CN112128936A - Intelligent control method and intelligent control equipment for air conditioner - Google Patents
Intelligent control method and intelligent control equipment for air conditioner Download PDFInfo
- Publication number
- CN112128936A CN112128936A CN202010889187.0A CN202010889187A CN112128936A CN 112128936 A CN112128936 A CN 112128936A CN 202010889187 A CN202010889187 A CN 202010889187A CN 112128936 A CN112128936 A CN 112128936A
- Authority
- CN
- China
- Prior art keywords
- air conditioner
- season
- starting
- operating
- prediction model
- 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.)
- Granted
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/65—Electronic processing for selecting an operating mode
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2130/00—Control inputs relating to environmental factors not covered by group F24F2110/00
- F24F2130/10—Weather information or forecasts
-
- 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
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
- Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention provides an intelligent control method and intelligent control equipment for an air conditioner. The intelligent control method of the air conditioner comprises the following steps: acquiring environmental parameters of an air conditioner running environment when the air conditioner is in a standby state; the method comprises the steps of obtaining a starting prediction model of the air conditioner, wherein the starting prediction model is obtained by training through a machine learning algorithm by using the starting state of the air conditioner and corresponding environmental data as training samples; inputting the environmental parameters into a starting prediction model; performing prediction calculation by using a starting prediction model to obtain starting conditions and starting parameters of the air conditioner; and controlling the air conditioner to start according to the starting parameters after the starting conditions are met. According to the scheme, the starting-up condition and the starting-up parameter of the intelligent air conditioner are obtained by performing prediction calculation on the environmental parameter acquired in the standby state through the starting-up prediction model, so that the requirement of a user on the comfort of the environment can be accurately met, and the intelligent level of the intelligent household appliance is improved.
Description
Technical Field
The invention relates to intelligent household appliance control, in particular to an intelligent control method and intelligent control equipment of an air conditioner.
Background
With the increasing living standard, consumers can choose household appliances no longer to pay attention to the quality of products alone, but to the use experience brought by the products.
With the rapid development of artificial intelligence, machine learning and other technologies, the use of related intelligent technologies in air conditioners is also becoming a hot point of technical research. However, the use result of the existing intelligent control method of the air conditioner applying the artificial intelligence technology cannot completely meet the use requirement of the user. The starting-up control of the air conditioner is the most important part in the intelligent control of the air conditioner because the influence of the starting-up starting stage on the use feeling of a user is the largest, and the starting-up parameters of the air conditioner directly influence the times of subsequent state adjustment.
Although many intelligent air conditioner starting schemes are provided in the prior art, the schemes are often questioned by users, and some users even feed back inaccurate starting conditions of the intelligent air conditioner, which brings more trouble.
Disclosure of Invention
An object of the present invention is to provide an intelligent control method and an intelligent control apparatus for an air conditioner that solve at least some of the above-mentioned problems of the related art.
A further object of the present invention is to accurately determine the startup conditions and startup parameters of the air conditioner using the startup prediction model.
Another further object of the present invention is to provide an air conditioner that can intelligently provide a comfortable indoor environment and improve the user experience.
Particularly, the invention provides an intelligent control method of an air conditioner, which comprises the following steps: acquiring environmental parameters of an air conditioner running environment when the air conditioner is in a standby state; the method comprises the steps of obtaining a starting prediction model of the air conditioner, wherein the starting prediction model is obtained by training through a machine learning algorithm by using the starting state of the air conditioner and corresponding environmental data as training samples; inputting the environmental parameters into a starting prediction model; performing prediction calculation by using a starting prediction model to obtain starting conditions and starting parameters of the air conditioner; and controlling the air conditioner to start according to the starting parameters after the starting conditions are met.
Optionally, after the step of controlling the air conditioner to start with the startup parameters, the method further includes: acquiring a manual adjustment instruction of the air conditioner; and (4) taking the setting parameters in the manual adjustment instruction and the environmental parameters during the manual adjustment as training samples, and performing iterative training on the open-loop prediction model.
Optionally, the step of obtaining a start-up prediction model of the air conditioner includes: determining the operating season of the air conditioner; and selecting a starting prediction model corresponding to the operating seasons from the multiple alternative prediction models, and training the multiple alternative prediction models by using the starting state and the environmental data of the air conditioner in each operating season as training samples through a machine learning algorithm.
Optionally, the step of determining the operating season in which the air conditioner is located comprises: acquiring installation position information of an air conditioner; determining the climate rule of the area where the air conditioner is located according to the installation position information; and matching the environmental data of the operating environment in the preset time period with the climate rule to determine the operating season of the air conditioner.
Optionally, the step of determining the operating season in which the air conditioner is located comprises: acquiring seasonal information of an area where an air conditioner is located, which is published by a weather platform; and determining the operating season of the air conditioner according to the season information.
Optionally, after the step of controlling the air conditioner to start with the startup parameters, the method further includes: acquiring a self-adjusting model corresponding to an operating season, wherein the self-adjusting model is obtained by taking the operating state of the air conditioner in the operating season and corresponding environmental data as training samples through a machine learning algorithm; acquiring the running state and environmental parameters of the air conditioner; inputting the running state and the environmental parameters into a self-adjusting model; carrying out prediction calculation by using a self-adjusting model to obtain a self-adjusting strategy of the air conditioner; and adjusting the air conditioner according to the self-adjusting strategy.
Optionally, after the step of determining the operating season of the air conditioner, the method further comprises: under the condition that the determined operating season changes from the operating season determined by the last operation of the air conditioner, outputting operating season replacement prompt information; and acquiring a response operation of the operating season replacement prompt information fed back by the user, and executing the step of acquiring the self-adjusting model corresponding to the operating season under the condition that the operating season is confirmed by the response operation instruction.
Optionally, the operating season includes any one or more of: the air conditioner comprises a refrigeration season, a heating season, a plum rain season and a haze removing season, wherein in the refrigeration season, the prior operation mode of the air conditioner is a refrigeration mode; in the heating season, the preferential operation mode of the air conditioner is a heating mode; in the refrigeration season, the prior operation mode of the air conditioner is a dehumidification mode; in the haze removing season, the preferential operation mode of the air conditioner is a purification mode.
Optionally, the step of obtaining a start-up prediction model of the air conditioner includes: acquiring an operation record of the air conditioner; judging whether the air conditioner calls a starting prediction model or not according to the operation record; if so, acquiring a previously called starting prediction model; if not, an initial starting prediction model configured for the area where the air conditioner is located is obtained.
According to another aspect of the present invention, there is also provided an intelligent control apparatus of an air conditioner, including: a processor; and a memory in which a control program is stored, the control program being executed by the processor to implement any one of the above-described intelligent control methods for an air conditioner.
The intelligent control method of the air conditioner provided by the invention is characterized in that the starting-up state of the air conditioner and corresponding environmental data are used as training samples to train to obtain a starting-up prediction model, and the starting-up condition and the starting-up parameter of the air conditioner are obtained by predicting and calculating the environmental parameters obtained in the standby state through the starting-up prediction model. The machine learning algorithm fully considers various influence factors of the air conditioner in the starting-up stage, can accurately meet the requirement of a user on the comfort of the environment, and provides the use experience of the user.
Furthermore, the intelligent control method of the air conditioner also considers that a single starting prediction model can not meet the starting requirements under various conditions, selects the operating seasons with clear use characteristics, trains the starting prediction model respectively for each operating season, fully considers the environmental regulation requirements of different operating seasons, and reduces the prediction calculation difficulty of the starting prediction model.
Furthermore, the intelligent control method of the air conditioner can select one or more of a refrigeration season, a heating season, a plum rain season and a haze removing season as operation seasons according to the installation area of the air conditioner, and the uncertainty of prediction calculation of the starting prediction model is greatly reduced because the operation seasons generally have a priority operation mode. Compared with the prior art in the fields of intelligent household appliances (intelligent household appliances) and intelligent air conditioners (intelligent air conditioners), the scheme provided by the invention is more intelligent and efficient, and the intelligent level is improved.
The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of specific embodiments thereof, taken in conjunction with the accompanying drawings.
Drawings
Some specific embodiments of the invention will be described in detail hereinafter, by way of illustration and not limitation, with reference to the accompanying drawings. The same reference numbers in the drawings identify the same or similar elements or components. Those skilled in the art will appreciate that the drawings are not necessarily drawn to scale. In the drawings:
fig. 1 is a schematic view of data interaction of an air conditioner according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an intelligent control apparatus of an air conditioner according to an embodiment of the present invention;
fig. 3 is a schematic view of an intelligent control method of an air conditioner according to an embodiment of the present invention; and
fig. 4 is a flowchart of an application example of an intelligent control method of an air conditioner according to an embodiment of the present invention. .
Detailed Description
Fig. 1 is a data interaction diagram of an air conditioner 10 according to an embodiment of the present invention. An air conditioner control application (App) or other control Client (Client) is installed on the terminal device 20 (including but not limited to various mobile terminals). The user of the air conditioner 10 may configure the functions and application scenarios of the air conditioner 10 through an application program or a client.
The network data platform 30 may be used to collect and record operational data of the air conditioner 10, collect and record user behavior information, and the like. The network data platform 30 may perform machine learning model training on the operation data of the air conditioner 10 and the user behavior information, and perform predictive computation of the air conditioner 10 by using the trained model. The decision conditions of the prediction calculation include indoor and outdoor environments (temperature, humidity, pollution condition, wind power, weather, etc.) of the air conditioner 10, user information (various physiological indexes, positions, dressing indexes, etc.), and the predicted targets include: the on-off state of the air conditioner 10 (including the on-parameter), the operation mode (cooling, heating, cleaning, dehumidifying, etc.), and the setting parameters (wind power, wind direction, temperature, humidity, etc.).
The air conditioner 10 obtains the self-running state and the indoor and outdoor environmental data, and performs the startup control on the air conditioner 10 according to the startup condition and the startup parameter predicted by the network data platform 30, and further performs the prediction calculation by using the self-adjusting model to obtain the self-adjusting strategy of the air conditioner.
In addition, the network data platform 30 may also send various alert messages to the air conditioner 10 and the terminal device 20, and receive information replied by the user through the air conditioner 10 and the terminal device 20.
The machine learning model (self-tuning model) used in the present embodiment may be capable of learning certain knowledge and capabilities from existing data (the operating state of the air conditioner 10 and environmental parameters) for processing new data, and may be designed to perform various tasks, in the present embodiment for determination of the control strategy of the air conditioner 10. Examples of machine learning models include, but are not limited to, deep neural networks of various types (DNNs), Support Vector Machines (SVMs), decision trees, random forest models, and so forth. In embodiments, the machine learning model may also be referred to as a "learning network". The neural network control model may adopt various known network structures suitable for supervised learning, such as a perceptron model, a classifier model, a Hopfield network and other basic neural network structures, and various corresponding mainstream training methods may also be used for determining the model parameters of the embodiment. Example machine learning models include neural networks or other multi-layered nonlinear models. Example neural networks include feed-forward neural networks, deep neural networks, recurrent neural networks, and convolutional neural networks.
The machine learning model may be included in or otherwise stored and implemented by a server computing system (network data platform 30) that communicates with terminal device 20 or air conditioner 10 according to a client-server relationship (or application-server). For example, the machine learning model may be implemented by a server computing system (network data platform 30) as part of a web service. Accordingly, one or more models may be stored and implemented at terminal device 20 and/or one or more models may be stored and implemented at a server computing system (network data platform 30).
The server computing system (network data platform 30) may include or otherwise be implemented by one or more server computing devices. Where the server computing system includes multiple server computing devices, such server computing devices may operate according to a sequential computing architecture, a parallel computing architecture, or some combination thereof.
The terminal device 20 or the air conditioner 10 and/or the server computing system (network data platform 30) may train the model via interaction with a training computing system communicatively coupled over a network. The training computing system may be separate from the server computing system (network data platform 30) or may be part of the server computing system (network data platform 30).
Those skilled in the art can distribute the processing and computing functions of the data among the terminal device 20, the air conditioner 10, and the network data platform 30 as necessary. For example, the data is subjected to certain preprocessing in the terminal device 20 and the air conditioner 10 to improve the efficiency of data transmission.
Fig. 2 is a schematic diagram of an intelligent control apparatus 300 of an air conditioner according to an embodiment of the present invention. The intelligent control device 300 may include, in general: a memory 320 and a processor 310, wherein the memory 320 stores a control program 321, and the control program 321 is used for implementing the intelligent control method of the air conditioner of the present embodiment when being executed by the processor 310. The processor 310 may be a Central Processing Unit (CPU), a digital processing unit, or the like. The processor 310 transmits and receives data through the communication interface. The memory 320 is used to store programs executed by the processor 310. The memory 320 is any medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, or a combination of memories. The control program 321 may be downloaded from a computer-readable storage medium to a corresponding computing/processing device or downloaded and installed to the smart control device 300 via a network (e.g., the internet, a local area network, a wide area network, and/or a wireless network).
The intelligent control device 300 may be arranged in the network data platform 30 as described above. Furthermore, the functionality of the intelligent control device 300 may also allow for configuration, combination, and division between the network data platform 30, the terminal 20, and the air conditioner 10, with the inherent flexibility of a computer-based system.
Fig. 3 is a schematic diagram of an intelligent control method of an air conditioner according to an embodiment of the present invention, which may include:
step S302, acquiring the environmental parameters of the air conditioner running environment when the air conditioner is in a standby state; environmental parameters may include, but are not limited to: indoor and outdoor temperature, indoor and outdoor humidity, weather, air particle data, air components and the like. Further, the environmental parameters may also include physical state of the user, such as physiological index data (body temperature, heart rate, etc.), location, etc.
Step S304, a starting prediction model of the air conditioner is obtained, and the starting prediction model is obtained by training through a machine learning algorithm by using the starting state of the air conditioner and corresponding environmental data as training samples. The power-on state may include a power-on mode, a power-on time, a power-on parameter, and the like of the air conditioner.
Step S306, inputting the environmental parameters into a starting prediction model;
step S308, the starting condition and the starting parameter of the air conditioner are obtained by utilizing the starting prediction model to carry out prediction calculation. The starting-up conditions can comprise environmental conditions, time conditions, user conditions and the like; the startup parameters comprise startup setting parameters of the air conditioner, startup initial parameters of each component and the like. It should be further noted that the starting condition is not only the threshold of each parameter, but is a condition of multiple influence factors obtained by comprehensively considering the influence factors of each parameter.
In step S310, the air conditioner is controlled to start up according to the start-up parameters after the start-up conditions are met. After the air conditioner is started, a manual adjustment instruction of the air conditioner can be obtained; and (4) taking the setting parameters in the manual adjustment instruction and the environmental parameters during the manual adjustment as training samples, and performing iterative training on the open-loop prediction model. The personalized requirements of the user can be better matched by carrying out iterative training on the starting prediction model by utilizing the manual adjustment instruction and the environmental parameters during the manual adjustment. For example, the last several times (e.g., 5 times, 10 times) of manual adjustment instructions and the environmental parameters during manual adjustment may be used as training samples.
After the air conditioner is started, a self-adjusting model of the air conditioner can be called; acquiring the running state and environmental parameters of the air conditioner; inputting the running state and the environmental parameters into a self-adjusting model; carrying out prediction calculation by using a self-adjusting model to obtain a self-adjusting strategy of the air conditioner; and adjusting the air conditioner according to a self-adjusting strategy, so that the air conditioner is continuously adjusted in time after the environmental parameters change by using the self-adjusting model, and the comfort requirement of a user is met.
The parameters of the air conditioner start-up stage have a great influence on the running state of the subsequent air conditioner, the air conditioner also needs to avoid frequent changing of the running state as much as possible, and all the states and target parameters need to be set in the air conditioner start-up stage. That is, the start-up control of the air conditioner is the most important part of the air conditioner control.
The existing intelligent air conditioner can realize more and more functions, only uses air supply as an example, and adds various air supply modes such as natural wind, circulating wind, fresh air, no wind sense and the like besides wind power and wind direction, and the comfort feeling of users is different in different seasons. For example, in spring and autumn, although the temperature is not very different, the demands of users are obviously different. In the case where the same environmental data occurs in different seasons, the air conditioner may need to be turned on in some seasons, and may not need to be turned on in some seasons. The same starting prediction model is used for prediction calculation, and obviously, the requirements of users cannot be met. Based on the problem, the intelligent control method of the air conditioner of the embodiment respectively carries out model training on the operation seasons with typical use characteristics, so that the starting prediction model corresponds to the operation seasons, the obtained starting strategy basically conforms to the characteristics of the operation seasons, and the use experience of users is improved.
In an embodiment using a start-up prediction model corresponding to a season of operation, the step of obtaining the start-up prediction model of the air conditioner includes: determining the operating season of the air conditioner; and selecting a starting prediction model corresponding to the operating seasons from the multiple alternative prediction models, and training the multiple alternative prediction models by using the starting state and the environmental data of the air conditioner in each operating season as training samples through a machine learning algorithm.
The operating season is determined according to the operating state of the air conditioner, and may be generally a period of time during which the air conditioner has a typical application environment. For example, the operating season includes any one or more of: a cooling season, a heating season, a plum rain season (or called a rain season or a wet season), and a haze removing season (or called a purification season), and those skilled in the art can configure an operating season according to the climate characteristics of the area where the air conditioner is located and the demand of the user on the environment. For example, for a hot zone, only a cooling season and a humid season may be configured; for areas with clear four seasons, a refrigeration season and a heating season can be configured; to the region that has monsoon weather and the environment is comparatively abominable, can increase and set up except that the haze season.
In the refrigeration season, the priority operation mode of the air conditioner is a refrigeration mode; in the heating season, the preferential operation mode of the air conditioner is a heating mode; in the refrigeration season, the prior operation mode of the air conditioner is a dehumidification mode; in the haze removing season, the preferential operation mode of the air conditioner is a purification mode.
According to the intelligent control method of the air conditioner, the starting state and the environmental data of the air conditioner in each operating season are respectively used as training samples, and a plurality of alternative prediction models are obtained through machine learning algorithm training. The multiple alternative prediction models correspond to the operating seasons one by one, and the selected startup prediction model is matched with the current operating season, so that the prediction calculation difficulty of the startup prediction model is reduced, the obtained startup adjustment and startup parameters better meet the environmental adjustment requirements of the operating seasons, and the use experience of users is improved.
One alternative way to determine the operating season in which the air conditioner is located is to: acquiring installation position information of an air conditioner; determining the climate rule of the area where the air conditioner is located according to the installation position information; and matching the environmental data of the operating environment in the preset time period with the climate rule to determine the operating season of the air conditioner. The installation position information of the air conditioner can be determined through the sales and maintenance records of the air conditioner, can also be determined through the report of a user of the air conditioner, and can also be determined through the position of a terminal bound with the air conditioner. For example, the environmental data of the previous 5 to 10 days of the operating environment is matched with the climate rule, so that the operating season of the air conditioner can be determined.
Due to the fact that different regions have different climate laws, the operating seasons can be determined by the climate laws, and as described above, the different regions can set the corresponding operating seasons according to the climate. For example, outdoor environment data within a set time (for example, 5 to 10 days) of the air conditioner may be matched with the climate rule, for example, for north China, the average temperature is lower than 10 ℃ for 5 consecutive days, which means that the air conditioner enters the heating season; the average temperature is higher than 22 ℃ for 5 continuous days, and the season can be considered to enter the refrigeration season.
Another alternative way to determine the operating season in which the air conditioner is located is: acquiring seasonal information of an area where an air conditioner is located, which is published by a weather platform; and determining the operating season of the air conditioner according to the season information. For example, for the Beijing area, 11 in the middle of the month to 3 in the next year may be the heating season, and 6 in the middle of the month to 3 in the next year may be the cooling season; for example, in the Shanghai region, the season of plum rain is from 6 to 7 in the middle of the month; the heating season may be from the middle ten days of 12 months to the end of 2 months. The weather platform can inform the season information according to the meteorological data, so that the operating season of the air conditioner can be determined according to the season information in the announcement.
The manner of determining the operating season of the air conditioner is not limited to the above manner, and may be determined by a manual setting manner in some embodiments. For example, a reminding message can be provided to the user when the season change time is close, and the operating season is manually set by the user.
Under the condition that the determined operating season changes from the operating season determined by the last operation of the air conditioner, operating season replacement prompt information can be output; and acquiring response operation for the operating season replacement prompt information fed back by the user, and determining operating season replacement under the condition that the operating season is confirmed by the response operation instruction. That is to say, under the condition of season change, the user can be reminded, and after the user confirms, the starting prediction model is adjusted according to the characteristics of the operating season.
The air conditioner on prediction model corresponding to the operating season preferably uses the on prediction model used in the same operating season of the last year. Because the starting prediction model used in the same operating season of the last year is generally subjected to iterative training by using the actual operating data of the air conditioner, the actual requirements of the user of the air conditioner are better met. The step of obtaining the start-up prediction model of the air conditioner may include: acquiring an operation record of the air conditioner; judging whether the air conditioner calls a starting prediction model or not according to the operation record; if so, acquiring a previously called starting prediction model; if not, an initial starting prediction model configured for the area where the air conditioner is located is obtained.
The operation records may be used to record various operation data of the air conditioner, including but not limited to: startup and shutdown records, parameter adjustment records, model use records, model training records, user manual adjustment records, environmental data and the like. The operation record of the air conditioner may determine whether the start-up prediction model used in the same operation season of the previous year or the currently determined start-up prediction model was invoked by the user. The used starting prediction model is preferably adopted, so that the use habit of a user can be better met.
The method also comprises the following steps under the condition that the air conditioner does not call a starting prediction model corresponding to the operating season: and acquiring an initial startup prediction model of the operating season configured for the area where the air conditioner is located. The initial startup prediction model in the operating season can be obtained by training the startup data of the area where the air conditioner is located, and the large data sample is preferentially used for training, so that the climate characteristics of the area and the use preference of the air conditioner of users in the area can be fully reflected. That is, in the case that the startup prediction model corresponding to the operating season has not been called before by the controlled air conditioner, the initial startup prediction model of the area where the controlled air conditioner is located is used to perform the prediction calculation of the self-adjusting model, and the comfort requirement of most users can be met with a high probability.
Further, after the air conditioner is started to operate, the self-adjusting model for self-adjusting the air conditioner may also correspond to an operating season, for example, after the step of controlling the air conditioner to start with the start-up parameters, the method further includes: acquiring a self-adjusting model corresponding to an operating season, wherein the self-adjusting model is obtained by taking the operating state of the air conditioner in the operating season and corresponding environmental data as training samples through a machine learning algorithm; acquiring the running state and environmental parameters of the air conditioner; inputting the running state and the environmental parameters into a self-adjusting model; carrying out prediction calculation by using a self-adjusting model to obtain a self-adjusting strategy of the air conditioner; and adjusting the air conditioner according to the self-adjusting strategy.
The self-adjusting model respectively carries out model training aiming at a specific operating season, so that the self-adjusting model corresponds to the operating season, the obtained control strategy basically accords with the characteristics of the operating season, and the use experience of a user is improved. The self-adjusting model mainly aims at adjusting the state of the air conditioner according to the change of environmental parameters and user states after the air conditioner is started. The determination mode of the self-adjusting model and the determination mode of the starting prediction model can be the same, the model used before is preferably selected, and then the big data of the area where the air conditioner is located can be selected to be trained to obtain the initial model. In some embodiments, the on-prediction model and the self-adjustment model may be determined simultaneously.
Fig. 4 is a flowchart of an application example of an intelligent control method of an air conditioner according to an embodiment of the present invention. The application example can comprise the following steps:
step S402, determining the operating season of the air conditioner, wherein the determining mode can comprise weather rule, receiving broadcast information of a weather platform, time judgment and the like.
Step S404, judging whether the operating season changes, namely judging whether the determined operating season changes with the operating season determined by the last operation of the air conditioner, thereby judging whether the season change occurs. For example, in the middle of 6 months, the average temperature is higher than 22 ℃ for 5 consecutive days, and it is judged that the season enters the cooling season.
Step S406, outputting operating season replacement prompt information after determining that the operating season changes;
step S408, whether a confirmation response for the replacement prompt information of the operating season fed back by the user is acquired or not is judged;
step S410, judging whether the air conditioner calls a starting prediction model and a self-adjusting model corresponding to the operating season;
step S412, if not, obtaining an initial starting prediction model and an initial self-adjusting model configured for the area where the air conditioner is located;
step S414, if the model is called, a starting prediction model and a self-adjusting model which are called before and correspond to the operating season are obtained;
step S416, acquiring the running state and the environmental parameters of the air conditioner, inputting the running state and the environmental parameters into a starting prediction model, and performing prediction calculation by using the starting prediction model to obtain the starting conditions and the starting parameters of the air conditioner;
step S418, after the starting condition is met, controlling the air conditioner to start according to the starting parameter;
step S420, obtaining the environmental parameters and the operating state of the air conditioner after the air conditioner is started, inputting the operating state and the environmental parameters into a self-adjusting model, and performing prediction calculation by using the self-adjusting model to obtain a self-adjusting strategy of the air conditioner;
step S422, adjusting the air conditioner according to a self-adjusting strategy;
step S424, acquiring a manual adjustment instruction of the air conditioner;
and step S426, taking the manual adjustment record and the environmental parameters during the manual adjustment as training samples, and performing iterative training on the startup prediction model and/or the self-adjustment model, wherein if the manual adjustment occurs within the set time after startup, the manual adjustment can be used for performing iterative training on the startup prediction model, and if the manual adjustment occurs in the stage after the set time after startup, the manual adjustment can be used for performing iterative training on the self-adjustment model.
It should be understood by those skilled in the art that the above-mentioned flow is only an application example, and the execution order of the steps and the addition and deletion of some steps may be adjusted based on the description of the intelligent control method for the air conditioner in this embodiment. For the case that the air conditioner is not in a typical operating season or there is no operating season or corresponding start-up prediction model and/or self-adjusting model (for example, the case that the weather changes frequently and randomly or the turn-on rate of the air conditioner is small), the method of this embodiment may also preferably provide a manual control option for the user or configure a general model.
Thus, it should be appreciated by those skilled in the art that while a number of exemplary embodiments of the invention have been illustrated and described in detail herein, many other variations or modifications consistent with the principles of the invention may be directly determined or derived from the disclosure of the present invention without departing from the spirit and scope of the invention. Accordingly, the scope of the invention should be understood and interpreted to cover all such other variations or modifications.
Claims (10)
1. An intelligent control method of an air conditioner comprises the following steps:
acquiring environmental parameters of the running environment of the air conditioner when the air conditioner is in a standby state;
acquiring a starting prediction model of the air conditioner, wherein the starting prediction model is obtained by training through a machine learning algorithm by using the starting state of the air conditioner and corresponding environmental data as training samples;
inputting the environmental parameters into the power-on prediction model; and
performing prediction calculation by using the starting prediction model to obtain starting conditions and starting parameters of the air conditioner;
and controlling the air conditioner to start according to the starting-up parameters after the starting-up conditions are met.
2. The intelligent control method of an air conditioner according to claim 1, further comprising, after the step of controlling the air conditioner to start up with the startup parameters:
acquiring a manual adjustment instruction of the air conditioner;
and taking the set parameters in the manual adjustment instruction and the environmental parameters during the manual adjustment as training samples, and performing iterative training on the starting prediction model.
3. The intelligent control method of an air conditioner according to claim 1, wherein the step of obtaining a turn-on prediction model of the air conditioner includes:
determining the operating season of the air conditioner;
and selecting a starting prediction model corresponding to the operating seasons from a plurality of alternative prediction models, and training the plurality of alternative prediction models by using the starting state and the environmental data of the air conditioner in each operating season as training samples through a machine learning algorithm.
4. The intelligent control method of an air conditioner according to claim 3, wherein the step of determining the operating season in which the air conditioner is located comprises:
acquiring installation position information of the air conditioner;
determining the climate rule of the area where the air conditioner is located according to the installation position information;
and matching the environmental data of the operating environment in the previously set time period with the climate rule to determine the operating season of the air conditioner.
5. The intelligent control method of an air conditioner according to claim 3, wherein the step of determining an operating season in which the air conditioner is located comprises:
acquiring seasonal information of an area where the air conditioner is located, which is published by a weather platform;
and determining the operating season of the air conditioner according to the season information.
6. The intelligent control method of the air conditioner according to claim 3, further comprising, after the step of controlling the air conditioner to start up with the startup parameters:
acquiring a self-adjusting model corresponding to the operating season, wherein the self-adjusting model is obtained by training through a machine learning algorithm by using the operating state of the air conditioner in the operating season and corresponding environmental data as training samples;
acquiring the running state and the environmental parameters of the air conditioner;
inputting the operating state and the environmental parameter into the self-adjusting model;
carrying out predictive calculation by using the self-adjusting model to obtain a self-adjusting strategy of the air conditioner; and
and adjusting the air conditioner according to the self-adjusting strategy.
7. The intelligent control method of an air conditioner according to claim 3, further comprising, after the step of determining an operating season in which the air conditioner is located:
under the condition that the determined operating season changes from the operating season determined by the last operation of the air conditioner, outputting operating season replacement prompt information;
and acquiring response operation of the operating season replacement prompt information fed back by a user, and executing the step of acquiring a self-adjusting model corresponding to the operating season under the condition that the response operation indicates that the operating season is confirmed.
8. The intelligent control method of an air conditioner according to claim 3, wherein,
the operating season includes any one or more of: a cooling season, a heating season, a plum rain season, and a haze removing season, wherein
In the refrigerating season, the priority operation mode of the air conditioner is a refrigerating mode;
in the heating season, the preferential operation mode of the air conditioner is a heating mode;
in the refrigerating season, the priority operation mode of the air conditioner is a dehumidification mode;
and in the haze removing season, the priority operation mode of the air conditioner is a purification mode.
9. The intelligent control method of an air conditioner according to claim 1, wherein the step of obtaining a turn-on prediction model of the air conditioner includes:
acquiring an operation record of the air conditioner;
judging whether the air conditioner calls a starting prediction model or not according to the operation record;
if so, acquiring the called starting prediction model;
if not, obtaining an initial starting prediction model configured for the area where the air conditioner is located.
10. An intelligent control apparatus of an air conditioner, comprising:
a processor; and
a memory in which a control program is stored, the control program being executed by the processor to implement the intelligent control method of the air conditioner according to any one of claims 1 to 9.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010889187.0A CN112128936B (en) | 2020-08-28 | 2020-08-28 | Intelligent control method and intelligent control equipment for air conditioner |
PCT/CN2021/102123 WO2022041988A1 (en) | 2020-08-28 | 2021-06-24 | Smart control method and smart control device for air conditioner |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010889187.0A CN112128936B (en) | 2020-08-28 | 2020-08-28 | Intelligent control method and intelligent control equipment for air conditioner |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112128936A true CN112128936A (en) | 2020-12-25 |
CN112128936B CN112128936B (en) | 2022-08-19 |
Family
ID=73847587
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010889187.0A Active CN112128936B (en) | 2020-08-28 | 2020-08-28 | Intelligent control method and intelligent control equipment for air conditioner |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN112128936B (en) |
WO (1) | WO2022041988A1 (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113790503A (en) * | 2021-11-11 | 2021-12-14 | 成都联帮医疗科技股份有限公司 | Dispersion oxygen supply terminal machine capable of intelligently adjusting oxygen supply state and control method thereof |
CN113847681A (en) * | 2021-08-31 | 2021-12-28 | 青岛海尔空调电子有限公司 | Air conditioner and control method thereof |
WO2022041988A1 (en) * | 2020-08-28 | 2022-03-03 | 青岛海尔空调器有限总公司 | Smart control method and smart control device for air conditioner |
WO2022156301A1 (en) * | 2021-01-19 | 2022-07-28 | 青岛海尔空调器有限总公司 | Control method for air conditioner, and terminal device, server, and control system for air conditioner |
EP4293432A4 (en) * | 2021-02-10 | 2024-03-20 | Digital Arts Inc | Information processing system, information processing method, and information processing program |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115065709A (en) * | 2022-03-10 | 2022-09-16 | 青岛海尔空调器有限总公司 | Information processing method, device and system |
CN114992814B (en) * | 2022-06-20 | 2023-12-15 | 南京天加环境科技有限公司 | Control method and system for comfort of air conditioner and air conditioner |
CN115200155B (en) * | 2022-07-26 | 2023-11-14 | 珠海格力电器股份有限公司 | Air conditioner control method and device, air conditioner and storage medium |
CN117308288B (en) * | 2023-09-21 | 2024-04-19 | 中国工业互联网研究院 | Method and device for predictive control of start and stop of wire-making air conditioner |
CN117216505B (en) * | 2023-11-09 | 2024-03-19 | 广州视声智能股份有限公司 | User habit prediction method and system based on smart home use record |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106547897A (en) * | 2016-10-31 | 2017-03-29 | 广东美的制冷设备有限公司 | The method and device of air-conditioner is matched based on geographical position |
CN108278737A (en) * | 2017-12-20 | 2018-07-13 | 珠海格力节能环保制冷技术研究中心有限公司 | A kind of control method of air-conditioning, device, storage medium, air-conditioning and remote controler |
CN108361927A (en) * | 2018-02-08 | 2018-08-03 | 广东美的暖通设备有限公司 | A kind of air-conditioner control method, device and air conditioner based on machine learning |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5012777B2 (en) * | 2008-12-03 | 2012-08-29 | パナソニック株式会社 | Air conditioner |
JP2010151337A (en) * | 2008-12-24 | 2010-07-08 | Daikin Ind Ltd | Air conditioning system |
CN110454930B (en) * | 2018-05-08 | 2020-10-30 | 中国科学院理化技术研究所 | Method and device for estimating optimal thermal comfort of human body and air conditioner control method and device |
CN110030699A (en) * | 2019-04-04 | 2019-07-19 | 珠海格力电器股份有限公司 | A kind of air-conditioning equipment control method, air-conditioning and storage medium |
CN112128936B (en) * | 2020-08-28 | 2022-08-19 | 青岛海尔空调器有限总公司 | Intelligent control method and intelligent control equipment for air conditioner |
-
2020
- 2020-08-28 CN CN202010889187.0A patent/CN112128936B/en active Active
-
2021
- 2021-06-24 WO PCT/CN2021/102123 patent/WO2022041988A1/en active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106547897A (en) * | 2016-10-31 | 2017-03-29 | 广东美的制冷设备有限公司 | The method and device of air-conditioner is matched based on geographical position |
CN108278737A (en) * | 2017-12-20 | 2018-07-13 | 珠海格力节能环保制冷技术研究中心有限公司 | A kind of control method of air-conditioning, device, storage medium, air-conditioning and remote controler |
CN108361927A (en) * | 2018-02-08 | 2018-08-03 | 广东美的暖通设备有限公司 | A kind of air-conditioner control method, device and air conditioner based on machine learning |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022041988A1 (en) * | 2020-08-28 | 2022-03-03 | 青岛海尔空调器有限总公司 | Smart control method and smart control device for air conditioner |
WO2022156301A1 (en) * | 2021-01-19 | 2022-07-28 | 青岛海尔空调器有限总公司 | Control method for air conditioner, and terminal device, server, and control system for air conditioner |
EP4293432A4 (en) * | 2021-02-10 | 2024-03-20 | Digital Arts Inc | Information processing system, information processing method, and information processing program |
CN113847681A (en) * | 2021-08-31 | 2021-12-28 | 青岛海尔空调电子有限公司 | Air conditioner and control method thereof |
CN113790503A (en) * | 2021-11-11 | 2021-12-14 | 成都联帮医疗科技股份有限公司 | Dispersion oxygen supply terminal machine capable of intelligently adjusting oxygen supply state and control method thereof |
Also Published As
Publication number | Publication date |
---|---|
CN112128936B (en) | 2022-08-19 |
WO2022041988A1 (en) | 2022-03-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112128936B (en) | Intelligent control method and intelligent control equipment for air conditioner | |
US10921760B2 (en) | Predictive control loops using time-based simulation and building-automation systems thereof | |
CN112128934A (en) | Intelligent control method and intelligent control equipment for air conditioner | |
CN108488987B (en) | Control method of air conditioning apparatus, storage medium, and apparatus | |
WO2021179958A1 (en) | Intelligent control method for air conditioner, and intelligent control device for air conditioner | |
CN108052010B (en) | Intelligent electric appliance self-adjusting method and device, computer equipment and storage medium | |
US11374409B2 (en) | Power system load flexibility forecasting | |
CN108767866B (en) | Energy management method, device and system | |
CN112128935B (en) | Intelligent control method and intelligent control equipment for air conditioner | |
CN106979599A (en) | Household appliance control method and device, server | |
CN113377018A (en) | Intelligent control method and intelligent control equipment of air conditioner | |
CN111895625A (en) | Indoor environment improvement method and system based on neural network algorithm and storage medium | |
CN112415902A (en) | Method and device for controlling intelligent household appliance and intelligent household appliance | |
CN112162492A (en) | Control method and device of household equipment, edge computing gateway and storage medium | |
CN114838470A (en) | Control method and system for heating, ventilating and air conditioning | |
CN110442171A (en) | Building environment control method, device, equipment, storage medium and system | |
CN108419439B (en) | Household equipment learning method and server | |
KR101779797B1 (en) | Self-learning HAVC energy management system using big data, and the operating method thereof | |
CN114442697B (en) | Temperature control method, equipment, medium and product | |
CN110726214A (en) | Method and device for controlling air conditioner | |
CN115051374A (en) | Control method and device for electric heating equipment to participate in electric power peak regulation and storage medium | |
CN109579216B (en) | Control method, control device, air conditioning equipment, remote control terminal and storage medium | |
CN113310176A (en) | Information processing apparatus | |
CN107436015A (en) | Control method, air-conditioning and the air-conditioning system of air-conditioning dominant parasitic device | |
WO2019084784A1 (en) | Intelligent temperature control method and apparatus, storage medium, central temperature controller and server |
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 | ||
CB03 | Change of inventor or designer information | ||
CB03 | Change of inventor or designer information |
Inventor after: Song Yujun Inventor after: Song Shifang Inventor after: Yan Changjuan Inventor after: Guo Li Inventor after: Wu Liqin Inventor after: Liu Wentao Inventor before: Song Shifang Inventor before: Guo Li Inventor before: Wu Liqin Inventor before: Liu Wentao |