CN114379325A - Method for adjusting temperature of vehicle-mounted air conditioner and related device - Google Patents
Method for adjusting temperature of vehicle-mounted air conditioner and related device Download PDFInfo
- Publication number
- CN114379325A CN114379325A CN202210163862.0A CN202210163862A CN114379325A CN 114379325 A CN114379325 A CN 114379325A CN 202210163862 A CN202210163862 A CN 202210163862A CN 114379325 A CN114379325 A CN 114379325A
- Authority
- CN
- China
- Prior art keywords
- temperature
- vehicle
- air conditioner
- mounted air
- dimension
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60H—ARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
- B60H1/00—Heating, cooling or ventilating [HVAC] devices
- B60H1/00642—Control systems or circuits; Control members or indication devices for heating, cooling or ventilating devices
- B60H1/0073—Control systems or circuits characterised by particular algorithms or computational models, e.g. fuzzy logic or dynamic models
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60H—ARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
- B60H1/00—Heating, cooling or ventilating [HVAC] devices
- B60H1/00642—Control systems or circuits; Control members or indication devices for heating, cooling or ventilating devices
- B60H1/00735—Control systems or circuits characterised by their input, i.e. by the detection, measurement or calculation of particular conditions, e.g. signal treatment, dynamic models
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60H—ARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
- B60H1/00—Heating, cooling or ventilating [HVAC] devices
- B60H1/00642—Control systems or circuits; Control members or indication devices for heating, cooling or ventilating devices
- B60H1/00735—Control systems or circuits characterised by their input, i.e. by the detection, measurement or calculation of particular conditions, e.g. signal treatment, dynamic models
- B60H1/0075—Control systems or circuits characterised by their input, i.e. by the detection, measurement or calculation of particular conditions, e.g. signal treatment, dynamic models the input being solar radiation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60H—ARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
- B60H1/00—Heating, cooling or ventilating [HVAC] devices
- B60H1/00642—Control systems or circuits; Control members or indication devices for heating, cooling or ventilating devices
- B60H1/00735—Control systems or circuits characterised by their input, i.e. by the detection, measurement or calculation of particular conditions, e.g. signal treatment, dynamic models
- B60H1/00785—Control systems or circuits characterised by their input, i.e. by the detection, measurement or calculation of particular conditions, e.g. signal treatment, dynamic models by the detection of humidity or frost
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Thermal Sciences (AREA)
- Mechanical Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Air-Conditioning For Vehicles (AREA)
Abstract
The application provides a temperature adjusting method of a vehicle-mounted air conditioner, which comprises the following steps: the method comprises the steps of modeling the relation between the temperature of the vehicle-mounted air conditioner and a multi-dimensional temperature influence factor according to historical data to obtain a temperature prediction model, obtaining the current value of the multi-dimensional temperature influence factor of the vehicle-mounted air conditioner during temperature adjustment, obtaining the predicted value of the set temperature of the vehicle-mounted air conditioner according to the current value and the temperature prediction model, and setting the temperature of the vehicle-mounted air conditioner based on the predicted value, so that the temperature adjustment of the vehicle-mounted air conditioner is realized. Because the multidimensional temperature influence factor is considered, the set temperature can be accurately predicted, the user is helped to realize the intelligent temperature adjustment of the vehicle-mounted air conditioner, and therefore the vehicle using experience of the user is improved to a great extent, and the comfort level in the vehicle is improved.
Description
Technical Field
The application relates to the technical field of vehicle networking, in particular to a method for adjusting the temperature of a vehicle-mounted air conditioner and a related device.
Background
To improve comfort, more and more vehicles are equipped with on-board air conditioners. When using the vehicle air conditioner, it is usually necessary to set a proper temperature so as to provide a user with a space in the vehicle with a proper temperature. Based on this, how to set a proper temperature becomes a problem of important attention in the industry.
At present, a temperature setting method of a vehicle-mounted air conditioner mainly determines a target temperature of the vehicle-mounted air conditioner by using external environment such as external temperature and direct sunlight information. The technology calculates a difference value between the external temperature and the target temperature, and determines a first supplement temperature corresponding to the temperature difference value when the difference value is greater than a preset temperature threshold value. And adjusting the initial temperature of the vehicle-mounted air conditioner according to the first supplementary temperature, so as to obtain the target temperature of the vehicle-mounted air conditioner.
However, the data referred to by the method for determining the target temperature is relatively single, which easily causes inaccurate temperature adjustment.
Disclosure of Invention
An object of the application is to provide a temperature regulation method of a vehicle-mounted air conditioner, so that the problem that data referred to for determining a target temperature in the correlation technique is single, and inaccurate temperature regulation is easily caused is solved, a user is helped to realize intelligent temperature regulation of the vehicle-mounted air conditioner, and accordingly the user's vehicle using experience is improved to a great extent, and the comfort level in a vehicle is improved.
The application can be realized by the following technical solutions:
in a first aspect, the present application provides a method for adjusting a temperature of a vehicle air conditioner. The method comprises the following steps:
acquiring the current value of the multidimensional temperature influence factor of the vehicle-mounted air conditioner;
obtaining a predicted value of the set temperature of the vehicle-mounted air conditioner according to the current value of the multidimensional temperature influence factor and a temperature prediction model, wherein the temperature prediction model is a model of the temperature of the vehicle-mounted air conditioner and the multidimensional temperature influence factor which is established through a deep learning algorithm according to historical data;
and setting the temperature of the vehicle-mounted air conditioner according to the predicted value so as to realize temperature regulation of the vehicle-mounted air conditioner.
In some possible implementations, the multi-dimensional temperature influencing factor includes temperature influencing factors in any two or more of the following dimensions:
a time dimension, an air conditioning dimension, an environmental dimension, a location dimension, a vehicle dimension, and a user perception dimension.
In some possible implementations, the temperature influencing factor of the time dimension includes a collection time, the temperature influencing factor of the air conditioner dimension includes one or more of an air conditioner circulation mode, an air conditioner switch, and an air conditioner target temperature, the temperature influencing factor of the environment dimension includes one or more of an atmospheric pressure, an outside temperature, an inside temperature, a precipitation amount, a wind speed, an air humidity, and an illumination intensity, the temperature influencing factor of the location dimension includes one or more of a longitude and a latitude, the temperature influencing factor of the vehicle dimension includes one or more of a vehicle identification code, a vehicle type, and the user perceived dimension includes one or more of a user's preference for cooling and heating, and a user's sensible temperature.
In some possible implementations, the temperature prediction model is obtained by training a long-short term memory network LSTM.
In some possible implementations, the temperature prediction model is trained by:
standardizing and cleaning the historical data;
performing characteristic engineering on the cleaned data to obtain a plurality of characteristics;
training the LSTM according to the plurality of features.
In some possible implementations, the cleaned data includes an outside temperature, an air pressure, an air speed, a relative humidity, a vehicle identification code, and an inside temperature, and the performing feature engineering on the cleaned data to obtain a plurality of features includes:
determining the cold and hot preference of a user according to the vehicle identification code, the in-vehicle temperature and the out-vehicle temperature;
and determining the body sensing temperature of the user according to the temperature outside the vehicle, the air pressure, the air speed and the relative humidity.
In some possible implementations, the method further includes:
determining the importance of the plurality of features by principal component analysis;
and screening K features with the importance meeting the conditions according to the importance of the features for training the LSTM, wherein K is a positive integer.
In a second aspect, the present application provides a thermostat for a vehicle air conditioner. The device comprises:
the acquisition module is used for acquiring the current value of the multidimensional temperature influence factor of the vehicle-mounted air conditioner;
the prediction module is used for obtaining a predicted value of the set temperature of the vehicle-mounted air conditioner according to the current value of the multidimensional temperature influence factor and a temperature prediction model, and the temperature prediction model is a model of the temperature of the vehicle-mounted air conditioner and the multidimensional temperature influence factor which is established through a deep learning algorithm according to historical data;
and the setting module is used for setting the temperature of the vehicle-mounted air conditioner according to the predicted value so as to realize the temperature regulation of the vehicle-mounted air conditioner.
In some possible implementations, the multi-dimensional temperature influencing factor includes temperature influencing factors in any two or more of the following dimensions:
a time dimension, an air conditioning dimension, an environmental dimension, a location dimension, a vehicle dimension, and a user perception dimension.
In some possible implementations, the temperature influencing factor of the time dimension includes a collection time, the temperature influencing factor of the air conditioner dimension includes one or more of an air conditioner circulation mode and an air conditioner switch, the temperature influencing factor of the environment dimension includes one or more of atmospheric pressure, temperature outside the vehicle, temperature inside the vehicle, precipitation, wind speed, air humidity and illumination intensity, the temperature influencing factor of the location dimension includes one or more of longitude and latitude, the temperature influencing factor of the vehicle dimension includes one or more of a vehicle identification code and a vehicle type, and the user perception dimension includes one or more of a user's preference for cold and hot, and a user's sensible temperature.
In some possible implementations, the temperature prediction model is obtained by training a long-short term memory network LSTM.
In some possible implementations, the apparatus further includes:
and the training module is used for standardizing and cleaning the historical data, performing characteristic engineering on the cleaned data to obtain a plurality of characteristics, and training the LSTM according to the plurality of characteristics.
In some possible implementation manners, the cleaned data includes an outside temperature, an air pressure, an air speed, a relative humidity, a vehicle identification code, and an inside temperature, and the training module is specifically configured to:
determining the cold and hot preference of a user according to the vehicle identification code, the in-vehicle temperature and the out-vehicle temperature;
and determining the body sensing temperature of the user according to the temperature outside the vehicle, the air pressure, the air speed and the relative humidity.
In some possible implementations, the training module is further to:
determining the importance of the plurality of features by principal component analysis;
and screening K features with the importance meeting the conditions according to the importance of the features for training the LSTM, wherein K is a positive integer.
In a third aspect, the present application provides a controller. The controller includes a processor and a memory. The processor and the memory are in communication with each other. The memory stores computer readable instructions which, when executed by the processor, cause the controller to perform the method of the first aspect of the present application.
In a fourth aspect, the present application provides a vehicle. The vehicle includes a controller and an on-board air conditioner. The controller is used for executing the method according to the first aspect of the application to realize the temperature adjustment of the vehicle-mounted air conditioner.
The present application can further combine to provide more implementations on the basis of the implementations provided by the above aspects.
Compared with the prior art, the temperature adjusting method of the vehicle-mounted air conditioner has the following beneficial effects:
according to the method, a temperature prediction model is obtained by modeling the relation between the temperature of the vehicle-mounted air conditioner and the multi-dimensional temperature influence factor according to historical data, so that the current value of the multi-dimensional temperature influence factor of the vehicle-mounted air conditioner can be obtained during temperature adjustment, then the predicted value of the set temperature of the vehicle-mounted air conditioner is obtained according to the current value and the temperature prediction model, and then the temperature of the vehicle-mounted air conditioner is set based on the predicted value, so that the temperature adjustment of the vehicle-mounted air conditioner is realized. Because the multidimensional temperature influence factor is considered, the set temperature can be accurately predicted, the user is helped to realize the intelligent temperature adjustment of the vehicle-mounted air conditioner, and therefore the vehicle using experience of the user is improved to a great extent, and the comfort level in the vehicle is improved.
Drawings
In order to more clearly illustrate the technical method of the embodiments of the present application, the drawings used in the embodiments will be briefly described below.
FIG. 1 is a flow chart of a method for training a temperature prediction model according to an embodiment of the present disclosure;
fig. 2 is a flowchart of a temperature adjustment method of a vehicle air conditioner according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a temperature adjustment device of a vehicle air conditioner according to an embodiment of the present application.
Detailed Description
The scheme in the embodiments provided in the present application will be described below with reference to the drawings in the present application. The terms "first," "second," and the like in the description and in the claims of the present application and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances and are merely descriptive of the various embodiments of the application and how objects of the same nature can be distinguished.
At present, a temperature setting method of a vehicle-mounted air conditioner mainly determines a target temperature of the vehicle-mounted air conditioner by using external environment such as external temperature and direct sunlight information. The technology calculates a difference value between the external temperature and the target temperature, and determines a first supplement temperature corresponding to the temperature difference value when the difference value is greater than a preset temperature threshold value. And adjusting the initial temperature of the vehicle-mounted air conditioner according to the first supplementary temperature, so as to obtain the target temperature of the vehicle-mounted air conditioner. However, the data referred to by the method for determining the target temperature is relatively single, which easily causes inaccurate temperature adjustment.
In view of this, the embodiment of the present application provides a temperature adjustment method for a vehicle-mounted air conditioner. The method comprises the steps of obtaining a current value of a multidimensional temperature influence factor of the vehicle-mounted air conditioner, obtaining a predicted value of a set temperature of the vehicle-mounted air conditioner according to the current value of the multidimensional temperature influence factor and a temperature prediction model, wherein the temperature prediction model is a model of the temperature of the vehicle-mounted air conditioner and the multidimensional temperature influence factor which is built through a deep learning algorithm according to historical data, and then setting the temperature of the vehicle-mounted air conditioner according to the predicted value so as to achieve temperature adjustment of the vehicle-mounted air conditioner.
Because the multidimensional temperature influence factor is considered, the set temperature can be accurately predicted, the user is helped to realize the intelligent temperature adjustment of the vehicle-mounted air conditioner, and therefore the vehicle using experience of the user is improved to a great extent, and the comfort level in the vehicle is improved.
The temperature adjusting method of the vehicle-mounted air conditioner in the embodiment of the application mainly depends on a temperature prediction model. The following describes the training process of the temperature prediction model with reference to the drawings.
In order to make the technical solution of the present application clearer and easier to understand, a temperature adjustment method of a vehicle air conditioner according to an embodiment of the present application is described below with reference to the accompanying drawings.
Referring to a flowchart of a temperature adjusting method of a vehicle air conditioner shown in fig. 1, the method includes:
s102: historical data is acquired.
Specifically, data of the vehicle during operation in a historical time period is collected, and data which may have an influence on the temperature setting of the vehicle-mounted air conditioner and a target temperature (set temperature) of the air conditioner are obtained by performing exploration and analysis on the data. The historical data can be roughly divided into a plurality of dimensions (types) such as a time dimension, an air conditioner dimension, an environment dimension, a position dimension, a vehicle dimension, a user perception dimension and the like:
TABLE 1 historical data
S104: and carrying out standardization processing on the historical data.
There are significant dimensional and magnitude differences between the above different dimensions of historical data. When the level difference between the data is large, if the original characteristic value is directly used for analysis, the function of the characteristic with higher value in the model is highlighted, and the function of the characteristic with lower value level is relatively weakened. Therefore, to ensure the reliability of the model results, the historical data may be normalized.
In the embodiment of the present application, a z-score normalization method may be adopted, in which the processed data conforms to a standard normal distribution, that is, the mean value is 0, the standard deviation is 1, and the transformation function is as follows:
it should be noted that the above-mentioned S104 is an optional step in the embodiment of the present application, and the method for executing the embodiment of the present application may not execute S104.
S106: and cleaning historical data.
In consideration of historical data acquired by the vehicle-mounted environment, data loss and vacancy caused by various reasons can exist, and the historical data can be cleaned. Specifically, for different variables, cleaning can be performed in different ways according to the distribution characteristics of the variables and the importance of the variables (which can be characterized by the information amount and the prediction capability).
The present application provides two cleaning strategies:
the first is to delete the variable, specifically, if the deletion rate of the variable is high, for example, greater than a first threshold, where the first threshold may be set according to an empirical value, and in some embodiments, the first threshold may be set to 80%, and the importance of the variable is low, the variable may be deleted directly.
The second is statistical filling, and in particular, if the missing rate of the variable is small, for example, smaller than a second threshold, which can be set according to an empirical value, for example, can be set to 5%, then filling can be performed according to the data distribution. In the filling, the mean or median of the data distribution may be filled, so that data cleansing may be achieved.
S108: and performing characteristic engineering on the cleaned data to obtain a plurality of characteristics.
Feature engineering is the process of utilizing relevant knowledge of the data domain to create features that enable machine learning algorithms to achieve optimal performance. In short, feature engineering is a process of transforming raw data into features that can describe the data well and the model built by using the features can perform optimally (or near-optimally) on unknown data. From a mathematical point of view, the feature engineering is to manually design the input variable X.
In this embodiment, the cleaned data includes an outside temperature, an air pressure, an air speed, a relative humidity, a vehicle identification code, and an inside temperature, the vehicle identification code VIN may be used to represent an Identifier (ID) of the user, and there is a certain difference in the preference of the user for the temperature, and by analyzing the vehicle identification code, the inside temperature, and the outside temperature in the history data, the preference of the user for the temperature, such as preference for hot, preference for cold, or neutral, may be determined. Furthermore, the sensible temperature of the user can be determined from the vehicle outside temperature (T), the air pressure (P), the wind speed (V), and the Relative Humidity (RH). The specific calculation formula is as follows:
AT＝1.07T+0.2e-0.65V-2.7 (1)
wherein, AT represents sensible temperature adaptive temperature, e represents vapor pressure, specifically the pressure of the generated vapor in the atmosphere, T represents the temperature outside the vehicle (ambient temperature), V represents the wind speed, and RH represents the relative humidity.
In addition, considering that users can obviously distinguish the adjustment and the use of the air conditioner at different time periods, the time data can be divided according to weekends, working days, early peaks, late peaks, seasons and the like on the basis of the time stamps, and the time characteristics are obtained as follows:
TABLE 2 temporal characteristics
In some possible implementation manners, the geographic position can be further divided into four regions according to the precision and the latitude, such as a north region, a south region, a southwest region and a northwest region, and the vehicle holding number, the driving frequency and the temperature feeling in different regions have different differences.
After data cleaning and feature engineering, the following features can be obtained:
TABLE 3 complete characterization
S110: determining the importance of the plurality of features through principal component analysis, and screening K features with the importance meeting conditions according to the importance of the plurality of features.
The feature screening is to retain the most important features from the high-dimensional feature data by a data preprocessing method and remove noise and unimportant features, thereby realizing the function of improving the calculation performance and the generalization capability of the model. The invention adopts PCA (principal Component analysis), namely a principal Component analysis method, which is the most widely used data dimension reduction algorithm, and converts a series of possible linearly related variables into a group of linearly unrelated new variables by using orthogonal transformation, thereby expressing the characteristics of data in smaller dimensions by using the new variables.
Assume that the input dataset X ═ X1,x2,x3,...,xnNeeds to be reduced to k dimension, calculatedThe method mainly comprises the following steps:
1) de-averaging (i.e., de-centering), i.e., each bit feature is subtracted by its respective average.
2) Calculation XXTThe covariance matrix M is calculated as follows:
Cov(X,Y)＝E[(X-E(X))(Y-E(Y))]
where E represents the expected value of the computation matrix.
3) And (3) calculating the eigenvalue and the eigenvector of the covariance matrix M by utilizing a matrix decomposition method (SVD), and selecting K vectors with the largest eigenvalue to form an eigenvector matrix P, thereby realizing the conversion of the data into K eigenvector spaces.
It should be noted that the method according to the embodiment of the present application may not perform S110.
S112: and training the long-term and short-term memory network LSTM by using the screened K characteristics to obtain a temperature prediction model.
The Long Short Term Memory (LSTM) is one of the most popular algorithms currently used in a time series prediction model, and the conventional BP neural network is propagated forward through neurons, so that samples are independent in a time dimension, and important time series information of time series data is lost. The LSTM can well utilize the time characteristic of data in the network, and hidden layer neurons rely on information of previous time, so that the circulation of time sequence behaviors of the data in the neural network is realized.
LSTM implements information protection and control through a 3-gate structure, these three gates being: forget gate, input gate, output gate.
1) Forgetting door
It determines the cell state c at the previous momentt-1How much to keep current time ct
Let the input of the neuron be x at time ttOutput is htThe cell state is ctThe weight is W and the offset is b. Forgetting gate at current moment reads last moment output ht-1And input x of the current timetReturning a forgetting gate state value f through a sigmoid functiont，ftIs calculated byThe formula is as follows:
ft＝σ(Wf.[ht-1,xt]+bf)
2) input gate
And calculating the unit state of the current input according to the output of the last time and the input of the current time.
Cell state c at the present timetFrom the last cell state ct-1By element by forgetting door ftReuse the current input state
Multiplying input Gate i by elementtThen, the two products are summed, and the calculation formula is as follows:
3) output gate
The output gate is also subjected to sigma function screening to obtain an output state value o between 0 and 1tThen using the tanh function and otObtaining the final output value h of the LSTM unitt：
σt＝σ(W.[HT-1,xt]+b0)
ht＝σt.tanh(Ct)
According to the method, the temperature prediction model is established by adopting the LSTM aiming at the collected data inside and outside the vehicle. The input data X of the model mainly comprises air conditioner parameters, vehicle internal and external environment data (internal and external temperature, air humidity, wind speed and the like), body sensing temperature, vehicle information, time data and the like, and the output data Y is the target temperature of the air conditioner. In a specific implementation, a temperature prediction model may be built based on a Tensorflow framework, and the temperature prediction model may include two layers of LSTMs, with 256 and 64 neurons, respectively. And then, carrying out model training by using the screened characteristics to obtain a temperature prediction model.
When performing model training, the features may be divided into different data sets, for example, the first 80% of the features are divided into a training set, and the last 20% of the features are divided into a testing set. Each sample data predicts, using the features of the previous _ size time points as input data, the history _ size +1 to history _ size +1+ target _ size target temperatures. The method comprises the steps of carrying out quantitative evaluation on the training effect of a model by adopting Root-mean-square error (RMSE) and fitting coefficients, wherein the smaller the RMSE value is, the smaller the deviation between a predicted value and a true value of the model is, and the more accurate the model prediction is; the closer the fitting coefficient is to 1, the greater the goodness of fit is, and the better the model fitting effect is. The specific formula is defined as follows:
wherein N is the number of samples used for prediction,
as a predicted value of the model, yiFor the true value of the model prediction,
is yiAverage value of (a). And setting the initial learning rate lr of model training to be 1e-4, the number of learned rounds Epoch to be 120 times, and after the model training is finished, the prediction accuracy is 96.58 percent, and the RMSE to be 0.023 predicts that the air-conditioning temperature is basically consistent with the target temperature.
For the model trained on the training set, the verification can be performed through the data of the test set. The accuracy of the test set is 89.48%, the accuracy is basically consistent with that of the training set, the error between the training result and the prediction result is closer and closer along with the increase of the iterative test, the predicted model is proved to have better generalization capability, and finally the prediction model of the set temperature of the air conditioner is stored and solidified, the solidified model can predict the target temperature of the air conditioner in a period of time in the future, and the intelligent regulation and control of the temperature of the air conditioner are facilitated.
After the temperature prediction model is trained based on the embodiment shown in fig. 1, the temperature prediction model can be used for predicting the set temperature of the vehicle-mounted air conditioner, so as to realize intelligent temperature adjustment of the vehicle-mounted air conditioner.
Referring to fig. 2, the method for adjusting the temperature of the vehicle air conditioner includes the steps of:
s202: and acquiring the current value of the multidimensional temperature influence factor of the vehicle-mounted air conditioner.
Specifically, current values of the temperature influence factors of different dimensions can be respectively collected through different sensors, and then the current values of the multi-dimensional temperature influence factors of the vehicle-mounted air conditioner are obtained from the different sensors. For example, the current value of the temperature influence factor of the location dimension may be acquired by vehicle navigation, such as Global Positioning System (GPS), and the current value of the temperature influence factor of the environment dimension, such as the outside temperature, the inside temperature, and the air humidity, may be measured by a thermometer and a hygrometer.
S204: and obtaining a predicted value of the set temperature of the vehicle-mounted air conditioner according to the current value of the multi-dimensional temperature influence factor and the temperature prediction model.
The temperature prediction model is a model of the temperature of the vehicle-mounted air conditioner and the multi-dimensional temperature influence factor, which is established through a deep learning algorithm such as LSTM according to historical data. The temperature prediction model takes the current value of the multidimensional temperature influence factor as input, and takes the predicted value of the set temperature (also called target temperature) of the vehicle-mounted air conditioner as output. Therefore, the current value of the multidimensional temperature influence factor is used as input, and the predicted value of the set temperature of the vehicle-mounted air conditioner is obtained based on the output of the temperature prediction model.
S206: and setting the temperature of the vehicle-mounted air conditioner according to the predicted value so as to realize temperature regulation of the vehicle-mounted air conditioner.
Specifically, the user may set the temperature of the Vehicle air conditioner to the predicted value by triggering a corresponding button or through an interface of an In-Vehicle Infotainment (IVI), thereby implementing the temperature condition of the Vehicle air conditioner.
According to the method, the set temperature of the air conditioner is predicted by taking the set temperature of the air conditioner expected by a user as a prediction target, and data mining modeling is carried out by combining data of different dimensions to predict the set temperature of the air conditioner, wherein the set temperature comprises parameters of the air conditioner, the internal and external environments of a vehicle, personal preference of the user, geographic positions, body sensing temperature and the like, and influence factors of the air conditioner temperature in time are reflected really. Moreover, the LSTM network is applied to the temperature setting prediction of the vehicle-mounted air conditioner, compared with the traditional method based on temperature deviation and threshold, the algorithm has higher precision and stronger robustness, and the landing effect in the vehicle-mounted environment is better. Further, when the temperature setting of the vehicle-mounted air conditioner is predicted, the temperature preference of different users and respective body sensing temperatures are considered, so that the predicted air conditioner temperature can improve the driving comfort of the users and can be accepted by the users more easily. In addition, the vehicle-mounted air conditioner temperature prediction can predict the set air conditioner temperature in a period of time in the future, the predicted time window can be dynamically adjusted, the intention of a future user can be predicted in advance, auxiliary services are recommended intelligently, and the driving experience of the user is improved.
Based on the methods provided by the embodiments shown in fig. 1 and fig. 2, the embodiment of the application also provides a temperature adjusting device of a vehicle-mounted air conditioner. The following describes a temperature control device of a vehicle air conditioner in detail with reference to the accompanying drawings.
Referring to a schematic structural view of a thermostat of a vehicle air conditioner shown in fig. 3, the thermostat 300 includes:
an obtaining module 302, configured to obtain a current value of a multidimensional temperature influence factor of the vehicle-mounted air conditioner;
the prediction module 304 is configured to obtain a predicted value of the set temperature of the vehicle-mounted air conditioner according to the current value of the multidimensional temperature influence factor and a temperature prediction model, where the temperature prediction model is a model of the temperature of the vehicle-mounted air conditioner and the multidimensional temperature influence factor, which is established through a deep learning algorithm according to historical data;
and the setting module 306 is used for setting the temperature of the vehicle-mounted air conditioner according to the predicted value so as to realize temperature adjustment of the vehicle-mounted air conditioner.
In some possible implementations, the multi-dimensional temperature influencing factor includes temperature influencing factors in any two or more of the following dimensions:
a time dimension, an air conditioning dimension, an environmental dimension, a location dimension, and a vehicle dimension.
In some possible implementations, the temperature influencing factor of the time dimension includes a collection time, the temperature influencing factor of the air conditioner dimension includes one or more of an air conditioner circulation mode and an air conditioner switch, the temperature influencing factor of the environment dimension includes one or more of an atmospheric pressure, an outside temperature, an inside temperature, a precipitation amount, a wind speed, an air humidity and an illumination intensity, the temperature influencing factor of the location dimension includes one or more of a longitude and a latitude, and the temperature influencing factor of the vehicle dimension includes one or more of a vehicle identification code and a vehicle type.
In some possible implementations, the temperature prediction model is obtained by training a long-short term memory network LSTM.
In some possible implementations, the apparatus further includes:
and the training module 308 is configured to normalize and clean the historical data, perform feature engineering on the cleaned data to obtain a plurality of features, and train the LSTM according to the plurality of features.
In some possible implementations, the cleaned data includes an outside temperature, an air pressure, an air speed, a relative humidity, a vehicle identification code, and an inside temperature, and the training module 308 is specifically configured to:
determining the cold and hot preference of a user according to the vehicle identification code, the in-vehicle temperature and the out-vehicle temperature;
and determining the body sensing temperature of the user according to the temperature outside the vehicle, the air pressure, the air speed and the relative humidity.
In some possible implementations, the training module 308 is further configured to:
determining the importance of the plurality of features by principal component analysis;
and screening K features with the importance meeting the conditions according to the importance of the features for training the LSTM, wherein K is a positive integer.
The method provided by the embodiment of the present application may be executed by a controller, where the controller may be a consumer control unit (VCU). The controller comprises a processor and a memory, wherein the memory stores computer readable instructions, and the processor executes the computer readable instructions to cause the controller to execute the method according to the embodiment shown in fig. 2 and fig. 3.
The present application further provides a vehicle. The vehicle comprises a controller and an on-board air conditioner, wherein the controller is used for executing the method according to the embodiment shown in the figures 2 and 3 so as to realize the temperature regulation of the on-board air conditioner.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by a person skilled in the art that the scope of the invention as referred to in the present application is not limited to the embodiments with a specific combination of the above-mentioned features, but also covers other embodiments with any combination of the above-mentioned features or their equivalents without departing from the inventive concept. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
It should be noted that the above-described system embodiments are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the system embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines.
Through the above description of the embodiments, those skilled in the art will clearly understand that the present application can be implemented by software plus necessary general-purpose hardware, and certainly can also be implemented by special-purpose hardware including special-purpose integrated circuits, special-purpose CPUs, special-purpose memories, special-purpose components and the like. Generally, functions performed by computer programs can be easily implemented by corresponding hardware, and specific hardware structures for implementing the same functions may be various, such as analog circuits, digital circuits, or dedicated circuits. However, for the present application, the implementation of a software program is more preferable. Based on such understanding, the technical solutions of the present application may be substantially embodied in the form of a software product, which is stored in a readable storage medium, such as a floppy disk, a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, an exercise device, or a network device) to execute the method according to the embodiments of the present application.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product.
The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, training device, or data center to another website site, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can store or a data storage device, such as a training device, a data center, etc., that incorporates one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
Claims (10)
1. A temperature adjusting method of a vehicle-mounted air conditioner is characterized by comprising the following steps:
acquiring the current value of the multidimensional temperature influence factor of the vehicle-mounted air conditioner;
obtaining a predicted value of the set temperature of the vehicle-mounted air conditioner according to the current value of the multidimensional temperature influence factor and a temperature prediction model, wherein the temperature prediction model is a model of the temperature of the vehicle-mounted air conditioner and the multidimensional temperature influence factor which is established through a deep learning algorithm according to historical data;
and setting the temperature of the vehicle-mounted air conditioner according to the predicted value so as to realize temperature regulation of the vehicle-mounted air conditioner.
2. The method of claim 1, wherein the multi-dimensional temperature influencing factors comprise temperature influencing factors in any two or more of the following dimensions:
a time dimension, an air conditioning dimension, an environmental dimension, a location dimension, a vehicle dimension, and a user perception dimension.
3. The method of claim 2, wherein the time dimension temperature impact factors comprise acquisition time, the air conditioning dimension temperature impact factors comprise one or more of air conditioning cycle mode, air conditioning switches, the environmental dimension temperature impact factors comprise one or more of atmospheric pressure, outside temperature, inside temperature, precipitation, wind speed, air humidity, and light intensity, the location dimension temperature impact factors comprise one or more of longitude and latitude, the vehicle dimension temperature impact factors comprise one or more of vehicle identification number, vehicle type, the user perceived dimension impact factors comprise: the user feels one or more of the temperature and the cold preference of the user.
4. The method of any one of claims 1 to 3, wherein the temperature prediction model is obtained by training a long-short term memory network (LSTM).
5. The method of claim 4, wherein the temperature prediction model is trained by:
standardizing and cleaning the historical data;
performing characteristic engineering on the cleaned data to obtain a plurality of characteristics;
training the LSTM according to the plurality of features.
6. The method of claim 5, wherein the cleaned data comprises an outside temperature, an air pressure, an air speed, a relative humidity, a vehicle identification code and an inside temperature, and the characteristic engineering is performed on the cleaned data to obtain a plurality of characteristics, comprising:
determining the cold and hot preference of a user according to the vehicle identification code, the in-vehicle temperature and the out-vehicle temperature;
and determining the body sensing temperature of the user according to the temperature outside the vehicle, the air pressure, the air speed and the relative humidity.
7. The method of claim 5, further comprising:
determining the importance of the plurality of features by principal component analysis;
and screening K features with the importance meeting the conditions according to the importance of the features for training the LSTM, wherein K is a positive integer.
8. A thermostat of a vehicle-mounted air conditioner, characterized in that the thermostat comprises:
the acquisition module is used for acquiring the current value of the multidimensional temperature influence factor of the vehicle-mounted air conditioner;
the prediction module is used for obtaining a predicted value of the set temperature of the vehicle-mounted air conditioner according to the current value of the multidimensional temperature influence factor and a temperature prediction model, and the temperature prediction model is a model of the temperature of the vehicle-mounted air conditioner and the multidimensional temperature influence factor which is established through a deep learning algorithm according to historical data;
and the setting module is used for setting the temperature of the vehicle-mounted air conditioner according to the predicted value so as to realize the temperature regulation of the vehicle-mounted air conditioner.
9. A controller, comprising a processor and a memory, the memory storing computer readable instructions, execution of the computer readable instructions by the at least one processor causing the controller to perform the method of any one of claims 1 to 7.
10. A vehicle, characterized in that the vehicle comprises a controller and an on-board air conditioner, the controller being configured to perform the method of any one of claims 1 to 7 to effect temperature regulation of the on-board air conditioner.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210163862.0A CN114379325A (en) | 2022-02-22 | 2022-02-22 | Method for adjusting temperature of vehicle-mounted air conditioner and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210163862.0A CN114379325A (en) | 2022-02-22 | 2022-02-22 | Method for adjusting temperature of vehicle-mounted air conditioner and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114379325A true CN114379325A (en) | 2022-04-22 |
Family
ID=81205691
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210163862.0A Pending CN114379325A (en) | 2022-02-22 | 2022-02-22 | Method for adjusting temperature of vehicle-mounted air conditioner and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114379325A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109899937A (en) * | 2019-03-12 | 2019-06-18 | 王馨仪 | Comfort level and the foreseeable air conditioning system of section and method based on LSTM model |
| CN110293818A (en) * | 2019-07-12 | 2019-10-01 | 腾讯科技（深圳）有限公司 | On-board air conditioner control method and device |
| US20200031195A1 (en) * | 2018-07-24 | 2020-01-30 | Saic Innovation Center Llc | Personalized adaptive hvac system control methods and devices |
| CN111251819A (en) * | 2020-01-03 | 2020-06-09 | 武汉理工大学 | Vehicle-mounted air conditioner intelligent adjusting method and system based on Internet of vehicles and big data |
| CN112050397A (en) * | 2020-08-27 | 2020-12-08 | 浙江省邮电工程建设有限公司 | Method and system for regulating and controlling temperature of machine room |
| CN112085285A (en) * | 2020-09-14 | 2020-12-15 | 南方电网数字电网研究院有限公司 | Bus load prediction method and device, computer equipment and storage medium |
| DE102020109299A1 (en) * | 2020-04-03 | 2021-10-07 | Bayerische Motoren Werke Aktiengesellschaft | Method for controlling an air conditioning device for a motor vehicle, air conditioning device and motor vehicle |
| CN114030336A (en) * | 2021-11-12 | 2022-02-11 | 上汽通用五菱汽车股份有限公司 | Air conditioner adjusting method and device, vehicle and computer readable storage medium |
-
2022
- 2022-02-22 CN CN202210163862.0A patent/CN114379325A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200031195A1 (en) * | 2018-07-24 | 2020-01-30 | Saic Innovation Center Llc | Personalized adaptive hvac system control methods and devices |
| CN109899937A (en) * | 2019-03-12 | 2019-06-18 | 王馨仪 | Comfort level and the foreseeable air conditioning system of section and method based on LSTM model |
| CN110293818A (en) * | 2019-07-12 | 2019-10-01 | 腾讯科技（深圳）有限公司 | On-board air conditioner control method and device |
| CN111251819A (en) * | 2020-01-03 | 2020-06-09 | 武汉理工大学 | Vehicle-mounted air conditioner intelligent adjusting method and system based on Internet of vehicles and big data |
| DE102020109299A1 (en) * | 2020-04-03 | 2021-10-07 | Bayerische Motoren Werke Aktiengesellschaft | Method for controlling an air conditioning device for a motor vehicle, air conditioning device and motor vehicle |
| CN113492641A (en) * | 2020-04-03 | 2021-10-12 | 宝马股份公司 | Method for controlling an air conditioning device of a motor vehicle, air conditioning device and motor vehicle |
| CN112050397A (en) * | 2020-08-27 | 2020-12-08 | 浙江省邮电工程建设有限公司 | Method and system for regulating and controlling temperature of machine room |
| CN112085285A (en) * | 2020-09-14 | 2020-12-15 | 南方电网数字电网研究院有限公司 | Bus load prediction method and device, computer equipment and storage medium |
| CN114030336A (en) * | 2021-11-12 | 2022-02-11 | 上汽通用五菱汽车股份有限公司 | Air conditioner adjusting method and device, vehicle and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108423005B (en) | Generation of feedback-based control model for autonomous vehicles | |
| CN111301426B (en) | Method for predicting energy consumption in future driving process based on GRU network model | |
| CN112289034A (en) | Deep neural network robust traffic prediction method based on multi-mode space-time data | |
| US11113168B2 (en) | Distributed architecture for fault monitoring | |
| CN110765980A (en) | Abnormal driving detection method and device | |
| US10402739B2 (en) | Method and device for determining a data-based functional model | |
| CN111460380B (en) | Multi-working-condition driving range prediction method and system based on Gaussian process regression | |
| CN114609008B (en) | Training method of gas concentration prediction model and gas concentration prediction method | |
| CN115858609A (en) | Electric vehicle charging pile state monitoring method, fault identification method and electronic equipment | |
| CN115759461A (en) | Internet of things-oriented multivariate time sequence prediction method and system | |
| CN114596726B (en) | Parking berth prediction method based on interpretable space-time attention mechanism | |
| CN113420506A (en) | Method for establishing prediction model of tunneling speed, prediction method and device | |
| CN104050349B (en) | External air temperature measuring apparatus and method | |
| CN112633074A (en) | Pedestrian information detection method and device, storage medium and electronic equipment | |
| CN114379325A (en) | Method for adjusting temperature of vehicle-mounted air conditioner and related device | |
| CN116384538A (en) | River basin runoff forecasting method, device and storage medium | |
| CN110009132A (en) | A kind of short-term electric load fining prediction technique based on LSTM deep neural network | |
| CN115079309A (en) | Method, device, equipment and medium for constructing prediction model of multi-type sea fog | |
| Carney et al. | Robust regional clustering and modeling of nonstationary summer temperature extremes across Germany | |
| CN112949947A (en) | Power failure early warning method and system based on convolution long-term and short-term memory network | |
| CN108960406B (en) | MEMS gyroscope random error prediction method based on BFO wavelet neural network | |
| CN113486748A (en) | Method for predicting friction coefficient of automatic driving road surface, electronic device and medium | |
| Fugiglando | Developing personal thermal comfort models for the control of HVAC in cars using field data | |
| CN111752976A (en) | Meteorological data processing method and device, computer equipment and readable storage medium | |
| CN110991685A (en) | Meteorological temperature prediction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |