Automobile air conditioning control method, device, system and storage medium

Abstract

The automobile air conditioning control method, device, system and storage medium provided by the present invention include: obtaining the thermal habits of passengers according to the human metabolic rate value, the thermal habits being the quantitative evaluation value of the passenger's current thermal sensation; obtaining the first reference information affecting the temperature in the car, the reference information including the measurement information detected by the car sensor and at least one of the external information obtained from the outside; obtaining the planned temperature according to the thermal habits and the first reference information; controlling the automobile air conditioning to adjust the temperature in the passenger compartment of the car to the planned temperature. By using a dynamic programming algorithm, the development of the planned temperature in the car is optimized according to information such as vehicle speed, passenger thermal comfort, weather information, and the number and weight of passengers, so as to achieve low energy consumption and good passenger thermal comfort. Then, using a temperature tracking control algorithm, the compressor speed and heater power are adjusted to adjust the passenger compartment temperature to the planned temperature. The temperature control is more comfortable, the control is more optimized, and the performance is better.

Description

Technical Field

[0001] The present invention relates to the field of automobile technology, and in particular to an automobile air-conditioning control method, device, system and storage medium. Background Art

[0002] The air conditioning system of automobiles, especially new energy electric vehicles, reduces its mileage by about 30% to 40% due to additional energy consumption. Therefore, it is very important to design an efficient air conditioning system control strategy to provide passengers with a comfortable thermal environment at a lower energy cost.

[0003] In the prior art, the control algorithm of automobile air conditioning adopts an on-off control strategy, which keeps the electric compressor in the air conditioning system running at a constant speed and performs on-off control when the target cabin temperature is reached. Although this control algorithm is simple and feasible, frequent "on / off" will cause fluctuations in cabin temperature, which will not only cause thermal discomfort to passengers, but also lead to additional energy consumption of the air conditioning system.

[0004] Therefore, the above problems existing in the prior art have yet to be solved. Summary of the invention

[0005] The present invention provides an automobile air-conditioning control method, device, system and storage medium, which determine the temperature control parameters of the automobile air-conditioning by comprehensively analyzing the user's thermal habits and multi-dimensional information, thereby solving the problem of inconvenient automobile air-conditioning temperature adjustment in the prior art.

[0006] A first aspect of the present invention provides an automobile air-conditioning control method for controlling the air-conditioning temperature in a passenger compartment of a vehicle, comprising: obtaining a passenger's thermal habit based on a human metabolic rate value, the thermal habit being a quantitative evaluation value of the passenger's current thermal sensation; obtaining first reference information that affects the temperature inside the vehicle, the reference information including measurement information detected by a vehicle sensor, and at least one of external information obtained from the outside; obtaining a planned temperature based on the thermal habit and the first reference information; and controlling the automobile air-conditioning to adjust the temperature in the passenger compartment of the vehicle to the planned temperature.

[0007] Optionally, the measurement information includes at least one of vehicle speed, number of passengers and vehicle load; and the external information includes weather information.

[0008] Optionally, before obtaining the thermal habits of the passenger based on the human metabolic rate value, the method also includes obtaining the human metabolic rate value, including: inputting second reference information into the first neural network model, the second reference information including time information, and at least one of environmental information detected by the vehicle sensor; obtaining the human metabolic rate value output by the first neural network model based on the second reference information.

[0009] Optionally, the time information includes at least one of the current month or the current time; the environmental information includes at least one of the current temperature or relative humidity in the passenger compartment.

[0010] Optionally, before obtaining the human metabolic rate value, the method also includes: training the first neural network model through multiple sets of training time information and training environment information, so that the first neural network model outputs a human metabolic rate that conforms to the actual situation according to the time information and the environment information.

[0011] Optionally, the first neural network model is trained using multiple sets of training time information and training environment information, including: inputting the training time information and the training environment information into the first neural network model so that the first neural network model outputs a training human metabolic rate value; obtaining the thermal habits of the passenger based on the training human metabolic rate value to obtain a training temperature in combination with the real-time first reference information; controlling the automobile air conditioner to adjust the temperature in the automobile passenger compartment to the training temperature; the tester adjusts the temperature in the passenger compartment to a comfortable temperature based on the perceived comfort of the training temperature; re-inputting the comfortable temperature into the first neural network model, and repeating the above steps until the first human metabolic rate value output by the first neural network model can directly obtain the comfortable temperature without intervention by the tester.

[0012] Optionally, the control of the automobile air conditioner to adjust the temperature in the automobile passenger compartment to the planned temperature includes: obtaining the planned temperature; obtaining the real-time temperature in the passenger compartment; and adjusting the compressor speed and / or heater power through a temperature tracking control algorithm according to the planned temperature and the real-time temperature to adjust the temperature in the passenger compartment from the real-time temperature to the planned temperature.

[0013] A second aspect of the present invention provides an automobile air-conditioning control device for controlling the air-conditioning temperature in a passenger compartment of a vehicle, comprising: a first acquisition unit for acquiring a passenger's thermal habits based on a human metabolic rate value, wherein the thermal habits are a quantitative evaluation value of the passenger's current thermal sensation; a second acquisition unit for acquiring first reference information that affects the temperature in the vehicle, wherein the reference information includes measurement information detected by a vehicle sensor and at least one of external information acquired from the outside; a calculation unit for acquiring a planned temperature based on the thermal habits acquired by the first acquisition unit and the first reference information acquired by the second acquisition unit; and a control unit for controlling the automobile air-conditioning to adjust the temperature in the passenger compartment of the vehicle to the planned temperature calculated by the calculation unit.

[0014] A third aspect of the present invention provides an automobile air-conditioning control system for controlling the air-conditioning temperature in a passenger compartment of a vehicle, comprising: a decision estimation layer and a local control layer, wherein the decision estimation layer is used to: obtain the thermal habits of the passenger based on the human metabolic rate value, the thermal habits being the passenger's current quantitative evaluation value of thermal sensation; obtain first reference information affecting the temperature inside the vehicle, the reference information comprising measurement information detected by the vehicle sensor, and at least one of external information obtained from the outside; obtain a planned temperature based on the thermal habits and the first reference information; the local control layer is used to: obtain the planned temperature from the decision estimation layer; and control the automobile air-conditioning to adjust the temperature in the passenger compartment of the vehicle to the planned temperature.

[0015] A fourth aspect of the present invention provides a medium for executing the automobile air-conditioning control method described in the first aspect and any optional implementation manner of the first aspect.

[0016] In summary, the automobile air conditioning control method, device, system and medium provided by the present invention include: obtaining the thermal habits of passengers according to the human metabolic rate value, the thermal habits being the quantitative evaluation value of the passenger's current thermal sensation; obtaining the first reference information affecting the temperature inside the vehicle, the reference information including the measurement information detected by the vehicle sensor, and at least one of the external information obtained from the outside; obtaining the planned temperature according to the thermal habits and the first reference information; and controlling the automobile air conditioning to adjust the temperature inside the passenger compartment of the vehicle to the planned temperature. By using a dynamic programming algorithm, the development of the planned temperature inside the vehicle is optimized according to information such as vehicle speed, passenger thermal comfort, weather information, and the number and weight of passengers, so as to achieve low energy consumption and good passenger thermal comfort. Then, using a temperature tracking control algorithm, the compressor speed and heater power are adjusted to adjust the passenger compartment temperature to the planned temperature. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flow chart of an embodiment of the automobile air conditioning control method provided by the present invention;

[0018] Figure 2 A flow chart of another embodiment of the automobile air conditioning control method provided by the present invention;

[0019] Figure 3 A flow chart of another embodiment of the automobile air conditioning control method provided by the present invention;

[0020] Figure 4 A flow chart of training the first neural network model in the automobile air-conditioning control method provided by the present invention;

[0021] Figure 5 A working schematic diagram of the automobile air conditioning control method provided by the present invention;

[0022] Figure 6 A schematic diagram of the automobile air conditioning control device provided by the present invention;

[0023] Figure 7 This is a schematic diagram of the automobile air conditioning control system provided by the present invention. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0025] See also Figure 1 and Figure 5 The automobile air conditioning control method provided by the embodiment of the present invention includes the following steps.

[0026] S1. Obtain the thermal habits of passengers based on human metabolic rate values.

[0027] In this embodiment, the human metabolic rate value P refers to the energy consumed by the human body per unit time, usually measured in calories (kcal). The metabolic rate reflects the energy required by the body to maintain basic physiological functions (such as heartbeat, breathing, body temperature regulation, etc.) and to carry out daily activities. It directly determines the passenger's perception of heat. Thermal habit refers to the passenger's current quantitative assessment of thermal sensation.

[0028] It should be noted that the human metabolic rate value P can be preset to a certain value, or preferably, the human metabolic rate value P can be obtained by calculating through a neural network model, which is described in detail below.

[0029] See also Figure 2 ,like Figure 2 As shown, the steps of obtaining the human metabolic rate value P through the neural network model include:

[0030] S11. Input the second reference information into the first neural network model.

[0031] In this embodiment, the second reference information includes time information and at least one of environmental information detected by the vehicle sensor. Since the human metabolic rate changes with time and environment, time information and environmental information are key parameters for calculating the human metabolic rate.

[0032] Optionally, the time information includes at least one of the current month or the current time; the environmental information includes at least one of the current temperature or relative humidity in the passenger compartment.

[0033] It can be seen that compared with the prior art, which generally assumes that the human metabolic rate value P is a constant, this application takes into account that the human metabolic rate varies in different seasons, different times, different temperatures and humidity, etc. Therefore, this patent intends to use a BP neural network model to estimate the human metabolic rate value P. It is more in line with the actual situation of the user, and the subsequent calculation is more accurate.

[0034] Optionally, the first neural network model is recorded as: ;

[0035] Where f is an unknown nonlinear function, which is composed of the month m={1,2,...,12}, the time (hour) t={1,2,...,24}, the cabin temperature T a and cabin relative humidity H a The input layer nodes of the BP neural network are 4, corresponding to month m, time (hour) t, cabin temperature T a and cabin relative humidity H a The number of nodes in the output layer is related to the actual controlled object, and the output of the hidden layer of the neural network is the human metabolic rate value P.

[0036] S12. Obtaining a human metabolic rate value output by the first neural network model according to the second reference information.

[0037] In this embodiment, the first neural network model is a trained model, which estimates the human metabolic rate value P based on the input information of different seasons, different times, different temperatures and humidity, which is more accurate than the method of using only a single constant in the prior art.

[0038] After obtaining the passenger's human metabolic rate value P through the above steps, the passenger's thermal habits are obtained. The specific calculation method of thermal habits can be obtained through predicted mean vote (PMV) calculation. The detailed description is as follows.

[0039] PMV (Predicted Mean Vote) represents the predicted mean vote, which is used to predict the thermal habits of passengers and is obtained by solving the following formula: ;

[0040] Among them, T S represents the average temperature of the closed surface of the cabin, H1, H2, H3, H4, H5 and H6 represent variables related to metabolic rate, temperature, etc., respectively, and are calculated by the following formula: ,

[0041] As shown above, P represents the human metabolic rate value, P Wis the vapor pressure in the air, which depends on the relative humidity H in the vehicle cabin a When H a Passengers feel comfortable when the temperature drops by 40% to 70%. a is the cabin temperature determined by the air conditioning system. r is the average radiation temperature in the cabin, assuming that a Same. a is the air speed next to the passengers, determined by the blower in the cabin, h c Represents the heat transfer coefficient between air and passengers. T cl is the temperature of the clothes worn by the passengers, I cl Refers to the thermal resistance of the clothing, I cl Set to 0.7.

[0042] Thus, the thermal habits of passengers are calculated through the above PMV formula.

[0043] Optionally, after obtaining the above passenger thermal habits, the target temperature T can also be calculated by the following algorithm: d , preferably, T d The calculation method is as follows: ;

[0044] Where PMV represents the predicted mean, i.e., thermal habit, T S represents the average temperature of the cabin closed surface, H1, H2, H3, H4 and H5 represent variables related to metabolic rate, temperature, etc., P represents the metabolic rate of the passenger, h c represents the heat transfer coefficient between air and passengers, T cl is the temperature of the clothes the passenger is wearing, and: ;

[0045] The above T d It is the target temperature calculated based on the current passenger's metabolic rate P. In the specific implementation process, in order to make the final in-car temperature meet the target temperature and make the passengers feel comfortable, the actual situation that affects the in-car temperature also needs to be considered. The detailed description is as follows.

[0046] S2. Acquire first reference information that affects the temperature inside the vehicle.

[0047] In this embodiment, the reference information includes at least one of measurement information detected by the vehicle sensor and external information obtained from the outside. Preferably, the measurement information can be obtained by the local sensor of the vehicle, including at least one of the vehicle speed, the number of passengers and the vehicle weight; the external information includes weather information, etc., which can be obtained from the outside by the communication system of the vehicle, or can be measured by the vehicle's own sensor, which is not limited in this embodiment of the application.

[0048] The first reference information obtained combines the real-time weather conditions and the actual condition of the car, and is the reference factor that can most affect the temperature of the passenger compartment, which is conducive to obtaining a more accurate passenger compartment temperature adjustment in the future.

[0049] S3. Obtaining a planned temperature according to thermal habits and the first reference information.

[0050] In this embodiment, the planned temperature can be optionally calculated by a dynamic programming algorithm. The detailed description is as follows: in order to enable the dynamic programming algorithm to calculate the most comfortable target temperature Td, the following formula is used.

[0051] In the dynamic programming algorithm, it is necessary to calculate the total heat Q in the cabin total , which is determined by the solar radiation heat Q that can be measured in the cabin s , heat convection between the car body and the surrounding air Q v , the heat load Q generated by the driver and passengers p , outside air enters the cabin through the ventilation system and brings heat Q m The specific calculation is based on the following formula:

[0052] ,

[0053] Where h(v) is the heat transfer coefficient between the car and the external ambient air, which is related to the car speed, To is the external ambient temperature obtained through weather information, and T s is the temperature of the cabin's enclosed components; n is the number of passengers in the vehicle, b is the correction factor, which is related to the passenger weight; m is the mass flow rate of air entering the cabin from the environment, c is the air recirculation coefficient, C pa is the specific heat of air, T d is the target temperature calculated in the previous step.

[0054] In the optimization process of dynamic programming, the entire dynamic programming cycle is discretized into N time steps, and the optimization time is set to t A The temperature control power of the automobile air conditioning system is defined as Q AC , in each time step Δt, the cooling capacity of the air conditioning system is evenly divided into M parts, and the change of each part is called U. The dynamic change of the cabin temperature is calculated by the following formula: ;

[0055] The subscripts k and k + 1 are the kth time step and k + 1th time step respectively. The cost function J at time step k is used in dynamic programming. k Optimize, which is defined as:

[0056] ,

[0057] Where, the subscript i is the i-th value in the cooling capacity, and a is a weight factor ranging from 0 to 1, in order to balance the optimization process of cooling power and target temperature. max{Q AC} is the maximum temperature control power, min{Q AC} is the minimum temperature control power, that is, 0. In the process of time step k, take U as the interval and take Q AC,k,i In 0~max{Q AC}, calculate J k When the minimum value is reached, the corresponding cooling capacity is the time step k, that is, Q AC,k Then, the cabin temperature T at time step k + 1 is calculated a,k+1 When the entire dynamic programming is optimized, the output plan temperature T p .

[0058] As a result, the ideal planned temperature was obtained through the dynamic programming algorithm.

[0059] The dynamic programming algorithm takes into account the thermal habits of passengers and first reference information, where the thermal habits are generated based on the real-time human metabolic rate (human metabolic rate value) output by the neural network model according to time and environmental information. The first reference information includes the combination of vehicle speed, number of passengers, vehicle weight, and weather information. In this way, the target temperature T is obtained based on the thermal habits of passengers. d In the actual implementation process, considering the actual situation and external objective information (i.e., the first reference information), the target temperature T d Obtain the planned temperature T p Through multi-dimensional dynamic planning calculations, accurate planned temperatures are obtained, which can meet the user's thermal needs to the greatest extent possible based on actual conditions.

[0060] S4. Control the automobile air conditioner to adjust the temperature in the automobile passenger compartment to a planned temperature.

[0061] In this embodiment, a planned temperature that meets the actual situation has been calculated in the previous steps, and the air-conditioning temperature is adjusted to the planned temperature, so that the passengers can obtain maximum comfort.

[0062] Alternatively, if Figure 3 As shown, temperature regulation includes the following steps.

[0063] S41. Obtain the planned temperature.

[0064] In this embodiment, the planned temperature refers to the temperature planned in the previous step to make the passengers feel comfortable.

[0065] S42. Obtain the real-time temperature in the passenger compartment.

[0066] In this embodiment, the real-time temperature refers to the actual temperature in the current passenger compartment measured by the in-vehicle sensor.

[0067] S43. According to the planned temperature and the real-time temperature, the compressor speed and / or the heater power are adjusted by a temperature tracking control algorithm to adjust the temperature in the passenger compartment from the real-time temperature to the planned temperature.

[0068] In this embodiment, the compressor is a device for cooling the air to achieve cooling, and the heater is a device for heating the air to achieve heating. Through the cooperation of the compressor and the heater, the temperature in the passenger compartment can be regulated. The specific types of the compressor and the heater are not limited in the embodiment of the present application. Preferably, based on the real-time temperature, the embodiment of the present application adjusts the operation of the compressor and the heater through a temperature tracking control algorithm, so as to adjust the temperature in the passenger compartment to the planned temperature.

[0069] The specific implementation of the temperature tracking control algorithm is described as follows:

[0070] First set the temperature error e T Real-time temperature in the cabin With the planned temperature T p The difference, that is: ;

[0071] The compressor power and heater power are assumed to be the control input u. According to the predefined time control based on the time base generator (TBG), that is, if a certain variable x satisfies ;

[0072] Where w is the control gain and G(t,tp) is the TBG function, which is calculated according to the following formula: ;

[0073] Control time t p can be set in TBG. Then this variable x will be p time converges to a sufficiently small value.

[0074] R134a heat pump air conditioning system can be used to heat electric vehicles. The compressor model uses volumetric efficiency, isentropic efficiency and mechanical efficiency for calculation. The efficiency value is obtained through compressor component testing. R134a refrigerant mass flow rate and heat exchange capacity of heat pump system Calculated according to the following formula: ,

[0075] Where: is the refrigerant mass flow rate, kg / s; is the refrigerant suction density, kg / m 3 ; N is the compressor speed, r / min; V disis the compressor displacement, cm3 / r; C p is the specific heat capacity of the refrigerant, J / (kg·K); is the temperature difference of the refrigerant at the inlet and outlet of the heat exchanger, K.

[0076] According to the temperature error e T Real-time temperature in the cabin With the planned temperature T p So we can get the difference: ;

[0077] In summary, the relationship between temperature difference and compressor speed is: ;

[0078] The real-time temperature in the cabin can be obtained through experimental data The nonlinear relationship between the control input u satisfies the following equation: ,

[0079] Therefore, f(u) is designed as the following dynamic equation: ;

[0080] Then we can further get: ;

[0081] Then the real-time temperature in the cabin At control time t p Converge to a sufficiently small value and complete the control process.

[0082] Through the above steps, we first consider the differences in human metabolic rate in different seasons, different times, different temperatures and humidity conditions to obtain the human metabolic rate value P, then obtain the current passenger's thermal habits through the PMV calculator, and then optimize the development of the planned temperature in the car based on vehicle speed, passenger thermal comfort, weather information, and passenger number and weight information to achieve low energy consumption and good passenger thermal comfort.

[0083] It should be noted that in the above step S1, in order to more accurately predict the current human metabolic rate value, it is necessary to train the first neural network model in advance. The training method includes: training the first neural network model through multiple sets of training time information and training environment information, so that the first neural network model outputs a human metabolic rate that conforms to the actual situation according to the time information and environmental information.

[0084] For ease of understanding, Figure 4 and Figure 5 As shown, a preferred training method is provided as follows.

[0085] A1. Input training time information and training environment information to the first neural network model 100 (ie, BP neural network topology structure), so that the first neural network model outputs a training human metabolic rate value P.

[0086] In this embodiment, the training sequence is pre-set before training, wherein the training time information sequence includes all the time information, and the training environment information includes different temperature and humidity information, etc. Thus, in each round of training, the first neural network model outputs different human metabolic rates according to different input parameters.

[0087] Alternatively, if Figure 5 As shown, the input parameter information 200 includes: the training time information sequence includes m={1,2,...,12}, the time (hour) t={1,2,...,24}, etc. The training environment information includes the cabin relative humidity H a =40%~70%, and cabin temperature T a wait.

[0088] A2. Obtain the thermal habits of the passenger according to the training human metabolic rate value, so as to obtain the training temperature in combination with the real-time first reference information.

[0089] In this embodiment, the specific implementation method of calculating the passenger's thermal habits according to the human metabolic rate value can be obtained by the predicted mean vote (PMV) calculator 300. The specific calculation method is the same as above and will not be repeated here.

[0090] Furthermore, the first reference information is consistent with the above, including vehicle speed, passenger thermal comfort, weather information, number and weight of passengers, etc. The most comfortable temperature calculator 400 uses a dynamic programming algorithm to combine the passengers' thermal habits and the first reference information to obtain the planned temperature for training, i.e., the training temperature.

[0091] A3. Control the car air conditioner to adjust the temperature in the car passenger compartment to the training temperature.

[0092] In this embodiment, after the temperature in the passenger compartment of the car is adjusted to the training temperature, the complete adjustment steps from input parameters to temperature are completed in this round of training.

[0093] A4. The tester adjusts the temperature in the passenger cabin to a comfortable temperature based on the perceived comfort level of the training temperature.

[0094] In this embodiment, whether the training temperature is comfortable and appropriate still needs to be actually felt by the test personnel. During the training stage, since the human metabolic rate value P output by the first training model is inaccurate, the training temperature finally output is inappropriate. At this time, the test personnel need to adjust the cabin temperature from the training temperature to the comfortable temperature.

[0095] A5. Re-input the comfortable temperature into the first neural network model, and repeat the above steps until the first human metabolic rate value output by the first neural network model can directly obtain the comfortable temperature without intervention by the tester.

[0096] In this embodiment, the comfortable temperature is the best temperature obtained in the previous round of training according to the input training time information and training environment information. Therefore, the comfortable temperature is used as one of the training environment information in the next round of training, and the first neural network model continues to train until the human metabolic rate value output by the first neural network model can reach the most ideal state, and the first neural network model is obtained:

[0097] P=f(m,t,T a ,H a );

[0098] Among them, m represents the month, and the value range is 1 to 12; t represents the time, and the value range is 1 to 24; T a Represents the cabin temperature, H a Represents relative humidity, ranging from 40% to 70%.

[0099] In the most ideal state, the first human metabolic rate value output by the first neural network model can directly obtain the comfortable temperature without the intervention of the tester. At this time, the first neural network model training is completed and can be used to estimate the human metabolic rate value in actual work.

[0100] Furthermore, the embodiment of the present application also provides a vehicle air conditioning control device for controlling the air conditioning temperature in the vehicle passenger compartment, for implementing the aforementioned method of the embodiment of the present application, wherein: Figure 6 As shown, the device comprises:

[0101] A first acquisition unit 10 is used to acquire the thermal habit of the passenger according to the human metabolic rate value, where the thermal habit is a quantitative evaluation value of the passenger's current thermal sensation;

[0102] A second acquisition unit 20 is used to acquire first reference information affecting the temperature inside the vehicle, wherein the reference information includes at least one of measurement information detected by a vehicle sensor and external information acquired from the outside;

[0103] A calculation unit 30, configured to obtain a planned temperature according to the thermal habit obtained by the first obtaining unit 10 and the first reference information obtained by the second obtaining unit 20;

[0104] The control unit 40 is used to control the automobile air conditioner to adjust the temperature in the automobile passenger compartment to the planned temperature calculated by the calculation unit 30 .

[0105] In the present embodiment, the automobile air conditioning control device optimizes the development of the planned temperature in the car according to information such as vehicle speed, passenger thermal comfort, weather information, and the number and weight of passengers, so as to achieve low energy consumption and good passenger thermal comfort. Then, the temperature tracking control algorithm is used to adjust the compressor speed and the heater power to adjust the temperature so that the actual temperature in the car reaches the planned temperature. On the other hand, regarding PMV calculation, the existing literature generally assumes that the human metabolic rate value P is a certain constant, but in real life, the human metabolic rate is different in different seasons, different times, different temperature and humidity, etc. Therefore, the present application intends to estimate the metabolic rate P based on the neural network model. More accurate and in line with the actual situation.

[0106] Furthermore, the present application also provides a vehicle air conditioning control system for controlling the air conditioning temperature in the vehicle passenger compartment, such as Figure 7 As shown, it includes: a decision estimation layer 1000 and a local control layer 2000, wherein:

[0107] The decision estimation layer 1000 is used to perform the above steps S1 to S3, that is, the decision estimation layer 1000 uses a dynamic programming algorithm to optimize the development of the planned temperature in the vehicle according to information such as vehicle speed, passenger thermal comfort, weather information, and the number and weight of passengers, so as to achieve low energy consumption and good passenger thermal comfort. Further, the decision estimation layer 1000 sends the obtained planned temperature to the local control layer 2000, which uses a temperature tracking control algorithm to adjust the compressor speed and heater power to adjust the temperature so that the actual vehicle temperature reaches the planned temperature.

[0108] In this way, the idea of ​​hierarchical control is realized. As two preferred implementation methods, the decision estimation layer and the local control layer can be both set in the car terminal, or the decision estimation layer can be set in the remote cloud server and the local control layer can be set in the local car terminal. The decision estimation layer and the local control layer are remotely connected through the network, thereby making full use of the cloud computing power and reducing the computing power cost of the car.

[0109] The present invention also provides a computer-readable storage medium. The computer-readable storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the following steps:

[0110] Obtaining the passenger's thermal habit based on the human metabolic rate value, wherein the thermal habit is a quantitative evaluation value of the passenger's current thermal sensation;

[0111] Acquire first reference information affecting the temperature inside the vehicle, wherein the reference information includes at least one of measurement information detected by a vehicle sensor and external information acquired from the outside;

[0112] acquiring a planned temperature according to the thermal habit and the first reference information;

[0113] The vehicle air conditioner is controlled to adjust the temperature in the vehicle passenger compartment to the planned temperature.

[0114] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0115] In summary, the automobile air conditioning control method, device, system and medium provided by the present invention include: obtaining the thermal habits of passengers according to the human metabolic rate value, the thermal habits being the quantitative evaluation value of the passenger's current thermal sensation; obtaining the first reference information affecting the temperature inside the vehicle, the reference information including the measurement information detected by the vehicle sensor, and at least one of the external information obtained from the outside; obtaining the planned temperature according to the thermal habits and the first reference information; and controlling the automobile air conditioning to adjust the temperature inside the passenger compartment of the vehicle to the planned temperature. By using a dynamic programming algorithm, the development of the planned temperature inside the vehicle is optimized according to information such as vehicle speed, passenger thermal comfort, weather information, and the number and weight of passengers, so as to achieve low energy consumption and good passenger thermal comfort. Then, using a temperature tracking control algorithm, the compressor speed and heater power are adjusted to adjust the passenger compartment temperature to the planned temperature.

[0116] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0117] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0118] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0119] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0120] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for controlling the air-conditioning temperature in a passenger compartment of a vehicle, characterized in that: include: Obtaining the passenger's thermal habit based on the human metabolic rate value, wherein the thermal habit is a quantitative evaluation value of the passenger's current thermal sensation; Acquire first reference information affecting the temperature inside the vehicle, wherein the reference information includes at least one of measurement information detected by a vehicle sensor and external information acquired from the outside; acquiring a planned temperature according to the thermal habit and the first reference information; Controlling the vehicle air conditioner to adjust the temperature in the vehicle passenger compartment to the planned temperature; Before obtaining the thermal habits of the passenger according to the human metabolic rate value, the method further includes obtaining the human metabolic rate value, including: Inputting second reference information into the first neural network model, wherein the second reference information includes time information and at least one of environmental information detected by a vehicle sensor; Obtaining the human metabolic rate value output by the first neural network model according to the second reference information; The time information includes at least one of the current month or the current time; the environmental information includes at least one of the current temperature or relative humidity in the passenger compartment; Before obtaining the human metabolic rate value, the method further includes: Training the first neural network model using multiple sets of training time information and training environment information, so that the first neural network model outputs a human metabolic rate that conforms to actual conditions according to the time information and the environment information; The training of the first neural network model by using multiple sets of training time information and training environment information includes: Inputting the training time information and the training environment information into the first neural network model so that the first neural network model outputs a training human metabolic rate value; Acquiring the thermal habits of the passenger according to the training human metabolic rate value, so as to acquire the training temperature in combination with the first reference information in real time; Controlling the vehicle air conditioner to adjust the temperature in the vehicle passenger compartment to the training temperature; The tester adjusts the temperature in the passenger cabin to a comfortable temperature based on the perceived comfort level of the training temperature; Re-input the comfortable temperature into the first neural network model, and return to the step of inputting the training time information and the training environment information into the first neural network model so that the first neural network model outputs a training human metabolic rate value, until the first human metabolic rate value output by the first neural network model can directly obtain the comfortable temperature without intervention by the tester.

2. The method according to claim 1, characterized in that The measurement information includes at least one of vehicle speed, number of passengers and vehicle load; and the external information includes weather information.

3. The method according to claim 1, characterized in that The controlling of the automobile air conditioner to adjust the temperature in the automobile passenger compartment to the planned temperature comprises: Obtaining the planned temperature; Get the real-time temperature in the passenger cabin; According to the planned temperature and the real-time temperature, the compressor speed and / or the heater power are adjusted by a temperature tracking control algorithm to adjust the temperature in the passenger compartment from the real-time temperature to the planned temperature.

4. An automobile air conditioning control device for controlling the air conditioning temperature in the passenger compartment of an automobile, characterized in that: include: A first acquisition unit is used to acquire the thermal habit of the passenger according to the human metabolic rate value, wherein the thermal habit is a quantitative evaluation value of the passenger's current thermal sensation; A second acquisition unit, configured to acquire first reference information affecting the temperature inside the vehicle, wherein the reference information includes at least one of measurement information detected by a vehicle sensor and external information acquired from the outside; a calculation unit, configured to obtain a planned temperature according to the thermal habit obtained by the first obtaining unit and the first reference information obtained by the second obtaining unit; A control unit, used for controlling the automobile air conditioner to adjust the temperature in the passenger compartment of the automobile to the planned temperature calculated by the calculation unit; Before executing the step of obtaining the thermal habits of the passenger according to the human metabolic rate value, the automobile air conditioning control device further obtains the human metabolic rate value, specifically: inputting second reference information into the first neural network model, the second reference information including time information and at least one of environmental information detected by the automobile sensor; obtaining the human metabolic rate value output by the first neural network model according to the second reference information; The time information includes at least one of the current month or the current time; the environmental information includes at least one of the current temperature or relative humidity in the passenger compartment; Before executing the step of obtaining the human metabolic rate value, the automobile air conditioning control device further executes: training the first neural network model through multiple sets of training time information and training environment information, so that the first neural network model outputs a human metabolic rate that conforms to the actual situation according to the time information and the environment information; When executing the step of training the first neural network model by using multiple sets of training time information and training environment information, the automobile air conditioning control device specifically performs the following steps: inputting the training time information and the training environment information into the first neural network model so that the first neural network model outputs a training human metabolic rate value; obtaining the thermal habits of passengers according to the training human metabolic rate value to obtain a training temperature in combination with the real-time first reference information; and controlling the automobile air conditioning to adjust the temperature in the passenger compartment of the automobile to the training temperature; The tester adjusts the temperature in the passenger compartment to a comfortable temperature based on the perceived comfort of the training temperature; re-inputs the comfortable temperature into the first neural network model, and returns to execute the step of inputting the training time information and the training environment information into the first neural network model so that the first neural network model outputs a training human metabolic rate value, until the first human metabolic rate value output by the first neural network model can directly obtain the comfortable temperature without intervention by the tester.

5. An automobile air conditioning control system, used to control the air conditioning temperature in the passenger compartment of an automobile, characterized in that: include: Decision estimation layer and local control layer, where The decision estimation layer is used to: Obtaining the passenger's thermal habit based on the human metabolic rate value, wherein the thermal habit is a quantitative evaluation value of the passenger's current thermal sensation; Acquire first reference information affecting the temperature inside the vehicle, wherein the reference information includes at least one of measurement information detected by a vehicle sensor and external information acquired from the outside; acquiring a planned temperature according to the thermal habit and the first reference information; The local control layer is used to: Obtaining the planned temperature from the decision estimation layer; Controlling the vehicle air conditioner to adjust the temperature in the vehicle passenger compartment to the planned temperature; Before executing the step of obtaining the thermal habits of the passenger according to the human metabolic rate value, the automobile air conditioning control system further obtains the human metabolic rate value, specifically: inputting second reference information into the first neural network model, the second reference information including time information and at least one of environmental information detected by the automobile sensor; obtaining the human metabolic rate value output by the first neural network model according to the second reference information; The time information includes at least one of the current month or the current time; the environmental information includes at least one of the current temperature or relative humidity in the passenger compartment; Before executing the step of obtaining the human metabolic rate value, the automobile air conditioning control system further executes: training the first neural network model through multiple sets of training time information and training environment information, so that the first neural network model outputs a human metabolic rate that conforms to the actual situation according to the time information and the environment information; When executing the step of training the first neural network model using multiple sets of training time information and training environment information, the automobile air conditioning control system specifically performs the following steps: inputting the training time information and the training environment information into the first neural network model so that the first neural network model outputs a training human metabolic rate value; obtaining the thermal habits of the passenger based on the training human metabolic rate value to obtain the training temperature in combination with the real-time first reference information; controlling the automobile air conditioning to adjust the temperature in the passenger compartment of the automobile to the training temperature; the tester adjusts the temperature in the passenger compartment to a comfortable temperature based on the perceived comfort of the training temperature; re-inputting the comfortable temperature into the first neural network model, and returning to execute the step of inputting the training time information and the training environment information into the first neural network model so that the first neural network model outputs a training human metabolic rate value, until the first human metabolic rate value output by the first neural network model can directly obtain the comfortable temperature without the intervention of the tester.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to execute the automobile air-conditioning control method as described in any one of claims 1 to 3.

Images