WO2023209968A1 - Dispositif de commande et procédé de commande - Google Patents

Dispositif de commande et procédé de commande Download PDF

Info

Publication number
WO2023209968A1
WO2023209968A1 PCT/JP2022/019331 JP2022019331W WO2023209968A1 WO 2023209968 A1 WO2023209968 A1 WO 2023209968A1 JP 2022019331 W JP2022019331 W JP 2022019331W WO 2023209968 A1 WO2023209968 A1 WO 2023209968A1
Authority
WO
WIPO (PCT)
Prior art keywords
final
defrosting operation
air conditioner
control device
execution
Prior art date
Application number
PCT/JP2022/019331
Other languages
English (en)
Japanese (ja)
Inventor
貴則 京屋
Original Assignee
三菱電機株式会社
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 三菱電機株式会社 filed Critical 三菱電機株式会社
Priority to PCT/JP2022/019331 priority Critical patent/WO2023209968A1/fr
Priority to JP2024517776A priority patent/JPWO2023209968A1/ja
Publication of WO2023209968A1 publication Critical patent/WO2023209968A1/fr

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/30—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
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/10—Temperature
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/10—Temperature
    • F24F2110/12—Temperature of the outside air
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/20—Humidity
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/20—Humidity
    • F24F2110/22—Humidity of the outside air
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2140/00—Control inputs relating to system states
    • F24F2140/60—Energy consumption

Definitions

  • the present disclosure relates to a control device and a control method for controlling execution of a defrosting operation for removing frost from at least one heat exchanger by an air conditioner.
  • Patent Document 1 discloses an air conditioning system configured to perform a defrosting operation when execution conditions are met.
  • the present disclosure has been made to solve the above problems, and aims to provide a technology that can avoid wasteful power consumption and user discomfort caused by execution of the final defrosting operation. purpose.
  • a control device is a control device that controls execution of a defrosting operation by an air conditioner to remove frost from at least one heat exchanger.
  • the control device includes an input/output interface for inputting and outputting data, and a processor.
  • the air conditioner performs a heating operation after performing a defrosting operation during the operating period.
  • the processor acquires air conditioning-related data regarding execution of defrosting operation by the air conditioner from the input/output interface, and uses at least one learned model to operate the air conditioner based on the air conditioning-related data acquired from the input/output interface. Determine whether to prohibit execution of the final defrosting operation scheduled during the operation period.
  • a control method is a control method in which a control device controls execution of a defrosting operation by an air conditioner to remove frost from at least one heat exchanger.
  • the air conditioner performs a heating operation after performing a defrosting operation during the operating period.
  • the control method includes the steps of acquiring air conditioning-related data regarding the execution of defrosting operation by the air conditioner, and using at least one learned model to perform scheduled operations during the operating period of the air conditioner based on the acquired air conditioning-related data. and determining whether to prohibit execution of the final defrosting operation.
  • the present disclosure it is determined whether to prohibit the execution of the final defrosting operation scheduled during the operation period of the air conditioner based on air conditioning related data regarding the execution of the defrosting operation by the air conditioner. Therefore, wasteful power consumption and user discomfort caused by execution of the final defrosting operation can be avoided.
  • FIG. 1 is a diagram showing the configuration of an air conditioning system according to Embodiment 1.
  • FIG. 1 is a diagram showing the configuration of an air conditioner according to Embodiment 1.
  • FIG. 3 is a diagram showing an example of the execution timing of the defrosting operation during the operation period of the air conditioner according to the first embodiment.
  • 1 is a diagram showing the configuration of a control device according to Embodiment 1.
  • FIG. 3 is a diagram showing a functional configuration of the control device according to Embodiment 1 in a utilization phase.
  • FIG. 3 is a diagram for explaining input and output in the control device according to the first embodiment.
  • 7 is a flowchart regarding processing executed by the control device according to Embodiment 1 in a utilization phase.
  • FIG. 3 is a diagram for explaining unsupervised learning in the first trained model according to the first embodiment.
  • FIG. 3 is a diagram for explaining input and output of unsupervised learning in the first trained model according to the first embodiment.
  • FIG. 3 is a diagram showing a functional configuration for generating a first trained model of the learning device according to the first embodiment.
  • FIG. 2 is a diagram for explaining an overview of reinforcement learning.
  • FIG. 6 is a diagram for explaining reinforcement learning in the second trained model according to the first embodiment.
  • FIG. 6 is a diagram for explaining input and output of reinforcement learning in the second trained model according to the first embodiment.
  • FIG. 7 is a diagram for explaining an example of reward calculation of reinforcement learning in the second trained model according to the first embodiment.
  • FIG. 3 is a diagram showing a functional configuration for generating a second trained model of the learning device according to the first embodiment.
  • 7 is a flowchart regarding processing executed by the learning device according to Embodiment 1 in a second learning phase.
  • FIG. 7 is a diagram illustrating a functional configuration of a control device in a utilization phase according to a second embodiment. 7 is a diagram for explaining input and output in a control device according to a second embodiment.
  • FIG. 7 is a flowchart regarding processing executed by the control device according to Embodiment 2 in a utilization phase.
  • FIG. 7 is a diagram for explaining supervised learning in a trained model according to Embodiment 2.
  • FIG. FIG. 7 is a diagram for explaining input and output of supervised learning in a trained model according to Embodiment 2; It is a figure which shows an example of the execution timing of the defrosting operation during
  • the air conditioner 2 includes an outdoor unit 3 and at least one indoor unit 4.
  • a plurality of indoor units 4 are installed to cool or heat a space to be air-conditioned.
  • the air conditioning system 1000 is configured such that a plurality of indoor units 4 are connected to one outdoor unit 3; however, one indoor unit 4 is connected to one outdoor unit 3. It may also be configured to do so.
  • FIG. 2 is a diagram showing the configuration of the air conditioner 2 according to the first embodiment. Note that FIG. 2 functionally shows the connection relationship and arrangement of each device in the air conditioner 2, and does not necessarily show the arrangement in a physical space.
  • the air conditioner 2 includes an outdoor unit 3, an indoor unit 4, and an air conditioner 200.
  • the indoor unit 4 is configured to be connectable to the outdoor unit 3 via an extension pipe 53 and an extension pipe 56.
  • connection port 41 of the four-way valve 40 is connected to the suction port 251 of the compressor 25 via a pipe 60.
  • the connection port 42 of the four-way valve 40 is connected to the indoor unit 4 via a pipe 52 and an extension pipe 53.
  • the connection port 43 of the four-way valve 40 is connected to the discharge port 252 of the compressor 25 via a pipe 51.
  • the connection port 44 of the four-way valve 40 is connected to one end of the outdoor heat exchanger 21 via a pipe 59.
  • the four-way valve 40 is configured to switch the internal communication state according to a control signal from the air conditioner 200.
  • the other end of the outdoor heat exchanger 21 is connected to one end of the expansion valve 26 via a pipe 58.
  • the other end side of the expansion valve 26 is connected to the indoor unit 4 via a pipe 57 and an extension pipe 56.
  • the compressor 25 is configured to operate and stop, and to change its rotational speed during operation, according to a control signal from the air conditioner 200.
  • the air conditioner 200 outputs a control signal to the compressor 25 to arbitrarily change the driving frequency of the compressor 25.
  • the compressor 25 changes the number of rotations per unit time, that is, the rotational speed, in accordance with changes in the drive frequency, thereby changing the amount of refrigerant discharged.
  • the outdoor heat exchanger 21 exchanges heat between the air sucked in from outside by the blower 22, that is, the outside air, and the refrigerant.
  • the expansion valve 26 is, for example, an electronic expansion valve whose opening degree is adjusted according to a control signal from the air conditioner 200.
  • the expansion valve 26 lowers the pressure of the refrigerant that has flowed in, and allows the refrigerant obtained by the pressure reduction to flow out.
  • the indoor heat exchanger 31 exchanges heat between the air sucked in from the room by the blower 32 and the refrigerant.
  • the air conditioner 200 is mounted on the outdoor unit 3. Air conditioner 200 controls actuators such as compressor 25, expansion valve 26, blower 32, blower 22, and four-way valve 40. Note that the air conditioner 200 may be separate from the outdoor unit 3.
  • the air conditioner 2 includes a temperature sensor 70 in the outdoor unit 3 that measures the temperature T0 of the outdoor heat exchanger 21 (hereinafter also referred to as “heat exchanger temperature”), and a temperature sensor 70 that measures the temperature outside the air-conditioned space ( It includes a temperature sensor 71 that measures T1 (hereinafter also referred to as “outside air temperature”), and a humidity sensor 81 that measures humidity H1 (hereinafter also referred to as “outside air humidity”) outside the air-conditioned space.
  • the air conditioner 2 includes a temperature sensor 72 in the indoor unit 4 that measures the temperature T2 in the air-conditioned space (hereinafter also referred to as "indoor temperature”) and the humidity in the air-conditioned space (hereinafter referred to as “indoor humidity”). ) is provided with a humidity sensor 82 that measures H2.
  • Heat exchanger temperature T0, outside air temperature T1, indoor temperature T2, outside air humidity H1, and indoor humidity H2 measured by each sensor are output to air conditioner 200.
  • the air conditioner 2 configured in this manner is capable of performing a heating operation to heat the air-conditioned space.
  • the internal communication state of the four-way valve 40 is such that the connection port 41 communicates with the connection port 44 and the connection port 42 communicates with the connection port 43, as shown by the solid line in FIG. That is, in the heating operation, the suction port 251 of the compressor 25 communicates with the outdoor heat exchanger 21, and the discharge port 252 of the compressor 25 communicates with the indoor unit 4.
  • the compressor 25 sucks in the low-temperature, low-pressure gas refrigerant that has flowed in from the outdoor heat exchanger 21, and increases the pressure of the gas refrigerant by compressing the sucked gas refrigerant.
  • the compressor 25 discharges the high-temperature, high-pressure gas refrigerant obtained by compression to the indoor heat exchanger 31 .
  • the indoor heat exchanger 31 works as a condenser.
  • the indoor heat exchanger 31 exchanges heat between the high-temperature, high-pressure gas refrigerant from the compressor 25 and the air sucked in from the air-conditioned space by the blower 32 .
  • the gas refrigerant that radiates heat to the air through this heat exchange condenses inside the indoor heat exchanger 31 and changes into a high-temperature, high-pressure liquid refrigerant.
  • the high temperature and high pressure liquid refrigerant obtained by the indoor heat exchanger 31 flows out to the expansion valve 26 .
  • the air that has absorbed heat from the gas refrigerant in the indoor heat exchanger 31 is sent into the air-conditioned space again. As a result, the air-conditioned space is heated.
  • the expansion valve 26 lowers the pressure of the high temperature and high pressure liquid refrigerant from the indoor heat exchanger 31.
  • the low-temperature, low-pressure gas-liquid two-phase refrigerant obtained by the expansion valve 26 flows out to the outdoor heat exchanger 21 .
  • the outdoor heat exchanger 21 works as an evaporator.
  • the outdoor heat exchanger 21 exchanges heat between the low-temperature, low-pressure gas-liquid two-phase refrigerant from the expansion valve 26 and the air sucked in from outside the air-conditioned space by the blower 22 .
  • the gas-liquid two-phase refrigerant that absorbs heat from the air through this heat exchange evaporates inside the outdoor heat exchanger 21 and changes into a low-temperature, low-pressure gas refrigerant.
  • the low-temperature, low-pressure gas refrigerant obtained by the outdoor heat exchanger 21 flows out to the compressor 25 .
  • the refrigerant flows through the compressor 25, the indoor heat exchanger 31 (condenser), the expansion valve 26, and the outdoor heat exchanger 21 (evaporator) in this order.
  • the air conditioner 2 is configured to perform a defrosting operation to remove frost from the outdoor heat exchanger 21 before performing the heating operation.
  • the air conditioner 2 further includes a heater 5 near the outdoor heat exchanger 21 in the outdoor unit 3, and operates the heater 5 to turn off the heater when the conditions for executing the defrosting operation are satisfied. Defrost is removed from the outdoor heat exchanger 21 using the heat generated by the heat exchanger 5.
  • the heater 5 is activated or deactivated based on the control of the air conditioner 200.
  • the air conditioner 200 periodically (for example, every hour) checks the heat exchanger temperature T0 acquired from the temperature sensor 70, and checks whether the heat exchanger temperature T0 is equal to or lower than a predetermined threshold (temperature). When this happens, the heater 5 is activated by outputting the control signal C to the heater 5. Thereby, the air conditioner 2 can remove frost from the outdoor heat exchanger 21 using the heat generated by the heater 5.
  • the air conditioner 200 periodically (for example, every hour) checks the heat exchanger temperature T0 acquired from the temperature sensor 70 and the outside air temperature T1 acquired from the temperature sensor 71, and checks the heat exchanger temperature T0 and the outside air temperature.
  • the heater 5 may be activated by outputting the control signal C to the heater 5 when the difference from the temperature T1 becomes equal to or greater than a predetermined threshold value.
  • the air conditioner 200 may perform a defrosting operation to remove frost from the outdoor heat exchanger 21 by a known method other than activating the heater 5.
  • FIG. 3 is a diagram showing an example of the execution timing of the defrosting operation during the operation period of the air conditioner 2 according to the first embodiment.
  • the air conditioner 2 repeatedly performs heating operation and defrosting operation during an operation period from starting a series of heating controls for heating operation to ending the series of heating controls.
  • the heating operation is started again at timing t5 when the defrosting operation is finished. Thereafter, the air conditioner 2 periodically determines whether the execution conditions for the defrosting operation are satisfied during the heating operation, and when the execution conditions for the defrosting operation are established at timing t6, the air conditioner 2 starts the defrosting operation. , the heating operation is restarted at timing t7 when the defrosting operation is finished. Thereafter, the air conditioner 2 ends a series of heating controls for heating operation at timing t8. In this case, the defrosting operation executed during the period from timing t6 to t7 becomes the "final defrosting operation", and the heating operation executed during the period from timing t7 to t8 becomes the "final heating operation". Further, the period from timing t1 to t8 is an "operation period".
  • the air conditioner 2 is able to maintain the heat exchanger temperature T0 or the difference between the heat exchanger temperature T0 and the outside air temperature T1. Since it is determined whether or not to perform the defrosting operation based on the following, there is a possibility that the final defrosting operation will be performed at the end of the operating period. As a result, in the example of FIG. 3(A), the air conditioner 2 may stop in the middle of the period from timing t6 to t7, which is the execution period of the final defrosting operation, and the operation period ends, or the final heating operation may be performed. The period from timing t7 to t8 may be extremely short.
  • the control device 1 controls the execution of the defrosting operation by the air conditioner 2, thereby reducing wasteful power consumption caused by executing the final defrosting operation. It is configured to avoid user discomfort.
  • the control device 1 acquires air conditioning-related data regarding the execution of defrosting operation by the air conditioner 2, utilizes AI (Artificial Intelligence), and determines the execution time of the final defrosting operation based on the air-conditioning related data. and inferring the execution time of the final heating operation scheduled after the final defrosting operation. Further, the control device 1 utilizes AI to calculate the power consumption when executing the final defrosting operation and the final heating operation, that is, the final defrosting operation and the final heating operation in the period from timing t6 to t8 shown in FIG. 3(A). Infer the power consumption when the final heating operation is executed.
  • AI Artificial Intelligence
  • control device 1 utilizes AI to calculate the power consumption when the final defrosting operation is not performed, that is, as shown in FIG. Continuing, the power consumption when only the heating operation (final heating operation) is executed during the period from timing t6 to timing t8 is inferred.
  • the control device 1 compares the power consumption of the air conditioner 2 during the period from timing t6 to t8 between the case where the final defrosting operation is executed and the case where the final defrosting operation is not executed, and based on the comparison result. , it is determined whether or not to prohibit the air conditioner 2 from performing the final defrosting operation.
  • control device 1 determines to prohibit execution of the final defrosting operation, it outputs a prohibition signal for prohibiting execution of the final defrosting operation to the air conditioner 200 that controls the air conditioner 2. Thereby, the air conditioner 2 is controlled not to perform the final defrosting operation based on the prohibition signal from the control device 1.
  • FIG. 4 is a diagram showing the configuration of the control device 1 according to the first embodiment. As shown in FIG. 4, the control device 1 includes a processor 11, a storage device 12, and an input/output interface 13.
  • the processor 11 is a computing entity (computer) that executes various processes by executing various programs.
  • the processor 11 includes, for example, at least one of a CPU (Central Processing Unit), an FPGA (Field-Programmable Gate Array), and a GPU (Graphics Processing Unit). Further, the processor 11 may be configured with a processing circuit such as an ASIC (application specific integrated circuit). Note that the processor 11 includes volatile memories such as DRAM (dynamic random access memory) and SRAM (static random access memory) that temporarily store program codes or work memory when executing various programs. Good too.
  • the storage device 12 includes a nonvolatile memory such as a ROM (Read Only Memory) and a flash memory that store various data necessary for the processor 11 to execute various programs.
  • a nonvolatile memory such as a ROM (Read Only Memory) and a flash memory that store various data necessary for the processor 11 to execute various programs.
  • the storage device 12 may be an SSD (solid state drive), an HDD (hard disk drive), or the like.
  • the input/output interface 13 receives air conditioning related data regarding the execution of the defrosting operation by the air conditioner 2.
  • the input/output interface 13 can also output a prohibition signal to the air conditioner 2 to prohibit execution of the final defrosting operation.
  • the processor 11 mainly includes a first inference section 111, a second inference section 112, a first model generation section 113, a second model generation section 114, a data acquisition section 115, and an output section 116. Equipped with
  • the first inference unit 111 uses a first trained model 121 (described later) to calculate the execution time of the final defrosting operation and the execution time of the final heating operation scheduled after the final defrosting operation based on the air conditioning related data. Infer final operating data for identification. Note that details of the final operation data will be described later using FIG. 6.
  • the second inference unit 112 determines whether to prohibit execution of the final defrosting operation based on the final operation data inferred by the first inference unit 111 using a second learned model 122 to be described later.
  • the first model generation unit 113 generates a first learned model 121 for inferring the final operation data based on the air conditioning related data by performing unsupervised learning on the relationship between the air conditioning related data and the final operation data.
  • the second model generation unit 114 performs the final defrosting operation based on the final operating data by performing reinforcement learning using a reward based on the power consumption when the final defrosting operation and the final heating operation are executed according to the final operating data.
  • a second trained model 122 is generated for determining whether to prohibit execution of the second trained model 122.
  • the data acquisition unit 115 acquires air conditioning related data from the air conditioner 2 via the input/output interface 13.
  • the output unit 116 outputs a prohibition signal for prohibiting the air conditioner 2 from performing the final defrosting operation via the input/output interface 13.
  • FIG. 5 is a diagram showing the functional configuration of the control device 1 in the utilization phase according to the first embodiment.
  • the data acquisition unit 115 acquires air conditioning related data as input 1.
  • the first inference unit 111 uses the first learned model 121 stored in the first learned model storage unit 1221 to infer final driving data as output 1 based on input 1.
  • the second inference unit 112 obtains the output 1 of the first inference unit 111 as input 2 using the second learned model 122 stored in the second learned model storage unit 1222, and outputs 2 based on the input 2.
  • the result of the decision as to whether or not to prohibit execution of the final defrosting operation is inferred as follows.
  • the output unit 116 outputs a prohibition signal to the air conditioner 2 based on the output 2 of the second reasoning unit 112. Note that the first trained model storage unit 1221 and the second trained model storage unit 1222 correspond to functional units of the storage device 12.
  • FIG. 6 is a diagram for explaining inputs and outputs in the control device 1 according to the first embodiment.
  • air conditioning related data is used as input 1 of the first inference section 111.
  • the air conditioning related data is data related to the execution of defrosting operation by the air conditioner 2, and specifically includes the operation history of the air conditioner 2 (for example, the history of heating operation and defrosting operation), the heat in the air conditioned space, etc. At least the following: load transition, date and time, day of the week, presence or absence of holidays, heat exchanger temperature T0, outside air temperature T1, indoor temperature T2, outside air humidity H1, indoor humidity H2, and power consumption of the air conditioner 2 during the operating period. Contains one. Note that the air conditioning related data of input 1 may include all of the plurality of parameters described above, or may include some of the plurality of parameters.
  • the final operation data is used as the output 1 of the first inference section 111, that is, the input 2 of the second inference section 112.
  • the final operation data is data for specifying the execution time of the final defrosting operation and the execution time of the final heating operation. Specifically, it includes the start time of the final defrosting operation, the end time of the final defrosting operation, and the final It includes the heating operation start time and the final heating operation end time.
  • control device 1 the result of whether to prohibit execution of the final defrosting operation is used as the output 2 of the second reasoning unit 112.
  • FIG. 7 is a flowchart regarding processing that the control device 1 according to the first embodiment executes in the utilization phase. The process shown in FIG. 7 is executed by the processor 11 of the control device 1. Note that in FIG. 7, "S” is used as an abbreviation for "STEP".
  • the control device 1 uses the data acquisition unit 115 to acquire air conditioning related data from the air conditioner 200 of the air conditioner 2 as input 1 (S1).
  • the control device 1 inputs the acquired input 1 to the first learned model 121 (S2).
  • the control device 1 uses the first trained model 121, the control device 1 infers final operation data as the output 1 based on the air conditioning related data as the input 1 (S3).
  • the control device 1 inputs the inferred output 1 to the second learned model 122 as input 2 (S4). Using the second learned model 122, the control device 1 determines whether to prohibit execution of the final defrosting operation as output 2 based on the final operation data as input 2 (S5).
  • control device 1 determines to prohibit execution of the final defrosting operation (YES in S6), it outputs a prohibition signal to the air conditioner 2 (S7) and ends this process. Thereby, the air conditioner 2 is controlled not to perform the final defrosting operation.
  • control device 1 determines not to prohibit execution of the final defrosting operation (NO in S6), it ends this process without outputting a prohibition signal to the air conditioner 2. Thereby, the air conditioner 2 is controlled to perform the final defrosting operation.
  • the first learned model 121 is generated by performing unsupervised learning on the relationship between air conditioning related data and final operation data.
  • Unsupervised learning is a method of learning features in the first learning data 131 using the first learning data 131 that does not include results (labels). Examples of unsupervised learning methods include grouping methods such as the K-means method, but the first model generation unit 113 uses a method that can output final operating data as output 1 from air conditioning related data as input 1. Any known unsupervised learning method may be used.
  • FIG. 9 is a diagram for explaining input and output of unsupervised learning in the first trained model 121 according to the first embodiment. As shown in FIG. 9, in the first learning phase, air conditioning related data is used as input 1, and final operation data is used as output 1.
  • the air conditioning related data includes the operation history of the air conditioner 2, changes in heat load in the air conditioned space, date and time, day of the week, presence or absence of holidays, heat exchanger temperature T0, outside air temperature T1, indoor temperature T2, outside air humidity H1,
  • the indoor humidity H2 and the power consumption of the air conditioner 2 during the operation period are both based on the start time of the final defrosting operation, the end time of the final defrosting operation, and the start time of the final heating operation, which are included in the final operation data. , and the end time of the final heating operation.
  • the learning device executes the first learning program 141 stored in the first learning program storage unit 1231, thereby acquiring the first learning data 131 based on the first learning data 131 including the input 1.
  • a trained model 121 is generated.
  • the data acquisition unit 115 acquires first learning data 131 including air conditioning related data as input 1.
  • the first model generation unit 113 uses the first learning data 131 acquired by the data acquisition unit 115 to generate a first learned model 121 for inferring final operation data based on air conditioning related data.
  • the first model generation unit 113 stores the generated first trained model 121 in the first trained model storage unit 1221.
  • FIG. 11 is a diagram showing the configuration of a neural network.
  • the first model generation unit 113 generates the first trained model 121 by unsupervised learning, for example, according to a neural network model.
  • a neural network is composed of an input layer consisting of multiple neurons, an intermediate layer (hidden layer) consisting of multiple neurons, and an output layer consisting of multiple neurons.
  • the intermediate layer may be one layer or two or more layers.
  • FIG. 11 a three-layer neural network is shown.
  • a configuration with three inputs and three outputs is shown.
  • the values multiplied by the weights w11 to w16 are input to the intermediate layers Y1 and Y2, and the values further multiplied by the weights w21 to w26 are input to the intermediate layers Y1 and Y2. are output from the output layers Z1, Z2, and Z3.
  • This output result changes depending on the values of weights w11 to w16 and w21 to w26.
  • the neural network performs unsupervised learning to obtain output 1 from input 1 by adjusting weights based on first learning data 131 including input 1 acquired by data acquisition unit 115. I do.
  • FIG. 12 is a flowchart related to processing performed by the learning device according to the first embodiment in the first learning phase. The process shown in FIG. 12 is executed by the processor 11 of the control device 1 corresponding to the learning device. Note that in FIG. 12, "S” is used as an abbreviation for "STEP".
  • the learning device uses the data acquisition unit 115 to acquire first learning data 131 including input 1 (S11).
  • the learning device generates the first trained model 121 by performing unsupervised learning using the first model generation unit 113 based on the first learning data 131 (S12).
  • the learning device stores the generated first trained model 121 in the first trained model storage unit 1221 (S13), and ends this process.
  • the second trained model 122 is generated by performing reinforcement learning using a reward based on the power consumption when the final defrosting operation and the final heating operation are executed according to the final operation data.
  • FIG. 13 is a diagram for explaining an overview of reinforcement learning.
  • an agent in reinforcement learning, an agent (behavior) in a certain environment observes the current state (parameters of the environment) and decides what action to take based on a policy.
  • a policy is a rule for determining an action, and by optimizing the policy, the selection of actions is optimized.
  • the environment changes dynamically depending on the agent's actions, and the agent is rewarded based on reward standards according to changes in the environment. The agent repeats these actions and learns the actions that yield the most rewards through a series of actions.
  • the current state is represented by B2 (state)
  • the agent's behavior is represented by B1 (behavior)
  • the reward standard is represented by D (reward standard).
  • Q-learning and TD-learning are known as typical methods of reinforcement learning.
  • a general updating formula for the action value function Q(s, a) is expressed by equation (1).
  • S t represents the state of the environment at time t
  • a t represents the behavior at time t.
  • the action a t changes the state to S t+1 .
  • r t+1 represents the reward that the agent receives due to the change in its state
  • ⁇ represents the discount rate
  • ⁇ represents the learning coefficient. Note that ⁇ is in the range of 0 ⁇ 1, and ⁇ is in the range of 0 ⁇ 1.
  • B1 (action) becomes action a t
  • B2 (state) becomes state S t
  • the best action a t in state S t at time t is learned.
  • the update formula expressed by equation (1) is that if the action value function Q of action a with the highest Q value at time t+1 is larger than the action value function Q of action a executed at time t, then the action value function Increase Q, and in the opposite case, decrease action value function Q.
  • the action value function Q(s, a) is updated so that the action value function Q of action a at time t approaches the best action value at time t+1.
  • the best action value in a certain environment is successively propagated to the action value in previous environments.
  • FIG. 14 is a diagram for explaining reinforcement learning in the second trained model 122 according to the first embodiment.
  • the control device 1 (second model generation unit 114) executes the second learning program 142, thereby controlling B1 (behavior) and B2 (corresponding to input 2).
  • the second learned model 122 is generated (updated) based on the second learning data 132 including the state) and D (reward standard).
  • the control device 1 can obtain C (output) corresponding to the output 2 based on the B2 (state) corresponding to the input 2 using the second learned model 122.
  • FIG. 15 is a diagram for explaining the input and output of reinforcement learning in the second trained model 122 according to the first embodiment.
  • the action of whether to prohibit execution of the final defrosting operation is used as B1 (action), and the final operation data is used as B2 (state) corresponding to input 2.
  • B1 action
  • B2 state
  • C output
  • D defrosting operation and final heating operation
  • FIG. 16 is a diagram for explaining an example of reward calculation for reinforcement learning in the second trained model 122 according to the first embodiment.
  • the reward in reinforcement learning is calculated based on the power consumption when the final defrosting operation and the final heating operation are executed according to the final operation data. Specifically, when the final defrosting operation and the final heating operation are performed according to the final operation data (for example, the operation from timing t6 to t8 shown in FIG. 3(A)), and when the final defrosting operation is not performed
  • the second learned model 122 can select the operation with the smaller power consumption as the output result when only the heating operation is executed (for example, the operation during the period from timing t6 to t8 shown in FIG. 3(B)). If the second trained model 122 selects the operation with higher power consumption as the output result, the reward is decreased.
  • FIG. 17 is a diagram showing a functional configuration for generating the second trained model 122 of the learning device according to the first embodiment.
  • the learning device is realized by the processor 11 of the control device 1.
  • the learning device can exchange data with each of the second learning program storage section 1232 and the second learned model storage section 1222.
  • the second learning program storage unit 1232 and the second learned model storage unit 1222 are realized by the storage device 12 of the control device 1.
  • the learning device executes the second learning program 142 stored in the second learning program storage unit 1232, thereby determining B1 (behavior) and B2 (state) corresponding to input 2.
  • the second learned model 122 is generated based on the second learning data 132 including the above and D (reward standard).
  • the data acquisition unit 115 acquires the action of whether or not to prohibit execution of the final defrosting operation as B1 (action), and acquires the final operation data as B2 (state) corresponding to input 2. .
  • the second model generation unit 114 uses the second learning data 132 acquired by the data acquisition unit 115 to generate a second model for determining whether to prohibit execution of the final defrosting operation based on the final operation data.
  • a trained model 122 is generated.
  • the second model generation unit 114 stores the generated second trained model 122 in the second trained model storage unit 1222.
  • the second model generation unit 114 includes a reward calculation unit 1141 and a function update unit 1142.
  • the remuneration calculation unit 1141 calculates remuneration based on D (remuneration standard). Specifically, the remuneration calculation unit 1141 calculates the remuneration based on the power consumption when performing the final defrosting operation and the final heating operation and the power consumption when only the final heating operation is performed, as D (remuneration standard). calculate.
  • the function update unit 1142 updates a function for determining whether to prohibit execution of the final defrosting operation based on the reward calculated by the reward calculation unit 1141. For example, in the case of Q learning, the function updating unit 1142 changes the action value function Q (S t , a t ) expressed by the above equation (1) to the result of whether or not to prohibit execution of the final defrosting operation. It is used as a function to calculate.
  • the second learned model storage unit 1222 stores the action value function Q(S t , a t ) updated by the function update unit 1142 as the second learned model 122 .
  • FIG. 18 is a flowchart related to processing performed by the learning device according to Embodiment 1 in the second learning phase. The process shown in FIG. 18 is executed by the processor 11 of the control device 1 corresponding to the learning device. Note that in FIG. 18, "S" is used as an abbreviation for "STEP".
  • the learning device uses the data acquisition unit 115 to acquire second learning data 132 including B1 (behavior) and B2 (state) corresponding to input 2 (S21).
  • the learning device calculates the reward based on the second learning data 132 (S22). Specifically, if the learning device determines whether or not to prohibit execution of the final defrosting operation based on the second learning data 132, and outputs the result with lower power consumption as the determination result. increases the reward (S23), and decreases the reward if the result with larger power consumption is output (S24).
  • the learning device updates the action value function Q(st, at) expressed by Equation 1 stored in the second trained model storage unit 1222 based on the calculated reward (S25).
  • the learning device repeatedly executes the processes of S21 to S25 described above, and stores the generated action value function Q (st, at) as the second trained model 122 in the second trained model storage unit 1222 (S26), This process ends.
  • the control device 1 generates the first learned model 121 by executing machine learning in the first learning phase described above with the air conditioner 2 installed in a property such as a building, and generates the first learned model 121 in the second learning phase.
  • a second learned model 122 is generated by performing machine learning. For example, when a user inputs an ON command for the final heating operation stop function to an air conditioner 2 placed in a certain property, the control device 1 starts machine learning and starts the first learned model 121. and generates a second trained model 122. That is, the control device 1 generates a first learned model 121 and a second learned model 122 that can be applied to the environment in which the air conditioner 2 is placed.
  • Such machine learning may also be executed in the utilization phase after generating the first learned model 121 and the second learned model 122, so that the control device 1 can perform the
  • the first trained model 121 and the second trained model 122 can be updated.
  • the control device 1 uses the first learned model 121 and the second learned model 122 to determine whether to prohibit execution of the final defrosting operation based on air conditioning-related data that varies depending on the environment. Decide whether or not.
  • the air conditioner 2 performs a final defrosting operation and a final heating operation, or performs a final heating operation without performing a final defrosting operation.
  • the control device 1 uses the first trained model 121 and the second trained model 122 that are suitable for the environment to acquire data from the air conditioner 2 via the input/output interface 13. Based on the air conditioning related data, it is determined whether to prohibit execution of the final defrosting operation scheduled during the operating period of the air conditioner 2. Specifically, the control device 1 uses the first trained model 121 to infer final operation data for specifying the execution time of the final defrosting operation and the execution time of the final heating operation based on the air conditioning related data. , the second learned model 122 is used to determine whether to prohibit execution of the final defrosting operation based on the final operation data.
  • the control device 1 is configured to perform the final defrosting operation at the end of the operating period of the air conditioner 2, so that the air conditioner 2 stops during the final defrosting operation and the operating period ends. It is possible to avoid the situation where the final heating operation is completed or the execution period of the final heating operation after the final defrosting operation becomes extremely short even though the final defrosting operation has been executed. Thereby, the control device 1 can avoid wasting the power consumption caused by the final defrosting operation and preventing the user from feeling uncomfortable during the final defrosting operation.
  • Embodiment 2 The control device 500 according to the second embodiment will be described with reference to FIGS. 19 to 23. Note that, in the following, only the parts of the control device 500 according to the second embodiment that are different from the control device 1 according to the first embodiment will be explained.
  • FIG. 19 is a diagram showing the functional configuration of the control device 500 in the utilization phase according to the second embodiment.
  • control device 500 uses one learned model 520 to perform air conditioning based on air conditioning related data acquired from the air conditioner 2 via the input/output interface 13. It is determined whether to prohibit execution of the final defrosting operation scheduled during the operating period of the machine 2.
  • the processor 511 of the control device 500 includes an inference section 510, a data acquisition section 515, and an output section 516 as main functional components.
  • the data acquisition unit 515 acquires air conditioning related data as input 11.
  • the inference unit 510 uses the learned model 520 stored in the learned model storage unit 5220 to infer a determination result of whether to prohibit execution of the final defrosting operation as an output 11 based on the input 11.
  • the output unit 516 outputs a prohibition signal to the air conditioner 2 based on the output 11 of the inference unit 510.
  • the learned model storage unit 5220 corresponds to a functional unit of the storage device 512 included in the control device 500.
  • FIG. 21 is a flowchart regarding processing that the control device 500 according to Embodiment 2 executes in the utilization phase. The process shown in FIG. 21 is executed by the processor 511 of the control device 500. Note that in FIG. 21, "S” is used as an abbreviation for "STEP".
  • the control device 500 uses the data acquisition unit 515 to acquire air conditioning related data from the air conditioner 200 of the air conditioner 2 as input 11 (S51).
  • the control device 500 inputs the acquired input 11 to the learned model 520 (S52).
  • the control device 500 determines whether to prohibit execution of the final defrosting operation as the output 11 based on the air conditioning related data as the input 11 (S53).
  • control device 500 determines to prohibit execution of the final defrosting operation (YES in S54), it outputs a prohibition signal to the air conditioner 2 (S55) and ends this process. Thereby, the air conditioner 2 is controlled not to perform the final defrosting operation.
  • control device 500 determines not to prohibit execution of the final defrosting operation (NO in S54)
  • the control device 500 ends this process without outputting a prohibition signal to the air conditioner 2.
  • the air conditioner 2 is controlled to perform the final defrosting operation.
  • [Learning phase] An application example of the control device 500 in the learning phase for generating the trained model 520 will be described with reference to FIGS. 22 and 23.
  • the learned model 520 is generated by performing supervised learning regarding the relationship between air conditioning related data and whether or not execution of the final defrosting operation is prohibited.
  • Supervised learning is a method of learning features in the learning data 530 using data sets of factors and results (labels), and inferring results from input.
  • FIG. 23 is a diagram for explaining the input and output of supervised learning in the trained model 520 according to the second embodiment.
  • air conditioning-related data is used as input 11
  • an action as to whether to prohibit execution of the final defrosting operation is used as input 12 corresponding to correct data
  • output 11 The action of whether or not to prohibit execution of the final defrosting operation is used.
  • the learned model 520 determines whether or not to prohibit execution of the final defrosting operation based on the air conditioning related data that is the input 11, and inputs the input 12 corresponding to the determination result and correct data. If the two match, the weights of the neural network shown in Figure 8 are maintained, and if the two do not match, the weights of the neural network shown in Figure 8 are maintained. Adjust the weights of the neural network. As a result, the learned model 520 can output a result (result of whether or not to prohibit execution of the final defrosting operation) that matches the input 12 corresponding to the correct data based on the air conditioning related data that is the input 11. become.
  • the control device 500 uses the learned model 520 to operate the air conditioner 2 based on the air conditioning related data acquired from the air conditioner 2 via the input/output interface 13. Determine whether to prohibit execution of the final defrosting operation scheduled during the period. Thereby, the control device 500 can avoid wasting the power consumption caused by the final defrosting operation and preventing the user from feeling uncomfortable during the final defrosting operation.
  • the air conditioner starts the heating operation at timing t1, and then starts the defrosting operation for the first heat exchanger 21A when the execution conditions for the defrosting operation are satisfied at timing t2.
  • the heating operation starts again at timing t3 when the defrosting operation ends.
  • a heating operation using the second heat exchanger 21B may be performed.
  • the air conditioner 2 starts the defrosting operation for the second heat exchanger 21B, and starts the heating operation again at timing t5 when the defrosting operation ends. Start.
  • the air conditioner 2 starts the final defrosting operation for the first heat exchanger 21A, and at timing t7 when the defrosting operation ends, the air conditioner 2 starts the final heating operation. start again.
  • a heating operation using the second heat exchanger 21B may be performed.
  • the final defrosting operation may be performed not only on the first heat exchanger 21A but also on the second heat exchanger 21B.
  • the control device 1 may use at least one learned model (for example, the first learned model 121 and the second learned model 122) to determine whether to prohibit execution of the final defrosting operation. .
  • first heat exchanger 21A and the second heat exchanger 21B are not limited to being included in one outdoor unit 3.
  • first heat exchanger 21A and the second heat exchanger 21B are included in the first outdoor unit, and the second heat exchanger 21B is included in the second outdoor unit. They may be included in different outdoor units.
  • the control device 1 outputting the prohibition signal, the air conditioner 2 ends its operating period without performing the final defrosting operation.
  • frost will adhere to the outdoor heat exchanger 21 when the air conditioner 2 operates next time.
  • the processor 11 of the control device 1 sends a reservation signal for causing the air conditioner 2 to execute the defrosting operation at the start of the next operation period. may be output.
  • the air conditioner 2 determines whether or not the execution conditions for the defrosting operation described above are met at the start of the next operating period based on the reservation signal received from the control device 1, and if the execution conditions are met. In addition, defrosting operation may be performed.
  • the processor 11 of the control device 1 prohibits the execution of the final defrosting operation when the duration of the final heating operation by the air conditioner 2 exceeds a threshold value.
  • a permission signal for permission may be output to the air conditioner 2.
  • the duration threshold may be set in advance by the user.
  • the air conditioner 2 prohibits execution of the final defrosting operation based on the permission signal received from the control device 1, and then executes the final defrosting operation when the duration of the final heating operation exceeds a threshold value. Good too. As a result, if the final heating operation continues for a long time after the execution of the final defrosting operation is prohibited, the final defrosting operation will be executed. It is possible to prevent heat exchange efficiency from decreasing.
  • the present disclosure provides a control device 1 that controls execution of a defrosting operation by an air conditioner 2 to remove frost from at least one heat exchanger.
  • the control device 1 includes an input/output interface 13 for inputting and outputting data, and a processor 11.
  • the processor 11 acquires air conditioning related data regarding the execution of defrosting operation by the air conditioner 2 from the input/output interface 13, and uses at least one learned model to perform air conditioning related data based on the air conditioning related data acquired from the input/output interface 13. It is determined whether to prohibit execution of the final defrosting operation scheduled during the operating period of the air conditioner 2.
  • control device 1 can avoid wasting the power consumption caused by the final defrosting operation and preventing the user from feeling uncomfortable during the final defrosting operation.
  • the processor 11 uses at least one learned model to determine the execution time of the final defrosting operation and the execution time of the final heating operation scheduled after the final defrosting operation based on the air conditioning related data.
  • the system infers the data and determines whether to prohibit execution of the final defrosting operation based on the final operation data.
  • control device 1 can infer the execution time of the final defrosting operation and the execution time of the final heating operation using at least one learned model, and can infer the execution time of the final defrosting operation and the final heating operation based on the inference result. It can be determined whether to prohibit execution of the defrosting operation.
  • control device 1 uses the first learned model 121 and the second learned model 122 to determine whether to prohibit execution of the final defrosting operation based on air conditioning related data. can do.
  • the first trained model 121 is generated by performing unsupervised learning on the relationship between air conditioning related data and final operation data.
  • control device 1 can use the first learned model 121 to infer the final operation data based on the air conditioning related data.
  • the second learned model 122 is generated by performing reinforcement learning using a reward based on the power consumption when the final defrosting operation and final heating operation are executed according to the final operation data.
  • control device 1 can use the second learned model 122 to determine whether to prohibit execution of the final defrosting operation based on the final operation data.
  • the air conditioning related data includes the operation history of the air conditioner 2, the change in heat load in the air conditioned space, the date and time, the day of the week, the presence or absence of holidays, the heat exchanger temperature T0 of at least one heat exchanger, and the outside air temperature outside the air conditioned space.
  • T1 the indoor temperature T2 in the air conditioned space
  • the outside air humidity H1 outside the air conditioned space the indoor humidity H2 in the air conditioned space
  • the power consumption of the air conditioner 2 during the operating period.
  • control device 1 can determine whether to prohibit execution of the final defrosting operation based on air conditioning-related data that varies depending on the environment in which the air conditioner 2 is placed. I can do it.
  • the final operation data includes the start time of the final defrosting operation, the end time of the final defrosting operation, the start time of the final heating operation, and the end time of the final heating operation.
  • the control device 1 can set the final defrosting operation start time, the final defrosting operation end time, the final heating operation start time, and the final heating operation start time as the final operation data based on the air conditioning related data.
  • the end time of the heating operation can be inferred.
  • At least one heat exchanger includes a first heat exchanger 21A and a second heat exchanger 21B.
  • the air conditioner alternately performs defrosting operation on the first heat exchanger 21A and the second heat exchanger 21B during the operating period.
  • the processor 11 prohibits execution of the final defrosting operation scheduled during the operating period of the air conditioner, of the defrosting operation for the first heat exchanger 21A and the defrosting operation for the second heat exchanger 21B. Decide whether or not to do so.
  • control device 1 can perform the defrosting operation on the first heat exchanger 21A and the second heat exchanger 21B even when the defrosting operation is performed alternately on the first heat exchanger 21A and the second heat exchanger 21B. Execution of the final defrosting operation on any of the heat exchangers 21B can be prohibited.
  • the processor 11 prohibits execution of the final defrosting operation, it outputs a prohibition signal for prohibiting the air conditioner 2 from executing the final defrosting operation.
  • control device 1 can prohibit the air conditioner 2 from performing the final defrosting operation.
  • the processor 11 prohibits execution of the final defrosting operation, it permits execution of the final defrosting operation when the duration of the heating operation by the air conditioner 2 exceeds a threshold value.
  • the control device 1 can prevent the execution of the final defrosting operation if the heating operation by the air conditioner 2 continues for a long time, for example. Since the final defrosting operation can be permitted, it is possible to prevent the heat exchange efficiency of the outdoor heat exchanger 21 from decreasing due to prohibition of execution of the final defrosting operation.
  • the present disclosure provides a control method in which the control device 1 controls execution of a defrosting operation by the air conditioner 2 to remove frost from at least one heat exchanger.
  • the control method includes a step (S1) of acquiring air conditioning related data regarding execution of defrosting operation by the air conditioner 2, and operating the air conditioner based on the acquired air conditioning related data using at least one learned model. and a step (S2) of determining whether to prohibit execution of the final defrosting operation scheduled during the period.
  • control device 1 can avoid wasting the power consumption caused by the final defrosting operation and preventing the user from feeling uncomfortable during the final defrosting operation.

Landscapes

  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

Un dispositif de commande (1) comprend : une interface d'entrée/sortie (13) à travers laquelle des données sont entrées/délivrées ; et un processeur (11). Le processeur (11) acquiert des données relatives à la climatisation qui sont associées à l'exécution d'une opération de dégivrage par un climatiseur (2) par l'intermédiaire de l'interface d'entrée/sortie (13), et détermine, à l'aide d'au moins un modèle entraîné, s'il faut ou non interdire l'exécution d'une opération de dégivrage finale planifiée pendant une période de fonctionnement du climatiseur (2), sur la base des données relatives à la climatisation acquises par l'intermédiaire de l'interface d'entrée/sortie (13).
PCT/JP2022/019331 2022-04-28 2022-04-28 Dispositif de commande et procédé de commande WO2023209968A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/JP2022/019331 WO2023209968A1 (fr) 2022-04-28 2022-04-28 Dispositif de commande et procédé de commande
JP2024517776A JPWO2023209968A1 (fr) 2022-04-28 2022-04-28

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2022/019331 WO2023209968A1 (fr) 2022-04-28 2022-04-28 Dispositif de commande et procédé de commande

Publications (1)

Publication Number Publication Date
WO2023209968A1 true WO2023209968A1 (fr) 2023-11-02

Family

ID=88518129

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/019331 WO2023209968A1 (fr) 2022-04-28 2022-04-28 Dispositif de commande et procédé de commande

Country Status (2)

Country Link
JP (1) JPWO2023209968A1 (fr)
WO (1) WO2023209968A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008064381A (ja) * 2006-09-07 2008-03-21 Hitachi Appliances Inc 空気調和機
JP2013195045A (ja) * 2012-03-23 2013-09-30 Sharp Corp 空気調和機
JP2018036029A (ja) * 2016-09-02 2018-03-08 ダイキン工業株式会社 冷凍装置
WO2021176689A1 (fr) * 2020-03-06 2021-09-10 三菱電機株式会社 Dispositif de traitement d'informations et système de réfrigération

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008064381A (ja) * 2006-09-07 2008-03-21 Hitachi Appliances Inc 空気調和機
JP2013195045A (ja) * 2012-03-23 2013-09-30 Sharp Corp 空気調和機
JP2018036029A (ja) * 2016-09-02 2018-03-08 ダイキン工業株式会社 冷凍装置
WO2021176689A1 (fr) * 2020-03-06 2021-09-10 三菱電機株式会社 Dispositif de traitement d'informations et système de réfrigération

Also Published As

Publication number Publication date
JPWO2023209968A1 (fr) 2023-11-02

Similar Documents

Publication Publication Date Title
EP2314942B1 (fr) Dispositif de contrôle d'appareil de climatisation et dispositif de contrôle d'appareil de réfrigération
CN108375175B (zh) 空调系统控制方法及装置
KR101626675B1 (ko) 공기조화기 및 그 제어방법
CN110186227B (zh) 空调室内机的电子膨胀阀控制方法
CN108759064B (zh) 一种降噪控制方法、装置及多联机空调系统
JP5951397B2 (ja) 空気調和機
US10612804B2 (en) Operating an HVAC system to reach target temperature efficiently
CN113531857B (zh) 多联机空调的控制方法、多联机空调及存储介质
CN113531801B (zh) 多联式空调器的控制方法、装置和可读存储介质
US20230116355A1 (en) Air conditioner and operation method thereof
CN115307280A (zh) 多联机空调系统的控制方法、控制器、空调系统及介质
CN115183400B (zh) 空调器和空调器除霜控制方法
US9696067B2 (en) Apparatus and method for controlling indoor airflow for heat pumps
WO2023209968A1 (fr) Dispositif de commande et procédé de commande
JP2010276287A (ja) 空調制御装置、空調制御プログラム及び空調システム
CN114688689B (zh) 一种电子膨胀阀的开度调节方法、装置及多联式空调器
CN113864978B (zh) 空调器及其换向控制方法、装置、存储介质及处理器
CN115930408A (zh) 冷水机组的制冷控制方法、装置、冷水机组和存储介质
CN114838487A (zh) 多联机空调的控制方法、多联机空调以及存储介质
JP2008101865A (ja) 空気調和機
CN114608125A (zh) 空调系统的自适应调节方法、装置、空调系统和介质
WO2023144927A1 (fr) Dispositif de commande et procédé de commande
US20240240820A1 (en) Inference device and learning device
US20240167716A1 (en) Information processing device and air conditioning system
WO2023095413A1 (fr) Dispositif de commande de climatisation, système de commande de climatisation et procédé de commande de climatisation

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: 22940242

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2024517776

Country of ref document: JP

Kind code of ref document: A