CN112810395B - Vehicle-mounted air conditioner intelligent control system and method based on fuzzy instruction and user preference - Google Patents
Vehicle-mounted air conditioner intelligent control system and method based on fuzzy instruction and user preference Download PDFInfo
- Publication number
- CN112810395B CN112810395B CN202011229326.3A CN202011229326A CN112810395B CN 112810395 B CN112810395 B CN 112810395B CN 202011229326 A CN202011229326 A CN 202011229326A CN 112810395 B CN112810395 B CN 112810395B
- Authority
- CN
- China
- Prior art keywords
- time
- instruction
- user
- fuzzy
- air conditioner
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000009191 jumping Effects 0.000 claims abstract description 16
- 238000013500 data storage Methods 0.000 claims abstract description 15
- 230000001105 regulatory effect Effects 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 37
- 230000007423 decrease Effects 0.000 claims description 7
- 230000001276 controlling effect Effects 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 230000005484 gravity Effects 0.000 claims 1
- 238000004364 calculation method Methods 0.000 abstract description 5
- 230000004044 response Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 8
- 238000012549 training Methods 0.000 description 8
- 230000001186 cumulative effect Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 235000008694 Humulus lupulus Nutrition 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000004378 air conditioning Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000008685 targeting Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
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
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/80—Technologies aiming to reduce greenhouse gasses emissions common to all road transportation technologies
- Y02T10/88—Optimized components or subsystems, e.g. lighting, actively controlled glasses
Abstract
The application disclosesAn intelligent control method of an air conditioner on a vehicle based on a fuzzy instruction and user preference is characterized by comprising the following steps: inquiring the current attribute value according to the fuzzy instruction, positioning the current attribute value to the corresponding row position of the data storage library, marking the current attribute value as a main row, and obtaining the weight for jumping to other attribute values or intervals; multiplying the jump attribute weight of adjacent lines by a regulating factor v m Deriving user preferences, where v m At [0,1]Within the range, m represents the number of rows from the main row; calculating the probability of jumping to other attribute values or intervals according to the weight of jumping to other attribute values or intervals, so that the falling point judgment is carried out through random numbers, and the falling point judgment is converted into an accurate instruction; and changing the temperature or the air quantity according to the accurate instruction. The application does not need online calculation and does not depend on network connectivity and quality, so the time delay is short, and the response speed of the fuzzy instruction can be greatly improved.
Description
Technical Field
The application belongs to the technical field of vehicle-mounted air conditioner control, and particularly relates to a vehicle-mounted air conditioner intelligent control system and method based on a fuzzy instruction and user preference.
Background
At present, the development potential of the intelligent cabin and the internet of vehicles platform is strong, and vehicle-mounted voice becomes necessary, so that on one hand, the intelligent technology is highlighted, on the other hand, a user releases both hands, and the intelligent cabin and the internet of vehicles platform are safer in the driving process through voice rather than touch control. Meanwhile, intelligent technologies such as gesture recognition and the like are transplanted into the vehicle, so that the vehicle control is more diversified. In summary, intelligence is a major trend.
However, the conventional speech recognition, gesture control, and the like cannot completely replace the touch control. The commands issued by voice recognition, gesture control, etc. are not enough to give accurate instructions to the vehicle. In the aspect of vehicle-mounted air conditioner control, when a non-touch instruction is processed, the prior art often faces the instruction that a user desires to adjust the temperature, the wind speed and the like of the air conditioner, but the instruction is likely to be fuzzy. In the prior art, when a fuzzy instruction is processed, one or more default values are often used for converting the fuzzy into definiteness, such as raising the temperature, and under the condition that the raising is not indicated, the prior art is often used for mainly replacing a user, but is quite far away from the user expectation, the user can give a plurality of fuzzy instructions to approach to the user, and the intelligent cannot be clearly embodied.
Meanwhile, most of the existing intelligent control technologies adopt an online cloud computing technology, intelligent instruction processing can be realized by depending on the cloud computing technology, but the following problems exist. 1. The network connection requirements are good: the cloud computing technology needs to be online, after a user issues an instruction, the instruction needs to be reported to the cloud, and the cloud feeds back an accurate control instruction, so that time delay is unavoidable, and good network connection is needed; 2. data traffic is frequently used: the deep learning of cloud computing requires a large number of training sets, records data of users, and if the data are transmitted in real time, the data interaction is required to be frequently carried out, or the data are recorded, and the data are transmitted regularly or quantitatively, so that the data are easily lost due to the influence of vehicle power-down; 3. the whole application cost-effective degree is low, and the technology is used, and finally, only accurate instructions are confirmed, so that the method is not cost-effective in the whole field of vehicle-mounted air conditioner control, the vehicle-mounted air conditioner control range is extremely limited, and the technology is not cost-effective only.
Disclosure of Invention
Aiming at the problems, the application provides an intelligent control system and method for an on-vehicle air conditioner with fuzzy instructions and user preferences, which aim at the defects of an on-line cloud computing mode, and adopt an off-line mode for processing, are not limited by network connectivity, and greatly improve the response speed of the fuzzy instructions.
The aim and the technical problems of the application are realized by adopting the following technical proposal.
An embodiment of the present application provides an intelligent control method for an air conditioner on a vehicle based on a fuzzy instruction and user preference, which is characterized by comprising:
inquiring the current attribute value according to the fuzzy instruction, positioning the current attribute value to the corresponding row position of the data storage library, marking the current attribute value as a main row, and obtaining the weight for jumping to other attribute values or intervals;
multiplying the jump attribute weight of adjacent lines by a regulating factor v m Deriving user preferences, where v m At [0,1]Within the range, m represents the number of rows from the main row;
calculating the probability of jumping to other attribute values or intervals according to the weight of jumping to other attribute values or intervals, so that the falling point judgment is carried out through random numbers, and the falling point judgment is converted into an accurate instruction;
and changing the temperature or the air quantity according to the accurate instruction.
According to the above embodiment of the present application, there is providedThe intelligent control method for the vehicle-mounted air conditioner based on the fuzzy instruction and the user preference is characterized by further comprising the step of establishing a data storage library before inquiring the current attribute value according to the fuzzy instruction, wherein the data storage library is based on temperature and air quantity which are both represented in a matrix M form, wherein the matrix M is a 7X 7 matrix table, and the ith row and jth column elements of the matrix M are recorded as M ij 。
According to the present application, the method for controlling the air conditioner on the vehicle based on the fuzzy instruction and the preference of the user is characterized in that the current attribute value includes a temperature M temp And the wind degree M level 。
According to the intelligent control method for the vehicle-mounted air conditioner provided by the embodiment of the application, the intelligent control method is characterized in that after the intelligent control method is converted into the accurate instruction, whether a user performs secondary adjustment is further required to be judged: if yes, correcting the regulating factor v, wherein the increase of v indicates that the user is more focused on the adjustment of the temperature difference, and the decrease of v indicates that the user is more focused on the setting of the specific temperature; if the judgment is no, the step is ended.
According to the vehicle-mounted air conditioner intelligent control method based on the fuzzy instruction and the user preference, the method is characterized by further comprising the step of iterating weight row values after the data storage library is established, and the method comprises the following steps:
in units of minutes, the cumulative usage time a of the user at the current attribute value is recorded, and the update time interval is denoted as b, so that when the update time point is reached, all data of the line is multiplied by (a+b)/a to update the cumulative time.
According to the vehicle-mounted air conditioner intelligent control method based on the fuzzy instruction and the user preference provided by the embodiment of the application, the method is characterized in that if an interrupt condition occurs after the matrix table is updated, whether the interrupt condition can be recovered is further judged: if yes, multiplying all data of the row by (a+c)/a, and updating accumulated time, wherein c represents time after setting or after updating point, and c is less than or equal to b; if the judgment is no, the method is not processed.
According to the vehicle-mounted air conditioner intelligent control method based on the fuzzy instruction and the user preference, the interruption condition comprises temperature change, air quantity or closing of the air conditioner.
According to the intelligent control method for the vehicle-mounted air conditioner provided by the embodiment of the application, the process of obtaining the weight for jumping to other attribute values or intervals is characterized by comprising the following steps: the main line is marked as i and needs to jump to the jth attribute value or interval m ij Its adjacent behavior i+k, corresponding to a jump to the j+k-th attribute value or interval, to m (i+k)(j+k) And (3) representing.
According to the intelligent control method of the vehicle-mounted air conditioner provided by the embodiment of the application, based on the fuzzy instruction and the user preference, the intelligent control method is characterized by further comprising a value reduction step after changing the temperature or the air quantity according to the accurate instruction, and the intelligent control method comprises the following steps:
taking the power-on time as a reference, regarding the operation time of the air conditioner as the power-on time during the power-on period, calculating a time difference t according to the last power-on time after the power-on, wherein the time difference t is obtained by recording the current time when each power-on is performed, subtracting the last power-on time (if any) to obtain the time difference t, and covering the last power-on time with the last power-on time;
for the temperature and wind matrix M temp And M level The whole value of (a) is multiplied by exp (-ut), wherein exp (a) represents a base number of a natural number e, a is an index, u is an adjustment parameter and is larger than 0, for adjusting the proportion of past information, "-" represents attenuation.
The aim and the technical problems of the application can be further realized by adopting the following technical proposal.
The application also provides an intelligent control system of the vehicle-mounted air conditioner based on the fuzzy instruction and the preference of the user, which is characterized by comprising:
the data storage module is used for controlling the temperature and the air quantity, establishing a database based on the temperature and the air quantity as variables, and recording weights from the current state to the next state in a matrix form;
the weight line value iteration module is used for recording the current temperature interval or the air quantity using time by taking a minute level as a unit and updating the matrix table at regular time;
the fuzzy control module is used for judging the falling point through the random number and converting a fuzzy instruction of a user into an accurate instruction; and
the verification feedback module is used for correcting the adjusting factor v if the user secondary adjustment occurs in a short time when the fuzzy instruction is used for control; if v increases, it means that the user is more focused on the adjustment of the temperature difference, and if v decreases, it means that the user is more focused on the setting of the specific temperature.
By means of the technical scheme, the application has at least the following advantages:
(1) The technical scheme of the application starts based on the fuzzy instruction, is irrelevant to instruction sources such as voice control, gesture recognition and the like, and abstracts specific operations into the fuzzy instruction and starts. Based on the theory of deep learning, the scheme takes the user operation habit as a training set, and the operation habit is derived from the following but not limited to: controlling air conditioner parameters by touch; and the accurate air conditioning parameters are issued by voice. In this way, the user operation habit characteristics are continuously and iteratively updated under the training set, and the newly-entered fuzzy instruction is taken as the verification set until the training set is enough, so that after the fuzzy instruction, the user supplements the modified content to finely adjust the model parameters, and convergence is ensured. Finally, after a period of use, when a user gives a fuzzy instruction, the fuzzy instruction is in place in one step with high probability, namely secondary adjustment can not be carried out in a short time, so that the fuzzy instruction meets the basic requirement of the user, and the intelligent effect is realized. Aiming at the defects of an online cloud computing mode, the scheme adopts offline processing, is not limited by network connectivity at first, and can calculate corresponding state transition in advance to realize second control aiming at the characteristic that the control instruction of the vehicle-mounted air conditioner is limited; secondly, the frequently used data flow and data loss do not exist, and each time of accurate control of a user can be timely a training set, so that the data is utilized; compared with an online scheme, the intelligent control method is limited in storage and the like, but is sufficient to be used for intelligent control of the vehicle-mounted air conditioner.
(2) Offline intelligent scheme: the application does not need online calculation and does not depend on network connectivity and quality, so the time delay is short, and the response speed of the fuzzy instruction can be greatly improved.
(3) The principle of approximation: the weight of the early use habit is attenuated, the weight of the user's recent use habit is larger, and the user's recent use habit is more fit.
(4) And (3) verification feedback: and the self-adaptive adjustment factors meet the basic requirements of different users.
The foregoing description is only an overview of the present application, and is intended to provide a better understanding of the present application, as it is embodied in the following description, with reference to the preferred embodiments of the present application and the accompanying drawings.
Drawings
FIG. 1 is a flow chart of an intelligent control method of an on-board air conditioner based on fuzzy instructions and user preferences;
fig. 2 is a flow chart of the weight row value iteration in the intelligent control method of the vehicle-mounted air conditioner based on the fuzzy instruction and the user preference.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement of the purposes and the effects of the present application easy to understand, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the embodiments of the present application and the accompanying drawings, and it is obvious that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
As shown in fig. 1 and 2, the preferred embodiment of the application discloses an intelligent control method of an on-vehicle air conditioner based on a fuzzy instruction and user preference, which specifically comprises the following steps:
inquiring the current attribute value according to the fuzzy instruction, positioning the current attribute value to the corresponding row position of the data storage library, marking the current attribute value as a main row, and obtaining the weight for jumping to other attribute values or intervals;
multiplying the jump attribute weight of adjacent lines by a regulating factor v m Deriving user preferences, where v m At [0,1]Within the range, m represents the number of rows from the main row;
calculating the probability of jumping to other attribute values or intervals according to the weight of jumping to other attribute values or intervals, so that the falling point judgment is carried out through random numbers, and the falling point judgment is converted into an accurate instruction;
and changing the temperature or the air quantity according to the accurate instruction.
In one embodiment, the method further comprises the step of establishing a data storage library before inquiring the current attribute value according to the fuzzy instruction, wherein the data storage library is based on temperature and air quantity as variables, and the temperature and the air quantity are expressed in a form of a matrix M, wherein the matrix M is a 7X 7 matrix table, and the element of the ith row and the jth column of the matrix M is marked as M ij 。
At present, a common vehicle-mounted air conditioner fuzzy instruction is generally used for controlling temperature and air quantity, so that a database is established according to the temperature and the air quantity, and weights from a current state to a next state are recorded in a matrix form. Considering that the temperature quantization is finer, the quantization precision can be properly enlarged according to specific conditions, namely, a plurality of adjacent temperatures are bundled together, so that the dimension of the matrix is reduced, the matrix is filled up more quickly, the verification stage is entered more quickly, and meanwhile, the calculation cost is reduced. Taking a specific project as an example, the temperature adjustment range is 18-32 degrees, the precision is 0.5 degrees, the air quantity is adjusted to 1-7 levels, and the precision is 1 level. Because the air quantity enumeration number is smaller, the accuracy is not expanded, and a matrix table M of 7 multiplied by 7 is established level The method comprises the steps of carrying out a first treatment on the surface of the However, the total number of temperature enumerations is 29, so that it is not suitable to build a 29×29 matrix, and a general user issues related fuzzy instructions to raise and lower the temperature, which is generally unsatisfactory to the current temperature, so that a certain span exists, and the temperature is rarely increased and reduced by 0.5 degrees. Thus, the expansion accuracy can be considered, targeting a set of 4 temperatures, 7 sets of which 1 set has 5 temperatures. Thus, 18 to 32 degrees can be divided into: [18, 19.5]，[20, 21.5]，[22, 23.5]，[24, 26]，[26.5, 28]，[28.5,30]，[30.5, 32]Wherein [ x, y]Represents all sets of values from the lower limit x to the upper limit y, thus removing [24,26 ]]There are 5 temperature data and 4 temperature data for the other 6 groups. Thus, the temperatures are divided into 7 groups, and a 7×7 matrix M is established temp . Since there are at least 2 data within each group, the matrix needs to record the weights of the hops within the group. Wherein the ith row and jth column elements of matrix M are denoted as M ij 。
In one embodiment, the current attribute value includes a temperature M temp And the wind degree M level 。
In one embodiment, after the conversion to the precise instruction, it is further required to determine whether the user makes a secondary adjustment: if yes, correcting the regulating factor v, wherein the increase of v indicates that the user is more focused on the adjustment of the temperature difference, and the decrease of v indicates that the user is more focused on the setting of the specific temperature; if the judgment is no, the step is ended.
The secondary adjustment is based on the situation that occurs when the fuzzy instruction is controlled after there are enough training sets. If a user secondary adjustment occurs for a short period of time, the adjustment factor v is modified. An increase in v indicates that the user is more focused on the adjustment of the temperature difference, while a decrease in v indicates that the user is more focused on the setting of a specific temperature. Therefore, an adjustment of v is necessary. The specific flow is shown in figure 1.
In one embodiment, the step of iterating the weight row values further includes, after the data repository is established, the steps of:
in units of minutes, the cumulative usage time a of the user at the current attribute value is recorded, and the update time interval is denoted as b, so that when the update time point is reached, all data of the line is multiplied by (a+b)/a to update the cumulative time.
Specifically, the iteration of the weight row value refers to that the user regards the accurate operation such as touch control as the training operation each time, and the temperature is controlled to train M temp The air quantity is controlled to train M level . The weight row value iterations include iterations a and B. Iteration A refers to the process of recording data by matrixEach accurate instruction is used as a training set and is given a corresponding weight +1 in the matrix. In consideration of the case of a user's multiple operations, it is not possible to use only the number of hops as a weight. Therefore, in addition to this, it is necessary to record the use time of the user in the corresponding temperature zone and the air volume. Therefore, the matrix needs to be updated regularly, and the usage time of each temperature interval or air volume is recorded, and the data of the corresponding row needs to be multiplied by the proportion, wherein the usage time of the current temperature interval or air volume is recorded in units of minutes, and the longer the usage time, the larger the sum of the corresponding rows in the matrix.
Iteration B means that the data corresponding attribute is accumulated and used for a minutes, and the attribute is switched to and updated every B minutes. Thus, every time b minutes expires, the row of all data is multiplied by (a+b)/a, the cumulative time is updated, and so on. If an interruption condition such as temperature change or air volume, air conditioner shutdown, etc., such as c minutes after setting or after updating the point, c must be b or less, all data of the row is multiplied by (a+c)/a, and the accumulated time is updated. If the interrupt is not recoverable, such as by powering down, it is not processed. Thus, the matrix records the jump weight, and the total number of each row reflects the use condition of the temperature interval or the air quantity, so that the use preference of a user is reflected.
Iteration a and iteration B are performed in parallel, acting together. The specific flow is shown in fig. 2.
In one embodiment, if an interrupt condition occurs after the matrix table is updated, it is further required to determine whether the interrupt condition is recoverable: if yes, multiplying all data of the row by (a+c)/a, and updating accumulated time, wherein c represents time after setting or after updating point, and c is less than or equal to b; if the judgment is no, the method is not processed.
In one embodiment, the interruption condition includes a temperature change, an air volume, or turning off the air conditioner.
In one embodiment, the process of deriving weights for jumping to other attribute values or intervals includes: the main line is marked as i and needs to jump to the jth attribute value or interval m ij Its adjacent behavior i+k corresponds to a jump to the j+k-th attribute value or intervalIn m (i+k)(j+k) And (3) representing.
In one embodiment, the method further comprises a step of reducing the temperature or the air quantity according to the precise instruction, and the method comprises the following steps: taking the power-on time as a reference, regarding the operation time of the air conditioner as the power-on time during the power-on period, calculating a time difference t according to the last power-on time after the power-on, wherein the time difference t is obtained by recording the current time when each power-on is performed, subtracting the last power-on time (if any) to obtain the time difference t, and covering the last power-on time with the last power-on time; for the temperature and wind matrix M temp And M level The whole value of (a) is multiplied by exp (-ut), wherein exp (a) represents a base number of a natural number e, a is an index, u is an adjustment parameter and is larger than 0, for adjusting the proportion of past information, "-" represents attenuation. In general, the operation desired by the user must be closer to the most recent use. If the calculation method of the tree weight is adopted, the calculation method is equivalent in each time period and does not accord with the nearby principle, so that the weight of the old data needs to be reduced. The best method is to record the adjustment time of each time, but the record quantity is larger, and the offline scheme is not met. The application takes the power-on time as a reference, and the operation time of the air conditioner during the power-on period is regarded as the power-on time, so that the storage is simplified. Thus, after power-up, according to the last power-up time, calculating time difference, for matrix M temp And M level And (5) performing the value reduction processing on the ownership value. Because of the particularity of the exponential function, i.e. multiplication with the base function, the exponential addition can be performed by taking the time difference t as an exponential reference, and multiplying the whole matrix value by exp (-ut) after power-up, wherein exp (a) represents a base with a natural number e and a is an exponent. Where u is an adjustment parameter and is greater than 0, and is used to adjust the proportion of past information, an empirical value may be assigned, t is a time difference, and the negative sign indicates attenuation, and is used for the degradation process. Thus, old information is weakened, and the nearby principle is embodied.
The application also provides an intelligent control system of the vehicle-mounted air conditioner based on the fuzzy instruction and the user preference, which is characterized by comprising the following steps:
the data storage module is used for controlling the temperature and the air quantity, establishing a database based on the temperature and the air quantity as variables, and recording weights from the current state to the next state in a matrix form;
the weight line value iteration module is used for recording the current temperature interval or the air quantity using time by taking a minute level as a unit and updating the matrix table at regular time;
the fuzzy control module is used for judging the falling point through the random number and converting a fuzzy instruction of a user into an accurate instruction; and
the verification feedback module is used for correcting the adjusting factor v if the user secondary adjustment occurs in a short time when the fuzzy instruction is used for control; if v increases, it means that the user is more focused on the adjustment of the temperature difference, and if v decreases, it means that the user is more focused on the setting of the specific temperature.
While the application has been described with respect to preferred embodiments, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the application, and that any such changes and modifications as described in the above embodiments are intended to be within the scope of the application.
Claims (10)
1. An intelligent control method of an air conditioner on a vehicle based on a fuzzy instruction and user preference is characterized by comprising the following steps:
inquiring the current attribute value according to the fuzzy instruction, positioning the current attribute value to the corresponding row position of the data storage library, marking the current attribute value as a main row, and obtaining the weight for jumping to other attribute values or intervals;
multiplying the jump attribute weight of adjacent lines by a regulating factor v m Deriving user preferences, where v m At [0,1]Within the range, m represents the number of rows from the main row;
calculating the probability of jumping to other attribute values or intervals according to the weight of jumping to other attribute values or intervals, so that the falling point judgment is carried out through random numbers, and the falling point judgment is converted into an accurate instruction;
and changing the temperature or the air quantity according to the accurate instruction.
2. The intelligent control method for vehicle-mounted air conditioner based on fuzzy instruction and user preference according to claim 1, further comprising the step of establishing a data storage library before inquiring the current attribute value according to the fuzzy instruction, wherein the data storage library is based on temperature and air quantity as variables, and the temperature and the air quantity are both represented in the form of a matrix M, wherein the matrix M is a 7 x 7 matrix table, and the element in the j th row and the j th column is recorded as M ij 。
3. The intelligent control method for the vehicle-mounted air conditioner based on the fuzzy instruction and the user preference according to claim 1, wherein the current attribute value comprises a temperature M temp And the wind degree M level 。
4. The intelligent control method of the vehicle-mounted air conditioner based on the fuzzy instruction and the user preference according to claim 1, wherein after the conversion to the accurate instruction, whether the user performs secondary adjustment is further required to be judged: if yes, correcting the regulating factor v, wherein the increase of v indicates that the user is more focused on the adjustment of the temperature difference, and the decrease of v indicates that the user is more focused on the setting of the specific temperature; if the judgment is no, the step is ended.
5. The intelligent control method for the vehicle-mounted air conditioner based on the fuzzy instruction and the user preference according to claim 2, further comprising the step of iterating the weight row value after the data storage library is established, comprising:
in units of minutes, the accumulated use time a of the user at the current attribute value is recorded, the update time interval is denoted as b, and when the update time point is reached, all data of the main line are multiplied by (a+b)/a to update the accumulated time.
6. The intelligent control method for the vehicle-mounted air conditioner based on the fuzzy instruction and the user preference according to claim 5, wherein if an interruption condition occurs after the matrix table is updated, it is further required to determine whether the interruption condition can be recovered: if yes, multiplying all data of the main line by (a+c)/a, and updating accumulated time, wherein c represents time after setting or after updating, and c is less than or equal to b; if the judgment is no, the method is not processed.
7. The intelligent control method for the vehicle-mounted air conditioner based on the fuzzy instruction and the user preference according to claim 6, wherein the interruption condition comprises temperature change, air quantity or turning off the air conditioner.
8. The intelligent control method for the vehicle-mounted air conditioner based on the fuzzy instruction and the user preference according to claim 1, wherein the process of deriving the weight for jumping to other attribute values or intervals comprises the following steps: the main line is marked as i and needs to jump to the jth attribute value or interval m ij The adjacent behavior i+k of the main row i corresponds to jumping to the j+k attribute value or interval to m (i+k)(j+k) And (3) representing.
9. The intelligent control method for the vehicle-mounted air conditioner based on the fuzzy instruction and the user preference according to claim 1, further comprising a step of reducing the temperature or the air volume according to the accurate instruction, comprising:
taking the power-on time as a reference, regarding the operation time of the air conditioner as the power-on time during the power-on period, calculating a time difference t according to the last power-on time after the power-on, wherein the time difference t is obtained by recording the current time when the power-on is performed each time, subtracting the last power-on time to obtain the time difference t, and covering the last power-on time with the last power-on time;
for the temperature and wind matrix M temp And M level Multiplying the whole value of (a) by exp (-ut), wherein exp (a) represents a base number of a natural number e, a is an index, u is an adjustment parameter and is greater than 0, for adjustingThe specific gravity of the information going away, "-" indicates the attenuation.
10. An intelligent control system of an air conditioner on board based on fuzzy instructions and user preferences is characterized by comprising:
the data storage module is used for controlling the temperature and the air quantity, establishing a database based on the temperature and the air quantity as variables, and recording weights from the current state to the next state in a matrix form;
the weight line value iteration module is used for recording the current temperature interval or the air quantity using time by taking a minute level as a unit and updating the matrix table at regular time;
the fuzzy control module is used for judging the falling point through the random number and converting a fuzzy instruction of a user into an accurate instruction; and
the verification feedback module is used for correcting the adjusting factor v if the user secondary adjustment occurs in a short time when the fuzzy instruction is used for control; if v increases, it means that the user is more focused on the adjustment of the temperature difference, and if v decreases, it means that the user is more focused on the setting of the specific temperature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011229326.3A CN112810395B (en) | 2020-11-06 | 2020-11-06 | Vehicle-mounted air conditioner intelligent control system and method based on fuzzy instruction and user preference |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011229326.3A CN112810395B (en) | 2020-11-06 | 2020-11-06 | Vehicle-mounted air conditioner intelligent control system and method based on fuzzy instruction and user preference |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112810395A CN112810395A (en) | 2021-05-18 |
| CN112810395B true CN112810395B (en) | 2023-12-12 |
Family
ID=75854336
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011229326.3A Active CN112810395B (en) | 2020-11-06 | 2020-11-06 | Vehicle-mounted air conditioner intelligent control system and method based on fuzzy instruction and user preference |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112810395B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05246233A (en) * | 1991-05-31 | 1993-09-24 | Suzuki Motor Corp | Air-conditioning control device for automobile |
| KR19990047378A (en) * | 1997-12-04 | 1999-07-05 | 박상록 | Vehicle air conditioning controller using fuzzy control |
| EP1335255A2 (en) * | 2002-02-08 | 2003-08-13 | Delphi Technologies, Inc. | Method for calibrating a control system |
| CN103542493A (en) * | 2013-09-25 | 2014-01-29 | 浙江吉利控股集团有限公司 | System and method for intelligent control over automobile air conditioner according to fuzzy control |
| CN106642525A (en) * | 2016-09-30 | 2017-05-10 | 广东美的制冷设备有限公司 | Fuzzy control method, fuzzy control device and air conditioner |
| CN110641250A (en) * | 2019-11-05 | 2020-01-03 | 重庆大学 | Intelligent control method of air conditioning system of electric automobile based on human body thermal comfort theory and fuzzy PID control |
| GB202002282D0 (en) * | 2020-02-19 | 2020-04-01 | Daimler Ag | Method of controlling air conditioner (AC) setting in a vehicle, and system thereof |
-
2020
- 2020-11-06 CN CN202011229326.3A patent/CN112810395B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05246233A (en) * | 1991-05-31 | 1993-09-24 | Suzuki Motor Corp | Air-conditioning control device for automobile |
| KR19990047378A (en) * | 1997-12-04 | 1999-07-05 | 박상록 | Vehicle air conditioning controller using fuzzy control |
| EP1335255A2 (en) * | 2002-02-08 | 2003-08-13 | Delphi Technologies, Inc. | Method for calibrating a control system |
| CN103542493A (en) * | 2013-09-25 | 2014-01-29 | 浙江吉利控股集团有限公司 | System and method for intelligent control over automobile air conditioner according to fuzzy control |
| CN106642525A (en) * | 2016-09-30 | 2017-05-10 | 广东美的制冷设备有限公司 | Fuzzy control method, fuzzy control device and air conditioner |
| CN110641250A (en) * | 2019-11-05 | 2020-01-03 | 重庆大学 | Intelligent control method of air conditioning system of electric automobile based on human body thermal comfort theory and fuzzy PID control |
| GB202002282D0 (en) * | 2020-02-19 | 2020-04-01 | Daimler Ag | Method of controlling air conditioner (AC) setting in a vehicle, and system thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112810395A (en) | 2021-05-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110688920B (en) | Unmanned control method and device and server | |
| CN101339404B (en) | Aircraft posture kinetics simplified model gain switching proportion-differential control design method | |
| JP2007264796A (en) | Plant control method and plant controller | |
| CN106708044A (en) | Full-hovering hovercraft course control method based on grey prediction hybrid genetic algorithm-PID | |
| CN109062040B (en) | PID (proportion integration differentiation) predicting method based on system nesting optimization | |
| EP3129839A1 (en) | Controlling a target system | |
| CN112810395B (en) | Vehicle-mounted air conditioner intelligent control system and method based on fuzzy instruction and user preference | |
| CN112622895A (en) | Prediction control method applied to trajectory control of automatic driving | |
| WO2018146802A1 (en) | Control customization system, control customization method, and control customization program | |
| CN111324358A (en) | Training method for automatic operation and maintenance strategy of information system | |
| JP2003256005A (en) | Control method and control device | |
| CN114488799B (en) | Parameter optimization method for controller of automobile self-adaptive cruise system | |
| CN114537391A (en) | Vehicle following servo control method and system based on forecasting observer | |
| CN110244752B (en) | Expert intelligent control method for hypersonic aircraft and aircraft | |
| CN111680720A (en) | Blast furnace molten iron silicon content prediction method based on improved CS-SVR model | |
| CN112685835A (en) | Elastic event trigger control method and system for autonomous driving of vehicle | |
| JP2738334B2 (en) | Production plan leveling system | |
| CN111581178A (en) | Ceph system performance tuning strategy and system based on deep reinforcement learning | |
| CN106300400B (en) | Storage battery capacity configuration system for tracking wind power prediction | |
| CN115141926B (en) | Method for generating billet target heating curve for guiding billet heating process control | |
| CN113238486B (en) | Self-adaptive multi-machine hydropower station speed regulator parameter regulation and control method | |
| CN113570066B (en) | Data processing method, system, electronic device and storage medium | |
| EP3739525A1 (en) | Informed imperceptible exploration based on control-policies | |
| CN113511736B (en) | Intelligent aeration method and device for sewage treatment | |
| CN115141926A (en) | Billet target temperature rise curve generation method for guiding billet heating process control |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |