WO2019214230A1 - 一种空调除霜的方法及设备 - Google Patents

一种空调除霜的方法及设备 Download PDF

Info

Publication number
WO2019214230A1
WO2019214230A1 PCT/CN2018/120931 CN2018120931W WO2019214230A1 WO 2019214230 A1 WO2019214230 A1 WO 2019214230A1 CN 2018120931 W CN2018120931 W CN 2018120931W WO 2019214230 A1 WO2019214230 A1 WO 2019214230A1
Authority
WO
WIPO (PCT)
Prior art keywords
air conditioner
frosting
level
operating parameters
defrosting
Prior art date
Application number
PCT/CN2018/120931
Other languages
English (en)
French (fr)
Inventor
陈翀
宋德超
杨赛赛
Original Assignee
珠海格力电器股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 珠海格力电器股份有限公司 filed Critical 珠海格力电器股份有限公司
Publication of WO2019214230A1 publication Critical patent/WO2019214230A1/zh

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
    • 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
    • F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
    • F24F11/41—Defrosting; Preventing freezing
    • 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
    • F24F11/89—Arrangement or mounting of control or safety devices

Definitions

  • the present application relates to the field of air conditioning technology, and in particular, to a method and an apparatus for defrosting an air conditioner.
  • the timing of determining the defrosting by the air conditioner is based on a fixed determination condition determined empirically. For example, the timing of the defrosting is determined based on the difference between the outdoor temperature and the evaporator temperature, although defrosting can be performed, but it is not flexible. For example, if the air conditioner does not have frost, but it is determined that the defrosting is required, or when the air conditioner frost is very serious, the defrosting is performed, that is, there is a case where the frost is not formed and the defrosting is frequently performed.
  • the embodiment of the present application provides a method and a device for defrosting an air conditioner, which are used for improving the accuracy of an air conditioner defrosting timing.
  • a method for defrosting an air conditioner comprising:
  • M is a positive integer
  • the embodiment of the present application considers that the operating parameters of the air conditioner have an impact on the settlement condition of the air conditioner. Therefore, the defrosting method provided by the embodiment of the present application comprehensively considers the operating parameters of the air conditioner, and determines the current frosting level of the air conditioner according to the operating parameters of the air conditioner. Therefore, it is determined whether the air conditioner needs to be defrosted according to the determined frosting level, and if the defrosting is required, a defrosting command for controlling the air conditioner to perform defrosting is generated.
  • the fixed judgment condition determined based on experience is more flexible as the timing of determining the defrosting time, and is more consistent with the actual frosting condition of the air conditioner, and the accuracy of determining the defrosting timing is improved, and the air conditioner can be prevented from frosting as much as possible.
  • determining the M operating parameters of the air conditioner operation including:
  • This optional method describes how to screen the operating parameters that have a greater impact on the frosting of the air conditioner, so that only the operating parameters that have a greater impact on the frosting of the air conditioner can be analyzed, without the need to analyze the full operation of the air conditioner.
  • the parameters reduce the amount of calculation and reduce the burden on the air conditioner.
  • the method before analyzing the M operating parameters to determine a current frost level of the air conditioner, the method further includes:
  • the training data set includes a relationship between a plurality of frosting levels and operating parameters, and each of the relationship pairs corresponds to a plurality of operating parameters;
  • the function model is trained by using the training data set until the value of the output of the function model reaches a set standard to obtain a defrost model;
  • the M operating parameters are analyzed to determine the current frost level of the air conditioner, including:
  • This alternative manner describes how to determine the current frosting level of the air conditioner according to the operating parameters of the air conditioner.
  • the embodiment of the present application learns the operating parameters of the air conditioner by means of deep learning, thereby obtaining a defrost model, wherein the defrost model
  • the input is the operating parameter and the output is the probability of multiple frost levels so that the current frost level of the air conditioner can be determined based on the probability of each frost level.
  • determining a frost level of the air conditioner according to a probability of a plurality of frosting levels output by the defrosting model including:
  • the first frost level is determined as the current frost level of the air conditioner.
  • This alternative provides two ways to determine the current frost level of the air conditioner by the probability of the frost level, and any one of the probabilities of satisfying the first condition, ie, multiple frost levels, is greater than a preset threshold. Then, the frosting level corresponding to any one of the probabilities can be determined as the frosting level of the air conditioner. If the probability of multiple frosting levels is less than or equal to the preset third threshold, then the probability of multiple frosting levels is not much different, which requires further determining which level of multiple frosting levels is the current knot of the air conditioner.
  • the frost level is such that it is more accurate to determine the current frost level of the air conditioner.
  • an air conditioning defrosting device comprising:
  • a first determining unit configured to determine M operating parameters of the air conditioning operation, where M is a positive integer
  • a second determining unit configured to analyze the M operating parameters to determine a current frosting level of the air conditioner, wherein the frosting level is used to indicate a current frosting condition of the air conditioner, and different operating parameters cause the air conditioner to The level of frosting varies differently;
  • the transmitting unit is configured to determine whether it is necessary to perform defrosting processing on the air conditioner according to the current frosting level, and if necessary, generate a defrosting command for controlling the air conditioner to perform defrosting.
  • the first determining unit is specifically configured to:
  • it also includes:
  • the training unit is configured to acquire a training data set and determine a function model of the frost level and the corresponding plurality of operating parameters of each relationship before analyzing the M operating parameters to determine a current frost level of the air conditioner.
  • the second determining unit is specifically configured to:
  • the second determining unit is specifically configured to:
  • the first frost level is determined as the current frost level of the air conditioner.
  • an air conditioning defrosting device is provided, and the air defrosting device includes:
  • At least one processor and
  • a memory coupled to the at least one processor
  • the memory stores instructions executable by the at least one processor, the at least one processor implementing the method of any of the first aspects by executing the memory stored instructions.
  • a computer storage medium having stored thereon a computer program, the computer program being executed by a processor to implement the method of any of the above embodiments.
  • the embodiment of the present application considers that the operating parameters of the air conditioner have an impact on the settlement condition of the air conditioner. Therefore, the defrosting method provided by the embodiment of the present application comprehensively considers the operating parameters of the air conditioner, and determines the current frosting level of the air conditioner according to the operating parameters of the air conditioner. Therefore, it is determined whether the defrosting process needs to be performed on the air conditioner according to the determined current frosting level, and if the defrosting is required, a defrosting command for controlling the air conditioner to perform defrosting is generated.
  • the fixed judgment condition determined based on experience is more flexible as the timing of determining the defrosting time, and is more consistent with the actual frosting condition of the air conditioner, and the accuracy of determining the timing of the defrosting is improved, and the air conditioner can be avoided as much as possible.
  • the frost is determined to be defrosted, or the defrosting is performed when the air conditioning frost is severe.
  • FIG. 1 is a schematic flow chart of a method for defrosting an air conditioner provided by one embodiment of the present application
  • FIG. 2 is a schematic structural diagram of an apparatus for defrosting an air conditioner according to an embodiment of the present disclosure
  • FIG. 3 is a schematic structural diagram of an apparatus for defrosting an air conditioner according to an embodiment of the present application.
  • the timing of determining the defrosting by the air conditioner is based on a fixed determination condition determined empirically. For example, the timing of the defrosting is determined based on the difference between the outdoor temperature and the evaporator temperature, although defrosting can be performed, but it is not flexible. For example, if the air conditioner does not have frost, but it is determined to be defrosted, or when the air conditioner frost is very serious, the defrosting is performed, and it can be seen that the current air conditioner determines the timing of the defrosting to be less accurate.
  • the embodiment of the present application considers that the operating parameters of the air conditioner may affect the settlement condition of the air conditioner. Therefore, the defrosting method provided by the embodiment of the present application comprehensively considers the operating parameters of the air conditioner, and determines the current knot of the air conditioner according to the operating parameters of the air conditioner. The frost level, thereby determining whether the air conditioner needs to be defrosted according to the determined current frosting level, and if the defrosting is required, a defrosting command for controlling the air conditioner to perform defrosting is generated.
  • the fixed judgment condition determined based on experience is more flexible as the timing of determining the defrosting time, and is more consistent with the actual frosting condition of the air conditioner, and the accuracy of determining the timing of the defrosting is improved, and the air conditioner can be avoided as much as possible.
  • the frost is determined to be defrosted, or the defrosting is performed when the air conditioning frost is severe.
  • the method for defrosting an air conditioner provided by one embodiment of the present application will be described in detail below with reference to FIG. 1.
  • the method can be applied to an air conditioner, and can also be applied to an electronic device connected to an air conditioner, such as a computer or a mobile phone.
  • the specific process is described as follows:
  • S102 analyzing M operating parameters to determine a current frosting level of the air conditioner, wherein the frosting level is used to indicate the current frosting condition of the air conditioner, and different operating parameters cause different changes in the frosting level of the air conditioner;
  • S103 Determine whether it is necessary to perform defrosting processing on the air conditioner according to the current frosting level, and if necessary, generate a defrosting command for controlling the air conditioner to perform defrosting.
  • the air conditioning frosting is related to the operating parameters of the air conditioner.
  • the operating parameters of the air conditioner may include condensation temperature, evaporation temperature, condensing pressure, evaporation pressure, oil temperature, duration and current, etc., and these operating parameters affect more or less
  • the frosting of air conditioners such as the thickness of frosting and/or the density of frosting, may also vary depending on the operating parameters.
  • the frosting level is used to indicate the frosting condition of the air conditioner, and the frosting condition can be divided into a plurality of frosting levels.
  • the frosting level is 0, it means that the air conditioner has no frosting; if the frosting level is 1, Then it means that the thickness of the air-conditioning frost is thinner or the density of frosting is sparse; if the frosting level is 2, it means that the thickness of the air-conditioning frost is thicker or the density of frosting is thicker.
  • the division of the frosting level can be divided according to experience, and the embodiment of the present application does not limit the number of levels of the frosting level.
  • the operating parameters of air conditioners include various types. The effects of different operating parameters on the frosting of air conditioners may also be different. Some operating parameters have a greater impact on the frosting of air conditioners, and some operating parameters are related to the air conditioning. The influence of the frost condition is small. If the frosting condition of the air conditioner is determined according to all the operating parameters of the air conditioner, it is obvious that the calculation amount is large. Therefore, the embodiment of the present application can determine the operating parameter that has a large influence on the frosting condition of the air conditioner. The frosting of the air conditioner reduces the amount of calculation and reduces the burden on the equipment for air conditioning defrosting.
  • the embodiment of the present application may determine M operating parameters of the air conditioner operation, where M is a positive integer, and the M operating parameters may be considered as operating parameters that have a greater influence on the frosting condition of the air conditioner, thereby operating the M
  • the parameters are analyzed to determine the current frost level of the air conditioner, ie the current frost condition of the air conditioner.
  • the data set of the air conditioner operation and the corresponding frost level may be collected, wherein the data set includes the values of the N operating parameters of the air conditioner, and N is a positive integer.
  • the N operating parameters may be all operating parameters of the air conditioning operation, or may be partial operating parameters selected from all operating parameters of the air conditioning operation according to experience.
  • the data set and the corresponding frost level can be analyzed, and the correlation degree between each running parameter and the frosting level is obtained.
  • the embodiment of the present application can reduce the type or quantity of operating parameters in the data set.
  • the thickness and/or density of the air conditioner frost is obtained by directly measuring or collecting the frosting image of the air conditioner through the photoelectric device, thereby determining the frosting of the air conditioner. grade.
  • the embodiment of the present application may select an operating parameter whose correlation degree is greater than the first threshold as the M operating parameters.
  • the first threshold may be a possible value set according to experience, for example 30%.
  • the embodiment of the present application can determine the defrosting model before analyzing the M operating parameters to determine the current frosting level of the air conditioner, wherein the defrosting model is obtained by layer-by-layer training of at least one operating parameter through the deep learning network.
  • the embodiment of the present application may obtain a training data set, where the training data set includes a relationship between a plurality of frosting levels and operating parameters, and each of the relationship pairs corresponds to a plurality of operating parameters.
  • the embodiment of the present application establishes a function model of each relationship centering frost level and a corresponding plurality of operating parameters, wherein the input of the function model is a plurality of operating parameters, and the output is a probability of multiple frosting levels. Therefore, after obtaining the training data set, the embodiment of the present application can perform the supervised training on the function model by using the training data set until the value of the function model output reaches the set standard, that is, the trained function model is a superior prediction model. Obtain a defrost model.
  • the setting criterion can be used to indicate the probability that the frosting level is close to the true level.
  • the value of the output of the function model after training reaches the set standard, that is, when the training function model is trained, the value of the output of the training function model indicates the error of the frost level. Small, at this time, it can be considered that the accuracy of the analysis of the operating parameters by the trained function model is high.
  • the process of obtaining the defrosting model in the training data set of the embodiment of the present application may be implemented on the air conditioning side, or may be implemented by a device connected to the air conditioner, such as a gateway device or a server, and may be sent to the air conditioner after the server obtains the defrosting model, for example, It is sent to the air conditioner via a wireless network or the like, thus reducing the burden on the air conditioner.
  • a device connected to the air conditioner such as a gateway device or a server
  • it can also be implemented by air conditioning and equipment connected to the air conditioner.
  • the training data set is implemented by equipment connected to the air conditioner.
  • the optimized defrost model can be implemented by the air conditioner itself, and the optional deployment can be determined according to cost and/or computing resources.
  • the data structure of the training data set obtained by the embodiment of the present application may be various.
  • the data in the data set may be stored in time series, may be stored in a matrix form, or may be stored in a list form.
  • embodiments of the present application may use different deep learning networks, such as a cyclic neural network or a convolutional neural network.
  • the input operational parameters can be considered to be time dependent
  • the deep learning network can be a cyclic neural network, taking into account the effects of time as much as possible, thereby improving the accuracy of the resulting defrost model.
  • the defrost model analyzes the operating parameters to determine the current frost level of the air conditioner.
  • the defrosting model outputs a probability of a plurality of frosting levels, so that the current frosting level of the air conditioner can be determined according to the probability of the plurality of frosting levels.
  • the sum of multiple probabilities is 100%.
  • the probability of a frosting level is large, so the current frosting level of the air conditioner is more likely to be the frosting level.
  • the frosting level corresponding to the first probability is determined as the current frosting level of the air conditioner.
  • the first probability may be regarded as any one of a plurality of probabilities, and the preset second threshold may be a value set in advance, for example, 90%. If the first probability is greater than a preset second threshold, then the first The frost level corresponding to a probability is more likely to be the current frost level of the air conditioner than the frost level corresponding to the other probability. Therefore, the embodiment of the present application can determine the frost level corresponding to the first probability.
  • the preset third threshold may be a value set in advance, for example, 30%, which may be for the first knot.
  • the frost level determines a plurality of probabilities that the first frosting level is within a preset time period, for example, the determined plurality of probabilities may be 89%, 90%, 88 %, 25%, etc., then it can be determined that if the number of the probability that the plurality of probabilities are less than or equal to the preset third threshold is small, it can be considered that the error of the first frost level determined at the current time is large, The probability of the current first frost level can be ignored.
  • the first frosting level is determined as the current frosting level of the air conditioner, so that it is more accurate to determine the current frosting level of the air conditioner.
  • the embodiment of the present application can determine whether the defrosting of the air conditioner is to be performed according to the actual frosting condition of the air conditioner, that is, the defrosting timing of the air conditioner is determined, and if it is determined that the air conditioner is to be defrosted, the air conditioner defrosting device in the embodiment of the present application, for example, The air conditioner or the electronic device connected to the air conditioner can generate a defrosting command for controlling the air conditioner to perform defrosting, and generate a defrosting command to send the defrosting command to the air conditioner, so that the air conditioner can defrost the air conditioner according to the received defrosting command.
  • the embodiment of the present application determines that the air conditioner is defrosted according to the current frosting level of the air conditioner, and generates a defrosting command for controlling the air conditioner to perform defrosting, wherein the defrosting parameter carried by the defrosting command, for example, the power parameter of the air conditioning operation Matches the current frost level of the air conditioner. Therefore, the air conditioner receives the defrosting command and executes the defrosting command to achieve defrosting of the air conditioner.
  • the embodiment of the present application considers that the operating parameters of the air conditioner may affect the frosting condition of the air conditioner. Therefore, the defrosting method provided by the embodiment of the present application comprehensively considers the operating parameters of the air conditioner, and determines the current air conditioning according to the operating parameters of the air conditioner. The frosting level is determined according to the determined current frosting level whether it is necessary to perform defrosting treatment on the air conditioner, and if defrosting is required, a defrosting command for controlling the air conditioner to perform defrosting is generated.
  • the fixed judgment condition determined based on experience is more flexible as the timing of determining the defrosting time, and is more consistent with the actual frosting condition of the air conditioner, and the accuracy of determining the timing of the defrosting is improved, and the air conditioner can be avoided as much as possible.
  • the frost is determined to be defrosted, or the defrosting is performed when the air conditioning frost is severe.
  • the embodiment of the present application can flexibly select the determining manner according to the multiple probabilities, thereby improving the accuracy of determining the current frosting level of the air conditioner.
  • an embodiment of the present application provides an air conditioning defrosting device, which may include a first determining unit 201, a second determining unit 202, and a transmitting unit 203.
  • the apparatus that the first determining unit 201 is set to support the air conditioning defrosting performs step S101 in FIG.
  • the second determining unit 202 is arranged to support the air conditioning defrosting device to perform step S102 in FIG.
  • the transmitting unit 203 is provided to support the air conditioner defrosting apparatus to perform step S103 in FIG. All the related content of the steps involved in the foregoing method embodiments may be referred to the functional descriptions of the corresponding functional modules, and details are not described herein again.
  • the first determining unit 201 is specifically configured to:
  • the data set and the corresponding frost level are analyzed to obtain the correlation degree between each running parameter and the frosting level;
  • the operating parameters whose correlation degree is greater than the first threshold are selected to determine M operating parameters, and M is less than or equal to N.
  • the training unit may further be configured to: before analyzing the M operating parameters, determining the current frost level of the air conditioner, acquiring the training data set, and establishing a frost level and corresponding correspondence in each relationship. a function model of the running parameters, using the training data set to train the function model until the value of the function model output reaches a set standard to obtain a defrost model; wherein the training data set includes a plurality of frosting levels and operating parameters Relationship pairs, one frost level of each relationship pair corresponds to multiple operating parameters; the input of the function model is a plurality of operating parameters, and the output is a probability of multiple frost levels;
  • the second determining unit 202 may be specifically configured to:
  • the current frost level of the air conditioner is determined based on the probability of a plurality of frosting levels output by the defrosting model.
  • the second determining unit 202 may be specifically configured to:
  • the probability of the plurality of frosting levels is less than or equal to the preset third threshold, determining a plurality of probabilities of the first frosting level within the preset time period, wherein the first frosting level is among the plurality of frosting levels Any of the frosting levels;
  • the first frosting level is determined as the current frosting level of the air conditioner.
  • an embodiment of the present application provides an air conditioning defrosting device, which may include at least one processor 301 configured to execute a computer stored in a memory.
  • the steps of the method for providing air conditioning defrosting in the embodiment of the present application are implemented in the program.
  • the processor 301 may be a central processing unit, an application specific integrated circuit (ASIC), and may be one or more integrated circuits configured to control program execution.
  • ASIC application specific integrated circuit
  • the air conditioner defrosting device further includes a memory 302 connected to the at least one processor, and the memory 302 may include a read only memory (English: Read Only Memory, ROM for short), and a random access memory (English: Random Access) Memory, referred to as: RAM) and disk storage.
  • the memory 302 is arranged to store data required for the processor 301 to operate, i.e., to store instructions executable by at least one processor 301, and at least one processor 301 executes the method as shown in FIG. 1 by executing instructions stored in the memory 302. .
  • the number of the memories 302 is one or more. Among them, the memory 302 is shown together in FIG. 3, but it should be understood that the memory 302 is not a mandatory functional module, and thus is shown by a broken line in FIG.
  • the physical devices corresponding to the first determining unit 201, the second determining unit 202, and the sending unit 203 may all be the foregoing processor 301.
  • the air conditioning defrost apparatus can be used to perform the method provided by the embodiment shown in FIG. Therefore, for the functions that can be implemented by the functional modules in the device, refer to the corresponding description in the embodiment shown in FIG. 1, and no further details are provided.
  • the embodiment of the present application further provides a computer storage medium, wherein the computer storage medium stores computer instructions, and when the computer instructions are run on the computer, causes the computer to perform the method as described in FIG.
  • the disclosed apparatus and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the modules or units is only a logical function division.
  • there may be another division manner for example, multiple units or components may be used. Combinations can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • a computer readable storage medium A number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) or a processor to perform all or part of the steps of the methods described in various embodiments of the present application.
  • the foregoing storage medium includes: a Universal Serial Bus flash disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a disk. Or a variety of media such as optical discs that can store program code.
  • the technical solution provided by the embodiment of the present application can be applied to the operation process of the air conditioner, and adopts M operating parameters for determining the air conditioning operation, analyzes the M operating parameters, determines the current frosting level of the air conditioner, and determines according to the current frosting level. Whether it is necessary to perform defrosting treatment on the air conditioner, and if necessary, generate a defrosting command for controlling the defrosting of the air conditioner, and it is more flexible to determine the defrosting timing based on the empirically determined fixed judgment condition as compared with the prior art. It is more consistent with the actual frosting of the air conditioner, which improves the accuracy of determining the timing of the defrosting. It can try to avoid problems such as defrosting when the air conditioner is not frosted, or defrosting when the air conditioner frost is serious.

Landscapes

  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

一种空调除霜的方法及设备，用于提高空调除霜时机的准确度。其中，空调除霜的方法包括：确定空调运行的M个运行参数，M为正整数；对所述M个运行参数进行分析，确定空调当前的结霜等级，其中，所述结霜等级用于指示空调当前的结霜情况，不同的运行参数使所述空调的结霜等级发生不同变化；根据所述当前的结霜等级确定是否需要对所述空调进行除霜处理，若需要则生成用于控制所述空调进行除霜的除霜指令。

Description

一种空调除霜的方法及设备 技术领域
本申请涉及空调技术领域，特别涉及一种空调除霜的方法及设备。
背景技术
冬天空调在制热模式下运行时，室外机容易结霜，影响制热效率，因此需要对空调进行除霜。目前空调确定除霜的时机是基于经验确定的固定判断条件，例如基于室外温度和蒸发器温度的差值确定除霜的时机，虽然可以进行除霜，但是不灵活。例如，空调没有结霜却确定要除霜，或者空调结霜很严重时才进行除霜等，即存在有霜不化、频繁化霜的情况。
可见，目前确定空调除霜时机的准确度较低。
发明内容
本申请实施例提供一种空调除霜的方法及设备，用于提高空调除霜时机的准确度。
在本申请其中一实施例中，提供了一种空调除霜的方法，该方法包括：
确定空调运行的M个运行参数，M为正整数；
对所述M个运行参数进行分析，确定空调当前的结霜等级，其中，所述结霜等级用于指示空调当前的结霜情况，不同的运行参数使所述空调的结霜等级发生不同变化；
根据所述当前的结霜等级确定是否需要对所述空调进行除霜处理，若需要则生成用于控制所述空调进行除霜的除霜指令。
本申请实施例考虑到空调的运行参数会对空调的结算情况有影响，因此，本申请实施例提供的除霜方法综合考虑空调的运行参数，根据空调的运行参数确定空调当前的结霜等级，从而根据确定的结霜等级决定是否需要对空调进行 除霜处理，如果需要除霜才生成用于控制空调进行除霜的除霜指令。相较于现有技术将基于经验确定的固定判断条件作为确定除霜时机更为灵活，更与空调的实际结霜情况相符，提高了确定除霜时机的准确度，可以尽量避免空调没有结霜却确定要除霜，或者空调结霜很严重时才进行除霜等问题。
可选的，确定空调运行的M个运行参数，包括：
采集所述空调运行的数据集及对应的结霜等级，其中，所述数据集包括所述空调的N个运行参数的值，N为正整数；
对所述数据集及对应的结霜等级进行分析，获得每个运行参数与结霜等级的关联度；
选取所述关联度大于第一阈值的运行参数，以确定所述M个运行参数，M小于或等于N。
这种可选的方式描述了如何筛选对空调的结霜情况影响较大的运行参数，这样就可以只分析对空调的结霜情况影响较大的运行参数，而不需要分析空调的全部的运行参数，减少了计算量，减轻了空调的负担。
可选的，在对所述M个运行参数进行分析，确定空调当前的结霜等级之前，还包括：
获取训练数据集，其中，所述训练数据集包括多个结霜等级与运行参数的关系对，每个关系对中一个结霜等级对应多个运行参数；
建立每个关系对中结霜等级与对应的多个运行参数的函数模型，其中，所述函数模型的输入为多个运行参数，输出为多个结霜等级的概率；
利用所述训练数据集对所述函数模型进行训练，直到所述函数模型输出的取值达到设定标准，以获得除霜模型；
对所述M个运行参数进行分析，确定空调当前的结霜等级，包括：
将所述M个运行参数输入所述除霜模型；
根据所述除霜模型输出的多个结霜等级的概率确定所述空调当前的结霜等级。
这种可选的方式描述了如何根据空调的运行参数确定空调当前的结霜等级，本申请实施例通过深度学习的方式对空调的运行参数进行学习，从而获得除霜模型，其中，除霜模型的输入是运行参数，输出是多个结霜等级的概率，从而可以根据每个结霜等级的概率确定空调当前的结霜等级。
可选的，根据所述除霜模型输出的多个结霜等级的概率确定所述空调的结霜等级，包括：
若所述多个结霜等级的概率中的第一概率大于预设第二阈值，则将与所述第一概率对应的结霜等级确定为所述空调当前的结霜等级；
或，
若多个结霜等级的概率都小于或等于预设第三阈值，则确定第一结霜等级在预设时间段内的多个概率，其中，所述第一结霜等级为所述多个结霜等级中的任意一个结霜等级；
确定所述多个概率中小于或等于所述预设第三阈值的概率的数量；
若确定的数量小于预设第四阈值，则将所述第一结霜等级确定为所述空调当前的结霜等级。
这种可选的方式提供了两种通过结霜等级的概率确定空调当前的结霜等级的方式，在满足第一种条件即多个结霜等级的概率中的任意一个概率大于预设阈值，则可以将与任意一个概率对应的结霜等级确定为空调的结霜等级。而如果多个结霜等级的概率都小于或等于预设第三阈值，那么就是多个结霜等级的概率相差不大，这就需要进一步确定多个结霜等级的哪个等级是空调当前的结霜等级，这样确定空调当前的结霜等级就更为准确。
在本申请其中一实施例中，提供了一种空调除霜的设备，该空调除霜的设备包括：
第一确定单元，设置为确定空调运行的M个运行参数，M为正整数；
第二确定单元，设置为对所述M个运行参数进行分析，确定空调当前的结霜等级，其中，所述结霜等级用于指示空调当前的结霜情况，不同的运行参 数使所述空调的结霜等级发生不同变化；
发送单元，设置为根据所述当前的结霜等级确定是否需要对所述空调进行除霜处理，若需要则生成用于控制所述空调进行除霜的除霜指令。
可选的，所述第一确定单元具体设置为：
采集所述空调运行的数据集及对应的结霜等级，其中，所述数据集包括所述空调的N个运行参数的值，N为正整数；
对所述数据集及对应的结霜等级进行分析，获得每个运行参数与结霜等级的关联度；
选取所述关联度大于第一阈值的运行参数，以确定所述M个运行参数，M小于或等于N。
可选的，还包括：
训练单元，设置为在对所述M个运行参数进行分析，确定空调当前的结霜等级之前，获取训练数据集，建立每个关系对中结霜等级与对应的多个运行参数的函数模型，利用所述训练数据集对所述函数模型进行训练，直到所述函数模型输出的取值达到设定标准，以获得除霜模型；其中，所述训练数据集包括多个结霜等级与运行参数的关系对，每个关系对中一个结霜等级对应多个运行参数；所述函数模型的输入为多个运行参数，输出为多个结霜等级的概率；
所述第二确定单元具体设置为：
将所述M个运行参数输入所述除霜模型；
根据所述除霜模型输出的多个结霜等级的概率确定所述空调当前的结霜等级。
可选的，第二确定单元具体设置为：
若所述多个结霜等级的概率中的第一概率大于预设第二阈值，则将与所述第一概率对应的结霜等级确定为所述空调当前的结霜等级；
或，
若多个结霜等级的概率都小于或等于预设第三阈值，则确定第一结霜等级 在预设时间段内的多个概率，其中，所述第一结霜等级为所述多个结霜等级中的任意一个结霜等级；
确定所述多个概率中小于或等于所述预设第三阈值的概率的数量；
若确定的数量小于预设第四阈值，则将所述第一结霜等级确定为所述空调当前的结霜等级。
本申请实施例提供的终端的技术效果可以参见上述实施例的各个实现方式的技术效果，此处不再赘述。
在本申请其中一实施例中，提供一种空调除霜的设备，该空调除霜的设备包括：
至少一个处理器，以及
与所述至少一个处理器连接的存储器；
其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述至少一个处理器通过执行所述存储器存储的指令实现如第一方面任一项所述的方法。
本申请实施例提供的终端的技术效果可以参见上述实施例的各个实现方式的技术效果，此处不再赘述。
在本申请其中一实施例中，提供一种计算机存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现如上述实施例任一项所述的方法。
本申请实施例考虑到空调的运行参数会对空调的结算情况有影响，因此，本申请实施例提供的除霜方法综合考虑空调的运行参数，根据空调的运行参数确定空调当前的结霜等级，从而根据确定的当前的结霜等级确定是否需要对空调进行除霜处理，如果需要除霜才生成用于控制空调进行除霜的除霜指令。相较于现有技术将基于经验确定的固定判断条件作为确定除霜时机更为灵活，更与空调的实际结霜情况相符，提高了确定除霜的时机的准确度，可以尽量避免空调没有结霜却确定要除霜，或者空调结霜很严重时才进行除霜等。
附图说明
图1是本申请其中一实施例提供的空调除霜的方法的流程示意图；
图2为本申请其中一实施例提供的空调除霜的设备的一种结构示意图；
图3为本申请其中一实施例提供的空调除霜的设备的一种结构示意图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚明白，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述。
目前空调确定除霜的时机是基于经验确定的固定判断条件，例如基于室外温度和蒸发器温度的差值确定除霜的时机，虽然可以进行除霜，但是不灵活。例如，空调没有结霜却确定要除霜，或者空调结霜很严重时才进行除霜等，可见，目前空调确定除霜的时机的准确度较低。
鉴于此，本申请实施例考虑到空调的运行参数会对空调的结算情况有影响，因此，本申请实施例提供的除霜方法综合考虑空调的运行参数，根据空调的运行参数确定空调当前的结霜等级，从而根据确定的当前的结霜等级确定是否需要对空调进行除霜处理，如果需要除霜才生成用于控制空调进行除霜的除霜指令。相较于现有技术将基于经验确定的固定判断条件作为确定除霜时机更为灵活，更与空调的实际结霜情况相符，提高了确定除霜的时机的准确度，可以尽量避免空调没有结霜却确定要除霜，或者空调结霜很严重时才进行除霜等。
下面结合说明书附图介绍本申请其中一实施例提供的技术方案。
下面结合图1对本申请其中一实施例提供的空调除霜的方法进行详细说明，该方法可以适用于空调，当然也可以适用于空调连接的电子设备，例如电脑、手机等。具体的流程描述如下：
S101：确定空调运行的M个运行参数，M为正整数；
S102：对M个运行参数进行分析，确定空调当前的结霜等级，其中，结霜等级用于指示空调当前的结霜情况，不同的运行参数使空调的结霜等级发生不同变化；
S103：根据当前的结霜等级确定是否需要对空调进行除霜处理，若需要则生成用于控制空调进行除霜的除霜指令。
冬天空调在制热模式下运行时，室外机容易结霜，影响制热效率，因此需要对空调进行除霜。而空调结霜的情况与空调的运行参数有关，空调的运行参数可以包括冷凝温度、蒸发温度、冷凝压力、蒸发压力、油温、时长及电流等，而这些运行参数或多或少都影响着空调的结霜情况，例如结霜的厚度和/或结霜的密度，不同的运行参数导致的空调的结霜情况也可能有所不同。本申请实施例用结霜等级指示空调的结霜情况，结霜情况可以分为多个结霜等级，例如结霜等级如果是0，那么就是表示空调没有结霜；结霜等级如果是1，那么就是表示空调结霜的厚度较薄或者结霜的密度较为稀疏；结霜等级如果是2，那么就是表示空调结霜的厚度较厚或者结霜的密度较为浓密。结霜等级的划分可以根据经验划分，本申请实施例不限制结霜等级的级数。
空调的运行参数包括多种，由于不同的运行参数对空调的结霜情况的影响也可能有所不同，有的运行参数对空调的结霜情况的影响较大，有的运行参数对空调的结霜情况的影响较小，如果根据空调的全部运行参数来确定空调的结霜情况，显然计算量较大，因此，本申请实施例可以根据对空调的结霜情况的影响较大的运行参数确定空调的结霜情况，从而减少了计算量，减轻空调除霜的设备的负担。
可选的，本申请实施例可以确定空调运行的M个运行参数，M为正整数，这M个运行参数可以认为是对空调的结霜情况的影响较大的运行参数，从而对M个运行参数进行分析，确定空调当前的结霜等级，即空调当前的结霜情况。
本申请实施例在确定空调运行的M个运行参数时，可以采集空调运行的数据集及对应的结霜等级，其中，数据集包括空调的N个运行参数的值，N为正整数。N个运行参数可以是空调运行的全部运行参数，也可以是根据经验从空调运行的全部运行参数中筛选出的部分运行参数。
本申请实施例采集数据集及对应的结霜等级可以对数据集进行分析，获得每个运行参数与结霜等级的关联度。例如，本申请实施例可以减少数据集中运行参数的种类或数量，此时通过直接测量或通过光电设备采集空调的结霜图像，获得空调结霜的厚度和/或密度，从而确定空调的结霜等级。如果减少数据集中的某种运行参数，空调结霜的厚度和/或密度变化不大，那么就可以认为该种运行参数对空调结霜的影响不大，即关联度较小，那么在根据运行参数确定空调当前的结霜等级时就可以忽略该种运行参数，以减少计算量。本申请实施例在获得每个运行参数与结霜等级的关联度后，可以选取关联度大于第一阈值的运行参数作为M个运行参数。其中，第一阈值可以是根据经验设定的一个可能的值，例如30％。
本申请实施例在对M个运行参数进行分析，确定空调当前的结霜等级之前，还可以确定除霜模型，其中，除霜模型是通过深度学习网络对至少一个运行参数进行逐层训练获得的运行参数集与结霜等级的概率的关系模型，从而可以通过除霜模型对M个运行参数进行分析，确定空调当前的结霜等级。
可选的，本申请实施例可以获取训练数据集，其中，训练数据集包括多个结霜等级与运行参数的关系对，每个关系对中一个结霜等级对应多个运行参数。本申请实施例建立每个关系对中结霜等级与对应的多个运行参数的函数模型，其中，函数模型的输入为多个运行参数，输出为多个结霜等级的概率。这样本申请实施例获取训练数据集后，可以利用训练数据集对函数模型进行有监督地训练，直到函数模型输出的取值达到设定标准，即训练后的函数模型为较优的预测模型，以获得除霜模型。设定标准可以用于指示接近结霜等级真实的概率，训练后的函数模型输出的取值达到设定标准，即训练函数模型时，训练到函数模型输出的取值指示结霜等级的误差较小，此时可以认为通过训练后的函数模型对运行参数进行分析的准确度较高。
本申请实施例训练数据集获得除霜模型这个过程可以在空调端实现，也可以通过与空调连接的设备，例如网关设备或服务器等实现，待服务器获得除霜 模型后可以发送给空调，例如，通过无线网络等发送给空调，这样就减轻了空调的负担。或者，也可以通过空调及与空调连接的设备实现，训练数据集由与空调连接的设备实现，优化除霜模型可以通过空调自身实现，可选的部署可以根据成本和/或计算资源进行确定。
本申请实施例获取的训练数据集的数据结构可能存在多种，例如，数据集中的数据可以是按时间序列存储的，也可以是按矩阵形式存储的，或者按列表形式存储的。针对不同的数据结构本申请实施例可以对应使用不同的深度学习网络，例如循环神经网络或卷积神经网络等。例如，如果数据结构是按时间序列存储，那么输入的运行参数可以认为是与时间相关，深度学习网络可以是循环神经网络，尽量考虑到时间的影响，从而提高得到的除霜模型的准确性。
除霜模型可以对运行参数进行分析以确定空调当前的结霜等级。其中，在向除霜模型输入M个运行参数时，除霜模型输出多个结霜等级的概率，从而可以根据多个结霜等级的概率确定空调当前的结霜等级。其中，多个概率之和是100％。
一个结霜等级的概率大，那么空调当前的结霜等级就是该结霜等级的可能性就较大。可选的，如果多个结霜等级的概率中的第一概率大于预设第二阈值，则将与第一概率对应的结霜等级确定为空调当前的结霜等级。其中，第一概率可以认为是多个概率中的任意一个概率，预设第二阈值可以是事先设定的一个值，例如90％，如果第一概率大于预设第二阈值，那么可以认为第一概率对应的结霜等级相较于其他概率对应的结霜等级来说是空调当前的结霜等级的可能性就较大，因此，本申请实施例可以将第一概率对应的结霜等级确定为空调当前的结霜等级。
而如果多个结霜等级的概率都差不多大，此时通过比较多个结霜等级的概率的大小进而确定空调当前的结霜等级显然是无法确定的。因此，本申请实施例在多个结霜等级的概率都小于或等于预设第三阈值时，其中，预设第三阈值可以是事先设定的一个值，例如30％，可以针对第一结霜等级，也就是多个结 霜等级中任意一个结霜等级，确定第一结霜等级在预设时间段内的多个概率，例如，确定的多个概率可以是89％、90％、88％、25％等，那么可以确定的是如果这多个概率中小于或等于预设第三阈值的概率的数量较少，可以认为是当前时刻确定的第一结霜等级的误差较大，此时可以忽略当前第一结霜等级的概率。从而综合考虑第一结霜等级在预设时间段内的多个概率，如果确定多个概率中小于或等于预设第三阈值的概率的数量小于预设第四阈值，即较少，则可以将第一结霜等级确定为空调当前的结霜等级，这样确定空调当前的结霜等级就更为准确。
本申请实施例可以根据空调实际的结霜情况确定是否要对空调进行除霜，即确定空调的除霜时机，一旦确定要对空调进行除霜，本申请实施例中空调除霜的设备，例如空调或与空调连接的电子设备可以生成用于控制空调进行除霜的除霜指令，生成除霜指令后将除霜指令发送给空调，从而空调可以根据接收的除霜指令对空调进行除霜。因此，本申请实施例根据空调当前的结霜等级确定要对空调进行除霜，生成用于控制空调进行除霜的除霜指令，其中除霜指令携带的除霜参数，例如空调运行的功率参数与空调当前的结霜等级相匹配。从而空调接收到除霜指令，执行除霜指令实现对空调的除霜。
综上，本申请实施例考虑到空调的运行参数会对空调的结霜情况有影响，因此，本申请实施例提供的除霜方法综合考虑空调的运行参数，根据空调的运行参数确定空调当前的结霜等级，从而根据确定的当前的结霜等级确定是否需要对空调进行除霜处理，如果需要除霜才生成用于控制空调进行除霜的除霜指令。相较于现有技术将基于经验确定的固定判断条件作为确定除霜时机更为灵活，更与空调的实际结霜情况相符，提高了确定除霜的时机的准确度，可以尽量避免空调没有结霜却确定要除霜，或者空调结霜很严重时才进行除霜等。
本申请实施例根据多个结霜等级的概率确定空调当前的结霜等级时，可以根据多个概率的大小灵活选择确定方式，从而提高确定空调当前的结霜等级的准确度。
下面结合说明书附图介绍本申请其中一实施例提供的设备。
请参见图2，基于同一发明构思，本申请一实施例提供一种空调除霜的设备，该空调除霜的设备可以包括第一确定单元201、第二确定单元202和发送单元203。第一确定单元201设置为支持空调除霜的设备执行图1中的步骤S101。第二确定单元202设置为支持空调除霜的设备执行图1中的步骤S102。发送单元203设置为支持空调除霜的设备执行图1中的步骤S103。其中，上述方法实施例涉及的各步骤的所有相关内容均可以援引到对应功能模块的功能描述，在此不再赘述。
可选的，第一确定单元201具体设置为：
采集空调运行的数据集及对应的结霜等级，其中，数据集包括空调的N个运行参数的值，N为正整数；
对数据集及对应的结霜等级进行分析，获得每个运行参数与结霜等级的关联度；
选取关联度大于第一阈值的运行参数，以确定M个运行参数，M小于或等于N。
可选的，还可以包括训练单元，具体设置为：在对M个运行参数进行分析，确定空调当前的结霜等级之前，获取训练数据集，建立每个关系对中结霜等级与对应的多个运行参数的函数模型，利用训练数据集对函数模型进行训练，直到函数模型输出的取值达到设定标准，以获得除霜模型；其中，训练数据集包括多个结霜等级与运行参数的关系对，每个关系对中一个结霜等级对应多个运行参数；函数模型的输入为多个运行参数，输出为多个结霜等级的概率；
可选的，第二确定单元202具体可以设置为：
将M个运行参数输入除霜模型；
根据除霜模型输出的多个结霜等级的概率确定空调当前的结霜等级。
可选的，第二确定单元202具体可以设置为：
若多个结霜等级的概率中的第一概率大于预设第二阈值，则将与第一概率 对应的结霜等级确定为空调当前的结霜等级；
或，
若多个结霜等级的概率都小于或等于预设第三阈值，则确定第一结霜等级在预设时间段内的多个概率，其中，第一结霜等级为多个结霜等级中的任意一个结霜等级；
确定多个概率中小于或等于预设第三阈值的概率的数量；
若确定的数量小于预设第四阈值，则将第一结霜等级确定为空调当前的结霜等级。
请参见图3，基于同一发明构思，本申请一实施例提供一种空调除霜的设备，该空调除霜的设备可以包括：至少一个处理器301，处理器301设置为执行存储器中存储的计算机程序时实现本申请实施例提供空调除霜的方法的步骤。
可选的，处理器301具体可以是中央处理器、特定应用集成电路(英文：Application Specific Integrated Circuit，简称：ASIC)，可以是一个或多个设置为控制程序执行的集成电路。
可选的，该空调除霜的设备还包括与至少一个处理器连接的存储器302，存储器302可以包括只读存储器(英文：Read Only Memory，简称：ROM)、随机存取存储器(英文：Random Access Memory，简称：RAM)和磁盘存储器。存储器302设置为存储处理器301运行时所需的数据，即存储有可被至少一个处理器301执行的指令，至少一个处理器301通过执行存储器302存储的指令，执行如图1所示的方法。其中，存储器302的数量为一个或多个。其中，存储器302在图3中一并示出，但需要知道的是存储器302不是必选的功能模块，因此在图3中以虚线示出。
其中，第一确定单元201、第二确定单元202和发送单元203所对应的实体设备均可以是前述的处理器301。该空调除霜的设备可以用于执行图1所示的实施例所提供的方法。因此关于该设备中各功能模块所能够实现的功能，可 参考图1所示的实施例中的相应描述，不多赘述。
本申请实施例还提供一种计算机存储介质，其中，计算机存储介质存储有计算机指令，当计算机指令在计算机上运行时，使得计算机执行如图1所述的方法。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将装置的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述模块或单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申 请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理器(processor)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：通用串行总线闪存盘(Universal Serial Bus flash disk)、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
显然，本领域的技术人员可以对本申请进行各种改动和变型而不脱离本申请的精神和范围。这样，倘若本申请的这些修改和变型属于本申请权利要求及其等同技术的范围之内，则本申请也意图包含这些改动和变型在内。
工业实用性
本申请实施例提供的技术方案可以应用于空调的运行过程中，采用确定空调运行的M个运行参数，对M个运行参数进行分析，确定空调当前的结霜等级，根据当前的结霜等级确定是否需要对空调进行除霜处理，若需要则生成用于控制空调进行除霜的除霜指令的方案，相较于现有技术将基于经验确定的固定判断条件作为确定除霜时机更为灵活，更与空调的实际结霜情况相符，提高了确定除霜的时机的准确度，可以尽量避免空调没有结霜却确定要除霜，或者空调结霜很严重时才进行除霜等问题。

Claims (10)

  1. 一种空调除霜的方法，包括：
    确定空调运行的M个运行参数，M为正整数；
    对所述M个运行参数进行分析，确定空调当前的结霜等级，其中，所述结霜等级用于指示空调当前的结霜情况，不同的运行参数使所述空调的结霜等级发生不同变化；
    根据所述当前的结霜等级确定是否需要对所述空调进行除霜处理，若需要则生成用于控制所述空调进行除霜的除霜指令。
  2. 如权利要求1所述的方法，其中，确定空调运行的M个运行参数，包括：
    采集所述空调运行的数据集及对应的结霜等级，其中，所述数据集包括所述空调的N个运行参数的值，N为正整数；
    对所述数据集及对应的结霜等级进行分析，获得每个运行参数与结霜等级的关联度；
    选取所述关联度大于第一阈值的运行参数，以确定所述M个运行参数，M小于或等于N。
  3. 如权利要求1或2所述的方法，其中，
    在对所述M个运行参数进行分析，确定空调当前的结霜等级之前，还包括：
    获取训练数据集，其中，所述训练数据集包括多个结霜等级与运行参数的关系对，每个关系对中一个结霜等级对应多个运行参数；
    建立每个关系对中结霜等级与对应的多个运行参数的函数模型，其中，所述函数模型的输入为多个运行参数，输出为多个结霜等级的概率；
    利用所述训练数据集对所述函数模型进行训练，直到所述函数模型输出的取值达到设定标准，以获得除霜模型；
    对所述M个运行参数进行分析，确定空调当前的结霜等级，包括：
    将所述M个运行参数输入所述除霜模型；
    根据所述除霜模型输出的多个结霜等级的概率确定所述空调当前的结霜等级。
  4. 如权利要求3所述的方法，其中，根据所述除霜模型输出的多个结霜等级的概率确定所述空调的结霜等级，包括：
    若所述多个结霜等级的概率中的第一概率大于预设第二阈值，则将与所述第一概率对应的结霜等级确定为所述空调当前的结霜等级；
    或，
    若多个结霜等级的概率都小于或等于预设第三阈值，则确定第一结霜等级在预设时间段内的多个概率，其中，所述第一结霜等级为所述多个结霜等级中的任意一个结霜等级；
    确定所述多个概率中小于或等于所述预设第三阈值的概率的数量；
    若确定的数量小于预设第四阈值，则将所述第一结霜等级确定为所述空调当前的结霜等级。
  5. 一种空调除霜的设备，包括：
    第一确定单元，设置为确定空调运行的M个运行参数，M为正整数；
    第二确定单元，设置为对所述M个运行参数进行分析，确定空调当前的结霜等级，其中，所述结霜等级用于指示空调当前的结霜情况，不同的运行参数使所述空调的结霜等级发生不同变化；
    发送单元，设置为根据所述当前的结霜等级确定是否需要对所述空调进行除霜处理，若需要则生成用于控制所述空调进行除霜的除霜指令。
  6. 如权利要求5所述的设备，其中，所述第一确定单元具体设置为：
    采集所述空调运行的数据集及对应的结霜等级，其中，所述数据集包括所述空调的N个运行参数的值，N为正整数；
    对所述数据集及对应的结霜等级进行分析，获得每个运行参数与结霜等级的关联度；
    选取所述关联度大于第一阈值的运行参数，以确定所述M个运行参数，M小于或等于N。
  7. 如权利要求5或6所述的设备，其中，还包括：
    训练单元，设置为在对所述M个运行参数进行分析，确定空调当前的结霜等级之前，获取训练数据集，建立每个关系对中结霜等级与对应的多个运行参数的函数模型，利用所述训练数据集对所述函数模型进行训练，直到所述函数模型输出的取值达到设定标准，以获得除霜模型；其中，所述训练数据集包括多个结霜等级与运行参数的关系对，每个关系对中一个结霜等级对应多个运行参数；所述函数模型的输入为多个运行参数，输出为多个结霜等级的概率；
    所述第二确定单元具体设置为：
    将所述M个运行参数输入所述除霜模型；
    根据所述除霜模型输出的多个结霜等级的概率确定所述空调当前的结霜等级。
  8. 如权利要求7所述的设备，其中，所述第二确定单元具体设置为：
    若所述多个结霜等级的概率中的第一概率大于预设第二阈值，则将与所述第一概率对应的结霜等级确定为所述空调当前的结霜等级；
    或，
    若多个结霜等级的概率都小于或等于预设第三阈值，则确定第一结霜等级在预设时间段内的多个概率，其中，所述第一结霜等级为所述多个结霜等级中的任意一个结霜等级；
    确定所述多个概率中小于或等于所述预设第三阈值的概率的数量；
    若确定的数量小于预设第四阈值，则将所述第一结霜等级确定为所述空调当前的结霜等级。
  9. 一种空调除霜的设备，包括：
    至少一个处理器，以及
    与所述至少一个处理器连接的存储器；
    其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述至少一个处理器通过执行所述存储器存储的指令实现如权利要求1-4任一项所述的方法。
  10. 一种计算机存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现如权利要求1-4任一项所述的方法。
PCT/CN2018/120931 2018-05-07 2018-12-13 一种空调除霜的方法及设备 WO2019214230A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810425639.2A CN110454910B (zh) 2018-05-07 2018-05-07 一种空调除霜的方法及设备
CN201810425639.2 2018-05-07

Publications (1)

Publication Number Publication Date
WO2019214230A1 true WO2019214230A1 (zh) 2019-11-14

Family

ID=68467784

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/120931 WO2019214230A1 (zh) 2018-05-07 2018-12-13 一种空调除霜的方法及设备

Country Status (2)

Country Link
CN (1) CN110454910B (zh)
WO (1) WO2019214230A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112484238B (zh) * 2020-11-16 2021-11-23 珠海格力电器股份有限公司 化霜控制方法、装置、多模块机组及暖通设备
CN112503725B (zh) * 2020-12-08 2021-11-30 珠海格力电器股份有限公司 空调自清洁控制方法、装置和空调
CN113566383B (zh) * 2021-07-20 2022-06-14 珠海格力电器股份有限公司 智能除霜方法、装置、电器及计算机可读存储介质
KR102607831B1 (ko) * 2021-08-18 2023-11-29 주식회사 프리즈 이미지를 기반으로 적상의 발생여부를 판단하여 제상 동작을 수행할 수 있는 냉동기 및 그 동작 방법

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS61175430A (ja) * 1985-01-31 1986-08-07 Tohoku Electric Power Co Inc 冷凍サイクル
WO2011122887A2 (en) * 2010-04-02 2011-10-06 Lg Innotek Co., Ltd. Defrosting system and method of refrigerator
EP2634512A1 (en) * 2012-02-28 2013-09-04 LG Electronics, Inc. Air conditioner and method of controlling the same
CN106152388A (zh) * 2015-04-23 2016-11-23 青岛海尔空调电子有限公司 一种空调机组的除霜方法及装置
CN106288162A (zh) * 2016-08-08 2017-01-04 广东美的暖通设备有限公司 一种除霜进入判定方法、系统和空调
CN106288144A (zh) * 2016-07-26 2017-01-04 广东美的暖通设备有限公司 空调器及其除霜方法
CN106352628A (zh) * 2016-09-27 2017-01-25 广东美的暖通设备有限公司 热泵系统的控制方法、系统及热泵
CN106765917A (zh) * 2016-12-07 2017-05-31 珠海格力电器股份有限公司 一种空调器控制方法及装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106594975A (zh) * 2016-11-15 2017-04-26 珠海格力电器股份有限公司 一种除霜方法、装置及空调系统
CN107860099B (zh) * 2017-09-15 2018-11-30 珠海格力电器股份有限公司 一种空调的结霜检测方法、装置、存储介质及设备

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS61175430A (ja) * 1985-01-31 1986-08-07 Tohoku Electric Power Co Inc 冷凍サイクル
WO2011122887A2 (en) * 2010-04-02 2011-10-06 Lg Innotek Co., Ltd. Defrosting system and method of refrigerator
EP2634512A1 (en) * 2012-02-28 2013-09-04 LG Electronics, Inc. Air conditioner and method of controlling the same
CN106152388A (zh) * 2015-04-23 2016-11-23 青岛海尔空调电子有限公司 一种空调机组的除霜方法及装置
CN106288144A (zh) * 2016-07-26 2017-01-04 广东美的暖通设备有限公司 空调器及其除霜方法
CN106288162A (zh) * 2016-08-08 2017-01-04 广东美的暖通设备有限公司 一种除霜进入判定方法、系统和空调
CN106352628A (zh) * 2016-09-27 2017-01-25 广东美的暖通设备有限公司 热泵系统的控制方法、系统及热泵
CN106765917A (zh) * 2016-12-07 2017-05-31 珠海格力电器股份有限公司 一种空调器控制方法及装置

Also Published As

Publication number Publication date
CN110454910B (zh) 2020-08-04
CN110454910A (zh) 2019-11-15

Similar Documents

Publication Publication Date Title
WO2019214230A1 (zh) 一种空调除霜的方法及设备
US10586177B1 (en) Training a mathematical model for a device using a smart plug
WO2020098606A1 (zh) 节点分类方法、模型训练方法、装置、设备及存储介质
WO2022037130A1 (zh) 网络流量异常的检测方法、装置、电子装置和存储介质
CN110166462B (zh) 访问控制方法、系统、电子设备及计算机存储介质
CN104676836B (zh) 多联机空调系统运行模式的确定方法
KR102131029B1 (ko) 사물인터넷 디바이스 식별 방법 및 시스템
CN113315716A (zh) 拥塞控制模型的训练方法和设备及拥塞控制方法和设备
JP2018528511A (ja) 生産システムにおける出力効率の最適化
CN110442623B (zh) 大数据挖掘方法、装置及数据挖掘服务器
US20240135323A1 (en) Ticket troubleshooting support system
US11711310B2 (en) System and method for determining a network performance property in at least one network
JP2015222882A (ja) 通信スループット予測装置、通信スループット予測方法、及び、プログラム
CN115170919B (zh) 图像处理模型训练及图像处理方法、装置、设备和存储介质
WO2023082792A1 (zh) 参数寻优方法和装置
WO2023012928A1 (ja) デバイス推定システム、デバイス推定装置、パケット解析モデル学習装置、波形解析モデル学習装置、および、プログラム
CN109547236A (zh) 电子数据上传存储方法、可读存储介质和终端
US20220358375A1 (en) Inference of machine learning models
CN114312213A (zh) 车辆的制冷剂容量异常预测方法、装置、设备及介质
CN114726892A (zh) 基于人工智能大数据的边缘数据收集方法
CN110020472A (zh) 一种产品剩余寿命预测方法、装置和系统
CN115361231B (zh) 基于访问基线的主机异常流量检测方法、系统及设备
TWI815202B (zh) 效率影響因子判定方法及裝置
CN110454904B (zh) 除湿机中冷媒含量的处理方法和装置
CN116996527B (zh) 一种汇聚分流器数据同步的方法及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18917965

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18917965

Country of ref document: EP

Kind code of ref document: A1