WO2026007402A1 - 预测模型的训练方法、空调最优运行参数的预测方法、装置、空调 - Google Patents

预测模型的训练方法、空调最优运行参数的预测方法、装置、空调

Info

Publication number
WO2026007402A1
WO2026007402A1 PCT/CN2025/075954 CN2025075954W WO2026007402A1 WO 2026007402 A1 WO2026007402 A1 WO 2026007402A1 CN 2025075954 W CN2025075954 W CN 2025075954W WO 2026007402 A1 WO2026007402 A1 WO 2026007402A1
Authority
WO
WIPO (PCT)
Prior art keywords
air conditioner
operating parameters
optimal operating
heat exchanger
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.)
Pending
Application number
PCT/CN2025/075954
Other languages
English (en)
French (fr)
Inventor
李伟
宋玉军
劳春峰
王东岳
代传民
陶瑞涛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qingdao Haier Air Conditioner Gen Corp Ltd
Qingdao Haier Air Conditioning Electric Co Ltd
Haier Smart Home Co Ltd
Original Assignee
Qingdao Haier Air Conditioner Gen Corp Ltd
Qingdao Haier Air Conditioning Electric Co Ltd
Haier Smart Home Co Ltd
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 Qingdao Haier Air Conditioner Gen Corp Ltd, Qingdao Haier Air Conditioning Electric Co Ltd, Haier Smart Home Co Ltd filed Critical Qingdao Haier Air Conditioner Gen Corp Ltd
Publication of WO2026007402A1 publication Critical patent/WO2026007402A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
    • F24F11/46—Improving electric energy efficiency or saving
    • 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
    • F24F11/70—Control systems characterised by their outputs; Constructional details thereof
    • F24F11/72—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure
    • F24F11/74—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure for controlling air flow rate or air velocity
    • F24F11/77—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure for controlling air flow rate or air velocity by controlling the speed of ventilators
    • 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
    • F24F11/70—Control systems characterised by their outputs; Constructional details thereof
    • F24F11/80—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air
    • F24F11/83—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling the supply of heat-exchange fluids to heat-exchangers
    • F24F11/84—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling the supply of heat-exchange fluids to heat-exchangers using valves
    • 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
    • F24F11/70—Control systems characterised by their outputs; Constructional details thereof
    • F24F11/80—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air
    • F24F11/86—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling compressors within refrigeration or heat pump circuits
    • 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
    • F24F11/70—Control systems characterised by their outputs; Constructional details thereof
    • F24F11/80—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air
    • F24F11/87—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling absorption or discharge of heat in outdoor units
    • F24F11/871—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling absorption or discharge of heat in outdoor units by controlling outdoor fans
    • 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
    • F24F11/88—Electrical aspects, e.g. circuits
    • 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

Definitions

  • This disclosure relates to the technical field of air conditioning control, such as a method for training a prediction model, a method for predicting optimal operating parameters of an air conditioner, an apparatus, and an air conditioner.
  • the optimal operating parameters of an air conditioner under various operating conditions are an important factor in achieving energy saving.
  • the optimal operating parameters of an air conditioner are set under the standard operating conditions of the enthalpy difference chamber when the air conditioner is newly manufactured, and under the conditions of no heat exchanger blockage and 100% refrigerant quantity. Setting accurate optimal operating parameters can ensure that the air conditioner operates with the best energy efficiency ratio under the latest conditions.
  • This disclosure provides a method for training a prediction model, a method for predicting the optimal operating parameters of an air conditioner, an apparatus, and an air conditioner.
  • the method can train a prediction model to predict the optimal operating parameters that are consistent with the current actual condition of the air conditioner, so that the air conditioner can operate in the optimal state based on the optimal operating parameters predicted by the prediction model, thereby reducing energy waste.
  • a method for training a prediction model for predicting optimal operating parameters of an air conditioner comprising:
  • the air conditioning hardware parameters were collected in the air conditioning enthalpy difference chamber under different heat exchanger blockage conditions and different refrigerant quantities.
  • a training dataset is constructed based on the heat exchanger clogging status, refrigerant quantity, tag data, and air conditioning hardware parameters.
  • the training dataset includes multiple data units, each containing the heat exchanger clogging status and refrigerant quantity, as well as the air conditioning hardware parameters and tag data under the heat exchanger clogging status and refrigerant quantity.
  • Each data unit is sequentially input into the initial prediction model for training, resulting in a target prediction model capable of predicting the optimal operating parameters of the air conditioner.
  • a method for predicting optimal operating parameters of an air conditioner comprising:
  • the air conditioning hardware parameters, heat exchanger blockage status, and refrigerant quantity are input into the target prediction model, wherein the target prediction model is obtained using the training method for the prediction model for predicting the optimal operating parameters of the air conditioner provided in the second aspect of this disclosure.
  • the optimal operating parameters of the air conditioner are predicted using a target prediction model.
  • inputting air conditioning hardware parameters into the target prediction model includes:
  • n sequences are constructed based on air conditioner hardware parameters, heat exchanger blockage status, and refrigerant quantity
  • Sequences 1 to (n-1) are input into a corresponding second network unit, and sequence n is input into a first network unit.
  • a training apparatus for a predictive model for predicting optimal operating parameters of an air conditioner comprising a processor and a memory storing program instructions, wherein the processor is configured to execute, when running the program instructions, the training method for the predictive model for predicting optimal operating parameters of an air conditioner provided in the first aspect of this disclosure.
  • an apparatus for predicting optimal operating parameters of an air conditioner comprising a processor and a memory storing program instructions, wherein the processor is configured to execute the method for predicting optimal operating parameters of an air conditioner provided in the second aspect of this disclosure when executing the program instructions.
  • an air conditioner comprising:
  • Air conditioner unit
  • the third aspect of this disclosure provides a training device for a predictive model used to predict optimal operating parameters of an air conditioner, the training device being disposed within the air conditioner body; and/or,
  • the fourth aspect of this disclosure provides an air conditioner optimal operating parameter prediction device, which is installed in the air conditioner body.
  • Figure 1 is a flowchart illustrating a training method for a prediction model used to predict the optimal operating parameters of an air conditioner, according to an embodiment of this disclosure.
  • Figure 2 is a schematic diagram of the structure of a prediction model provided in an embodiment of this disclosure.
  • Figure 3 is a flowchart illustrating a method for predicting optimal operating parameters of an air conditioner according to an embodiment of this disclosure
  • Figure 4 is a schematic diagram of the structure of a training device for a prediction model used to predict the optimal operating parameters of an air conditioner, provided in an embodiment of this disclosure.
  • Figure 5 is a schematic diagram of the structure of a predictive device for optimal operating parameters of an air conditioner provided in an embodiment of this disclosure
  • Figure 6 is a schematic diagram of the structure of an air conditioner provided in an embodiment of this disclosure.
  • A/B means: A or B.
  • a and/or B means: A or B, or A and B.
  • correspondence can refer to an association or binding relationship.
  • correspondence between A and B means that there is an association or binding relationship between A and B.
  • This disclosure provides a training apparatus for a predictive model used to predict optimal operating parameters of an air conditioner.
  • the training apparatus is a device with computing capabilities, such as a personal computer, server, or network device. Electronic devices can be used to execute the training method for the predictive model provided in this disclosure.
  • this disclosure provides a method for training a prediction model for predicting optimal operating parameters of an air conditioner.
  • the method for training a prediction model for predicting optimal operating parameters of an air conditioner includes:
  • S101 collects air conditioning hardware parameters under different heat exchanger blockage states and different refrigerant quantities in the air conditioning enthalpy difference chamber;
  • a training dataset is constructed based on the heat exchanger's dirt and blockage status, refrigerant quantity, tag data, and air conditioning hardware parameters;
  • each data unit is sequentially input into the initial prediction model for training, to obtain the target prediction model that can predict the optimal operating parameters of the air conditioner.
  • An air conditioning enthalpy difference chamber is a specialized laboratory primarily used to test the performance of air conditioners, heat pumps, and other refrigeration equipment, particularly their key performance indicators such as cooling capacity, heating capacity, and energy efficiency ratio under different operating conditions.
  • This embodiment of the invention allows for variations in the heat exchanger clogging status and refrigerant quantity within the air conditioning enthalpy difference chamber, enabling the collection of air conditioning hardware parameters under different heat exchanger clogging states and refrigerant quantities.
  • the air conditioning hardware parameters include exhaust temperature, intake temperature, defrost sensor temperature, ambient temperature, subcooler bypass inlet temperature, total current, external valve opening, external coil temperature, auxiliary valve opening, heat exchanger inlet temperature, heat exchanger outlet temperature, oil temperature, compressor frequency, expansion valve opening, internal fan speed, and external fan speed.
  • the training dataset includes multiple data units, each data unit containing the heat exchanger clogging status and refrigerant quantity, as well as the air conditioning hardware parameters and tag data under the heat exchanger clogging status and refrigerant quantity.
  • This disclosure provides a training method for a predictive model to predict the optimal operating parameters of an air conditioner.
  • a training dataset is constructed based on the air conditioner hardware parameters and optimal operating parameters under different heat exchanger clogging states and refrigerant quantities, as well as the corresponding heat exchanger clogging states and refrigerant quantities.
  • This training dataset is then used to train the predictive model, enabling it to predict the optimal operating parameters of the air conditioner.
  • the model can obtain the optimal operating parameters that match the current actual condition of the air conditioner. This allows the air conditioner to operate in an optimal state based on the predicted optimal operating parameters, achieving a higher energy efficiency ratio and reducing energy waste.
  • a training dataset is constructed based on the heat exchanger clogging status, refrigerant quantity, tag data, and air conditioning hardware parameters. This includes: using the temperature and pressure points of the air conditioning enthalpy difference chamber as input features of a preset algorithm; preprocessing the collected air conditioning hardware parameters using the preset algorithm, wherein the preprocessing includes removing non-steady-state data and feature extraction; and dividing the heat exchanger clogging status and refrigerant quantity, as well as the air conditioning hardware parameters and tag data under the heat exchanger clogging status and refrigerant quantity, into a data unit to obtain multiple data units.
  • the preset algorithm can be the SHAP (SHapley Additive exPlanations) algorithm.
  • SHAP SHapley Additive exPlanations
  • the SHAP algorithm is an algorithm used to interpret the prediction results of machine learning models. It provides interpretability of the model by calculating the contribution of each feature to the model output.
  • the subcooler bypass inlet temperature is the most important modeling input variable, showing a Shapley value of approximately 0.8. This indicates that the opening of the subcooler bypass valve has a significant impact on heat exchanger fouling.
  • condensing temperature, valve opening, and heat exchange temperature difference are important variables affecting the degree of heat exchanger fouling.
  • the features that directly or indirectly affect these variables are highly consistent with the feature importance ranking results, which means that the developed prediction model can be physically interpreted based on domain knowledge.
  • the air conditioning hardware parameters can be normalized. For example, if the maximum value of the compressor frequency is 116Hz, the maximum value of the expansion valve opening is 480°, the maximum value of the indoor fan speed is 1200RPM, and the maximum value of the outdoor fan speed is 1200RPM, dividing the compressor frequency, expansion valve opening, indoor fan speed, and outdoor fan speed by their maximum values will normalize the range of these parameters to between 0 and 1. This can improve the convergence speed of the model during training.
  • a recurrent neural network is a weight-sharing artificial neural network, meaning that the current output of a sequence is related to the previous output. Specifically, the network memorizes previous information and applies it to the calculation of the current output; that is, the nodes between hidden layers are no longer disconnected but connected, and the input to the hidden layer includes not only the output of the input layer but also the output of the hidden layer at the previous time step.
  • the initial prediction model using the improved recurrent neural network includes first network units corresponding to each optimal operating parameter of the air conditioner. Each first network unit corresponding to an optimal operating parameter is used to predict that optimal operating parameter. The first network units corresponding to each optimal operating parameter are connected in series according to the sequence of the optimal operating parameters, and the output of the next first network unit is related to the output of the previous first network unit.
  • the optimal operating parameters of the air conditioner include the optimal compressor frequency, the optimal expansion valve opening, the optimal indoor fan speed, and the optimal outdoor fan speed.
  • the optimal compressor frequency, the optimal expansion valve opening, the optimal indoor fan speed, and the optimal outdoor fan speed are sequentially increased, and the first network unit corresponding to the optimal compressor frequency, the first network unit corresponding to the optimal expansion valve opening, the first network unit corresponding to the optimal indoor fan speed, and the first network unit corresponding to the optimal outdoor fan speed are connected in series.
  • the output of the first network unit corresponding to the optimal expansion valve opening is related to the output of the first network unit corresponding to the optimal compressor frequency; the output of the first network unit corresponding to the optimal internal fan speed is related to the output of the first network unit corresponding to the optimal expansion valve opening; and the output of the first network unit corresponding to the optimal external fan speed is related to the output of the first network unit corresponding to the optimal internal fan speed.
  • the initial prediction model further includes multiple second network units connected in series, with the last second network unit connected to the first first network unit.
  • the output of each subsequent second network unit is related to the output of the preceding second network unit, and the output of the first first network unit is related to the output of the last second network unit.
  • the output of the first network unit corresponding to the optimal compressor frequency is related to the output of the last second network unit.
  • each data unit is sequentially input into the initial prediction model for training, including: sequentially performing the following steps on each data unit: constructing n sequences based on the data unit, wherein the number of second network units is (n-1); inputting sequence 1 to sequence (n-1) into a corresponding second network unit, and inputting sequence n into a first network unit; training the initial prediction model based on each input sequence.
  • the predictive device is a computing device, such as a personal computer, server, or network device. Electronic devices can be used to execute the method for predicting optimal operating parameters of an air conditioner provided in this disclosure.
  • this disclosure embodiment provides a method for predicting the optimal operating parameters of an air conditioner. As shown in Figure 3, the prediction method includes:
  • S303 inputs the air conditioning hardware parameters, heat exchanger blockage status and refrigerant quantity into the target prediction model
  • S304 uses a target prediction model to predict the current optimal operating parameters of the air conditioner.
  • the target prediction model is obtained by the training method of the prediction model for predicting the optimal operating parameters of the air conditioner provided in the above embodiments.
  • inputting air conditioning hardware parameters into the target prediction model includes: constructing n sequences based on air conditioning hardware parameters, heat exchanger blockage status, and refrigerant quantity; inputting sequence 1 to sequence (n-1) into a corresponding second network unit, and inputting sequence n into a first network unit.
  • this embodiment of the present disclosure provides a training device 400 for a predictive model used to predict the optimal operating parameters of an air conditioner.
  • the training device 400 includes a processor 401 and a memory 402.
  • the training device 400 may further include a communication interface 403 and a bus 404.
  • the processor 401, communication interface 403, and memory 402 can communicate with each other via the bus 404.
  • the communication interface 403 can be used for information transmission.
  • the processor 401 can call logical instructions in the memory 402 to execute the training method for the predictive model used to predict the optimal operating parameters of an air conditioner according to the above embodiment.
  • the logical instructions in the aforementioned memory 402 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.
  • the memory 402 can be used to store software programs and computer-executable programs, such as program instructions/modules corresponding to the methods in the embodiments of this disclosure.
  • the processor 401 executes functional applications and data processing by running the program instructions/modules stored in the memory 402, that is, it implements the training method for the prediction model used to predict the optimal operating parameters of the air conditioner in the above embodiments.
  • the memory 402 may include a program storage area and a data storage area.
  • the program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the terminal device.
  • the memory 402 may include high-speed random access memory and may also include non-volatile memory.
  • this embodiment of the present disclosure provides an air conditioner optimal operating parameter prediction device 500, which includes a processor 501 and a memory 502.
  • the prediction device 500 may further include a communication interface 503 and a bus 504.
  • the processor 501, communication interface 503, and memory 502 can communicate with each other via the bus 504.
  • the communication interface 503 can be used for information transmission.
  • the processor 501 can call logical instructions in the memory 502 to execute the air conditioner optimal operating parameter prediction method of the above embodiment.
  • logic instructions in the aforementioned memory 502 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.
  • the memory 502 as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions/modules corresponding to the methods in the embodiments of this disclosure.
  • the processor 501 executes functional applications and data processing by running the program instructions/modules stored in the memory 502, that is, it implements the method for predicting the optimal operating parameters of the air conditioner in the above embodiments.
  • the memory 502 may include a program storage area and a data storage area.
  • the program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the terminal device.
  • the memory 502 may include high-speed random access memory and may also include non-volatile memory.
  • this embodiment of the present disclosure provides an air conditioner 600, which includes an air conditioner body 601, and further includes a training device 400 for predicting the optimal operating parameters of the air conditioner and/or a prediction device 500 for predicting the optimal operating parameters of the air conditioner, as provided in the above embodiments.
  • the air conditioner 600 includes the training device 400
  • the training device 400 is disposed on the air conditioner body 601.
  • the prediction device 500 is disposed on the air conditioner body 601.
  • This disclosure provides a computer-readable non-transitory storage medium storing program instructions that, when executed, perform the following steps:
  • the air conditioning hardware parameters were collected in the air conditioning enthalpy difference chamber under different heat exchanger blockage conditions and different refrigerant quantities.
  • a training dataset is constructed based on the heat exchanger clogging status, refrigerant quantity, tag data, and air conditioning hardware parameters.
  • the training dataset includes multiple data units, each containing the heat exchanger clogging status and refrigerant quantity, as well as the air conditioning hardware parameters and tag data under the heat exchanger clogging status and refrigerant quantity.
  • Each data unit is sequentially input into the initial prediction model for training, resulting in a target prediction model capable of predicting the optimal operating parameters of the air conditioner.
  • This disclosure provides a computer-readable non-transitory storage medium storing program instructions that, when executed, perform the following steps:
  • the optimal operating parameters of the air conditioner are predicted using a target prediction model.
  • This disclosure provides a computer program that, when executed by a computer, enables the computer to implement the above-described training method for a prediction model used to predict optimal operating parameters of an air conditioner or the prediction method for optimal operating parameters of an air conditioner.
  • This disclosure provides a computer program product, which includes computer instructions stored on a computer-readable storage medium.
  • the program instructions When executed by a computer, the computer implements the training method for the prediction model used to predict the optimal operating parameters of an air conditioner or the prediction method for the optimal operating parameters of an air conditioner.
  • the technical solutions of this disclosure can be embodied in the form of a software product.
  • This computer software product is stored in a storage medium and includes one or more instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in this disclosure.
  • the aforementioned storage medium can be a non-transitory storage medium, such as a USB flash drive, external hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, etc., and other media capable of storing program code.
  • the training method for the prediction model, the prediction method for the optimal operating parameters of an air conditioner, the apparatus, and the air conditioner provided in this disclosure can achieve the following technical effects:
  • This disclosure provides a training method for a predictive model to predict the optimal operating parameters of an air conditioner.
  • a training dataset is constructed based on the air conditioner hardware parameters and optimal operating parameters under different heat exchanger clogging states and refrigerant quantities, as well as the corresponding heat exchanger clogging states and refrigerant quantities.
  • This training dataset is then used to train the predictive model, enabling it to predict the optimal operating parameters of the air conditioner.
  • the model can obtain the optimal operating parameters that match the current actual condition of the air conditioner. This allows the air conditioner to operate in an optimal state based on the predicted optimal operating parameters, achieving a higher energy efficiency ratio and reducing energy waste.
  • the term “comprise” and its variations “comprises” and/or “comprising” refer to the presence of stated features, integrals, steps, operations, elements, and/or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and/or groups thereof.
  • an element defined by the phrase “comprises a" does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element.
  • each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.
  • the devices and equipment can be implemented in other ways.
  • the device embodiments described above are merely illustrative.
  • the division of units may be merely a logical functional division, and in actual implementation, there may be other division methods.
  • multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.
  • the coupling or direct coupling or communication connection between the shown or discussed units may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.
  • the units described as separate components may or may not be physically separate.
  • the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to implement this embodiment according to actual needs. Furthermore, the functional units in the embodiments of this disclosure 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.
  • each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function.
  • the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved.

Landscapes

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

Abstract

一种预测模型的训练方法、空调最优运行参数的预测方法、装置、空调，训练方法包括：在空调焓差室中采集不同换热器脏堵状态和不同冷媒量下的空调硬件参数；确定不同换热器脏堵状态和不同冷媒量下的空调最优运行参数，将确定出的空调最优运行参数作为标签数据；基于换热器脏堵状态、冷媒量、标签数据、空调硬件参数构建训练数据集，训练数据集包括多个数据单元，每个数据单元对应一种换热器脏堵状态和冷媒量；依次将各个数据单元输入初始预测模型进行训练，得到能够预测空调最优运行参数的目标预测模型。

Description

预测模型的训练方法、空调最优运行参数的预测方法、装置、空调
本申请基于申请号为202410886464.0、申请日为2024年7月3日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本公开涉及空调控制的技术领域，例如涉及一种预测模型的训练方法、空调最优运行参数的预测方法、装置、空调。
背景技术
空调在各种工况下最优运行参数是空调实现节能的重要因素，空调的最优运行参数是空调在新出厂时焓差室的标准工况下，以及无换热器脏堵和冷媒量100％条件下设定的，设定准确的最优运行参数能保证空调在最新状态下以最优能耗比运行。
然而随着空调使用时间的增加，空调会出现换热器脏堵和冷媒量泄漏等软故障会造成的空调制热或制冷性能的衰减，使空调的最优控制参数发生偏离，这会导致先前在标准状态下设定的最优运行参数无法使空调以真实的最优状态运行，造成能量的浪费。
需要说明的是，在上述背景技术部分公开的信息仅用于加强对本公开的背景的理解，因此可以包括不构成对本领域普通技术人员已知的现有技术的信息。
发明内容
为了对披露的实施例的一些方面有基本的理解，下面给出了简单的概括。所述概括不是泛泛评述，也不是要确定关键/重要组成元素或描绘这些实施例的保护范围，而是作为后面的详细说明的序言。
本公开实施例提供了一种预测模型的训练方法、空调最优运行参数的预测方法、装置、空调，能够训练得到用于预测出符合空调当前的实际状况的最优运行参数的预测模型，以便空调基于预测模型预测出的最优运行参数能够在最优状态运行，减少能量的浪费。
根据本公开的第一方面，提供了一种用于预测空调最优运行参数的预测模型的训练方法，包括：
在空调焓差室中采集不同换热器脏堵状态和不同冷媒量下的空调硬件参数；
确定不同换热器脏堵状态和不同冷媒量下的空调最优运行参数，将确定出的空调最优运行参数作为标签数据；
基于换热器脏堵状态、冷媒量、标签数据、空调硬件参数构建训练数据集，其中，训练数据集包括多个数据单元，每个数据单元包含换热器脏堵状态和冷媒量，以及该换热器脏堵状态和冷媒量下的空调硬件参数和标签数据；
依次将各个数据单元输入初始预测模型进行训练，得到能够预测空调最优运行参数的目标预测模型。
根据本公开的第二方面，提供了一种空调最优运行参数的预测方法，包括：
采集空调当前的空调硬件参数；
确定空调当前的换热器脏堵状态和冷媒量；
将空调硬件参数、换热器脏堵状态和冷媒量输入到目标预测模型，其中，目标预测模型是使用本公开的第二方面提供的用于预测空调最优运行参数的预测模型的训练方法得到的；
利用目标预测模型预测出当前的空调最优运行参数。
在一些实施例中，将空调硬件参数输入到目标预测模型，包括：
基于空调硬件参数、换热器脏堵状态和冷媒量构建n个序列；
将序列1至序列(n-1)分别输入到对应的一个第二网络单元，将序列n分别输入到第一网络单元。
根据本公开的第三方面，提供了一种用于预测空调最优运行参数的预测模型的训练装置，包括处理器和存储有程序指令的存储器，处理器被配置为在运行程序指令时，执行本公开的第一方面提供的用于预测空调最优运行参数的预测模型的训练方法。
根据本公开的第四方面，提供了一种空调最优运行参数的预测装置，包括处理器和存储有程序指令的存储器，处理器被配置为在运行程序指令时，执行本公开的第二方面提供的空调最优运行参数的预测方法。
根据本公开的第五方面，提供了一种空调，包括：
空调本体；
本公开的第三方面提供的用于预测空调最优运行参数的预测模型的训练装置，训练装置设置于空调本体；和/或，
本公开的第四方面提供的空调最优运行参数的预测装置，空调最优运行参数的预测装置设置于空调本体。
以上的总体描述和下文中的描述仅是示例性和解释性的，不用于限制本公开。
附图说明
一个或多个实施例通过与之对应的附图进行示例性说明，这些示例性说明和附图并不构成对实施例的限定，附图中具有相同参考数字标号的元件示为类似的元件，附图不构成比例限制，并且其中：
图1是本公开实施例提供的一种用于预测空调最优运行参数的预测模型的训练方法的流程示意图；
图2是本公开实施例提供的一种预测模型的结构示意图；
图3是本公开实施例提供的一种空调最优运行参数的预测方法的流程示意图；
图4是本公开实施例提供的一种用于预测空调最优运行参数的预测模型的训练装置的结构示意图；
图5是本公开实施例提供的一种空调最优运行参数的预测装置的结构示意图；
图6是本公开实施例提供的一种空调的结构示意图。
具体实施方式
为了能够更加详尽地了解本公开实施例的特点与技术内容，下面结合附图对本公开实施例的实现进行详细阐述，所附附图仅供参考说明之用，并非用来限定本公开实施例。在以下的技术描述中，为方便解释起见，通过多个细节以提供对所披露实施例的充分理解。然而，在没有这些细节的情况下，一个或多个实施例仍然可以实施。在其它情况下，为简化附图，熟知的结构和装置可以简化展示。
说明书中对任何现有技术的引用不是也不应被视为承认或以任何形式暗示该现有技术构成申请地区或任何其他司法管辖区的公知常识的一部分，或者该现有技术可以被本领域技术人员合理地理解和视为相关。
本公开实施例的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本公开实施例的实施例。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含。
除非另有说明，术语“多个”表示两个或两个以上。
本公开实施例中，字符“/”表示前后对象是一种“或”的关系。例如，A/B表示：A或B。
术语“和/或”是一种描述对象的关联关系，表示可以存在三种关系。例如，A和/或B，表示：A或B，或，A和B这三种关系。
术语“对应”可以指的是一种关联关系或绑定关系，A与B相对应指的是A与B之间是一种关联关系或绑定关系。
本公开实施例提供了一种用于预测空调最优运行参数的预测模型的训练装置，训练装置是具有计算能力的设备，例如训练装置可以是个人计算机，服务器，或者网络设备等。电子设备可以用于执行本公开实施例提供的用于预测空调最优运行参数的预测模型的训练方法。
结合本公开实施例提供的训练装置，本公开实施例提供了一种用于预测空调最优运行参数的预测模型的训练方法，结合图1所示，用于预测空调最优运行参数的预测模型的训练方法包括：
S101，在空调焓差室中采集不同换热器脏堵状态和不同冷媒量下的空调硬件参数；
S102，确定不同换热器脏堵状态和不同冷媒量下的空调最优运行参数，将确定出的空调最优运行参数作为标签数据；
S103，基于换热器脏堵状态、冷媒量、标签数据、空调硬件参数构建训练数据集；
S104，依次将各个数据单元输入初始预测模型进行训练，得到能够预测空调最优运行参数的目标预测模型。
空调焓差室是一种专业实验室，主要用于测试空调、热泵以及其他制冷设备的性能，特别是它们在不同工况下的制冷量、制热量、能效比等关键指标。本公开实施例可以在空调焓差室中改变孔田的换热器脏堵状态和冷媒量，并在不同换热器脏堵状态和不同冷媒量下采集空调硬件参数。
在本公开实施例中，空调硬件参数包括排气温度、吸气温度、除霜传感器温度、外环温、过冷器旁通进口温度、总电流、外阀开度、外盘管温度、辅阀开度、板换进口温度、板换出口温度、油温、压缩机频率、膨胀阀开度、内风机转速和外风机转速等。
关于S103，在本公开实施例中，训练数据集包括多个数据单元，每个数据单元包含换热器脏堵状态和冷媒量，以及该换热器脏堵状态和冷媒量下的空调硬件参数和标签数据。
本公开实施例提供了一种用于预测空调最优运行参数的预测模型的训练方法，通过基于不同换热器脏堵状态和不同冷媒量下的空调硬件参数和空调最优运行参数、以及空调硬件参数和空调最优运行参数对应的热器脏堵状态和冷媒量构建训练数据集，利用训练数据集对预测模型进行训练，使得预测模型具有预测空调最优运行参数的能力。通过将当前的换热器脏堵状态、冷媒量和空调硬件参数输入到预测模型，利用预测模型可以得到符合空调当前的实际状况的最优运行参数，以便空调基于预测出的最优运行参数能够在最优状态运行，达到较高的能耗比，减少能量的浪费。
在一些实施例中，基于换热器脏堵状态、冷媒量、标签数据、空调硬件参数构建训练数据集，包括：将空调焓差室布置的温度点位和压力点位作为预设算法的输入特征；利用预设算法对采集的空调硬件参数进行预处理，其中，预处理包括剔除非稳态数据和特征提取；将换热器脏堵状态和冷媒量，以及换热器脏堵状态和冷媒量下的空调硬件参数和标签数据划分到一个数据单元，得到多个数据单元。
在本公开实施例中，预设算法可以是SHAP(SHapley Additive exPlanations)算法。SHAP算法是一种用于解释机器学习模型预测结果的算法，它通过计算每个特征对模型输出的贡献来提供模型的可解释性。这里，过冷器旁通进口温度是最重要的建模输入变量，显示出Shapley(夏普利)值约为0.8。这说明过冷器旁通阀的开度于换热器脏堵而言具有重要影响。过冷器旁通进口温度，冷凝器盘管温a，高压干管温度，风机送风温度下，蒸发器高压分歧管温度等五个变量的Shapley值均超过0.2，是最重要的前五个输入变量。根据相关专业知识，冷凝温度，阀的开度和换热温差是影响换热器脏堵程度的重要变量，直接或间接影响这些变量的特征与特征重要性排序结果非常一致，这意味着所开发的预测模型可根据领域知识进行物理解释。
在本公开实施例中，为了在训练时让预测模型快速收敛，可以对空调硬件参数进行归一化操作。例如，压缩机频率的最大值为116Hz、膨胀阀开度的最大值为480、内风机转速的最大值为1200RPM、外风机转速的最大值为1200RPM，将压缩机频率、膨胀阀开度、内风机转速和外风机转速分别除以其最大值，从而将压缩机频率、膨胀阀开度、内风机转速和外风机转速的范围归一化到0至1之间，这可以提升模型训练时的收敛速度。
通过对空调运行状态与空调硬件参数之间的关系分析，空调的运行参数之间有一定的序列性和耦合性。具体地，在本公开实施例中，空调最优运行参数的数量为多个，空调最优运行参数之间具有序列性和耦合性。基于此，本公开实施例的预测模型采用改进的循环神经网络。循环神经网络是一种权重共享人工神经网络，即一个序列当前的输出与前面的输出也有关。具体的表现形式为网络会对前面的信息进行记忆并应用于当前输出的计算中，即隐藏层之间的节点不再无连接而是有连接的，并且隐藏层的输入不仅包括输入层的输出还包括上一时刻隐藏层的输出。结合图2所示，这里，使用改进的循环神经网络的初始预测模型包括与各个空调最优运行参数分别对应的第一网络单元，每个空调最优运行参数对应的第一网络单元用于预测该空调最优运行参数。各个空调最优运行参数对应的第一网络单元按照空调最优运行参数的序列性串联连接，后一个第一网络单元的输出结果与前一个第一网络单元的输出结果相关。
在本公开实施例中，空调最优运行参数包括最优压缩机频率、最优膨胀阀开度、最优内风机转速和最优外风机转速。最优压缩机频率、最优膨胀阀开度、最优内风机转速和最优外风机转速的序列依次增加，最优压缩机频率对应的第一网络单元、最优膨胀阀开度对应的第一网络单元、最优内风机转速对应的第一网络单元和最优外风机转速对应的第一网络单元依次串联连接。
最优膨胀阀开度对应的第一网络单元的输出结果与最优压缩机频率对应的第一网络单元的输出结果相关，最优内风机转速对应的第一网络单元的输出结果与最优膨胀阀开度对应的第一网络单元的输出结果相关，最优外风机转速对应的第一网络单元的输出结果与最优内风机转速对应的第一网络单元出结果相关。
在本公开实施例中，初始预测模型还包括多个第二网络单元，多个第二网络单元串联连接，最后一个第二网络单元与最前面的第一网络单元连接。后一个第二网络单元的输出结果与前一个第二网络单元的输出结果相关，最前面的第一网络单元连接的输出结果与最后一个第二网络单元的输出结果相关。结合图2所示，最优压缩机频率对应的第一网络单元输出结果与最后一个第二网络单元的输出结果相关。
在本公开实施例中，依次将各个数据单元输入初始预测模型进行训练，包括：依次将各个数据单元执行以下步骤：基于数据单元构建n个序列，其中，第二网络单元的数量为(n-1)；将序列1至序列(n-1)分别输入到对应的一个第二网络单元，将序列n分别输入到第一网络单元；基于输入的各个序列对初始预测模型进行训练。
本公开实施例提供了一种空调最优运行参数的预测装置，预测装置是具有计算能力的设备，例如预测装置可以是个人计算机，服务器，或者网络设备等。电子设备可以用于执行本公开实施例提供的空调最优运行参数的预测方法。
结合本公开实施例提供的预测装置，本公开实施例提供了一种空调最优运行参数的预测方法，结合图3所示，预测方法包括：
S301，采集空调当前的空调硬件参数；
S302，确定空调当前的换热器脏堵状态和冷媒量；
S303，将空调硬件参数、换热器脏堵状态和冷媒量输入到目标预测模型；
S304，利用目标预测模型预测出当前的空调最优运行参数。
关于S303，在本公开实施例中，目标预测模型是上述实施例提供的用于预测空调最优运行参数的预测模型的训练方法得到的。
在一些实施例中，将空调硬件参数输入到目标预测模型，包括：基于空调硬件参数、换热器脏堵状态和冷媒量构建n个序列；将序列1至序列(n-1)分别输入到对应的一个第二网络单元，将序列n分别输入到第一网络单元。
结合图4所示，本公开实施例提供了一种用于预测空调最优运行参数的预测模型的训练装置400，训练装置400包括处理器(processor)401和存储器(memory)402。可选地，训练装置400还可以包括通信接口(Communication Interface)403和总线404。其中，处理器401、通信接口403、存储器402可以通过总线404完成相互间的通信。通信接口403可以用于信息传输。处理器401可以调用存储器402中的逻辑指令，以执行上述实施例的用于预测空调最优运行参数的预测模型的训练方法。
此外，上述的存储器402中的逻辑指令可以通过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。
存储器402作为一种计算机可读存储介质，可用于存储软件程序、计算机可执行程序，如本公开实施例中的方法对应的程序指令/模块。处理器401通过运行存储在存储器402中的程序指令/模块，从而执行功能应用以及数据处理，即实现上述实施例中的用于预测空调最优运行参数的预测模型的训练方法。
存储器402可包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序；存储数据区可存储根据终端设备的使用所创建的数据等。此外，存储器402可以包括高速随机存取存储器，还可以包括非易失性存储器。
结合图5所示，本公开实施例提供了一种空调最优运行参数的预测装置500，预测装置500包括处理器(processor)501和存储器(memory)502。可选地，预测装置500还可以包括通信接口(Communication Interface)503和总线504。其中，处理器501、通信接口503、存储器502可以通过总线504完成相互间的通信。通信接口503可以用于信息传输。处理器501可以调用存储器502中的逻辑指令，以执行上述实施例的空调最优运行参数的预测方法。
此外，上述的存储器502中的逻辑指令可以通过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。
存储器502作为一种计算机可读存储介质，可用于存储软件程序、计算机可执行程序，如本公开实施例中的方法对应的程序指令/模块。处理器501通过运行存储在存储器502中的程序指令/模块，从而执行功能应用以及数据处理，即实现上述实施例中的空调最优运行参数的预测方法。
存储器502可包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序；存储数据区可存储根据终端设备的使用所创建的数据等。此外，存储器502可以包括高速随机存取存储器，还可以包括非易失性存储器。
结合图6所示，本公开实施例提供了一种空调600，空调600包括空调本体601，还包括上述实施例提供的用于预测空调最优运行参数的预测模型的训练装置400和/或空调最优运行参数的预测装置500。在空调600包括训练装置400的情况下，训练装置400设置于空调本体601。在空调600包括预测装置500的情况下，预测装置500设置于空调本体601。
本公开实施例提供了一种计算机可读非暂态存储介质(computer-readable non-transitory storage media)，存储有程序指令，程序指令在运行时，执行以下步骤的程序指令：
在空调焓差室中采集不同换热器脏堵状态和不同冷媒量下的空调硬件参数；
确定不同换热器脏堵状态和不同冷媒量下的空调最优运行参数，将确定出的空调最优运行参数作为标签数据；
基于换热器脏堵状态、冷媒量、标签数据、空调硬件参数构建训练数据集，其中，训练数据集包括多个数据单元，每个数据单元包含换热器脏堵状态和冷媒量，以及该换热器脏堵状态和冷媒量下的空调硬件参数和标签数据；
依次将各个数据单元输入初始预测模型进行训练，得到能够预测空调最优运行参数的目标预测模型。
本公开实施例提供了一种计算机可读非暂态存储介质(computer-readable non-transitory storage media)，存储有程序指令，程序指令在运行时，执行以下步骤的程序指令：
采集空调当前的空调硬件参数；
确定空调当前的换热器脏堵状态和冷媒量；
将空调硬件参数、换热器脏堵状态和冷媒量输入到目标预测模型；
利用目标预测模型预测出当前的空调最优运行参数。
本公开实施例提供了一种计算机程序，当所述计算机程序被计算机执行时，使所述计算机实现上述用于预测空调最优运行参数的预测模型的训练方法或空调最优运行参数的预测方法。
本公开实施例提供了一种计算机程序产品，所述计算机程序产品包括存储在计算机可读存储介质上的计算机指令，当所述程序指令被计算机执行时，使所述计算机实现上述用于预测空调最优运行参数的预测模型的训练方法或空调最优运行参数的预测方法。
本公开实施例的技术方案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，包括一个或多个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)执行本公开实施例所述方法的全部或部分步骤。而前述的存储介质可以是非暂态存储介质，例如：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等多种可以存储程序代码的介质。
本公开实施例提供的预测模型的训练方法、空调最优运行参数的预测方法、装置、空调，可以实现以下技术效果：
本公开实施例提供了一种用于预测空调最优运行参数的预测模型的训练方法，通过基于不同换热器脏堵状态和不同冷媒量下的空调硬件参数和空调最优运行参数、以及空调硬件参数和空调最优运行参数对应的热器脏堵状态和冷媒量构建训练数据集，利用训练数据集对预测模型进行训练，使得预测模型具有预测空调最优运行参数的能力。通过将当前的换热器脏堵状态、冷媒量和空调硬件参数输入到预测模型，利用预测模型可以得到符合空调当前的实际状况的最优运行参数，以便空调基于预测出的最优运行参数能够在最优状态运行，达到较高的能耗比，减少能量的浪费。
以上描述和附图充分地示出了本公开的实施例，以使本领域的技术人员能够实践它们。其他实施例可以包括结构的、逻辑的、电气的、过程的以及其他的改变。实施例仅代表可能的变化。除非明确要求，否则单独的部件和功能是可选的，并且操作的顺序可以变化。一些实施例的部分和特征可以被包括在或替换其他实施例的部分和特征。而且，本申请中使用的用词仅用于描述实施例并且不用于限制权利要求。如在实施例以及权利要求的描述中使用的，除非上下文清楚地表明，否则单数形式的“一个”(a)、“一个”(an)和“所述”(the)旨在同样包括复数形式。类似地，如在本申请中所使用的术语“和/或”是指包含一个或一个以上相关联的列出的任何以及所有可能的组合。另外，当用于本申请中时，术语“包括”(comprise)及其变型“包括”(comprises)和/或包括(comprising)等指陈述的特征、整体、步骤、操作、元素，和/或组件的存在，但不排除一个或一个以上其它特征、整体、步骤、操作、元素、组件和/或这些的分组的存在或添加。在没有更多限制的情况下，由语句“包括一个…”限定的要素，并不排除在包括所述要素的过程、方法或者设备中还存在另外的相同要素。本文中，每个实施例重点说明的可以是与其他实施例的不同之处，各个实施例之间相同相似部分可以互相参见。对于实施例公开的方法、产品等而言，如果其与实施例公开的方法部分相对应，那么相关之处可以参见方法部分的描述。
本领域技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，可以取决于技术方案的特定应用和设计约束条件。所述技术人员可以对每个特定的应用来使用不同方法以实现所描述的功能，但是这种实现不应认为超出本公开实施例的范围。所述技术人员可以清楚地了解到，为描述的方便和简洁，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。
本文所披露的实施例中，所揭露的方法、产品(包括但不限于装置、设备等)，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，所述单元的划分，可以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。另外，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。另外，在本公开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。
附图中的流程图和框图显示了根据本公开实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或代码的一部分，所述模块、程序段或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这可以依所涉及的功能而定。在附图中的流程图和框图所对应的描述中，不同的方框所对应的操作或步骤也可以以不同于描述中所披露的顺序发生，有时不同的操作或步骤之间不存在特定的顺序。例如，两个连续的操作或步骤实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这可以依所涉及的功能而定。框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。

Claims (14)

  1. 一种用于预测空调最优运行参数的预测模型的训练方法，包括：
    在空调焓差室中采集不同换热器脏堵状态和不同冷媒量下的空调硬件参数；
    确定不同换热器脏堵状态和不同冷媒量下的空调最优运行参数，将确定出的空调最优运行参数作为标签数据；
    基于换热器脏堵状态、冷媒量、标签数据、空调硬件参数构建训练数据集，其中，训练数据集包括多个数据单元，每个数据单元包含换热器脏堵状态和冷媒量，以及该换热器脏堵状态和冷媒量下的空调硬件参数和标签数据；
    依次将各个数据单元输入初始预测模型进行训练，得到能够预测空调最优运行参数的目标预测模型。
  2. 根据权利要求1的所述的方法，其中，基于换热器脏堵状态、冷媒量、标签数据、空调硬件参数构建训练数据集，包括：
    将空调焓差室布置的温度点位和压力点位作为预设算法的输入特征；
    利用预设算法对采集的空调硬件参数进行预处理，其中，预处理包括剔除非稳态数据和特征提取；
    将换热器脏堵状态和冷媒量，以及换热器脏堵状态和冷媒量下的空调硬件参数和标签数据划分到一个数据单元，得到多个数据单元。
  3. 根据权利要求1的所述的方法，其中，空调最优运行参数的数量为多个，空调最优运行参数之间具有序列性和耦合性；
    初始预测模型包括与各个空调最优运行参数分别对应的第一网络单元，每个空调最优运行参数对应的第一网络单元用于预测该空调最优运行参数；
    各个空调最优运行参数对应的第一网络单元按照空调最优运行参数的序列性串联连接，后一个第一网络单元的输出结果与前一个第一网络单元的输出结果相关。
  4. 根据权利要求3的所述的方法，其中，空调最优运行参数包括最优压缩机频率、最优膨胀阀开度、最优内风机转速和最优外风机转速；
    最优压缩机频率、最优膨胀阀开度、最优内风机转速和最优外风机转速的序列依次增加，最优压缩机频率对应的第一网络单元、最优膨胀阀开度对应的第一网络单元、最优内风机转速对应的第一网络单元和最优外风机转速对应的第一网络单元依次串联连接。
  5. 根据权利要求3的所述的方法，其中，初始预测模型还包括多个第二网络单元，多个第二网络单元串联连接，最后一个第二网络单元与最前面的第一网络单元连接；
    后一个第二网络单元的输出结果与前一个第二网络单元的输出结果相关，最前面的第一网络单元连接的输出结果与最后一个第二网络单元的输出结果相关。
  6. 根据权利要求5的所述的方法，其中，依次将各个数据单元输入初始预测模型进行训练，包括：
    依次将各个数据单元执行以下步骤：
    基于数据单元构建n个序列，其中，第二网络单元的数量为(n-1)；
    将序列1至序列(n-1)分别输入到对应的一个第二网络单元，将序列n分别输入到第一网络单元；
    基于输入的各个序列对初始预测模型进行训练。
  7. 一种空调最优运行参数的预测方法，包括：
    采集空调当前的空调硬件参数；
    确定空调当前的换热器脏堵状态和冷媒量；
    将空调硬件参数、换热器脏堵状态和冷媒量输入到目标预测模型，其中，目标预测模型是使用如权利要求1至6任一项所述的用于预测空调最优运行参数的预测模型的训练方法得到的；
    利用目标预测模型预测出当前的空调最优运行参数。
  8. 一种用于预测空调最优运行参数的预测模型的训练装置，包括处理器和存储有程序指令的存储器，所述处理器被配置为在运行所述程序指令时，执行如权利要求1至6中任一项所述的用于预测空调最优运行参数的预测模型的训练方法。
  9. 一种空调最优运行参数的预测装置，包括处理器和存储有程序指令的存储器，所述处理器被配置为在运行所述程序指令时，执行如权利要求7所述的空调最优运行参数的预测方法。
  10. 一种空调，包括：
    空调本体；
    如权利要求8所述的用于预测空调最优运行参数的预测模型的训练装置，训练装置设置于空调本体；和/或，
    如权利要求9所述的空调最优运行参数的预测装置，空调最优运行参数的预测装置设置于空调本体。
  11. 一种计算机可读非暂态存储介质，存储有程序指令，所述程序指令在运行时，执行以下步骤的程序指令：
    在空调焓差室中采集不同换热器脏堵状态和不同冷媒量下的空调硬件参数；
    确定不同换热器脏堵状态和不同冷媒量下的空调最优运行参数，将确定出的空调最优运行参数作为标签数据；
    基于换热器脏堵状态、冷媒量、标签数据、空调硬件参数构建训练数据集，其中，训练数据集包括多个数据单元，每个数据单元包含换热器脏堵状态和冷媒量，以及该换热器脏堵状态和冷媒量下的空调硬件参数和标签数据；
    依次将各个数据单元输入初始预测模型进行训练，得到能够预测空调最优运行参数的目标预测模型。
  12. 一种计算机可读非暂态存储介质，存储有程序指令，所述程序指令在运行时，执行以下步骤的程序指令：
    采集空调当前的空调硬件参数；
    确定空调当前的换热器脏堵状态和冷媒量；
    将空调硬件参数、换热器脏堵状态和冷媒量输入到目标预测模型，其中，目标预测模型是使用如下的训练方法得到的：
    在空调焓差室中采集不同换热器脏堵状态和不同冷媒量下的空调硬件参数；
    确定不同换热器脏堵状态和不同冷媒量下的空调最优运行参数，将确定出的空调最优运行参数作为标签数据；
    基于换热器脏堵状态、冷媒量、标签数据、空调硬件参数构建训练数据集，其中，训练数据集包括多个数据单元，每个数据单元包含换热器脏堵状态和冷媒量，以及该换热器脏堵状态和冷媒量下的空调硬件参数和标签数据；
    依次将各个数据单元输入初始预测模型进行训练，得到能够预测空调最优运行参数的目标预测模型；
    利用目标预测模型预测出当前的空调最优运行参数。
  13. 一种计算机程序，当所述计算机程序被计算机执行时，使所述计算机实现如权利要求1至6中任一项所述的用于预测空调最优运行参数的预测模型的训练方法。
  14. 一种计算机程序产品，所述计算机程序产品包括存储在计算机可读存储介质上的计算机指令，当所述程序指令被计算机执行时，使所述计算机实现如权利要求1至6中任一项所述的用于预测空调最优运行参数的预测模型的训练方法。
PCT/CN2025/075954 2024-07-03 2025-02-06 预测模型的训练方法、空调最优运行参数的预测方法、装置、空调 Pending WO2026007402A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202410886464.0A CN118757869A (zh) 2024-07-03 2024-07-03 预测模型的训练方法、空调最优运行参数的预测方法、装置、空调
CN202410886464.0 2024-07-03

Publications (1)

Publication Number Publication Date
WO2026007402A1 true WO2026007402A1 (zh) 2026-01-08

Family

ID=92940641

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2025/075954 Pending WO2026007402A1 (zh) 2024-07-03 2025-02-06 预测模型的训练方法、空调最优运行参数的预测方法、装置、空调

Country Status (2)

Country Link
CN (1) CN118757869A (zh)
WO (1) WO2026007402A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118757869A (zh) * 2024-07-03 2024-10-11 青岛海尔空调器有限总公司 预测模型的训练方法、空调最优运行参数的预测方法、装置、空调

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108981097A (zh) * 2018-06-19 2018-12-11 广东美的暖通设备有限公司 空调系统及其能需调整方法与装置
CN113405217A (zh) * 2021-06-11 2021-09-17 珠海格力电器股份有限公司 空调换热器脏堵的清理方法、装置和空调
CN113654192A (zh) * 2021-07-15 2021-11-16 青岛海尔空调器有限总公司 室外换热器的管内自清洁控制方法
CN114484729A (zh) * 2022-03-18 2022-05-13 上海美控智慧建筑有限公司 空调器容错控制方法、装置、空调器及存储介质
CN115247869A (zh) * 2021-04-28 2022-10-28 芜湖美智空调设备有限公司 空调器的控制方法、装置、空调器及存储介质
CN116066964A (zh) * 2021-10-29 2023-05-05 广东美的制冷设备有限公司 脏堵检测方法、存储介质、控制装置和空调器
CN116717892A (zh) * 2023-06-19 2023-09-08 宁波奥克斯电气股份有限公司 一种换热器的脏堵控制方法、装置及空调器
US20240068721A1 (en) * 2022-08-31 2024-02-29 Johnson Controls Tyco IP Holdings LLP Systems and methods for refrigerant leakage diagnosis
CN118757869A (zh) * 2024-07-03 2024-10-11 青岛海尔空调器有限总公司 预测模型的训练方法、空调最优运行参数的预测方法、装置、空调

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108981097A (zh) * 2018-06-19 2018-12-11 广东美的暖通设备有限公司 空调系统及其能需调整方法与装置
CN115247869A (zh) * 2021-04-28 2022-10-28 芜湖美智空调设备有限公司 空调器的控制方法、装置、空调器及存储介质
CN113405217A (zh) * 2021-06-11 2021-09-17 珠海格力电器股份有限公司 空调换热器脏堵的清理方法、装置和空调
CN113654192A (zh) * 2021-07-15 2021-11-16 青岛海尔空调器有限总公司 室外换热器的管内自清洁控制方法
CN116066964A (zh) * 2021-10-29 2023-05-05 广东美的制冷设备有限公司 脏堵检测方法、存储介质、控制装置和空调器
CN114484729A (zh) * 2022-03-18 2022-05-13 上海美控智慧建筑有限公司 空调器容错控制方法、装置、空调器及存储介质
US20240068721A1 (en) * 2022-08-31 2024-02-29 Johnson Controls Tyco IP Holdings LLP Systems and methods for refrigerant leakage diagnosis
CN116717892A (zh) * 2023-06-19 2023-09-08 宁波奥克斯电气股份有限公司 一种换热器的脏堵控制方法、装置及空调器
CN118757869A (zh) * 2024-07-03 2024-10-11 青岛海尔空调器有限总公司 预测模型的训练方法、空调最优运行参数的预测方法、装置、空调

Also Published As

Publication number Publication date
CN118757869A (zh) 2024-10-11

Similar Documents

Publication Publication Date Title
Li et al. Data partitioning and association mining for identifying VRF energy consumption patterns under various part loads and refrigerant charge conditions
Guo et al. Optimized neural network-based fault diagnosis strategy for VRF system in heating mode using data mining
Sun et al. A novel efficient SVM-based fault diagnosis method for multi-split air conditioning system’s refrigerant charge fault amount
CN114484731A (zh) 一种基于stacking融合算法的中央空调故障诊断方法及装置
CN115406055B (zh) 用于冷媒泄漏诊断的空调系统及其控制方法
CN118705724B (zh) 用于空调节能的方法、装置、空调和计算机可读存储介质
CN114154689B (zh) 一种冷水主机单机能耗预测方法、系统及存储介质
CN105160345B (zh) 一种诊断列车空调机组故障的方法
Guo et al. Research on fault detection and diagnosis of carbon dioxide heat pump systems in buildings based on transfer learning
WO2024114675A1 (zh) 多联机空调系统及其控制方法
Guo et al. Research on attention-based fault diagnosis and multi-parameter joint optimization of CO2 heat pump system
CN110702438B (zh) 一种离心式冷水机组与新风系统联合故障诊断方法
CN113865009B (zh) 化霜方法、系统、空调器、存储介质及电子设备
Bai et al. Optimizing energy efficiency in multi-chiller systems: A comprehensive Modelica-based approach
CN118757869A (zh) 预测模型的训练方法、空调最优运行参数的预测方法、装置、空调
CN111895605A (zh) 空调化霜的控制方法、装置、空调及计算机可读存储介质
He et al. Cross-unit soft fault diagnosis for VRF systems using deep transfer learning: A comparative study across multiple scenarios
WO2025204957A1 (ja) 冷媒漏洩判定装置、空気調和機、冷媒漏洩判定プログラム及び冷媒漏洩判定方法
JPH0979650A (ja) 多室空気調和機
CN117436007A (zh) 一种冷水机组故障诊断方法、系统、介质及设备
JP7817602B2 (ja) 空調ゾーニング方法
CN116558861B (zh) 一种变工况冷水主机健康状态评估方法及系统
CN119222706B (zh) 用于除霜的方法、装置、电子设备及存储介质
CN116085990B (zh) 用于空调换热器疏通控制的方法、装置、空调及存储介质
Sohani et al. Application of machine learning and artificial intelligence in design, optimization, and control of VRF systems

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: 25831765

Country of ref document: EP

Kind code of ref document: A1