adjustment mode of the air conditioning system of the target vehicle, obtaining the current passenger compartment occupant information, vehicle speed information, vehicle body status information, vehicle paint information, light intensity, light projection area, external ambient temperature, passenger compartment temperature, and air conditioning set temperature of the target vehicle;

[0075] In this step, it should be noted that the automatic temperature control mode can be a pre-set mode, and the automatic temperature control mode can be manually turned on by the people in the car or turned on by voice. The automatic temperature control mode can set the initial temperature before the vehicle goes online, and a window interface is reserved for the user to customize the temperature of the automatic temperature control mode when the user uses the target vehicle. For example, when the initial setting temperature of the automatic temperature control mode of the air-conditioning system of the target vehicle is 28°C, when driving in winter, the user can reset it to a higher temperature, such as heating 31°C, or when driving in hotter summer, the user needs a lower temperature, the user can reset it to a lower temperature, such as cooling 20°C, and then adaptively control through the method of this embodiment to maintain the set temperature.

[0076] Of course, in one example, the automatic temperature control mode can also respond adaptively. In the summer, when the user just enters the passenger compartment, the user will set the air-conditioning system to a lower temperature, such as 16°C. After rapid cooling, the temperature sensor in the passenger compartment, such as the temperature sensor installed on the seat, detects that the temperature in the car has dropped to equal to or lower than the average body temperature of a normal person, triggering the response of the automatic temperature control mode, and then prompting the user through the in-car entertainment system. At this time, the user can selectively turn it off according to needs.

[0077] Optionally, the method of this embodiment is mainly used for pure electric vehicles to reduce the vehicle's power consumption. Of course, in some cases, the method can also be used for hybrid vehicles or other models. The method of this embodiment can also be implemented by making reasonable arrangements according to different models. This implementation takes pure electric vehicles as an example, and the implementation of other models will not be elaborated here.

[0078] In some embodiments, the current passenger compartment occupant information of the target vehicle can be detected by in-vehicle sensors (such as infrared sensors, pressure sensors, or seat sensors) to detect the occupant status of each seat, including the number of people, position, body temperature, etc. In this step, the passenger compartment occupant information mainly collects the number of people. The vehicle speed information can be obtained by obtaining real-time vehicle speed data through an on-board speed sensor (such as a GPS system or a vehicle speedometer). The paint information can be set at the factory. In some cases, the user may change the car cover on their own, resulting in a change in color. In this case, the paint color and reflection information of the vehicle surface can be obtained through a color temperature sensor or color detection sensor on the outside of the vehicle. The light intensity and light projection area can be tested under CLTC-P conditions on a four-wheel drive chassis dynamometer system with environmental simulation, and relevant data can be collected at the same time. The environmental simulation system has a sunlight simulation system, which reads the external light intensity through the built-in light sensor of the vehicle, identifies the light projection area through the vehicle digital simulation, and can use a light sensor (usually an on-board light intensity sensor) to detect the external light intensity.

[0079] Optionally, the vehicle body status information mainly includes the window lifting and opening information and the door opening and closing angle information, which can be collected through position sensors and angle sensors. The external temperature sensor on the vehicle (such as a temperature probe or a meteorological sensor) can obtain the real-time temperature outside the vehicle, and the passenger compartment temperature can be monitored by the interior temperature sensor (such as a temperature probe or a sensor array). The air-conditioning setting temperature can be directly collected through the set value.

[0080] Step S200: determining a first heat load of heat exchange between the passenger compartment of the target vehicle and the external environment based on the vehicle speed information, the external environment temperature, the passenger compartment temperature, and the vehicle body state information;

[0081] In some embodiments, the first heat load refers to the heat generated by direct heat exchange between the passenger compartment of the target vehicle and the external environment. For this part of the heat, this step mainly considers that in some cases, the user will open the window or door on his own, resulting in direct heat exchange between the passenger compartment and the external environment. For example, while the target vehicle is driving, the user may open the window for some reason, and the degree of opening of the window may also be different. At the same time, when the target vehicle is stopped, the user may open the door for some reason, and the degree of opening of the door may also be different. Heat exchange will occur in these cases, which will have a greater impact on the temperature inside the vehicle. Therefore, considering these influencing factors can not only achieve adaptive adjustment to improve the control accuracy of the air conditioner, but also further reduce the energy consumption of the air conditioning system.

[0082] Optionally, determine whether the vehicle speed information is zero; if so, determine the lifting and opening information of each window and the opening and closing angle information of each door of the target vehicle based on the vehicle body status information; if not, determine the lifting and opening information of each window of the target vehicle and the airflow influencing factor corresponding to the current vehicle speed information; based on the lifting and opening information and the opening and closing angle information, the effective area of ​​heat exchange of the current windows and doors of the target vehicle; based on the effective area, the external ambient temperature, the passenger compartment temperature and the airflow influencing factor, determine the first heat load of the heat exchange between the passenger compartment inside the target vehicle and the external environment.

[0083] Of course, it should be noted that since the car door cannot be opened when the vehicle speed is not zero, the car door can only be opened when the vehicle speed is zero. When the car window is opened, the outside air enters through the car window, and the air inside the car will flow out of the car window. The higher the speed, the faster the external airflow, resulting in more intense air flow between the inside of the car and the outside world. This fast-flowing air increases the heat exchange efficiency. Based on this, the influence of vehicle speed needs to be considered.

[0084] It can be understood that, for the effective area of ​​heat exchange of the current windows and doors of the target vehicle based on the lifting opening information and the opening and closing angle information, the data can be converted through a linear relationship established in advance, and the specific selective settings can be made according to different vehicle models. The opening and closing angle information is converted into the effective area of ​​heat exchange of the door. The corresponding effective area of ​​heat exchange at different angles of the door opening can be determined through experiments, thereby obtaining the corresponding linear relationship and correlation coefficient. The current window lifting opening of the target vehicle and the corresponding effective area of ​​heat exchange can also be determined by this method.

[0085] Similarly, for different vehicle speeds, preliminary simulation experiments can be conducted to determine the impact of different vehicle speeds on the air flow between the vehicle interior and the outside world, thereby determining the relevant airflow influence factors. For example, when the vehicle speed is 40 km / h, 80 km / h or 100 km / h, the airflow influence factor can be 0.4, 0.45 or 0.5. The specific airflow influence factor can be obtained based on actual conditions and is not limited here.

[0086] Optionally, the calculation expression of the first heat load is:

[0087]

[0088] Where, and They represent the start and close time of the door opening, h represents the heat exchange coefficient, Indicates the effective area corresponding to the door opening and closing angle, and Respectively represent the start time and closing time of the window opening, Indicates the effective area corresponding to the window opening, Indicates the external ambient temperature, Indicates the passenger compartment temperature, represents the time step, Indicates the airflow impact factor.

[0089] Step S300: determining a second heat load absorbed by a passenger compartment of the target vehicle based on the vehicle paint information, the light intensity, and the light projection area;

[0090] In this step, unlike the traditional method, since it is found in actual applications that different colors of car paint have a great influence on the absorption rate of light, this step takes into account the color of the car paint to further improve the actual situation of the heat absorption process, thereby obtaining a more accurate heat load.

[0091] In some embodiments, for vehicle paint information, the corresponding average RGB value is determined based on the vehicle paint information; the corresponding light absorption rate is determined based on the average RGB value and based on a preset light absorption linear regression model; and the second heat load of heat absorption in the passenger compartment of the target vehicle is determined based on the light absorption rate, light intensity and light projection area.

[0092] Among them, the linear regression model expression of light absorption is:

[0093]

[0094] Where, represents the light absorption rate, 、 as well as Respectively represent the weight coefficient of each color component to the light absorption rate, 、 and Represent the red, green and blue components respectively, represents the bias term, for 、 as well as The weight coefficient can be obtained through preliminary experiments.

[0095] Optionally, for different car paints with different light absorption rates, if higher accuracy is required, different car paint colors can also be subdivided according to RGB values, for example: low absorption rate colors (0-40%): white series: pure white: 25-30%, pearl white: 30-35%, ivory white: 35-40%, glacier white: 25-30%; silver series: crystal silver: 35-40%, meteor silver: 35-40%, champagne silver: 38-42%, platinum silver: 35-40%; medium absorption rate colors (40-60%): gray series: silver gray: 45-50%, titanium gray: 50-55%, moonlight gray: 45-50%, smoky gray: 50-55%; light colors: light blue: 50-55%, light green: 45-50%, beige: 40-45%; high absorption rate colors (60-80%): red series: Chinese red: 65-70%,

[0096] Burgundy: 70-75%, coral red: 60-65%, cherry red: 65-70%; blue series: sapphire blue: 65-70%, deep sea blue: 75-80%, aurora blue: 60-65%, starry sky blue: 75-80%; extremely high absorption rate colors (80-95%): black series: pure black: 90-95%, metallic black: 85-90%, carbon crystal black: 88-92%, starry sky black: 85-90%; dark series: dark brown: 80-85%, dark green: 80-85%, dark purple: 85-90%.

[0097] Optionally, the calculation expression for the second heat load is:

[0098]

[0099] Where, and They represent the start and end time of the vehicle body being illuminated. Indicates the light intensity outside the target vehicle, represents the vehicle body light projection area, represents the light absorption rate corresponding to the target vehicle paint, Indicates the time step.

[0100] Step S400: determining a third heat load generated by heat in the passenger compartment of the target vehicle based on the passenger compartment occupant information;

[0101] In some embodiments, the passenger compartment occupant information may be the number of occupants in the passenger compartment. Of course, if the weight or age of the occupants in the passenger compartment can also be considered, in order to simplify the data processing process, this step is implemented by only considering the number of occupants in the passenger compartment. Specifically, the heat generation corresponding to different occupants can be determined through preliminary experiments, thereby establishing a relevant mathematical model, and using the following calculation expression to obtain the total metabolic heat load of the occupants in the pure electric vehicle: :

[0102]

[0103] in, and They represent the start time and end time of the user in the cabin respectively, is the standard human metabolic heat load, is the number of passengers in the car, that is Take the average of the standard human metabolism.

[0104] Optionally, the number of people can be collected and identified by sensors installed under the seats, or by camera image processing. The calculation can be performed in sections, that is, when there are changes in the number of people in the car, the solution can be performed in sections.

[0105] Step S500: Determine an electronic expansion valve opening signal and a compressor speed signal for controlling the temperature of the air conditioning system in the passenger compartment according to the air conditioning set temperature, the first heat load, the second heat load, and the third heat load and based on a preset target CNN-GRU neural network model.

[0106] In this step, it should be noted that the target CNN-GRU neural network model combines the advantages of convolutional neural networks (CNN) and gated recurrent units (GRU). It is mainly suitable for sequence data processing, especially when processing images, videos, and time series data. For the time series data in this step, CNN can automatically extract useful features, and GRU can capture the temporal dynamics of the sequence. Therefore, the model itself can reduce dependence on manual feature engineering. When faced with complex data, it can reduce manual intervention and automatically optimize the feature extraction process.

[0107] In some embodiments, the creation of a target CNN-GRU neural network model includes: obtaining an initial data sample of the historical thermal load corresponding to the target vehicle model, preprocessing and normalizing the initial data sample to obtain a target data sample; segmenting the target data sample based on a preset time window to obtain a sample subset, and dividing the sample subset into a training set and a validation set; creating an initial CNN-GRU neural network model, inputting the training set into the initial CNN-GRU neural network model, and outputting a predicted value; determining the difference between the predicted value and the true value based on a preset target loss function, and validating the trained initial CNN-GRU neural network model based on the validation set to obtain a target CNN-GRU neural network model.

[0108] Optionally, the initial data samples of historical heat load are mainly various heat load data of the vehicle under different scenarios and the opening of the electronic expansion valve in the passenger compartment of the corresponding air-conditioning system, the air-conditioning set temperature and the compressor speed, etc., wherein the time series length of data acquisition is set to 1800 seconds to ensure the continuity and comprehensiveness of the data, and the normalized data is segmented based on the time window. The length of each time window is set to 1 time point to facilitate subsequent model training, and all the data obtained after window segmentation are used as the training data set; the training data set is split into two parts: a training set and a validation set; the training set consists of the first 70% of the data of the training data set, and the validation set consists of 30% of the data of the training data set. The subsequent CNN-GRU model is trained, and the training model can be independently programmed through MATLAB or Python, or it can be completed using a mature deep learning framework such as MindSpore. In this step, MATLAB autonomous programming can be used.

[0109] Optionally, an improved initial CNN-GRU neural network model is constructed, and the normalized heat load is used as an input value, and the normalized passenger compartment electronic expansion valve opening and compressor speed are used as outputs, and the initial CNN-GRU neural network model is trained to obtain a trained target CNN-GRU neural network model;

[0110] The initial CNN-GRU neural network model includes a convolutional neural network module and a gated recurrent neural network module. The convolutional neural network module may include two convolutional layers, one pooling layer, and one flattening layer for feature extraction and dimensionality reduction; the gated recurrent neural network module may include one GRU layer, one dropout layer, and one fully connected layer for time series prediction and output.

[0111] Optionally, in the convolutional neural network module, the two convolution layers are the first one-dimensional convolution layer and the second one-dimensional convolution layer, respectively. The first one-dimensional convolution layer includes 32 convolution kernels with a convolution kernel size of 3, and the activation function adopts the ReLU function. The second one-dimensional convolution layer includes 62 convolution kernels with a convolution kernel size of 3, and the activation function adopts the ReLU function. The first one-dimensional convolution layer performs preliminary feature extraction on the input data. In order to make the data features more obvious, the second one-dimensional convolution layer is set for further feature extraction; the pooling layer is to extract important features and suppress noise signals; the flattening layer is to perform single-dimensional processing on the data processed by the convolutional neural network module, so as to facilitate a smooth transition from the convolutional neural network module to the gated recurrent neural network module.

[0112] Optionally, in order to enable the model to learn and simulate the temporal links and dependencies of the time series, the feature vector of the flattened layer is fed as input to the GRU layer to complete the transition from the convolutional neural network module to the gated recurrent neural network module. The GRU layer is used to process time series data. The number of neurons in the GRU layer is set to 128, and the ratio of the dropout layer is set to 0.2 to prevent overfitting. The fully connected layer is used as the output layer, and a linear activation function is used.

[0113] Optionally, in the gated recurrent neural network module, based on the information passed from the previous moment Input information at the current moment A reset gate and an update gate are set, wherein the gated recurrent neural network module satisfies the following formula:

[0114]

[0115]

[0116]

[0117]

[0118] Where, To update the gate, To reset the gate, For candidate information, To transmit information to the next moment, is the sigmoid function, is the tanh function, 、 as well as They are the update gate, reset gate and weight matrix of candidate information respectively.

[0119] In the above-mentioned air-conditioning control method, in response to the automatic temperature adjustment mode of the target vehicle, by obtaining the current passenger cabin occupant information, vehicle speed information, vehicle body status information, vehicle paint information, light intensity, light projection area, external ambient temperature, passenger cabin temperature and air-conditioning setting temperature, when determining that the heat generated by the external light on the target vehicle causes the temperature change in the passenger cabin, the light absorption linear regression model is created to fully consider the influence of the paint color on the light absorption rate, so that the temperature change caused by the external light in the passenger cabin can be determined more accurately. By considering the window opening degree of the target vehicle and the influence of the gas flow caused by different vehicle speeds on the heat exchange when driving, and considering the possible influence of the door opening when not driving, the temperature change caused by the external light in the passenger cabin can be determined more accurately. And more accurately determine the temperature changes in the passenger compartment caused by heat exchange, and consider the temperature changes caused by different numbers of people in the passenger compartment. Finally, combined with the target CNN-GRU neural network model, a more accurate heat load is input into the target CNN-GRU neural network model for prediction to output the electronic expansion valve opening signal and compressor speed signal used to control the temperature of the air-conditioning system in the passenger compartment, so as to achieve precise temperature control of the air-conditioning system in the passenger compartment, fully consider a variety of influencing factors, improve control accuracy and further reduce the energy consumption of the air-conditioning system. At the same time, the created target CNN-GRU neural network model has high calculation efficiency for time series data, thereby making the prediction accuracy higher and generating feedback signals faster.

[0120] See also Figures 2 to 4 This embodiment provides the actual simulation process of the target CNN-GRU neural network model. Figures 2 to 4 The data graph of the actual training simulation process is shown. The trained target CNN-GRU neural network model is used to analyze multiple heat load data collected in real time to obtain the output results of the passenger compartment electronic expansion valve opening and compressor speed. The vehicle thermal management system controls the passenger compartment air conditioning system based on the output results. Among them, the hyperparameters of the trained target CNN-GRU neural network model are adjusted, and the hyperparameters include learning rate, batch size, dropout ratio, etc. The change trend of the loss function after training is shown as follows Figure 2 As stated by Figure 2 It can be seen that the training loss tends to be stable as the number of iterations increases, and the model can fit well. The model is verified on the test set, and the verification results are as follows Figure 3 and Figure 4 As shown by Figure 3 and Figure 4It can be seen that the predicted values ​​of the passenger compartment electronic expansion valve opening and compressor speed are almost consistent with the true values, indicating that the trained target CNN-GRU neural network model has good prediction ability for the validation set data. The trained target CNN-GRU neural network model can be applied to solving the passenger compartment electronic expansion valve opening and compressor speed.

[0121] See also Figure 5 In some embodiments, the air conditioning control method of the pure electric vehicle of the above embodiment is tested. Under the same working conditions and test environment, the compressor control results obtained by the traditional method and the compressor control results obtained by the present invention are tested and compared. The traditional method refers to the PID independent control method. The results are as follows: Figure 5 As shown, from Figure 5 It can be seen that the method of the present invention has a faster control rate for the compressor than the traditional method, has better stability in the compressor speed control, and has lower energy consumption for the vehicle thermal management system.

[0122] See also Figure 6 This embodiment provides an air conditioning control device for a pure electric vehicle. The air conditioning control device 200 for a pure electric vehicle includes:

[0123] an acquisition module 210 configured to acquire, in response to an automatic temperature adjustment mode of the air conditioning system of the target vehicle, current passenger compartment occupant information, vehicle speed information, vehicle body status information, vehicle paint information, light intensity, light projection area, external ambient temperature, passenger compartment temperature, and air conditioning set temperature of the target vehicle;

[0124] The first heat load determination module 220 is configured to determine a first heat load of heat exchange between the passenger compartment of the target vehicle and the external environment based on vehicle speed information, external environment temperature, passenger compartment temperature, and vehicle body state information;

[0125] The second heat load determination module 230 is configured to determine a second heat load absorbed by the passenger compartment of the target vehicle based on the vehicle paint information, the light intensity, and the light projection area;

[0126] The third heat load determination module 240 is configured to determine a third heat load generated by heat in the passenger compartment of the target vehicle based on the passenger compartment occupant information;

[0127] The data processing module 250 is configured to determine the electronic expansion valve opening signal and the compressor speed signal for controlling the temperature of the air conditioning system in the passenger compartment based on the air conditioning set temperature, the first heat load, the second heat load and the third heat load and based on a preset target CNN-GRU neural network model.

[0128] In some embodiments, the first heat load determination module 220 is also used to determine whether the vehicle speed information is zero; if so, determine the lifting and opening information of each window and the opening and closing angle information of each door of the target vehicle based on the vehicle body status information; if not, determine the lifting and opening information of each window of the target vehicle and the airflow influence factor corresponding to the current vehicle speed information; based on the lifting and opening information and the opening and closing angle information, the effective area of ​​the current windows and doors of the target vehicle for heat exchange; based on the effective area, the external ambient temperature, the passenger compartment temperature and the airflow influence factor, determine the first heat load of the heat exchange between the passenger compartment inside the target vehicle and the external environment.

[0129] Optionally, the calculation expression of the first heat load is:

[0130]

[0131] Where, and They represent the start and close time of the door opening, h represents the heat exchange coefficient, Indicates the effective area corresponding to the door opening and closing angle, and Respectively represent the start time and closing time of the window opening, Indicates the effective area corresponding to the window opening, Indicates the external ambient temperature, Indicates the passenger compartment temperature, represents the time step, Indicates the airflow impact factor.

[0132] In some embodiments, the second heat load determination module 230 is further configured to determine a corresponding average RGB value based on the vehicle paint information;

[0133] According to the average RGB value and based on the preset light absorption linear regression model, the corresponding light absorption rate is determined, wherein the light absorption linear regression model expression is:

[0134]

[0135] Where, represents the light absorption rate, 、 as well as Respectively represent the weight coefficient of each color component to the light absorption rate, 、 and Represent the red, green and blue components respectively, represents the bias term.

[0136] A second heat load absorbed by a passenger compartment of the target vehicle is determined according to the light absorption rate, the light intensity, and the light projection area.

[0137] Optionally, the calculation expression for the second heat load is:

[0138]

[0139] Where, and They represent the start and end time of the vehicle body being illuminated. Indicates the light intensity outside the target vehicle, represents the vehicle body light projection area, represents the light absorption rate corresponding to the target vehicle paint, Indicates the time step.

[0140] In some embodiments, creation of a target CNN-GRU neural network model in the data processing module 250 includes: obtaining an initial data sample of the historical thermal load corresponding to the target vehicle model, preprocessing and normalizing the initial data sample to obtain a target data sample; segmenting the target data sample based on a preset time window to obtain a sample subset, and dividing the sample subset into a training set and a validation set; creating an initial CNN-GRU neural network model, inputting the training set into the initial CNN-GRU neural network model, and outputting a predicted value; determining the difference between the predicted value and the true value based on a preset target loss function, and validating the trained initial CNN-GRU neural network model based on the validation set to obtain a target CNN-GRU neural network model.

[0141] Optionally, the initial CNN-GRU neural network model includes a convolutional neural network module and a gated recurrent neural network module, and the convolutional neural network module includes at least two convolutional layers, a pooling layer, and a flattening layer for feature extraction and dimensionality reduction;

[0142] The gated recurrent neural network module includes at least one GRU layer, one dropout layer, and one fully connected layer for time series prediction and output;

[0143] In the convolutional neural network module, the two convolution layers include the first one-dimensional convolution layer and the second one-dimensional convolution layer. The first one-dimensional convolution layer includes 32 convolution kernels with a convolution kernel size of 3, and the second one-dimensional convolution layer includes 62 convolution kernels with a convolution kernel size of 3. The activation function of the first one-dimensional convolution layer and the second one-dimensional convolution layer adopts the ReLU function.

[0144] The pooling layer is used to extract important features and suppress noise signals;

[0145] The flattening layer is used to process the data processed by the convolutional neural network module into a single dimension to facilitate a smooth transition from the convolutional neural network module to the gated recurrent neural network module;

[0146] In the gated recurrent neural network module, based on the information passed from the previous moment Input information at the current moment Set the reset gate and update gate, where the gated recurrent neural network module satisfies the following formula:

[0147]

[0148]

[0149]

[0150]

[0151] Where, To update the gate, To reset the gate, For candidate information, To transmit information to the next moment, is the sigmoid function, is the tanh function, 、 as well as They are the update gate, reset gate and weight matrix of candidate information respectively.

[0152] It should be understood that Figure 6 In the structural block diagram of the air conditioning control device 200 of the pure electric vehicle shown, each module is used to execute Figure 1 The steps in the corresponding embodiments, and Figure 1 Each step in the corresponding embodiment has been explained in detail in the above embodiment. Figure 1 as well as Figure 1 The relevant descriptions in the corresponding embodiments will not be repeated here.

[0153] Compared with the related art, the above embodiment has the following beneficial effects: in response to the automatic temperature control mode of the target vehicle, by obtaining the current passenger compartment occupant information, vehicle speed information, vehicle body status information, vehicle paint information, light intensity, light projection area, external ambient temperature, passenger compartment temperature and air conditioning setting temperature, when determining that the heat generated by external light on the target vehicle causes the temperature change in the passenger compartment, the light absorption linear regression model created fully considers the influence of the paint color on the light absorption rate, so that the temperature change caused by external light in the passenger compartment can be determined more accurately, and by considering the window opening degree of the target vehicle and the influence of gas flow caused by different vehicle speeds on heat exchange when driving, as well as the possible opening of the door when not driving. The influence of heat exchange can more accurately determine the temperature change in the passenger compartment caused by heat exchange, and the temperature change caused by different numbers of people taking into account the personnel information in the passenger compartment. Finally, combined with the target CNN-GRU neural network model, a more accurate heat load is input into the target CNN-GRU neural network model for prediction to output the electronic expansion valve opening signal and the compressor speed signal for controlling the temperature of the air-conditioning system in the passenger compartment, so as to achieve precise temperature control of the air-conditioning system in the passenger compartment, fully consider a variety of influencing factors, improve control accuracy and further reduce the energy consumption of the air-conditioning system. At the same time, the created target CNN-GRU neural network model has high calculation efficiency for time series data, which makes the prediction accuracy higher and the feedback signal generation faster.

[0154] See also Figure 7 , Figure 7 FIG2 is a block diagram of a vehicle 800 according to an exemplary embodiment. For example, vehicle 800 may be a pure electric vehicle, or, for example, an extended-range electric vehicle. The pure electric vehicle may be a pure electric SUV, a pure electric MPV, a pure electric sports car, or a pure electric commercial vehicle.

[0155] like Figure 7 As shown, vehicle 800 may include various subsystems, such as an infotainment system 810, a perception system 820, a decision control system 830, a drive system 840, and a computing platform 850. Vehicle 800 may also include more or fewer subsystems, and each subsystem may include multiple components. Furthermore, each subsystem and each component of vehicle 800 may be interconnected via wired or wireless means.

[0156] In some embodiments, the infotainment system 810 may include a communication system, an entertainment system, a navigation system, and the like.

[0157] The perception system 820 may include several sensors for sensing information about the environment surrounding the vehicle 800. For example, the perception system 820 may include a global positioning system (which may be a GPS system, a BeiDou system, or another positioning system), an inertial measurement unit (IMU), a laser radar, a millimeter-wave radar, an ultrasonic radar, and a camera.

[0158] The decision control system 830 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

[0159] The drive system 840 may include components that provide power to the vehicle 800. In one embodiment, the drive system 840 may include an engine, a power source, a transmission system, and wheels. The engine may be an internal combustion engine, an electric motor, an air compression engine, or a combination thereof. The engine is capable of converting energy provided by the power source into mechanical energy.

[0160] Some or all functions of the vehicle 800 are controlled by a computing platform 850. The computing platform 850 may include at least one processor 851 and a memory 852. The processor 851 may execute instructions 853 stored in the memory 852.

[0161] The processor 851 can be any conventional processor, such as a commercially available CPU. The processor can also include a graphics processor (GPU), a field programmable gate array (FPGA), a system on chip (SOC), an application specific integrated circuit (ASIC), or a combination thereof.

[0162] The memory 852 may be implemented by any type of volatile or nonvolatile memory 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.

[0163] In addition to instructions 853 , memory 852 may also store data, such as road maps, route information, and vehicle location, direction, speed, etc. The data stored in memory 852 may be used by computing platform 850 .

[0164] In some embodiments, the processor 851 may execute the instruction 853 to complete all or part of the steps of the above-mentioned air conditioning control method for a pure electric vehicle.

[0165] In some embodiments, a vehicle is also provided, comprising a processor;

[0166] a memory for storing processor-executable instructions;

[0167] The processor is configured to implement the steps of the air conditioning control method for a pure electric vehicle provided in the aforementioned method embodiment.

[0168] In some embodiments, a computer-readable storage medium is further provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the air-conditioning control method for a pure electric vehicle provided in the present disclosure are implemented.

[0169] In some embodiments, a computer program product is further provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the air conditioning control method for a pure electric vehicle provided in the present disclosure are implemented.

[0170] In the specification, claims, and accompanying drawings of this application, the terms "first," "second," "third," and the like are used to distinguish different objects and are not used to describe a particular order. Furthermore, the terms "including," "comprising," "having," and any variations thereof are intended to cover non-exclusive inclusions. For example, a list of steps or elements may be included, or alternatively, steps or elements not listed may be included, or other steps or elements may be included that are inherent to the process, method, product, or apparatus.

[0171] Only portions relevant to the present application are shown in the accompanying drawings, not all of them. Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the various operations (or steps) as sequential processes, many of the operations can be performed in parallel, concurrently, or simultaneously. In addition, the order of the various operations can be rearranged. The process can be terminated when its operations are completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0172] As used in this specification, the terms "component," "module," "system," "unit," and the like are used to refer to computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a unit can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or distributed between two or more computers. In addition, these units can be executed from various computer-readable media having various data structures stored thereon. Units can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from a second unit interacting with another unit in a local system, a distributed system, and / or a network, such as the Internet, which interacts with other systems via signals).

[0173] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "illustrative embodiments," "example," "specific example," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example.

[0174] Obviously, the described embodiments are only some of the embodiments of the present application, rather than all of the embodiments. Mentioning "embodiment" in this article means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present embodiment application. The appearance of this phrase in various positions in the specification does not necessarily mean that they are all the same embodiments, nor are they independent or alternative embodiments that are mutually exclusive with other embodiments. It can be understood explicitly and implicitly by those skilled in the art that the embodiments described herein can be combined with other embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without making creative work are within the scope of protection of this application.

[0175] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and intent of the present application, and that the scope of the present application is defined by the claims and their equivalents.

[0176] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

Claims

1. A method for controlling air conditioning of a pure electric vehicle, characterized in that: include: In response to an automatic temperature adjustment mode of the air conditioning system of the target vehicle, obtaining current passenger compartment occupant information, vehicle speed information, vehicle body status information, vehicle paint information, light intensity, light projection area, external ambient temperature, passenger compartment temperature, and air conditioning setting temperature of the target vehicle; determining a first heat load of heat exchange between the passenger compartment of the target vehicle and the external environment based on the vehicle speed information, the external environment temperature, the passenger compartment temperature, and the vehicle body state information; determining a second heat load absorbed by a passenger compartment of the target vehicle based on the vehicle paint information, the light intensity, and the light projection area; determining a third heat load generated by heat in the passenger compartment of the target vehicle based on the passenger compartment occupant information; An electronic expansion valve opening signal and a compressor speed signal for controlling the temperature of the air conditioning system in the passenger compartment are determined according to the air conditioning set temperature, the first heat load, the second heat load, and the third heat load and based on a preset target CNN-GRU neural network model.

2. The air conditioning control method for a pure electric vehicle according to claim 1, characterized in that: The determining, based on the vehicle speed information, the ambient temperature, the passenger compartment temperature, and the vehicle body state information, a first heat load of heat exchange between the passenger compartment of the target vehicle and the external environment includes: determining whether the vehicle speed information is zero; If yes, determine the lifting and lowering opening information of each window and the opening and closing angle information of each door of the target vehicle according to the vehicle body state information; If not, determining the airflow impact factor corresponding to the lift opening information of each window of the target vehicle and the current vehicle speed information; Determining the effective area of ​​heat exchange between the current windows and doors of the target vehicle based on the lifting opening information and the opening and closing angle information; A first heat load of heat exchange between the passenger compartment in the target vehicle and the external environment is determined based on the effective area, the external environment temperature, the passenger compartment temperature, and the airflow influencing factor.

3. The air conditioning control method for a pure electric vehicle according to claim 2, characterized in that: The determining, based on the effective area, the ambient temperature, the passenger compartment temperature, and the airflow influencing factor, a first heat load of heat exchange between the passenger compartment of the target vehicle and the external environment includes: The calculation expression of the first heat load is: Where, and They represent the start and close time of the door opening, h represents the heat exchange coefficient, Indicates the effective area corresponding to the door opening and closing angle, and Respectively represent the start time and closing time of the window opening, Indicates the effective area corresponding to the window opening, Indicates the external ambient temperature, Indicates the passenger compartment temperature, represents the time step, Indicates the airflow impact factor.

4. The air conditioning control method for a pure electric vehicle according to claim 1, characterized in that: The determining, based on the vehicle paint information, the light intensity, and the light projection area, a second heat load absorbed by the passenger compartment of the target vehicle includes: Determine the corresponding average RGB value according to the vehicle paint information; The corresponding light absorption rate is determined according to the average RGB value and based on a preset light absorption linear regression model, wherein the light absorption linear regression model expression is: Where, represents the light absorption rate, 、 as well as Respectively represent the weight coefficient of each color component to the light absorption rate, 、 and Represent the red, green and blue components respectively, represents the bias term; A second heat load absorbed by a passenger compartment of the target vehicle is determined according to the light absorption rate, the light intensity, and the light projection area.

5. The air conditioning control method for a pure electric vehicle according to claim 4, characterized in that: The determining, based on the light absorption rate, the light intensity, and the light projection area, a second heat load absorbed by the passenger compartment of the target vehicle includes: The calculation expression of the second heat load is: Where, and They represent the start and end time of the vehicle body being illuminated. Indicates the light intensity outside the target vehicle, represents the vehicle body light projection area, represents the light absorption rate corresponding to the target vehicle paint, Indicates the time step.

6. The air conditioning control method for a pure electric vehicle according to claim 1, characterized in that: In the step of determining the electronic expansion valve opening signal and the compressor speed signal for controlling the temperature of the air conditioning system in the passenger compartment based on the air conditioning set temperature, the first heat load, the second heat load, and the third heat load and based on a preset target CNN-GRU neural network model, creating the target CNN-GRU neural network model includes: Obtaining an initial data sample of historical thermal load corresponding to a target vehicle model, and performing preprocessing and normalization on the initial data sample to obtain a target data sample; Segmenting the target data sample based on a preset time window to obtain a sample subset, and dividing the sample subset into a training set and a validation set; Creating an initial CNN-GRU neural network model, inputting the training set into the initial CNN-GRU neural network model, and outputting a predicted value; The difference between the predicted value and the true value is determined based on a preset target loss function, and the trained initial CNN-GRU neural network model is verified based on the verification set to obtain the target CNN-GRU neural network model.

7. The air conditioning control method for a pure electric vehicle according to claim 6, characterized in that: The step of creating an initial CNN-GRU neural network model, inputting the training set into the initial CNN-GRU neural network model, and outputting a predicted value includes: The initial CNN-GRU neural network model includes a convolutional neural network module and a gated recurrent neural network module, wherein the convolutional neural network module includes at least two convolutional layers, a pooling layer, and a flattening layer for feature extraction and dimensionality reduction; The gated recurrent neural network module includes at least one GRU layer, one dropout layer, and one fully connected layer for time series prediction and output; In the convolutional neural network module, the two convolution layers include a first one-dimensional convolution layer and a second one-dimensional convolution layer, the first one-dimensional convolution layer includes 32 convolution kernels with a convolution kernel size of 3, the second one-dimensional convolution layer includes 62 convolution kernels with a convolution kernel size of 3, and the activation functions of the first one-dimensional convolution layer and the second one-dimensional convolution layer adopt the ReLU function; The pooling layer is used to extract important features and suppress noise signals; The flattening layer is used to process the data processed by the convolutional neural network module into a single dimension, so as to facilitate a smooth transition from the convolutional neural network module to the gated recurrent neural network module; In the gated recurrent neural network module, based on the information passed from the previous moment Input information at the current moment A reset gate and an update gate are set, wherein the gated recurrent neural network module satisfies the following formula: Where, To update the gate, To reset the gate, For candidate information, To transmit information to the next moment, is the sigmoid function, is the tanh function, 、 as well as They are the update gate, reset gate and weight matrix of candidate information respectively.

8. An air conditioning control device for a pure electric vehicle, characterized in that: include: an acquisition module configured to acquire, in response to an automatic temperature adjustment mode of an air conditioning system of a target vehicle, current passenger compartment occupant information, vehicle speed information, vehicle body status information, vehicle paint information, light intensity, light projection area, external ambient temperature, passenger compartment temperature, and air conditioning set temperature of the target vehicle; a first heat load determination module configured to determine a first heat load of heat exchange between the passenger compartment of the target vehicle and the external environment based on the vehicle speed information, the external environment temperature, the passenger compartment temperature, and the vehicle body state information; a second heat load determination module configured to determine a second heat load absorbed by a passenger compartment of the target vehicle based on the vehicle paint information, the light intensity, and the light projection area; a third heat load determination module configured to determine a third heat load generated by heat in the passenger compartment of the target vehicle based on the passenger compartment occupant information; The data processing module is configured to determine an electronic expansion valve opening signal and a compressor speed signal for controlling the temperature of the air conditioning system in the passenger compartment based on the air conditioning set temperature, the first heat load, the second heat load, and the third heat load and based on a preset target CNN-GRU neural network model.

9. A vehicle, characterized in that: include: processor; a memory for storing instructions executable by the processor; Wherein, the processor is configured to: Implement the steps of the air conditioning control method for a pure electric vehicle as described in any one of claims 1 to 7.

10. 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 air-conditioning control method for a pure electric vehicle according to any one of claims 1 to 7 are implemented.

Images