CN115139746A - Method and system for automatically adjusting vehicle-mounted air conditioner - Google Patents
Method and system for automatically adjusting vehicle-mounted air conditioner Download PDFInfo
- Publication number
- CN115139746A CN115139746A CN202210958840.3A CN202210958840A CN115139746A CN 115139746 A CN115139746 A CN 115139746A CN 202210958840 A CN202210958840 A CN 202210958840A CN 115139746 A CN115139746 A CN 115139746A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- information
- user
- air conditioner
- conditioning
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000004378 air conditioning Methods 0.000 claims abstract description 63
- 230000007613 environmental effect Effects 0.000 claims abstract description 38
- 238000012549 training Methods 0.000 claims abstract description 29
- 230000008569 process Effects 0.000 claims abstract description 8
- 238000005286 illumination Methods 0.000 claims description 18
- 230000003750 conditioning effect Effects 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000010200 validation analysis Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 9
- 230000008859 change Effects 0.000 description 2
- 238000002790 cross-validation Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 201000003152 motion sickness Diseases 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 206010037660 Pyrexia Diseases 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
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
- B60H1/00735—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
- B60H1/00742—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 detection of the vehicle occupants' presence; by detection of conditions relating to the body of occupants, e.g. using radiant heat detectors
-
- 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
-
- 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
- B60H1/00964—Control systems or circuits characterised by including features for automatic and non-automatic control, e.g. for changing from automatic to manual control
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Thermal Sciences (AREA)
- Mechanical Engineering (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Air-Conditioning For Vehicles (AREA)
Abstract
The invention relates to a method for automatically adjusting a vehicle-mounted air conditioner, which comprises the following steps: collecting user information and environmental information of a vehicle (S1); training an air-conditioning model of the own vehicle based on the collected information, wherein the trained air-conditioning models of other vehicles of the same type and the same region are used as an initial model of the air-conditioning model of the own vehicle (S2); and automatically adjusting the vehicle-mounted air conditioner through the trained air conditioner adjusting model based on the current user information and the environmental information (S3). The invention also relates to a system for automatically adjusting an on-board air conditioner, a method for carrying out the method according to the invention and a vehicle comprising the system according to the invention. According to the invention, the air conditioner can be automatically adjusted according to the air conditioner use habit of the user without any operation of the user, the driving comfort is improved, and the frequent manual adjustment of the vehicle-mounted air conditioner by the user in the driving process is avoided.
Description
Technical Field
The present invention relates to the field of vehicles, in particular to a method for automatically adjusting an on-board air conditioner, a system for automatically adjusting an on-board air conditioner, a computer program product for performing the method according to the invention and a vehicle comprising the system according to the invention.
Background
As vehicle technology develops, more and more vehicles are equipped with automatic on-board air conditioners that are capable of automatically adjusting operating parameters (e.g., air volume) of the on-board air conditioners at a set target temperature so that the in-vehicle temperature quickly reaches and is maintained at the set target temperature. Such automatic vehicle air conditioners still require the user to manually set the target temperature. However, the working environment of the vehicle-mounted air conditioner is generally severe, for example, the external environments such as insolation, wind and snow, severe cold and the like are prone to have strong influence on the temperature change in the vehicle, and the space in the vehicle compartment is narrow, so the temperature change in the vehicle is severe, the driver is required to frequently adjust the target temperature to adjust the temperature in the vehicle to a comfortable temperature, and the frequent operation undoubtedly disperses the attention of the driver in the driving process.
Furthermore, the definition of the comfort of the user for the in-vehicle temperature is complex and fuzzy and has strong individual relevance, and especially the target temperatures desired to be set by different passengers in the same compartment may not be comparable at all.
Therefore, how to automatically adjust the vehicle-mounted air conditioner without any operation of a user becomes a technical problem to be solved at present.
Disclosure of Invention
It is an object of the present invention to provide a method for automatically adjusting a vehicle air conditioner, a system for automatically adjusting a vehicle air conditioner, a computer program product for performing the method according to the present invention and a vehicle comprising the system according to the present invention to solve the problems of the prior art. The core concept of the invention is that: and training an air-conditioning adjustment model based on the collected user information and environmental information, wherein the trained air-conditioning adjustment models of other vehicles of the same type and the same region are used as initial models of the air-conditioning adjustment model of the vehicle for training, and the vehicle-mounted air conditioner is automatically adjusted through the trained air-conditioning adjustment model. According to the invention, the air conditioner can be automatically adjusted according to the air conditioner use habit of the user without any operation of the user, the driving comfort is improved, and the frequent manual adjustment of the vehicle-mounted air conditioner by the user in the driving process is avoided.
According to a first aspect of the present invention, there is provided a method for automatically adjusting an in-vehicle air conditioner, the method comprising:
step S1: collecting user information and environmental information of the vehicle;
step S2: training an air-conditioning regulation model of the vehicle based on the collected information, wherein the trained air-conditioning regulation models of other vehicles of the same type and the same region are used as initial models of the air-conditioning regulation model of the vehicle; and
and step S3: and automatically adjusting the vehicle-mounted air conditioner through the trained air conditioner adjusting model based on the current user information and the current environment information.
According to an optional embodiment of the invention, the initial model of the vehicle's climate control model may be trained by machine learning algorithms comprising artificial neural networks, support vector machines and/or random forests based on the collected information.
According to an alternative embodiment of the invention, the method may further comprise:
and step S4: judging whether the user performs manual adjustment on the vehicle-mounted air conditioner or not in the operation process of automatic adjustment of the vehicle-mounted air conditioner;
step S5: if the user executes the manual adjustment of the vehicle-mounted air conditioner, recording the manual adjustment information of the vehicle-mounted air conditioner by the user and the user information and the environment information when the manual adjustment is executed, and exiting the automatic adjustment running mode of the vehicle-mounted air conditioner for a preset time period; and
step S6: training and updating an air conditioning adjustment model of the vehicle based on the recorded manual adjustment information, user information and environmental information.
By the method, the air conditioner adjusting model can be matched with the real requirements of the user more quickly and effectively, and the air conditioner adjusting strategy customized by the user is realized.
According to an alternative embodiment of the present invention, the step S2 may include:
step S21: dividing the collected information into a training data set and a testing data set according to a preset rule, wherein the training data set comprises a verification data set;
step S22: training an air conditioning regulation model of the vehicle based on the training data set, and evaluating the accuracy of a first regulation parameter output by the trained air conditioning regulation model based on the test data set;
step S23: further training the trained climate conditioning model based on the validation dataset and evaluating an accuracy of a second conditioning parameter output by the further trained climate conditioning model based on the test dataset;
step S24: judging whether the difference value between the accuracy of the first adjusting parameter and the accuracy of the second adjusting parameter is smaller than a preset threshold value or not; and
step S25: and if the difference value between the accuracy of the first adjusting parameter and the accuracy of the second adjusting parameter is smaller than a preset threshold value, stopping collecting the information corresponding to the verification data set.
By the method, the number of the vehicle-mounted sensors can be reduced and matched through the cross validation of data under the condition of ensuring the accuracy of certain air conditioner regulation model output parameters, so that the cost is controlled to the maximum extent.
According to an optional embodiment of the present invention, the user information comprises user identity information, user location information, user physical sign information and/or user air conditioner usage information, for example. The user information may be collected by a user information collection module. Illustratively, the user sign information comprises a heart rate of a user and/or a body surface temperature of the user, particularly the temperature of an exposed part of the skin, and the user sign information can be acquired through a thermal infrared imager and/or a wearable device; the user air conditioner use information comprises air conditioner set temperature, air volume and/or wind direction of each air conditioner air outlet and the like, the wind direction of the air conditioner air outlets comprises transverse wind direction and/or longitudinal wind direction, and the user air conditioner use information can be acquired through a vehicle-mounted air conditioner control panel; the user identity information and the user position information can be acquired through a camera in the vehicle.
According to an alternative embodiment of the invention, the environmental information comprises, for example, time information, vehicle position information, in-vehicle environmental information and/or out-of-vehicle environmental information. The environmental information may be collected by an environmental information collection module. For example, the vehicle position information may be acquired by a positioning sensor. The in-vehicle environment information includes, for example, an in-vehicle temperature and/or an in-vehicle humidity, where the temperature of each region in the vehicle compartment is acquired by an in-vehicle temperature sensor, and the humidity of each region in the vehicle compartment is acquired by an in-vehicle humidity sensor. The external environment information comprises external temperature, external humidity, external wind speed and/or external illumination intensity, wherein the external temperature is acquired through the external temperature sensor, the external humidity is acquired through the external humidity sensor, the external wind speed is acquired through the external wind speed sensor, and the external illumination intensity is acquired through the external illumination sensor.
According to an optional embodiment of the present invention, in step S3, an air conditioner adjustment model adapted to the current user identity information may be selected based on the current user identity information, and the current user information and the environmental information are used as input parameters of the selected air conditioner adjustment model, thereby outputting an adjustment parameter matched with the air conditioner usage habit of the current user for automatically adjusting the vehicle-mounted air conditioner.
According to a second aspect of the invention, a system for automatically adjusting an onboard air conditioner is provided, the system being adapted to perform the method according to the invention. The system comprises one or more of the following components: a user information collection module configured to collect user information; an environmental information collection module configured to collect environmental information; a control module configured to train an air conditioning model of the own vehicle based on the collected information and output a conditioning parameter through the trained air conditioning model based on current user information and environmental information; and the communication module is used for acquiring the trained air conditioning regulation models of other vehicles in the same type and region from the server and/or uploading the trained and/or updated air conditioning regulation models of the vehicle to the server.
According to a third aspect of the invention, a computer program product, such as a computer-readable program carrier, is provided, containing computer program instructions which, when executed by a processor, implement the steps of the method according to the invention.
According to a fourth aspect of the invention, a vehicle is provided, said vehicle comprising a system according to the invention.
Drawings
The principles, features and advantages of the present invention may be better understood by describing the invention in more detail below with reference to the accompanying drawings. The figures show:
fig. 1 illustrates a work flow diagram of a method for automatically adjusting an in-vehicle air conditioner according to an exemplary embodiment of the present invention;
fig. 2 illustrates an operational flow diagram of a method for automatically adjusting an in-vehicle air conditioner according to another exemplary embodiment of the present invention;
fig. 3 illustrates an operational flow diagram of a method for automatically adjusting an in-vehicle air conditioner according to still another exemplary embodiment of the present invention;
fig. 4 illustrates a block diagram of a system for automatically adjusting an in-vehicle air conditioner according to an exemplary embodiment of the present invention;
fig. 5 shows a schematic view of an exemplary air conditioning outlet according to the present invention; and
FIG. 6 illustrates a schematic contour diagram of an exemplary vehicle according to the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantageous technical effects of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings and exemplary embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the scope of the invention.
Fig. 1 illustrates an operational flowchart of a method for automatically adjusting an in-vehicle air conditioner according to an exemplary embodiment of the present invention. The following exemplary examples describe the process according to the invention in more detail.
The method comprises steps S1 to S3. In step S1, user information and environment information of the own vehicle are collected. In the current embodiment of the present invention, the user information includes, for example, user identity information, user location information, user physical sign information, and/or user air conditioner usage information, and the user information may be obtained by the user information collecting module 11. For example, the user identity information and the user location information (i.e., the location area of the user in the vehicle, including the main driving position, the assistant driving position, the left rear ranking and/or the right rear ranking) may be obtained by a camera in the vehicle through a face recognition technology. The user sign information comprises the heart rate of a user and/or the body surface temperature of the user, particularly the temperature of an exposed skin part, and can be acquired through a thermal infrared imager and/or a wearable device. The user air-conditioning usage information includes air-conditioning set temperature, air volume and/or wind direction of each air-conditioning outlet, and the like, and the wind direction of the air-conditioning outlet includes, for example, a transverse wind direction (herein, denoted as wind direction X) and/or a longitudinal wind direction (herein, denoted as wind direction Y) as shown in fig. 5. The air conditioner use information of the user in the process of manually adjusting the air conditioner by the user can be acquired through the vehicle-mounted air conditioner control panel.
The environmental information includes, for example, time information, vehicle position information, in-vehicle environmental information, and/or out-of-vehicle environmental information, which may be collected by the environmental information collection module 12. The vehicle position information, i.e., the vehicle position when the user manually adjusts the air conditioner, may be acquired, for example, by a positioning sensor, and at the same time, the time information when the user manually adjusts the air conditioner may be recorded. The in-vehicle environment information includes, for example, an in-vehicle temperature and/or an in-vehicle humidity, where, for example, the temperature of each region (including, for example, a main driver seat, a sub-driver seat, a left rear seat, and/or a right rear seat) inside the vehicle cabin may be acquired by an in-vehicle temperature sensor, and the humidity of each region inside the vehicle cabin may be acquired by an in-vehicle humidity sensor. As shown in fig. 6, the schematic outline of the exemplary vehicle according to the present invention, for example, the temperature of the primary driving seat obtained by the thermal infrared imager is labeled as temperature zone 1, the temperature of the secondary driving seat is labeled as temperature zone 2, the temperature of the right rear rank is labeled as temperature zone 3, and the temperature of the left rear rank is labeled as temperature zone 4. It should be noted that, here, only two rows of vehicle seats are shown by way of example, the reference numbers of the temperature ranges can be adjusted depending on the actual seating arrangement of the vehicle, for example, for a passenger vehicle with three rows of vehicle seats, the temperature ranges of the third left rear row and the third right rear row can be additionally marked, or for a passenger vehicle with only one row of vehicle seats, the temperature ranges of the zones of the main driving position and the temperature ranges of the secondary driving position can be marked.
Further, the off-board environment information includes, for example, an off-board temperature, an off-board humidity, an off-board wind speed, and/or an off-board illumination intensity. As shown in the outline diagram of the vehicle shown in fig. 6, for example, an outside temperature sensor 21, an outside illumination sensor 22 (which is integrated in the autopilot camera, for example), an outside wind speed sensor 23 (which is integrated in the antenna of the roof, for example), and/or an outside humidity sensor 24 are respectively arranged outside the vehicle, wherein, for example, the temperature of the environment outside the vehicle cabin can be acquired by the outside temperature sensor 21, the humidity of the environment outside the vehicle cabin can be acquired by the outside humidity sensor 24, the wind speed of the environment outside the vehicle cabin can be acquired by the outside wind speed sensor 23, and the illumination intensity of the environment outside the vehicle cabin can be acquired by the outside illumination sensor 22.
For example, the collected user information and environment information of the own vehicle may be stored in the form shown in table 1.
| Data classes | Data content |
| Time information (date-time) | 2022-3-24 18:45:30 |
| Geographic location | City |
| Driver/passenger | ID 234 |
| Ambient temperature of the environment | 20℃ |
| Humidity outside vehicle | 40％ |
| External wind speed of vehicle | 4m/s |
| Intensity of illumination outside of vehicle | 7Lux |
| Temperature zone | M (for example comprising 1-4) |
| In-vehicle temperature of temperature region M | 28℃ |
| Body surface temperature of person in temperature region M | 35℃ |
Table 1: collected user information and environmental information of the own vehicle
In step S2, the climate control model of the host vehicle is trained on the basis of the collected information, wherein the trained climate control models of other vehicles of the same type and region are used as initial models of the climate control model of the host vehicle. In the current embodiment of the present invention, when the on-vehicle air conditioner 32 of the own vehicle is initially used, since the air conditioning regulation model of the own vehicle has not learned the air conditioning usage habit of the user, the identity information of the user is not considered for the time being, and the trained air conditioning regulation models of other vehicles of the same type and the same region are directly adopted as the initial model of the air conditioning regulation model of the own vehicle. Here, trained air conditioning models of other vehicles of the same type and region can be obtained from the server 31 via the communication module 14 and stored in the control module 13 (e.g., electronic control unit) of the vehicle.
Here, an initial model of the climate adjustment model of the host vehicle may be trained by machine learning algorithms, including, for example, artificial neural networks, support vector machines, and/or random forests, based on the collected information. The control module 13 of the system 10 for automatically adjusting the vehicle air conditioner 32 can enable the air conditioner adjustment model of the vehicle to learn the air conditioner use habits of common users (including drivers and/or passengers) of the vehicle through the training and correspondingly modify the parameters of the air conditioner adjustment model of the vehicle.
In step S3, the on-board air conditioner 32 is automatically adjusted by the trained air conditioner adjustment model based on the current user information and environmental information. Here, it is possible to select an air conditioner adjustment model adapted to current user identity information based on the current user identity information, and use the current user information and environment information as input parameters of the selected air conditioner adjustment model, thereby outputting adjustment parameters matching with the air conditioner usage habits of the current user for automatically adjusting the in-vehicle air conditioner 32.
The output control parameters for controlling the vehicle air conditioner 32 are shown in table 2 by way of example. According to the schematic diagram of an exemplary air-conditioning outlet according to the invention shown in fig. 5, the outputted conditioning parameters include the outlet direction (i.e. the value of the transverse wind direction X and the value of the longitudinal wind direction Y) of the air-conditioning outlet 7 of the temperature area 1, the outlet air volume and the outlet temperature setting.
| Data classes | Data |
| Temperature region | |
| 1,7 air outlet direction | X:(0-180)Y:(0-180) |
| Air quantity of air outlet in |
3 |
| |
21℃ |
Table 2: outputted adjustment parameters for adjusting the on-board air conditioner 32
According to the present invention, the air conditioner can be automatically adjusted in accordance with the air conditioner use habit of the user without any operation of the user, driving comfort is improved, and the user is prevented from frequently manually adjusting the in-vehicle air conditioner 32 during driving.
Fig. 2 shows a work flow diagram of a method for automatically adjusting an in-vehicle air conditioner according to another exemplary embodiment of the present invention. Only the differences from the embodiment shown in fig. 1 are set forth below, and the same steps are not repeated for the sake of brevity.
The method may further comprise steps S4 to S6. In step S4, during the operation of the automatic adjustment of the in-vehicle air conditioner 32, it is determined whether the user performs manual adjustment of the in-vehicle air conditioner 32. It is understood that when the adjustment parameters output by the air conditioning adjustment model do not completely match the current air conditioning usage habits of the user (for example, the user has symptoms of fever, carsickness and the like), or when the environmental information changes drastically (for example, the weather changes suddenly, the air conditioning adjustment model enters or exits a long tunnel and the like) and the air conditioning adjustment model does not respond timely enough, the user usually chooses to manually adjust the setting parameters of the vehicle air conditioner.
If the user performs the manual adjustment of the in-vehicle air conditioner 32, manual adjustment information of the in-vehicle air conditioner 32 by the user and user information and environment information when the manual adjustment is performed are recorded and the automatic adjustment operation mode of the in-vehicle air conditioner 32 is exited for a preset time period (e.g., 20 minutes) in step S5. In particular, a body surface temperature, an in-vehicle temperature and/or an in-vehicle humidity can be recorded when the user performs the manual adjustment. The user's rhythm of the heart can also be recorded under the condition that the user carries wearable equipment (for example intelligent bracelet, intelligent wrist-watch etc.), and it is used for judging whether the user appears symptoms such as carsickness.
In step S6, an air conditioning adjustment model of the own vehicle is trained and updated based on the recorded manual adjustment information, user information, and environmental information. By the method, the air conditioner adjusting model can be matched with the real requirements of the user more quickly and effectively, and the method is favorable for realizing the air conditioner adjusting strategy customized by the user.
Fig. 3 illustrates an operational flowchart of a method for automatically adjusting an in-vehicle air conditioner according to still another exemplary embodiment of the present invention. Only the differences from the embodiment shown in fig. 1 are set forth below, and the description of the same steps is not repeated for the sake of brevity.
As shown in fig. 3, the step S2 may include S21 to S27. In step S21, the collected information is divided into a training data set and a testing data set according to a preset rule, wherein the training data set includes a verification data set. Here, the training data set is configured to train an air conditioning model of the own vehicle; the verification data set in the training data set is configured to further train the air-conditioning adjusting model of the vehicle and improve the accuracy of the output parameters of the air-conditioning adjusting model; the test data set is configured to evaluate an accuracy of a conditioning parameter output by the conditioning model of the air conditioner.
In step S22, the climate control model of the vehicle is trained based on the training data set, and the accuracy of the first adjustment parameter output by the trained climate control model is evaluated based on the test data set. In step S23, the trained climate conditioning model is further trained based on the validation data set, and the accuracy of the second conditioning parameter output by the further trained climate conditioning model is evaluated based on the test data set. In step S24, it is determined whether the difference between the accuracy of the first adjustment parameter and the accuracy of the second adjustment parameter is smaller than a preset threshold. If the difference between the accuracy of the first adjustment parameter and the accuracy of the second adjustment parameter is smaller than the preset threshold, which means that the improvement effect of the information corresponding to the verification data set on the accuracy of the output parameter of the air conditioning adjustment model is small, the collection of the information corresponding to the verification data set is stopped in step S25. Illustratively, the training data set includes, for example, an outside temperature, an inside temperature, and an outside illumination intensity, the verification data set includes the outside illumination intensity, and the outside illumination intensity mainly affects the outside temperature and the inside temperature, that is, there is a certain correlation between these three parameters. Because the temperature outside the vehicle and the temperature inside the vehicle are used as training parameter sets for training the air conditioner regulation model, the influence of the illumination intensity outside the vehicle as a verification data set on the accuracy of the output parameters of the air conditioner regulation model during further training of the air conditioner regulation model is small, and even overfitting of the training result of the air conditioner regulation model can be caused, so that the illumination intensity outside the vehicle can be stopped being collected by the illumination sensor outside the vehicle in the subsequent information collection process. It will be appreciated that the validation data sets may be selected according to different preset rules.
According to the alternative embodiment of the invention, when the collected data volume is large enough, the number of the vehicle-mounted sensors can be reduced through the cross validation of the data under the condition that certain accuracy of the output parameters of the air conditioner adjusting model is ensured, so that the cost is controlled to the maximum extent.
In addition, it should be noted that the sequence numbers of the steps described herein do not necessarily represent a sequential order, but merely one kind of reference numeral, and the order may be changed according to circumstances as long as the technical object of the present invention can be achieved.
Fig. 4 illustrates a block diagram of a system for automatically adjusting an in-vehicle air conditioner according to an exemplary embodiment of the present invention.
As shown in fig. 4, the system 10 includes one or more of the following components: a user information collecting module 11 configured to collect user information, the user information collecting module 11 including, for example, a thermal infrared imager, a wearable device, an in-vehicle camera, and/or an in-vehicle air conditioner control panel; an environmental information collection module 12 configured to collect environmental information, the environmental information collection module 12 including, for example, an outside-vehicle temperature sensor, an outside-vehicle humidity sensor, an outside-vehicle wind speed sensor, an outside-vehicle illumination sensor, a positioning sensor, an inside-vehicle temperature sensor, and/or an inside-vehicle humidity sensor; a control module 13 configured to train an air conditioning model of the own vehicle based on the collected information and output a conditioning parameter for automatically conditioning an on-board air conditioner 32 disposed outside the system 10 through the trained air conditioning model based on current user information and environmental information; a communication module 14, through which the trained air-conditioning model of the other vehicles of the same type and region is obtained from the server 31 and/or the trained and/or updated air-conditioning model of the vehicle is uploaded to the server 31.
Although specific embodiments of the invention have been described herein in detail, they have been presented for purposes of illustration only and are not to be construed as limiting the scope of the invention. Various alternatives and modifications can be devised without departing from the spirit and scope of the present invention.
Claims (10)
1. A method for automatically adjusting an on-board air conditioner (32), the method comprising:
step S1: collecting user information and environmental information of the vehicle;
step S2: training an air-conditioning regulation model of the vehicle based on the collected information, wherein the trained air-conditioning regulation models of other vehicles of the same type and the same region are used as initial models of the air-conditioning regulation model of the vehicle; and
and step S3: the vehicle air conditioner (32) is automatically adjusted through the trained air conditioner adjustment model based on the current user information and the environmental information.
2. The method according to any of the preceding claims, wherein the method further comprises:
and step S4: during the operation process of the automatic adjustment of the vehicle-mounted air conditioner (32), judging whether the user performs the manual adjustment of the vehicle-mounted air conditioner (32);
step S5: if the user performs manual adjustment of the vehicle-mounted air conditioner (32), recording manual adjustment information of the vehicle-mounted air conditioner (32) by the user and user information and environment information when the manual adjustment is performed, and exiting an automatic adjustment operation mode of the vehicle-mounted air conditioner (32) for a preset time period; and
step S6: training and updating an air conditioning adjustment model of the vehicle based on the recorded manual adjustment information, user information and environmental information.
3. The method according to any of the preceding claims, wherein said step S2 comprises:
step S21: dividing the collected information into a training data set and a testing data set according to a preset rule, wherein the training data set comprises a verification data set;
step S22: training an air conditioning model of the vehicle based on the training data set, and evaluating the accuracy of a first adjusting parameter output by the trained air conditioning model based on the testing data set;
step S23: further training the trained air conditioning model based on the validation dataset, and evaluating the accuracy of a second conditioning parameter output by the further trained air conditioning model based on the test dataset;
step S24: judging whether the difference value between the accuracy of the first adjusting parameter and the accuracy of the second adjusting parameter is smaller than a preset threshold value or not; and
step S25: and if the difference value between the accuracy of the first adjusting parameter and the accuracy of the second adjusting parameter is smaller than a preset threshold value, stopping collecting the information corresponding to the verification data set.
4. Method according to any one of the preceding claims, wherein the user information comprises user identity information, user location information, user sign information and/or user air conditioning usage information, wherein the user sign information comprises a heart rate of the user and/or a body surface temperature of the user, in particular a temperature of an exposed skin area, the user air conditioning usage information comprises an air conditioning setting temperature, an air volume and/or a wind direction of each air conditioning outlet, and the wind direction of the air conditioning outlet comprises a transverse wind direction and/or a longitudinal wind direction.
5. The method according to any of the preceding claims, wherein the environmental information comprises time information, vehicle position information, in-vehicle environmental information comprising in-vehicle temperature and/or in-vehicle humidity, and/or out-vehicle environmental information comprising out-vehicle temperature, out-vehicle humidity, out-vehicle wind speed and/or out-vehicle illumination intensity.
6. The method according to any one of the preceding claims, wherein the user information is collected by a user information collection module (11), wherein the user sign information is obtained by a thermal infrared imager and/or a wearable device, the user identity information and the user location information are obtained by an in-vehicle camera, and the user air-conditioning usage information is obtained by an in-vehicle air-conditioning control panel; and/or
Environmental information is collected through environmental information collection module (12), wherein, acquire the temperature of carriage external environment through outer temperature sensor (21), acquire the humidity of carriage external environment through outer humidity transducer (24), acquire the wind speed of carriage external environment through outer wind speed sensor (23), acquire the illumination intensity of carriage external environment through outer illumination sensor (22), acquire through positioning sensor vehicle positional information, acquire the temperature in each region of carriage inside through temperature sensor in the car, acquire the humidity in each region of carriage inside through humidity sensor in the car.
7. The method according to any one of the preceding claims, wherein in step S3, an air-conditioning adjustment model adapted to current user identity information is selected based on the current user identity information, and the current user information and environmental information are used as input parameters of the selected air-conditioning adjustment model, thereby outputting adjustment parameters matching with the air-conditioning usage habits of the current user for automatically adjusting the vehicle-mounted air conditioner; and/or
Training an initial model of an air conditioning model of the vehicle through a machine learning algorithm based on the collected information, wherein the machine learning algorithm comprises an artificial neural network, a support vector machine and/or a random forest.
8. A system (10) for automatically adjusting an on-board air conditioner (32), the system (10) being configured to perform the method according to any one of the preceding claims, wherein the system (10) comprises one or more of the following components:
a user information collection module (11) configured to collect user information;
an environmental information collection module (12) configured for collecting environmental information;
a control module (13) configured to train an air conditioning model of the own vehicle based on the collected information and output a conditioning parameter through the trained air conditioning model based on current user information and environmental information; and
a communication module (14) by means of which the trained climate control models of other vehicles of the same type and in the same region are obtained from the server (31) and/or the trained and/or updated climate control models of the vehicle are uploaded to the server (31).
9. A computer program product, such as a computer-readable program carrier, containing computer program instructions which, when executed by a processor, implement the steps of the method according to any one of the preceding claims.
10. A vehicle comprising a system (10) according to claim 8.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210958840.3A CN115139746A (en) | 2022-08-10 | 2022-08-10 | Method and system for automatically adjusting vehicle-mounted air conditioner |
| DE102023003240.9A DE102023003240A1 (en) | 2022-08-10 | 2023-08-05 | Method and system for automatically adjusting a vehicle air conditioning system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210958840.3A CN115139746A (en) | 2022-08-10 | 2022-08-10 | Method and system for automatically adjusting vehicle-mounted air conditioner |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115139746A true CN115139746A (en) | 2022-10-04 |
Family
ID=83416498
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210958840.3A Pending CN115139746A (en) | 2022-08-10 | 2022-08-10 | Method and system for automatically adjusting vehicle-mounted air conditioner |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115139746A (en) |
| DE (1) | DE102023003240A1 (en) |
-
2022
- 2022-08-10 CN CN202210958840.3A patent/CN115139746A/en active Pending
-
2023
- 2023-08-05 DE DE102023003240.9A patent/DE102023003240A1/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| DE102023003240A1 (en) | 2024-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11155141B2 (en) | Facilitating personalized vehicle occupant comfort | |
| US20170349027A1 (en) | System for controlling vehicle climate of an autonomous vehicle socially | |
| US9120365B2 (en) | Automatic temperature override pattern recognition system | |
| CN109733161B (en) | Intelligent control method for automobile air conditioner and vehicle-mounted system | |
| CN107584986A (en) | Climate controlling method and system | |
| US11634005B2 (en) | Automatic control of heating and cooling of a vehicle seating assembly pursuant to predictive modeling that recalibrates based on occupant manual control | |
| CN107771133A (en) | Automate atmosphere control system | |
| KR20170078732A (en) | Vehicle microclimate system and method of controlling same | |
| US10640137B2 (en) | Automatic control of a heating element in a steering wheel of a vehicle pursuant to predictive modeling that recalibrates based on occupant manual control of the heating element | |
| EP3582030A1 (en) | Method and system for smart interior of a vehicle | |
| CN109624649A (en) | A kind of control system for intelligent air condition | |
| US10675943B2 (en) | Method and apparatus for adaptive HVAC control | |
| US11163270B2 (en) | Vehicle occupant data collection and processing with artificial intelligence | |
| US20230103173A1 (en) | Machine learning algorithm for controlling thermal comfort | |
| CN115139746A (en) | Method and system for automatically adjusting vehicle-mounted air conditioner | |
| CN113492641A (en) | Method for controlling an air conditioning device of a motor vehicle, air conditioning device and motor vehicle | |
| CN117067857A (en) | Air conditioner parameter recommendation method, training device, training equipment and training medium for model | |
| CN110968341B (en) | Method and device for setting air conditioner parameters | |
| CN108068573A (en) | Air conditioner system control method and device applied to bus | |
| WO2023045717A1 (en) | Method and device for intelligent health management of a cabin of a vehicle | |
| US11167769B2 (en) | Method and apparatus for managing operator-selectable settings on-vehicle | |
| CN113386521A (en) | Control method and device for customized vehicle-mounted air conditioner, customized vehicle-mounted air conditioner system and computer readable storage medium | |
| Hintea et al. | Mutual information-based sensor positioning for car cabin comfort control | |
| JP2020075668A (en) | Vehicle air conditioner | |
| KR20230015539A (en) | Customized air conditioning control system and method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |