WO2024114675A1 - 多联机空调系统及其控制方法 - Google Patents

多联机空调系统及其控制方法 Download PDF

Info

Publication number
WO2024114675A1
WO2024114675A1 PCT/CN2023/134965 CN2023134965W WO2024114675A1 WO 2024114675 A1 WO2024114675 A1 WO 2024114675A1 CN 2023134965 W CN2023134965 W CN 2023134965W WO 2024114675 A1 WO2024114675 A1 WO 2024114675A1
Authority
WO
WIPO (PCT)
Prior art keywords
conditioning system
fault
split air
operation data
air conditioning
Prior art date
Application number
PCT/CN2023/134965
Other languages
English (en)
French (fr)
Inventor
石靖峰
任兆亭
张佳舒
阮岱玮
夏兴祥
盛凯
矫晓龙
Original Assignee
青岛海信日立空调系统有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from CN202211542019.XA external-priority patent/CN115950045A/zh
Priority claimed from CN202310432299.7A external-priority patent/CN116697523A/zh
Application filed by 青岛海信日立空调系统有限公司 filed Critical 青岛海信日立空调系统有限公司
Publication of WO2024114675A1 publication Critical patent/WO2024114675A1/zh

Links

Classifications

    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00Control or safety arrangements
    • F24F11/30Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
    • F24F11/32Responding to malfunctions or emergencies
    • F24F11/38Failure diagnosis

Definitions

  • the present disclosure relates to the technical field of air conditioning equipment, and in particular to an air conditioning system.
  • air conditioners have become an indispensable electrical appliance in daily life.
  • a multi-split air conditioning system is a system used to provide heating and cooling for a building or room, usually including an outdoor unit and multiple indoor units. Each indoor unit can control the temperature independently, so multiple indoor units can be installed in different rooms or areas to meet the needs of different rooms.
  • a multi-split air conditioning system comprising an outdoor unit, at least one indoor unit, an expansion valve and a controller.
  • the outdoor unit comprises a compressor and an outdoor heat exchanger; the compressor is connected to the outdoor heat exchanger. Any one of the at least one indoor unit comprises an indoor heat exchanger.
  • the indoor heat exchanger is connected to the outdoor heat exchanger through the expansion valve. Refrigerant circulates in the compressor, the outdoor heat exchanger, the expansion valve and the indoor heat exchanger to form a refrigerant circuit.
  • the controller is configured to: in the case of determining that the multi-split air conditioning system fails, determine multiple fault identification results according to the characteristic data of the multi-split air conditioning system and multiple fault identification models based on support vector machines; any one of the multiple fault identification models is configured to identify a fault type, and the fault identification result output by any one of the fault identification models is configured to indicate the probability of the multi-split air conditioning system having the fault type corresponding to any one of the fault identification models; and the fault type corresponding to the fault identification result with the maximum probability among the multiple fault identification results is used as the target fault type of the multi-split air conditioning system.
  • a control method for a multi-split air-conditioning system includes an outdoor unit, at least one indoor unit and an expansion valve.
  • the outdoor unit includes a compressor and an outdoor heat exchanger. Any one of the at least one indoor unit includes an indoor heat exchanger. Refrigerant circulates in the compressor, the outdoor heat exchanger, the expansion valve and the indoor heat exchanger to form a refrigerant circuit.
  • the method includes: in the case of determining that the multi-split air-conditioning system fails, determining multiple fault identification results based on characteristic data of the multi-split air-conditioning system and multiple fault identification models based on support vector machines; any one of the multiple fault identification models is configured to identify a fault type, and the fault identification result output by any one of the fault identification models is configured to indicate the probability of the multi-split air-conditioning system having the fault type corresponding to any one of the fault identification models; and taking the fault type corresponding to the fault identification result with the maximum probability among the multiple fault identification results as the target fault type of the multi-split air-conditioning system.
  • a multi-split air-conditioning system comprising: an outdoor unit, at least one indoor unit, at least one expansion valve and a controller.
  • the at least one indoor unit is connected to the outdoor unit.
  • the at least one expansion valve corresponds to the at least one indoor unit. Any one of the at least one expansion valve is arranged on a pipeline between the corresponding indoor unit and the outdoor unit.
  • the controller is configured to: obtain real-time operation data of the multi-split air-conditioning system; perform fault identification on the real-time operation data through a preset graph attention model to obtain a fault identification result; the fault identification result includes whether any one of the expansion valves in the multi-split air-conditioning system is in a faulty operation state or a normal operation state; and when any one of the expansion valves is in a faulty operation state, perform fault location on any one of the expansion valves through the preset graph attention model to determine the indoor unit serial number of any one of the expansion valves.
  • a control method for a multi-split air-conditioning system includes an outdoor unit, at least one indoor unit and at least one expansion valve.
  • the at least one expansion valve corresponds to the at least one indoor unit. Any one of the at least one expansion valve is arranged on a pipeline between the corresponding indoor unit and the outdoor unit.
  • the method comprises: acquiring real-time operation data of the multi-split air-conditioning system; performing fault identification on the real-time operation data through a preset graph attention model to obtain a fault identification result; wherein the fault identification result comprises that any one of the expansion valves in the multi-split air-conditioning system is in a faulty operation state or a normal operation state; and when any one of the expansion valves is in a faulty operation state, performing fault location on any one of the expansion valves through the preset graph attention model to determine the indoor unit serial number of any one of the expansion valves.
  • FIG1A is a block diagram of a multi-split air conditioning system according to some embodiments.
  • FIG1B is a structural diagram of an indoor heat exchanger, a gas pipe, and a liquid pipe of a multi-split air conditioning system according to some embodiments;
  • FIG2A is another block diagram of a multi-split air conditioning system according to some embodiments.
  • FIG2B is a structural diagram of a multi-split air conditioning system according to some embodiments.
  • FIG2C is a structural diagram of an indoor heat exchanger, pipelines, and sensors of a multi-split air conditioning system according to some embodiments;
  • FIG3 is a structural diagram of a controller and a terminal device of a multi-split air conditioning system according to some embodiments
  • FIG4 is a block diagram of a controller according to some embodiments.
  • FIG5 is a flow chart of a control method of a multi-split air conditioning system according to some embodiments.
  • FIG6 is a flow chart of another method for controlling a multi-split air conditioning system according to some embodiments.
  • FIG7 is a schematic diagram showing the impact of a fault level on a multi-split air conditioning system according to some embodiments.
  • FIG8 is a schematic diagram of a fault level warning for a multi-split air conditioning system according to some embodiments.
  • FIG9 is a flow chart of another method for controlling a multi-split air conditioning system according to some embodiments.
  • FIG10 is a flow chart of another method for controlling a multi-split air conditioning system according to some embodiments.
  • FIG11 is a flow chart of another method for controlling a multi-split air conditioning system according to some embodiments.
  • FIG12 is a schematic diagram of a management interface of a terminal device according to some embodiments.
  • FIG13 is a schematic diagram of a management interface of another terminal device according to some embodiments.
  • FIG14 is a schematic diagram of a management interface of another terminal device according to some embodiments.
  • FIG15 is a flow chart of another control method of a multi-split air conditioning system according to some embodiments.
  • FIG16 is a flow chart of a method for training a graph attention model of a multi-split air conditioning system according to some embodiments
  • FIG17 is a flow chart of another method for training a graph attention model for a multi-split air conditioning system according to some embodiments.
  • FIG. 18 is a flow chart of yet another control method for a multi-split air conditioning system according to some embodiments.
  • first and second are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features.
  • a feature defined as “first” or “second” may explicitly or implicitly include one or more of the features.
  • plural means two or more.
  • connection and its derivative expressions may be used.
  • connection should be understood in a broad sense.
  • connection can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection or an indirect connection through an intermediate medium.
  • At least one of A, B, and C has the same meaning as “at least one of A, B, or C” and both include the following combinations of A, B, and C: A only, B only, C only, the combination of A and B, the combination of A and C, the combination of B and C, and the combination of A, B, and C.
  • the term “if” is optionally interpreted to mean “when” or “upon” or “in response to determining” or “in response to detecting,” depending on the context.
  • the phrases “if it is determined that” or “if [a stated condition or event] is detected” are optionally interpreted to mean “upon determining that” or “in response to determining that” or “upon detecting [a stated condition or event]” or “in response to detecting [a stated condition or event],” depending on the context.
  • air conditioners are increasingly widely used in entertainment, home and work.
  • a multi-split air conditioning system consisting of one outdoor unit and multiple indoor units is often used to control the room temperature in multiple areas in order to save electricity.
  • multi-split air conditioning systems will inevitably have various faults.
  • the specific problems manifested by multiple failures may be similar, making it impossible to accurately identify which component in the multi-split air conditioning system has failed.
  • FIG1A is a block diagram of a multi-split air conditioning system according to some embodiments.
  • the multi-split air conditioning system 10 includes a throttling device 11 , a plurality of indoor units 12 and an outdoor unit 13 .
  • a plurality of indoor units 12 are connected to an outdoor unit 13 through a pipeline, and a refrigerant can circulate in the pipeline.
  • the indoor unit 12 is an indoor hanging unit or an indoor cabinet unit, and is configured to exchange heat with indoor air.
  • the throttling device 11 is arranged on the pipeline between the plurality of indoor units 12 and the outdoor unit 13, and is configured to adjust the flow rate of the fluid in the pipeline between the plurality of indoor units 12 and the outdoor unit 13, and to adjust the refrigerant flow rate.
  • the outdoor unit 13 is configured to exchange heat with outdoor air.
  • FIG1B is a structural diagram of an indoor heat exchanger, an air pipe, and a liquid pipe of a multi-split air conditioning system according to some embodiments.
  • the pipeline connecting the outdoor unit 13 and the plurality of indoor units 12 includes a gas pipe 15 and a liquid pipe 16.
  • the gas pipe 15 is configured to transmit a gaseous refrigerant
  • the liquid pipe 16 is configured to transmit a liquid refrigerant.
  • the throttling device 11 is also configured to adjust the flow rate of the fluid in the gas pipe 15 and the liquid pipe 16.
  • the throttling device 11 includes a plurality of expansion valves 111, and the plurality of expansion valves 111 correspond to the plurality of indoor units 12 and are respectively connected to the plurality of indoor units 12.
  • the expansion valve 111 is arranged on a pipeline between the corresponding indoor unit 12 and the outdoor unit 13.
  • the expansion valve 111 is arranged on the liquid pipe 16 between the corresponding indoor unit 12 (such as the indoor heat exchanger 121) and the outdoor unit 13.
  • the expansion valve 111 is configured to expand and reduce the pressure of the refrigerant flowing through the expansion valve 111 to adjust the supply of the refrigerant in the pipeline. For example, when the opening of the expansion valve 111 decreases, the flow resistance of the refrigerant flowing through the expansion valve 111 will increase, and when the opening of the expansion valve 111 increases, the flow resistance of the refrigerant flowing through the expansion valve 111 will decrease. In this way, when the states of other components in the refrigerant circuit remain unchanged, the flow rate of the refrigerant flowing to the indoor unit 12 can be adjusted by controlling the change in the opening of the expansion valve 111.
  • the expansion valve 111 may be an electronic expansion valve.
  • the indoor unit 12 includes an indoor heat exchanger 121.
  • the indoor heat exchanger 121 includes a first port and a second port.
  • the first port is configured to be connected to the corresponding expansion valve 111 through the liquid pipe 16 so that the liquid refrigerant can flow between the indoor heat exchanger 121 and the corresponding expansion valve 111.
  • the second port is configured to be connected to the outdoor unit 13 through the gas pipe 15 so that the gaseous refrigerant can flow between the indoor heat exchanger 121 and the outdoor unit 13.
  • the indoor heat exchanger 121 includes a heat transfer pipe connected between the first port and the second port and configured to allow the refrigerant flowing in the heat transfer pipe to exchange heat with the indoor air.
  • the outdoor unit 13 includes a compressor 131 and a liquid accumulator 133.
  • the compressor 131 is disposed between the throttling device 11 and the liquid accumulator 133, and is configured to compress the low-temperature and low-pressure gaseous refrigerant into a high-temperature and high-pressure gaseous refrigerant, and to direct the gaseous refrigerant to the condenser (i.e., the indoor heat exchanger or the outdoor heat exchanger).
  • the compressor 131 may be a variable capacity inverter compressor that performs inverter-based speed control.
  • the second port of the indoor heat exchanger 121 is connected to the outdoor unit 13 through the gas pipe 15 so that the gaseous refrigerant flows between the indoor heat exchanger 121 and the discharge port of the compressor 131 .
  • the outdoor unit 13 further includes an outdoor heat exchanger 132 and a four-way valve 134 .
  • the outdoor heat exchanger 132 includes a third port and a fourth port.
  • the third port is configured to allow the refrigerant to flow between the outdoor heat exchanger 132 and the suction port of the compressor 131 via the accumulator 133
  • the fourth port is configured to allow the refrigerant to flow between the outdoor heat exchanger 132 and the throttling device 11.
  • the outdoor heat exchanger 132 further includes a heat transfer pipe connected between the third port and the fourth port and configured to perform heat exchange between the refrigerant and the outdoor air flowing in the heat transfer pipe.
  • one end of the liquid accumulator 133 is connected to the compressor 131, and the other end is connected to the outdoor heat exchanger 132 through the four-way valve 134.
  • the liquid accumulator 133 is configured to separate the gas-liquid two-phase refrigerant from the outdoor heat exchanger 132 (e.g., the refrigerant flowing from the outdoor heat exchanger 132 to the compressor 131 via the four-way valve 134) into gaseous refrigerant and liquid refrigerant, and to supply the gas-liquid two-phase refrigerant to the suction port of the compressor 131. Gaseous refrigerant.
  • the four ports of the four-way valve 134 are respectively connected to the compressor 131, the outdoor heat exchanger 132, the liquid storage tank 133 and the plurality of expansion valves 111.
  • the four-way valve 134 is configured to be in a switching state to change the flow direction of the refrigerant in the refrigerant circuit, thereby realizing the switching between the cooling mode and the heating mode of the multi-split air conditioning system 10.
  • the outdoor unit 13 further includes an outdoor fan 135.
  • the outdoor fan 135 is disposed near the outdoor heat exchanger 132, and the outdoor fan 135 is configured to deliver an airflow of outdoor air to the outdoor heat exchanger 132 to promote heat exchange between the refrigerant flowing in the heat transfer pipe between the third port and the fourth port and the outdoor air.
  • the indoor unit 12 further includes a display 122 , and the display 122 is configured to display the indoor temperature or the current operation mode of the indoor unit 12 .
  • the indoor unit 12 further includes an indoor fan 123.
  • the indoor fan 123 is disposed near the indoor heat exchanger 121 and is configured to deliver an airflow of indoor air to the indoor heat exchanger 121 to promote heat exchange between the refrigerant flowing in the heat transfer pipe between the first port and the second port and the outdoor air.
  • the indoor unit 12 further includes an indoor fan motor, and the indoor fan motor is configured to drive the indoor fan 123 to rotate and adjust the rotation speed of the indoor fan 123.
  • the refrigerant circulates in the refrigerant circuit of the multi-split air conditioning system to enable the multi-split air conditioning system to achieve cooling or heating mode.
  • the refrigerant circuit includes a compressor 131, a condenser, an expansion valve 111 and an evaporator connected in sequence.
  • the process of the refrigerant circulating in the refrigerant circuit includes: the compressor 131 sucks the low-temperature and low-pressure gaseous refrigerant after evaporation by the evaporator into the compressor chamber, compresses it into a high-temperature and high-pressure gaseous refrigerant, and transports it to the condenser.
  • the high-temperature and high-pressure gaseous refrigerant is condensed into a high-temperature and high-pressure liquid refrigerant in the condenser, and then, after passing through the throttling device 11 (such as the expansion valve 111), it becomes a low-temperature and low-pressure liquid refrigerant.
  • the low-temperature and low-pressure liquid refrigerant enters the evaporator, is evaporated, and then returns to the compressor 131 to enter the next round of heating cycle.
  • the outdoor heat exchanger 132 is used as an evaporator, and the indoor heat exchanger 121 is used as a condenser.
  • the outdoor heat exchanger 132 is used as a condenser, and the indoor heat exchanger 121 is used as an evaporator.
  • 2C is a structural diagram of an indoor heat exchanger, pipes, and sensors of a multi-split air conditioning system according to some embodiments.
  • the multi-split air conditioning system 10 further includes a plurality of first temperature sensors 101 and a controller 50.
  • the plurality of first temperature sensors 101 are in communication connection with the controller 50.
  • Multiple first temperature sensors 101 correspond to multiple indoor units 12. Any one of the multiple first temperature sensors 101 is arranged on the air pipe 15 between the corresponding indoor unit 12 and the outdoor unit 13, and is configured to detect the temperature value of the air pipe 15 and send the detected temperature value of the air pipe 15 to the controller 50.
  • the plurality of first temperature sensors 101 may detect the temperatures of the plurality of air pipes 15 between the plurality of indoor units 12 and the outdoor units 13 , and transmit the temperature values of the plurality of air pipes 15 to the controller 50 .
  • the controller 50 is configured to control the operation of the compressor 131 and the expansion valve 111 so that the multi-split air conditioning system 10 can operate to realize the various predetermined functions of the multi-split air conditioning system. In some embodiments, the controller 50 is also configured to obtain the operating frequency of the compressor 131 at each moment and the operating current value at each moment.
  • the multi-split air conditioning system 10 further includes a plurality of second temperature sensors 102 .
  • the plurality of second temperature sensors 102 are communicatively connected to the controller 50 .
  • Multiple second temperature sensors 102 correspond to multiple indoor units 12. Any one of the multiple second temperature sensors 102 is arranged on the liquid pipe 16 between the corresponding indoor unit 12 and the outdoor unit 13, and is configured to detect the temperature value of the liquid pipe and send the detected temperature value of the liquid pipe to the controller 50.
  • the multi-split air conditioning system 10 further includes a plurality of third temperature sensors 103, and the plurality of third temperature sensors 103 are all communicatively connected to the controller 50.
  • Any third temperature sensor among the plurality of third temperature sensors 103 is disposed at the air outlet of the indoor unit, and is configured to detect the air outlet temperature of the indoor unit and send the detected air outlet temperature to the controller 50.
  • a plurality of third temperature sensors 103 correspond to a plurality of indoor units 12 , and any third temperature sensor is configured to detect the outlet air temperature of the corresponding indoor unit 12 and send the detected air temperature to the controller 50 .
  • the multi-split air conditioning system 10 further includes a plurality of fourth temperature sensors 104, and the plurality of fourth temperature sensors 104 are all communicatively connected to the controller 50.
  • Any fourth temperature sensor 104 of the plurality of fourth temperature sensors 104 is disposed at the air inlet (i.e., the return air inlet) of the indoor unit, and is configured to detect the air inlet temperature (i.e., the return air temperature) of the indoor unit, and send the result to the controller 50.
  • a plurality of fourth temperature sensors 104 correspond to a plurality of indoor units 12 , and any fourth temperature sensor 104 is configured to detect the inlet air temperature of the corresponding indoor unit 12 and send the detected air temperature to the controller 50 .
  • the multi-split air conditioning system 10 further includes a fifth temperature sensor 105, which is communicatively connected to the controller 50.
  • the fifth temperature sensor 105 is disposed at the air intake port of the compressor, and is configured to detect the air intake temperature value of the compressor, and send the detected air intake temperature value to the controller 50.
  • the multi-split air conditioning system 10 further includes a sixth temperature sensor 106, which is communicatively connected to the controller 50.
  • the sixth temperature sensor 106 is disposed at the exhaust port of the compressor, and is configured to detect the exhaust temperature value of the compressor, and send the detected exhaust temperature value to the controller 50.
  • the multi-split air conditioning system 10 further includes a first pressure sensor 107.
  • the first pressure sensor 107 is communicatively connected to the controller 50.
  • the first pressure sensor 107 is disposed at the exhaust port of the compressor and is configured to detect the exhaust pressure value of the compressor and send the detected exhaust pressure value to the controller 50.
  • the multi-split air conditioning system 10 further includes a second pressure sensor 108, which is communicatively connected to the controller 50.
  • the second pressure sensor 108 is disposed at the suction port of the compressor, and is configured to detect the suction pressure value of the compressor, and send the detected suction pressure value to the controller 50.
  • controller 50 in some embodiments of the present disclosure refers to a device that can generate an operation control signal according to an instruction operation code and a timing signal to instruct the multi-split air-conditioning system 10 to execute a control instruction.
  • the controller 50 includes at least one of a central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller or a programmable logic device (PLD).
  • CPU central processing unit
  • NP network processor
  • DSP digital signal processor
  • PLD programmable logic device
  • the controller may also be other devices with processing functions, such as circuits, devices, or software modules, etc., which is not limited in the present disclosure.
  • the multi-split air conditioning system 10 further includes a remote controller, which is configured to communicate with the controller 50 via infrared or other communication methods. In this way, the user can control the multi-split air conditioning system (such as controlling the multi-split air conditioning system 10 to execute a heating mode, etc.) through the remote controller, thereby realizing the interaction between the user and the multi-split air conditioning system 10.
  • a remote controller which is configured to communicate with the controller 50 via infrared or other communication methods. In this way, the user can control the multi-split air conditioning system (such as controlling the multi-split air conditioning system 10 to execute a heating mode, etc.) through the remote controller, thereby realizing the interaction between the user and the multi-split air conditioning system 10.
  • the controller 50 includes a communicator configured to establish a communication connection with other network entities (such as a remote controller or a terminal device, etc.).
  • the communicator includes a radio-frequency (RF) device, and the RF device is configured to receive and send signals.
  • the RF device can send received information to the controller 50 for processing, or send out a signal generated by the controller.
  • the RF device may include an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (Low noise amplifier, LNA), a duplexer, etc.
  • LNA low noise amplifier
  • controller 50 can receive control instructions issued by the user's terminal device through the communicator, and control the multi-split air-conditioning system 10 to perform corresponding processing according to the control instructions, thereby realizing the interaction between the user and the multi-split air-conditioning system 10.
  • FIG. 3 is a structural diagram of a controller and terminal devices of a multi-split air conditioning system according to some embodiments.
  • the terminal device 300 can establish a communication connection with the controller 50.
  • a variety of network communication protocols can be used to establish a communication connection between the terminal device 300 and the controller 50.
  • multiple network communication protocols can include Ethernet, Universal serial bus (USB), FIREWIRE, cellular network communication protocols (such as 3G/4G/5G), Bluetooth, Wireless fidelity (Wi-Fi), NFC, etc.
  • USB Universal serial bus
  • FIREWIRE FireWire
  • cellular network communication protocols such as 3G/4G/5G
  • Bluetooth Wireless fidelity
  • Wi-Fi Wireless fidelity
  • NFC NFC
  • terminal device 300 shown in FIG3 is only an example of a terminal device.
  • the terminal device 300 in the present disclosure may be a remote controller, a mobile phone, a tablet computer, etc.
  • FIG. 4 is a block diagram of a controller according to some embodiments.
  • the controller 50 includes an outdoor control device 501 and an indoor control device 502.
  • the outdoor control device 501 includes a first memory 5011
  • the indoor control device 502 includes a second memory 5021.
  • the indoor control device 502 is connected to the outdoor control device 501 by wired or wireless communication.
  • the outdoor control device 501 can be installed in the outdoor unit 13 or can be independent of the outdoor unit 13.
  • the outdoor control device 501 is configured to control the outdoor unit 13 to perform related operations.
  • the indoor control device 502 can be installed in the indoor unit 12 or can be independent of the indoor unit 12.
  • the indoor control device 502 is configured to control the components of the indoor unit 12 and the throttling device 11 to perform related operations.
  • the above division of devices is only a functional division, for example, the outdoor control device 501 and the indoor control device 502 may also be integrated into one device.
  • the first memory 5011 and the second memory 5021 may also be integrated into one memory.
  • the first memory 5011 is configured to store applications and data related to the outdoor unit 13.
  • the outdoor control device 501 executes various functions and data processing of the multi-split air conditioning system by running the applications and data stored in the first memory 5011.
  • the first memory 5011 includes a program storage area and a data storage area.
  • the program storage area can store an operating system and an application required for at least one function (such as an outdoor fan start function, an outdoor temperature measurement function, etc.).
  • the data storage area can store data created based on the use of a multi-split air conditioning system (such as outdoor temperature, the opening of each expansion valve, etc.).
  • the first memory 5011 also includes a high-speed random access memory, or a non-volatile memory, such as a disk storage device, a flash memory device, or other volatile solid-state storage devices.
  • the second memory 5021 is configured to store applications and data related to multiple indoor units 12 and multiple expansion valves 111.
  • the indoor control device 502 executes various functions and data processing of the multi-split air-conditioning system by running the applications and data stored in the memory 5021.
  • the second memory 5021 includes a program storage area and a data storage area.
  • the program storage area can store an operating system and an application required for at least one function (such as an indoor temperature measurement function).
  • the data storage area can store data created by using the multi-split air conditioning system (such as indoor temperature, etc.).
  • the second memory 5021 is further configured to store a correspondence between an address of the indoor unit 12 and an address of the expansion valve 111 .
  • the outdoor control device 501 is communicatively connected to the outdoor unit 13 and is configured to control the outdoor unit 13 to perform related operations according to user instructions or system default instructions.
  • the outdoor control device 501 can control the speed of the outdoor fan according to the air conditioning operation mode selected by the user.
  • the outdoor control device 501 can also obtain the outdoor temperature according to the user instruction or the system instruction, and store the obtained outdoor temperature in the first memory 5011.
  • the outdoor control device 501 can also control the rotation of the four-way valve 134 in the outdoor unit 13 according to the air conditioning operation mode selected by the user to achieve the selection of the cooling or heating mode.
  • the outdoor control device 501 can also control the operation mode, compressor frequency, etc. of the outdoor unit 13 during the address correction process.
  • the indoor control device 502 is connected to the indoor unit 12 and is configured to control the indoor unit 12 to perform related operations according to user instructions or system default instructions.
  • the indoor control device 502 can also control the indoor unit to turn on the indoor temperature sensor to detect the indoor temperature according to the user instructions.
  • the indoor control device 502 is in communication with the plurality of expansion valves 111 and is configured to control the plurality of expansion valves 111 to perform related operations according to user instructions or system default instructions.
  • the indoor control device 502 can control the opening of each expansion valve 111 according to user instructions or system instructions.
  • the hardware structure of the multi-split air conditioning system shown in Figure 2A does not constitute a limitation on the multi-split air conditioning system.
  • the multi-split air conditioning system may include more or fewer components than shown, or combine certain components, or arrange components differently.
  • Some embodiments of the present disclosure also provide a control method for a multi-split air conditioning system, which can input characteristic data of the multi-split air conditioning system into multiple fault identification models to obtain multiple identification results, and can exclude irrelevant data in the operating data, thereby helping to improve the accuracy of fault identification in the multi-split air conditioning system.
  • the control method for the multi-split air conditioning system will be described in detail below in conjunction with the accompanying drawings.
  • control method of the multi-split air conditioning system is executed by a controller.
  • the controller may be the controller 50 described in any of the above embodiments, or may be other controllers, which are not limited in the present disclosure.
  • FIG5 is a flow chart of a method for controlling a multi-split air conditioning system according to some embodiments.
  • control method of the multi-split air conditioning system includes step S101 and step S102 .
  • step S101 when it is determined that a multi-split air-conditioning system fails, multiple fault identification results are determined according to feature data of the multi-split air-conditioning system and multiple fault identification models based on support vector machines.
  • the memory of the multi-split air conditioning system pre-stores multiple trained fault identification models based on support vector machines.
  • the controller 50 can input the characteristic data of the multi-split air conditioning system into multiple fault identification models based on support vector machines.
  • the characteristic data of the multi-split air-conditioning system is obtained after correlation analysis of the operating data of the multi-split air-conditioning system.
  • the characteristic data is the data related to the fault that is retained after removing data unrelated to the fault from the operating data of the multi-split air-conditioning system.
  • the characteristic data of the multi-split air-conditioning system is input into multiple fault identification models, one fault identification model corresponds to one fault type, and the fault identification result output by one fault identification model is configured to indicate the probability of the multi-split air-conditioning system having the fault type corresponding to the fault identification model.
  • a fault identification model is configured to identify a fault type.
  • a fault identification model performs fault identification on a multi-split air-conditioning system, it only identifies the probability of the multi-split air-conditioning system having the fault type corresponding to the fault identification model, and will not be affected by other fault types during fault identification.
  • multiple fault identification results are determined, that is, the probability of the multi-split air-conditioning system having the fault type corresponding to each fault identification model is obtained.
  • the failure types of multi-split air conditioning systems include: abnormal refrigerant charge, dirty and blocked outdoor heat exchanger, dirty and blocked indoor heat exchanger, compressor wear and expansion valve failure.
  • the characteristic data of the multi-split air-conditioning system includes at least one of the operating frequency of the compressor, the exhaust pressure value of the compressor, the suction pressure value of the compressor, the suction temperature value of the compressor, the exhaust temperature value of the compressor, the exhaust superheat of the compressor, the suction superheat of the compressor, the opening of the outdoor fan gear expansion valve, the outlet air temperature of each indoor unit, the return air temperature of each indoor unit, the temperature value of the air pipe 15 and the temperature value of the liquid pipe 16.
  • the support vector machine is a binary classification model, and the basic model of the support vector machine is a linear classifier with the largest interval defined in the feature space.
  • the support vector machine also includes the kernel technique, which makes the support vector machine a substantially nonlinear classifier.
  • the support vector machine is based on the VC dimension theory (Vapnik-Chervonenkis Dimension) of statistical learning theory and the principle of structural risk minimization. Based on limited sample information, it seeks the best compromise between the complexity of the model (i.e., the learning accuracy of a specific training sample) and the learning ability (i.e., the ability to identify any sample without error) in order to obtain better generalization ability.
  • the controller 50 can train multiple fault identification models based on support vector machines based on the historical operation data of the multi-split air conditioning system, and store the multiple fault identification models that have been trained in a memory, so that when executing the fault identification function, the controller 50 can timely identify the type of fault that has occurred in the multi-split air conditioning system according to the trained fault identification model.
  • the historical operation data of the multi-split air conditioning system includes normal operation data of the multi-split air conditioning system during normal operation and abnormal operation data during abnormal operation (also referred to as historical fault data).
  • the training process of the fault identification model includes: establishing a data regression line, a regression plane and a hyperplane for fitting, and adjusting the accuracy and range of the fitting through a loss function, setting a deviation value and a relaxation variable.
  • the controller 50 is further configured to perform model testing after the fault identification model training is completed.
  • the test results of the fault identification model can be visualized through the confusion matrix and the diagnostic timing diagram to perform diagnostic results, and three model evaluation indicators are introduced: Geometric mean accuracy (GMA), false alarm rate (FAR) and miss alarm rate (MAR) for evaluation.
  • GMA Geometric mean accuracy
  • FAR false alarm rate
  • MAR miss alarm rate
  • GMA indicator represents the geometric mean of the accuracy of each classification category, and after obtaining the real result, a judgment is made. If the accuracy does not meet the requirements, the parameter update and tuning device will be started for self-optimization.
  • step S102 the fault type corresponding to the fault identification result with the highest probability among the multiple fault identification results is used as the target fault type of the multi-split air conditioning system.
  • one fault identification model corresponds to one fault type.
  • the greater the fault probability indicated by a fault identification result the higher the probability of the multi-split air-conditioning system having the fault type corresponding to the fault identification result. Therefore, the fault type corresponding to the fault identification result with the highest probability among multiple fault identification results can be used as the target fault type of the multi-split air-conditioning system.
  • the fault identification model includes A1, B1 and C1, A1 corresponds to fault type A, B1 corresponds to fault type B, and C1 corresponds to fault type C.
  • A1 corresponds to fault type A
  • B1 corresponds to fault type B
  • C1 corresponds to fault type C.
  • fault identification result output by A1 indicates that the probability of the multi-split air-conditioning system having fault type A is 50%
  • the fault identification result output by B1 indicates that the probability of the multi-split air-conditioning system having fault type B is 80%
  • the fault identification result output by C1 indicates that the probability of the multi-split air-conditioning system having fault type C is 30%
  • fault type B can be used as the target fault type of the multi-split air-conditioning system.
  • control method of the multi-split air conditioning system after determining that the multi-split air conditioning system has a fault, inputs the characteristic data of the multi-split air conditioning system into multiple fault identification models respectively, thereby obtaining multiple identification results. Since the characteristic data of the multi-split air conditioning system is obtained after correlation analysis based on the operating data of the multi-split air conditioning system, multiple identification results are obtained. The identification result excludes the influence of irrelevant data in the operating data on the accuracy of fault identification.
  • the fault type corresponding to the fault identification result with the highest probability among multiple fault identification results is used as the target fault type of the multi-split air-conditioning system, which is conducive to improving the accuracy of fault identification in the multi-split air-conditioning system.
  • FIG. 6 is a flow chart of another method for controlling a multi-split air conditioning system according to some embodiments.
  • the method further includes steps S201 to S202 .
  • step S201 a fault level identification result is determined according to the characteristic data of the multi-split air conditioning system and a fault level identification model corresponding to the target fault type.
  • a plurality of fault level identification models are pre-stored in the memory of the multi-split air conditioning system, and a fault level identification model is configured to identify the fault level of a fault type.
  • the characteristic data of the multi-split air-conditioning system can be input into the fault level identification model corresponding to the target fault type to obtain the fault level identification result.
  • the fault level identification result represents the degree of influence of the target fault type on the multi-split air-conditioning system.
  • the fault level identification model may be a fault level identification model based on a machine learning algorithm.
  • the fault level identification results include: fault level 1, fault level 2, fault level 3, fault level 4 and fault level 5. If the fault level identification result is fault level 1 or fault level 2, it means that the user needs to pay attention and it is recommended that the user pay attention to the inspection. If the fault level identification result is fault level 3, it means that the user needs to pay attention and it is recommended to repair it in the near future. If the fault level identification result is fault level 4, it means that the user needs to pay enough attention and it is recommended to repair it in time. If the fault level identification result is fault level 5, it means that the user needs to pay great attention and it is recommended to repair it immediately.
  • step S202 when the fault level indicated by the fault level identification result is above a preset fault level, an alarm message is issued.
  • the alarm information includes a target fault type so that maintenance personnel can conduct targeted maintenance on the multi-split air-conditioning system based on the target fault type, which helps to improve the fault repair efficiency of the multi-split air-conditioning system.
  • the preset fault level may be preset when the multi-split air conditioning system leaves the factory.
  • FIG. 7 is a schematic diagram showing the impact of a fault level on a multi-split air conditioning system according to some embodiments.
  • the multi-split air conditioning system is at fault level 5 or below, it means that the fault in the multi-split air conditioning system is minor, and the impact on the multi-split air conditioning system is small when the fault level is below 5. If the multi-split air conditioning system is at fault level above 5, it means that the fault in the multi-split air conditioning system is serious, that is, the impact on the multi-split air conditioning system is large when the fault level is above 5.
  • FIG8 is a schematic diagram of a fault level warning for a multi-split air conditioning system according to some embodiments.
  • the preset fault level can be fault level 2. That is, when it is determined that the fault level of the multi-split air conditioning system is above fault level 2, the controller sends out an alarm message to remind maintenance personnel to perform maintenance to prevent a minor fault in the multi-split air conditioning system from developing into a serious fault. For example, the fault level of the multi-split air conditioning system is prevented from developing from fault level 2 to fault level 5.
  • the controller 50 may issue warning information in a variety of ways, such as way 1, way 2, and way 3.
  • Method 1 includes: the controller controls the display of the indoor unit to display the alarm information.
  • the content of the alarm information may be "The outdoor heat exchanger is seriously dirty and blocked, and it is recommended to inspect it immediately!”.
  • the controller in order to facilitate users to promptly learn that a serious fault has occurred in the multi-split air-conditioning system, the controller can control the display of each indoor unit in the multi-split air-conditioning system to display the above-mentioned alarm information.
  • Method 2 includes: the controller sends an alarm message to the terminal device through the communicator.
  • the target fault type of the multi-split air-conditioning system is that the outdoor heat exchanger is dirty and blocked
  • the content of the alarm information received by the terminal device from the controller 50 via the Wi-Fi network or Bluetooth may be "The outdoor heat exchanger is seriously dirty and blocked, and immediate maintenance is recommended!”.
  • Method 3 includes: the controller sends an alarm message to the terminal device through a voice prompt device.
  • the indoor unit further includes a voice device, and the voice prompt device may be a speaker, etc.
  • the controller may control the voice device to broadcast an alarm message to attract the user's attention and remind the user to perform maintenance.
  • FIG. 9 is a flow chart of yet another method for controlling a multi-split air conditioning system according to some embodiments.
  • the method further includes steps S301 to S303 .
  • step S301 before determining that a failure occurs in the multi-split air-conditioning system, operation data of the multi-split air-conditioning system is obtained.
  • the fault type can be further identified only after it is determined that the multi-split air conditioning system has failed. Therefore, before determining that the multi-split air conditioning system has failed, the operating data of the multi-split air conditioning system can be obtained to determine whether the multi-split air conditioning system has failed.
  • Fig. 10 is a flow chart of another control method of a multi-split air conditioning system according to some embodiments.
  • step S301 includes steps S3011 to S3012.
  • step S3011 original operation data of the multi-split air conditioning system is obtained.
  • the controller can obtain original operation data generated by various components of the multi-split air-conditioning system during operation.
  • step S3012 the original operation data of the multi-split air-conditioning system is preprocessed to obtain the operation data of the multi-split air-conditioning system.
  • the preprocessing includes outlier removal and smoothing.
  • the abnormal value elimination process includes: in the process of the controller acquiring the original operation data, eliminating abnormal operation data with a higher degree of discreteness compared with other operation data.
  • the original operation data of the multi-split air-conditioning system is not subjected to outlier elimination, the abnormal operation data may affect the accuracy of the fault diagnosis results during the subsequent fault diagnosis. Therefore, after obtaining the original operation data of the multi-split air-conditioning system, the original operation data of the multi-split air-conditioning system can be subjected to outlier elimination processing, thereby improving the accuracy of fault diagnosis.
  • the smoothing process includes: after removing outliers from the original operating data of the multi-split air conditioning system, using a smoothing algorithm to perform least square curve fitting on the original operating data after the outliers have been removed, and replacing the removed data with the fitted data.
  • Least square fitting is a mathematical approximation and optimization method that obtains a straight line or curve in a coordinate system based on known data, so that the sum of the squares of the distances between the fitting points and the known data is minimized.
  • the smoothing algorithm includes the Savitzky-Golay algorithm.
  • data smoothing processing of the original operating data of the multi-split air-conditioning system may also include: inputting the original operating data after outlier elimination processing into the generative network adversarial model to obtain the operating data of the multi-split air-conditioning system.
  • the generative adversarial network model is a deep learning model, which includes a generative model and a discriminative model through a framework.
  • the generative model is configured to generate fitting data
  • the discriminative model is configured to judge the fitting data.
  • the discriminative model can determine whether the data is smooth.
  • the generative model and the discriminative model compete with each other to obtain smoothed data.
  • the operating data of the multi-split air-conditioning system may include: the compressor current value of the outdoor unit in the multi-split air-conditioning system during operation, the operating frequency of the compressor, the exhaust pressure value of the compressor, the suction pressure value of the compressor, the suction temperature value of the compressor, the exhaust temperature value of the compressor, the exhaust superheat of the compressor, the suction superheat of the compressor, the gear of the outdoor fan, the opening of the expansion valve, the outlet air temperature of each indoor unit, the return air temperature of each indoor unit, the temperature value of the air pipe, the temperature value of the liquid pipe, and at least one of the discharge pressure value and the discharge temperature value at the refrigerant discharge pipe of the outdoor unit.
  • the operating data of the multi-split air-conditioning system shown above is merely exemplary, and the operating data of the multi-split air-conditioning system may also include other data, which will not be described in detail here.
  • step S302 a correlation analysis is performed on the operation data of the multi-split air-conditioning system based on the maximum information coefficient method, and characteristic data of the multi-split air-conditioning system is extracted from the operation data of the multi-split air-conditioning system.
  • the operation data of the multi-split air-conditioning system can be analyzed for correlation based on the maximum information coefficient method, and the characteristic data of the multi-split air-conditioning system can be extracted from the operation data of the multi-split air-conditioning system.
  • the maximum information coefficient method is a feature selection algorithm used to measure the degree of association between two variables. This method can measure the correlation between various fault types and the operating data of the multi-split air-conditioning system, and analyze and screen the operating data according to the correlation between the operating data and the fault types.
  • Operation data with a lower correlation with the fault type means that the correlation between the operation data and the fault type is relatively small. Therefore, the operation data can be used as redundant data.
  • operation data with a higher correlation with the fault means that the correlation between the operation data and the fault type is relatively large. Therefore, the operation data can be used as characteristic data.
  • the importance of different operating data for different fault types can also be calculated based on the Gini variable importance and the association rule algorithm, and the operating data can be sorted according to the importance.
  • the characteristic data of the multi-split air conditioning system is extracted from the operating data of the multi-split air conditioning system by performing correlation analysis on the operating data of the multi-split air conditioning system, and the characteristic data of the multi-split air conditioning system can reflect the operating conditions of the multi-split air conditioning system.
  • the characteristic data of the multi-split air conditioning system will also fluctuate.
  • the process of evaporation and heat absorption begins.
  • the expansion valve connected to the indoor unit is normal (i.e., there is no fault)
  • the temperature value of the gas pipe connected to the indoor unit and the temperature value of the liquid pipe should be equal, that is, the temperature difference between the temperature value of the liquid pipe and the temperature value of the gas pipe is approximately 0.
  • the expansion valve fails, for example, if the expansion valve is opened too small due to the failure of the expansion valve, the refrigerant flow rate will be insufficient, resulting in excessive superheat of the refrigerant during the process of evaporation and heat absorption, which in turn causes the temperature difference between the temperature value of the liquid pipe connected to the indoor unit and the temperature value of the gas pipe to increase. Therefore, whether the expansion valve is faulty can be determined based on characteristic data (such as the temperature value of the gas pipe and the temperature value of the liquid pipe).
  • FIG. 11 is a flow chart of yet another method for controlling a multi-split air conditioning system according to some embodiments.
  • step S3031 a fault diagnosis result is determined based on the characteristic data and the fault diagnosis model of the multi-split air conditioning system.
  • a trained fault diagnosis model is pre-stored in the memory of the multi-split air-conditioning system.
  • characteristic data of the multi-split air-conditioning system can be input into the trained fault diagnosis model to obtain a fault diagnosis result, which indicates whether a fault occurs in the multi-split air-conditioning system.
  • the fault diagnosis model may be a fault diagnosis model based on a support vector machine.
  • the fault diagnosis model training process includes: setting up a gradient multi-split air-conditioning system simulation experiment for each fault type, collecting experimental data for each fault type and classifying the experimental data according to normal and abnormal multi-split air-conditioning systems for training the fault diagnosis model.
  • step S3032 when the fault diagnosis result is yes, it is determined that a fault occurs in the multi-split air conditioning system.
  • the fault diagnosis result when the fault diagnosis result is no, it is determined that no fault occurs in the multi-split air conditioning system.
  • control method can perform correlation analysis on the operating data of the multi-split air-conditioning system based on the maximum information coefficient method, and extract feature data from the operating data of the multi-split air-conditioning system, so that fault diagnosis, fault identification and fault level identification can be performed based on the feature data with small data volume and strong representativeness, thereby improving the efficiency and accuracy of fault diagnosis, fault identification and fault level identification.
  • a control method for a multi-split air conditioning system provided by an embodiment of the present disclosure further includes a training process for a fault level identification model.
  • the training process for the fault level identification model includes steps A1 to A4.
  • step A1 data acquisition is performed.
  • the data collection includes: collecting data for fault level identification model training.
  • a gradient multi-split air-conditioning system simulation experiment is set up for each fault type, and the experimental data of each fault type is collected.
  • the experimental data is classified according to the fault level of the multi-split air-conditioning system for training the fault diagnosis model.
  • step A2 data preprocessing is performed.
  • the experimental data configured for fault level identification model training is collected, it is necessary to preprocess the collected experimental data to remove abnormal experimental data and perform data smoothing on the experimental data. It should be noted that the specific steps of data preprocessing have been described in detail above and will not be repeated here.
  • step A3 important feature data selection is performed.
  • the importance of different operating data for different fault types is calculated according to the Gini variable importance and the association rule algorithm, and the operating data is sorted according to the importance.
  • the experimental data is analyzed for correlation using the maximum information coefficient method to remove redundant data in the experimental data that is not related to the fault.
  • selecting important characteristic data further includes: decoupling faults.
  • Decoupling means turning a mathematical equation containing multiple variables into a set of equations that can be expressed by a single variable, that is, the variables no longer directly affect the result of an equation at the same time, thereby simplifying the analysis and calculation.
  • Decoupling faults means excluding the influence of other faults on a fault when analyzing the correlation between experimental data and the fault.
  • the selection of important characteristic data further includes: analyzing the existing experimental data in combination with the expert knowledge system. After the experimental data is sorted according to the importance and the correlation analysis is performed by the maximum information coefficient method, the important characteristic data can also be selected in combination with the expert knowledge system. According to the working principle of the multi-split air conditioning system, an expert knowledge system is constructed, and the experimental data after the importance sorting and the correlation analysis by the maximum information coefficient method are comprehensively analyzed to select the important characteristic data.
  • step A4 model training is performed.
  • a fault level identification model is trained based on a support vector machine model. After the training is completed, the fault level identification model is evaluated. If the accuracy of the fault level identification model does not meet the requirements, the parameter update and tuning model will be started for self-optimization.
  • FIG12 is a schematic diagram of a management interface of a terminal device according to some embodiments.
  • the terminal device 300 is further configured to display a management interface 301 of the multi-split air conditioning system, so that the user can set the operating mode of the multi-split air conditioning system through the terminal device 300 .
  • the management interface 301 includes a first button 302.
  • the terminal device 300 is configured to: when it is detected that the user clicks the first button 302 in the management interface 301, a drop-down selection box 303 pops up in the management interface 301.
  • the terminal device 300 is also configured to: when it is detected that the user selects an instruction in the drop-down selection box 303 and confirms the instruction, send the instruction confirmed by the user to the multi-split air conditioning system to complete the setting of the operation mode.
  • the user may select a cooling mode instruction in the drop-down selection box 303 .
  • FIG13 is a schematic diagram of a management interface of another terminal device according to some embodiments.
  • the management interface 301 further includes a second button 304.
  • the second button 304 is configured to switch between a closed state and an open state when clicked by a user.
  • the terminal device 300 is further configured to: when the second button is switched to the open state, transmit an instruction to turn on fault detection to the controller of the multi-split air conditioning system, so that the multi-split air conditioning system enters a fault detection mode. In this way, the user can turn on the fault detection function through the management interface of the terminal device 300, thereby facilitating improving the interaction efficiency between the user and the multi-split air conditioning system.
  • FIG14 is a schematic diagram of a management interface of another terminal device according to some embodiments.
  • the controller 50 is further configured to: after detecting an expansion valve failure in the multi-split air-conditioning system, send an instruction indicating that a failure exists in the multi-split air-conditioning system to the terminal device 300 through the communicator.
  • the management interface 301 is also configured to: after the terminal device 300 receives an instruction indicating that there is a fault in the multi-split air-conditioning system, a prompt message "An expansion valve fault is detected in the multi-split air-conditioning system. Do you want to locate the fault immediately?" is displayed to prompt the user to choose whether to turn on the fault location function. In this case, if the user chooses to click the "OK" button, it means that the user chooses to locate the fault immediately. In response to the user's confirmation instruction, the terminal device 300 sends the confirmation instruction (i.e., the fault location instruction) to the controller 50. The controller 50 is also configured to turn on the fault location mode after receiving the fault location instruction. If the user chooses to click the "Cancel" button, This means that the user chooses not to locate the fault for the time being.
  • the management interface 301 further includes a third button 305.
  • the third button 305 is configured to switch between a closed state and an open state when clicked by a user.
  • the terminal device 300 is further configured to send the fault location instruction to the controller 50 when the third button 305 switches to the open state.
  • FIG. 15 is a flow chart of yet another control method for a multi-split air conditioning system according to some embodiments.
  • Some embodiments of the present disclosure also provide another control method for a multi-split air conditioning system.
  • the other control method for a multi-split air conditioning system is executed by a controller.
  • the controller may be the controller 50 described in any of the above embodiments, or may be another controller.
  • the method includes steps S401 to S404 .
  • step S401 real-time operation data of the multi-split air conditioning system is obtained.
  • the controller is further configured to: after the multi-split air conditioning system is started, obtain the real-time operation data of the multi-split air conditioning system with a first preset time as a cycle. In this way, the controller can periodically perform fault detection on the multi-split air conditioning system, thereby facilitating improving the stability and reliability of the operation of the multi-split air conditioning system.
  • the first preset time length is data that has been preset in the memory of the multi-split air-conditioning system when it leaves the factory.
  • the value of the first preset time length can be set according to actual usage requirements, and the present disclosure does not limit this.
  • the real-time operation data of the multi-split air conditioning system includes the operation data of the outdoor unit and the operation data of each indoor unit.
  • the operation data of the outdoor unit includes: compressor frequency, pressure value, pressure top temperature value, exhaust gas superheat value, defrost temperature value and ambient temperature value.
  • the operation data of the indoor unit includes: variable frequency heat dissipation value, liquid pipe temperature value, gas pipe temperature value, return air temperature value and outlet air temperature value.
  • step S402 fault identification is performed on real-time operation data through a preset graph attention model to obtain a fault identification result.
  • the Graph Attention Networks is a graph neural network model that uses the self-attention mechanism.
  • the network uses a method similar to the self-attention in the neural network model to calculate the attention of any node in the graph relative to each adjacent node, and combines the characteristics of the node itself and the attention characteristics as the characteristics of the node, and performs tasks such as node classification on this basis.
  • the graph attention model includes a fault detection model.
  • the fault detection model is configured to detect whether any one of the plurality of expansion valves is in a faulty operating state.
  • the fault identification result includes whether any one of the expansion valves is in a faulty operating state or a normal operating state.
  • the controller obtains the real-time operating data of the multi-split air-conditioning system, by inputting the real-time operating data into the preset graph attention model, it can perform fault identification on multiple expansion valves and obtain fault identification results.
  • the preset graph attention model can be a fault detection model in the GAT model.
  • step S403 it is determined whether the fault identification result is a faulty operation state. If so, step S404 is executed; if not, step S401 is executed again.
  • step S404 it is necessary to continue to perform step S404 to locate the any one of the expansion valves. If the multiple expansion valves are all in a normal operating state, it is not necessary to perform fault location. In this case, the controller re-executes step S401.
  • step S403 includes: when the fault identification result is that the expansion valve in the multi-split air-conditioning system is in a normal operating state, re-execute step S401 after a second preset time period.
  • the second preset time length is data that has been preset in the memory of the multi-split air-conditioning system when it leaves the factory.
  • the value of the second preset time length can be set according to actual usage requirements, and the present disclosure does not limit this.
  • step S404 the expansion valve fault is located by using a preset graph attention model to determine the internal unit serial number of the expansion valve.
  • the graph attention model further includes a fault location model, which is configured to locate the internal unit serial number of the expansion valve that is in a faulty operating state.
  • each original node feature vector (which will be described in detail below) is input into the fault location model in the GAT model, so that the fault location model in the faulty operating state can be located.
  • the serial number of the indoor unit of the expansion valve is input into the GAT model, so that the fault location model in the faulty operating state can be located.
  • the preset graph attention model may be a fault localization model in the graph attention model.
  • another control method for a multi-split air-conditioning system inputs the acquired real-time operation data of the multi-split air-conditioning system into a preset graph attention model to obtain a fault identification result of the expansion valve in the multi-split air-conditioning system, thereby facilitating improving the efficiency of fault detection of the expansion valve.
  • the expansion valve is located by using a preset graph attention model, and the internal unit serial number of the first expansion valve is obtained, thereby reducing the data stream preprocessing process, which is facilitating improving the accuracy of fault location of the expansion valve.
  • FIG16 is a flowchart of a method for training a graph attention model of a multi-split air conditioning system according to some embodiments.
  • the GAT model can be obtained by training the controller.
  • the training method of the GAT model is shown in FIG16 , which is executed by the controller and includes steps S11 to S12.
  • step S11 normal operation data and fault operation data of the multi-split air conditioning system are obtained.
  • the normal operation data refers to the operation data of the multi-split air conditioning system when the expansion valve is in a normal operation state
  • the fault operation data refers to the operation data of the multi-split air conditioning system when the expansion valve is in a fault operation state.
  • the controller can input the normal operation data and fault operation data of the multi-split air conditioning system into the GAT model for training, so that the GAT model can obtain the operation data characteristics of the expansion valve in the normal operation state and the operation data characteristics of the expansion valve in the fault operation state.
  • the controller can more accurately identify whether there is fault operation data in the real-time operation data of the multi-split air conditioning system.
  • the training principle of the GAT model can be based on a graph neural network model (GNN).
  • the graph neural network model is a connection model that obtains dependencies in the graph by passing information between nodes in the network.
  • the GNN updates the node state from neighbors at any depth of the node, and this state can represent state information.
  • step S12 the initial graph attention model is trained according to the normal operation data and the fault operation data to obtain a preset graph attention model after the training is completed.
  • the controller before the controller inputs the normal operation data and the fault operation data into the initial graph attention model to obtain the preset graph attention model after training, the controller can also convert the normal operation data and the fault operation data into a graph structure through a GNN model, perform node aggregation operations on the graph structure, iteratively update the GAT model parameters, and finally output the fault detection and positioning results of the expansion valve.
  • Fig. 17 is a flow chart of another method for training a graph attention model of a multi-split air conditioning system according to some embodiments. As shown in Fig. 17, the method includes step S21.
  • step S21 the normal operation data and the fault operation data are converted into a graph structure through a preset graph neural network model.
  • the controller before the controller trains an initial graph attention model based on the normal operation data and the fault operation data, the controller converts the normal operation data and the fault operation data into a graph structure through a preset graph neural network model.
  • the graph structure includes original node feature vectors and connection relationships between original node feature vectors.
  • the original feature vectors are vector representations of normal operation data and fault operation data.
  • connection relationship between the original node feature vectors may be presented in the form of edges, and the edges are represented in the form of an adjacency matrix.
  • the Pearson correlation coefficient is calculated for different data information between two original node feature vectors. If the Pearson correlation coefficient is greater than a second preset threshold, the two original node feature vectors are connected by an edge, that is, the two original node feature vectors are correlated; if the Pearson correlation coefficient is less than the second preset threshold, the two original node feature vectors are not connected by an edge, that is, the two original node feature vectors are not correlated.
  • the second preset threshold is 0.5.
  • the Pearson correlation coefficient A is greater than the second preset threshold, that is, A>0.5, the two original node feature vectors are connected by an edge. If A ⁇ 0.5, the two original node feature vectors are not connected by an edge.
  • AM [S 1 , T 1 ], [S 2 , T 2 ], [S 3 , T 3 ], ..., [S n , T n ]]
  • AM is the adjacency matrix
  • S and T are different running data
  • n is the location of the running data.
  • the controller converts the normal operation data and the fault operation data into a graph structure
  • the controller converts the original node feature vector into a target node feature vector according to the graph structure, and allocates attention to the target node feature vector.
  • the controller after the controller converts the normal operation data and the fault operation data into a graph structure, the controller inputs the original node feature vector into the attention layer through linear transformation to obtain the target node feature vector.
  • x is the original node feature vector
  • x' is the target node feature vector
  • self-attention is an important mechanism in the neural network model, which is used to perform self-attention calculation on each element in the input sequence and obtain the self-attention representation of each element.
  • the relationship satisfied by the range matrix W of the target node feature vector and the linear change manner of the attention coefficient e ij are shown in formulas (4) and (5): W ⁇ R F′*F Formula (4)
  • R is the feature space of the target node feature vector
  • F' is the dimension of the target node feature vector
  • F is the dimension of the original node feature vector, that is, the influence coefficient of the target node feature vector i on the target node feature vector j
  • a represents a single-layer feedforward neural network
  • the output is a numerical value.
  • an aggregation operation is performed on the target node feature vector according to the attention coefficient.
  • the nodes ⁇ V a , V b , . . . , V n ⁇ associated with the surrounding of the target node feature vector V i are weighted to V i as an aggregation of the target node feature vector.
  • G() is the aggregation function
  • wj is the weight
  • xj is the target node feature vector
  • Ni is the set of node feature vectors connected to the target node feature vector.
  • the preset graph attention model is updated through the iteration of the preset graph neural network model, and the controller determines whether the original node feature vector reaches the preset convergence condition.
  • the attention coefficient is updated to obtain the influence relationship between the original node feature vectors.
  • L is the original node feature vector and Fw is the compressed map.
  • the controller determines that the original node feature vector does not meet the preset convergence condition, the training of the initial graph attention model is stopped to obtain the preset graph attention model after the training is completed.
  • the method for determining whether the state vector of the original node feature vector x has reached the convergence condition is as shown in formula (8):
  • the controller when the GAT model stops updating, inputs the real-time operation data of the multi-split air conditioning system into the GAT model and outputs the real-time result.
  • the real-time result is compared with the operation status of the expansion valve and the serial number of the indoor unit in the model result to confirm whether the GAT model is successfully trained.
  • the operating status of the expansion valve in the real-time result matches the operating status of the expansion valve in the model result
  • the indoor unit serial number in the real-time result matches the indoor unit serial number in the model result
  • the parameters of the GAT model are updated.
  • the parameters of the GAT model are updated.
  • the real-time operation data of the multi-split air-conditioning system is input into the fault detection model in the GAT model, and the fault identification result is obtained after the back-propagation parameters are updated.
  • the controller constructs maintenance information of the multi-split air-conditioning system through actual operation data and status of the multi-split air-conditioning system in multiple stages and actual operation data and status of other units, thereby continuously updating the GAT model.
  • FIG. 18 is a flow chart of yet another control method for a multi-split air conditioning system according to some embodiments.
  • control method includes steps S1 to S8.
  • step S1 normal operation data and fault operation data of the multi-split air-conditioning system are obtained.
  • the normal operation data is the operation data of the multi-split air-conditioning system when the expansion valve is in a normal operation state
  • the fault operation data is the operation data of the multi-split air-conditioning system when the expansion valve is in a fault operation state.
  • step S2 the normal operation data and the fault operation data are input into the initial GAT model.
  • the initial GAT model is trained by the GNN model.
  • the training method of the GNN model for the initial GAT model is as described in step S21 above, and will not be repeated here.
  • the controller first inputs the normal operation data and the fault operation data into the fault detection model of the initial GAT model, converts the normal operation data and the fault operation data into a graph structure through the GNN model, and determines whether the expansion valve of the multi-split air-conditioning system is in a faulty operation state according to the graph structure.
  • the controller determines that the expansion valve of the multi-split air conditioning system is in a faulty operating state
  • the controller inputs the normal operating data and the faulty operating data into the fault location model of the initial GAT model to locate the internal unit serial number of the expansion valve in the faulty operating state.
  • step S3 it is determined whether the result output by the initial GAT model meets the preset conditions. If so, step S5 is executed; if not, step S4 is executed.
  • the preset condition includes: the expansion valve fault state output by the initial GAT model and the internal unit serial number of the expansion valve in the faulty operation state are both correct.
  • step S4 the parameters of the initial GAT model are updated.
  • the controller updates the parameters of the initial GAT model.
  • step S5 it is determined that the initial GAT model is successfully trained as a preset GAT model.
  • step S6 the real-time operation data of the multi-split air conditioner is obtained, and the real-time operation data is input into a preset GAT model.
  • the controller first inputs the real-time operation data into the fault detection model of the preset GAT model, converts the real-time operation data into a graph structure through the GNN model, and determines whether the expansion valve of the multi-split air-conditioning system is in a faulty operating state based on the graph structure.
  • the controller determines that the expansion valve of the multi-split air conditioning system is in a faulty operating state
  • the controller inputs real-time operating data into the fault location model of the preset GAT model to locate the internal unit serial number of the expansion valve in the faulty operating state.
  • step S7 it is determined whether the result output by the initial GAT model meets the preset conditions. If so, step S8 is executed; if not, step S4 is executed.
  • step S8 the preset GAT model is controlled to learn and improve according to the real-time operation data of the multi-split air conditioner.
  • the controller controls the preset GAT model to learn and improve according to the real-time operating data of the multi-split air conditioner.

Landscapes

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

Abstract

一种多联机空调系统(10),包括室外机(13)、至少一个室内机(12)、膨胀阀(111)和控制器(50)。所述室外机(13)包括压缩机(131)和室外换热器(132)。所述室内机(12)中包括室内换热器(121)。所述室内换热器(121)通过所述膨胀阀(111)连接所述室外换热器(132)。所述控制器(50)被配置为:在确定所述多联机空调系统(10)发生故障的情况下,根据所述多联机空调系统(10)的特征数据和多个基于支持向量机的故障识别模型,确定多个故障识别结果;和将所述多个故障识别结果中的最大概率的故障识别结果对应的故障类型作为所述多联机空调系统(10)的目标故障类型。

Description

多联机空调系统及其控制方法
本申请要求于2022年12月2日提交的、申请号为202211542019.X的中国专利申请的优先权,以及于2023年4月20日提交的、申请号为202310432299.7的中国专利申请的优先权,其全部内容通过引用结合在本公开中。
技术领域
本公开涉及空气调节设备技术领域,尤其涉及一种空调系统。
背景技术
随着科技的不断进步和人们生活水平的提高,空调成为日常生活中不可缺少的电器。
多联机空调系统是一种用于为建筑物或房间提供冷暖空调的系统,通常包括位于室外机和多个室内机。每个室内机可以独立控制温度,因此,多个室内机可以安装在不同的房间或区域,从而可以满足不同房间的需求。
发明内容
一方面,提供一种多联机空调系统,包括室外机、至少一个室内机、膨胀阀和控制器。所述室外机包括压缩机和室外换热器;所述压缩机连接所述室外换热器。所述至少一个室内机中的任一个室内机包括室内换热器。所述室内换热器通过所述膨胀阀连接所述室外换热器。冷媒在所述压缩机、所述室外换热器、所述膨胀阀和所述室内换热器中循环流动,以形成冷媒回路。所述控制器被配置为:在确定所述多联机空调系统发生故障的情况下,根据所述多联机空调系统的特征数据和多个基于支持向量机的故障识别模型,确定多个故障识别结果;所述多个故障识别模型中的任一个故障识别模型被配置为识别一种故障类型,且所述任一个故障识别模型输出的故障识别结果被配置为指示所述多联机空调系统发生所述任一个故障识别模型对应的所述故障类型的概率;和将所述多个故障识别结果中的最大概率的故障识别结果对应的故障类型作为所述多联机空调系统的目标故障类型。
另一方面,提供一种多联机空调系统的控制方法,所述多联机空调系统包括室外机、至少一个室内机和膨胀阀。所述室外机包括压缩机和室外换热器。所述至少一个室内机中的任一个室内机包括室内换热器。冷媒在所述压缩机、所述室外换热器、所述膨胀阀和所述室内换热器中循环流动,以形成冷媒回路。所述方法包括:在确定所述多联机空调系统发生故障的情况下,根据所述多联机空调系统的特征数据和多个基于支持向量机的故障识别模型,确定多个故障识别结果;所述多个故障识别模型中的任一个故障识别模型被配置为识别一种故障类型,且所述任一个故障识别模型输出的故障识别结果被配置为指示所述多联机空调系统发生所述任一个故障识别模型对应的所述故障类型的概率;以及将所述多个故障识别结果中的最大概率的故障识别结果对应的故障类型作为所述多联机空调系统的目标故障类型。
又一方面,提供一种多联机空调系统,包括:室外机、至少一个室内机、至少一个膨胀阀和控制器。所述至少一个室内机与所述室外机相连接。所述至少一个膨胀阀与所述至少一个室内机相对应。所述至少一个膨胀阀中的任一个膨胀阀设置在对应的室内机与所述室外机之间的管路上。所述控制器被配置为:获取所述多联机空调系统的实时运行数据;通过预设图注意力模型对所述实时运行数据进行故障识别,以得到故障识别结果;所述故障识别结果包括所述多联机空调系统中的所述任一个膨胀阀处于故障运行状态或正常运行状态;以及在所述任一个膨胀阀处于故障运行状态的情况下,通过所述预设图注意力模型对所述任一个膨胀阀进行故障定位,以确定所述任一个膨胀阀的内机序号。
又一方面,提供一种多联机空调系统的控制方法,所述多联机空调系统包括室外机、至少一个室内机和至少一个膨胀阀。所述至少一个膨胀阀与所述至少一个室内机相对应。所述至少一个膨胀阀中的任一个膨胀阀设置在对应的室内机与所述室外机之间的管路上。所述方法包括:获取所述多联机空调系统的实时运行数据;通过预设图注意力模型对所述实时运行数据进行故障识别,以得到故障识别结果;其中,所述故障识别结果包括所述多联机空调系统中的所述任一个膨胀阀处于故障运行状态或正常运行状态;以及在所述任一个膨胀阀处于故障运行状态的情况下,通过所述预设图注意力模型对所述任一个膨胀阀进行故障定位,以确定所述任一个膨胀阀的内机序号。
附图说明
图1A为根据一些实施例的一种多联机空调系统的框图;
图1B为根据一些实施例的一种多联机空调系统的室内换热器、气管以及液管的结构图;
图2A为根据一些实施例的一种多联机空调系统的另一种框图;
图2B为根据一些实施例的一种多联机空调系统的结构图;
图2C为根据一些实施例的一种多联机空调系统的室内换热器、管路和传感器的结构图;
图3为根据一些实施例的一种多联机空调系统的控制器与终端设备的结构图;
图4为根据一些实施例的一种控制器的框图;
图5为根据一些实施例的一种多联机空调系统的控制方法的流程图;
图6为根据一些实施例的另一种多联机空调系统的控制方法的流程图;
图7为根据一些实施例的一种故障等级对多联机空调系统影响程度示意图;
图8为根据一些实施例的一种多联机空调系统故障等级预警示意图;
图9为根据一些实施例的又一种多联机空调系统的控制方法的流程图;
图10为根据一些实施例的又一种多联机空调系统的控制方法的流程图;
图11为根据一些实施例的又一种多联机空调系统的控制方法的流程图;
图12为根据一些实施例的一种终端设备的管理界面示意图;
图13为根据一些实施例的另一种终端设备的管理界面示意图;
图14为根据一些实施例的又一种终端设备的管理界面示意图;
图15为根据一些实施例的一种多联机空调系统的又一种控制方法的流程图;
图16为根据一些实施例的一种多联机空调系统的图注意力模型的训练方法的流程图;
图17为根据一些实施例的一种多联机空调系统的另一种图注意力模型的训练方法的流程图;
图18为根据一些实施例的一种多联机空调系统的又一种控制方法的流程图。
具体实施方式
下面将结合附图,对本公开一些实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本公开一部分实施例,而不是全部的实施例。基于本公开所提供的实施例,本领域普通技术人员所获得的所有其他实施例,都属于本公开保护的范围。
除非上下文另有要求,否则,在整个说明书和权利要求书中,术语“包括(comprise)”及其其他形式例如第三人称单数形式“包括(comprises)”和现在分词形式“包括(comprising)”被解释为开放、包含的意思,即为“包含,但不限于”。在说明书的描述中,术语“一个实施例(one embodiment)”、“一些实施例(some embodiments)”、“示例性实施例(exemplary embodiments)”、“示例(example)”、“特定示例(specific example)”或“一些示例(some examples)”等旨在表明与该实施例或示例相关的特定特征、结构、材料或特性包括在本公开的至少一个实施例或示例中。上述术语的示意性表示不一定是指同一实施例或示例。此外,所述的特定特征、结构、材料或特点可以以任何适当方式包括在任何一个或多个实施例或示例中。
以下,术语“第一”、“第二”仅用于描述目的,而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此,限定有“第一”、“第二”的特征可以明示或者隐含地包括一个或者更多个该特征。在本公开的一些实施例的描述中,除非另有说明,“多个”的含义是两个或两个以上。
在描述一些实施例时,可能使用了“连接”及其衍伸的表达。术语“连接”应做广义理解,例如,“连接”可以是固定连接,也可以是可拆卸连接,或成一体;可以是直接相连,也可以通过中间媒介间接相连。
“A、B和C中的至少一个”与“A、B或C中的至少一个”具有相同含义,均包括以下A、B和C的组合:仅A,仅B,仅C,A和B的组合,A和C的组合,B和C的组合,及A、B和C的组合。
如本文中所使用,根据上下文,术语“如果”任选地被解释为意思是“当……时”或“在……时”或“响应于确定”或“响应于检测到”。类似地,根据上下文,短语“如果确定……”或“如果检测到[所陈述的条件或事件]”任选地被解释为是指“在确定……时”或“响应于确定……”或“在检测到[所陈述的条件或事件]时”或“响应于检测到[所陈述的条件或事件]”。
本文中“适用于”或“被配置为”的使用意味着开放和包容性的语言,其不排除适用于或被配置为执行额外任务或步骤的设备。
如本文所使用的那样,“约”、“大致”或“近似”包括所阐述的值以及处于特定值的可接受偏差范围内的平均值,其中所述可接受偏差范围如由本领域普通技术人员考虑到正在讨论的测量以及与特 定量的测量相关的误差(即,测量系统的局限性)所确定。
随着经济社会的发展,空调在娱乐、居家及工作等多种场所越来越被广泛使用。当在同一区域中的多个小区域需要使用空调时,考虑到电能的节省,常采用由一个室外机和多个室内机组成的多联机空调系统实现对多区域室温的调控。
然而,多联机空调系统在经过长时间运行后,不可避免的会发生各种故障。在导致多联机空调系统发生故障的原因中,有一部分是由于多联机空调系统设备的性能下降而产生的渐变故障,如,换热器结垢、冷媒泄露和压缩机磨损等。这些故障多表征为部件老化或磨损,难以检测,并且,多联机空调系统发生故障时,多种故障表现出的具体问题可能相似,从而导致无法准确地识别是多联机空调系统中的何部件发生的故障。
为此,本公开的一些实施例提供了一种多联机空调系统。图1A为根据一些实施例的一种多联机空调系统的框图,如图1A所示,多联机空调系统10包括节流装置11、多个室内机12和室外机13。
多个室内机12与室外机13通过管路连接,冷媒可以在管路中循环流动。例如,室内机12为室内挂机或室内柜机,且被配置为与室内空气换热。节流装置11设置在多个室内机12与室外机13之间的管路上,且被配置为调节多个室内机12与室外机13之间的管路内的流体的流速,以及调节冷媒流量。室外机13被配置为与室外空气换热。
图1B为根据一些实施例的一种多联机空调系统的室内换热器、气管以及液管的结构图。
例如,参见图1B,连接室外机13与多个室内机12的管路包括气管15和液管16。气管15被配置为传输气态的冷媒,且液管16被配置为传输液态的冷媒。
例如,节流装置11还被配置为调节气管15和液管16内的流体的流速。例如,节流装置11包括多个膨胀阀111,多个膨胀阀111与多个室内机12相对应,且分别与多个室内机12相连。膨胀阀111设置在对应的室内机12与室外机13之间的管道上。例如,参见图1B,膨胀阀111设置在对应的室内机12(如室内换热器121)与室外机13之间的液管16上。
在一些实施例中,膨胀阀111被配置为使流经膨胀阀111的冷媒膨胀而减压,以调节管道内冷媒的供应量。例如,当膨胀阀111的开度减小时,流经膨胀阀111的冷媒的流路阻力会增加,当膨胀阀111的开度增大时,则流经膨胀阀111的冷媒的流路阻力会减小。这样,在冷媒回路中的其他器件的状态不变的情况下,通过控制膨胀阀111的开度变化,可以调节流向室内机12的冷媒的流量。
在一些实施例中,膨胀阀111可以是电子膨胀阀。在一些实施例中,如图2A和图2B所示,室内机12包括室内换热器121。室内换热器121包括第一端口和第二端口。
第一端口被配置为通过液管16与对应的膨胀阀111连接,以使液态的冷媒可以在室内换热器121与对应的膨胀阀111之间流动。第二端口被配置为通过气管15与室外机13相连接,以使气态的冷媒可以在室内换热器121与室外机13之间流动。
在一些实施例中,室内换热器121包括热传管,热传管连接在第一端口与第二端口之间,且被配置为使流动在的热传管中的冷媒与室内空气进行热交换。
在一些实施例中,如图2A和图2B所示,室外机13包括压缩机131和储液器133。压缩机131设置于节流装置11与储液器133之间,且被配置为将低温低压的气态冷媒压缩成高温高压的气态冷媒,并排处至冷凝器(即,室内换热器或室外换热器)。压缩机131可以是进行基于逆变器的转速控制的容量可变的逆变器压缩机。
例如,室内换热器121的第二端口通过气管15与室外机13相连接,以使气态的冷媒在室内换热器121与压缩机131的排出口之间流通。
在一些实施例中,如图2A和图2B所示,室外机13还包括室外换热器132和四通阀134。
室外换热器132的一端通过四通阀134与储液器133相连,另一端与节流装置11相连。室外换热器132包括第三端口和第四端口。第三端口被配置为使冷媒经由储液器133在室外换热器132与压缩机131的吸入口之间流通,第四端口被配置为使冷媒在室外换热器132与节流装置11之间流通。
例如,室外换热器132还包括传热管,传热管使连接于第三端口和第四端口之间,且被配置为使在传热管中流动的冷媒室外空气之间进行热交换。
在一些实施例中,储液器133的一端连接压缩机131,另一端通过四通阀134与室外换热器132相连。储液器133被配置为将来自室外换热器132的气液两相态的冷媒(如,从室外换热器132经由四通阀134流向压缩机131的冷媒),分离为气态的冷媒和液态的冷媒,以及,向压缩机131的吸入口供给 气态的冷媒。
在一些实施例中,四通阀134的四个端口分别连接压缩机131,室外换热器132、储液器133以及多个膨胀阀111。四通阀134被配置为切换状态,以改变冷媒在冷媒回路中的流向,从而实现多联机空调系统10的制冷模式和制热模式的切换。
在一些实施例中,如图2B所示,室外机13还包括室外风扇135。室外风扇135靠近室外换热器132设置,且室外风扇135被配置为向室外换热器132输送室外空气的气流,以促使在第三端口和第四端口之间的传热管中流动的冷媒与室外空气的热交换。
在一些实施例中,如图2B所示,室内机12还包括显示器122,显示器122被配置为显示室内温度或室内机12的当前运行模式。
在一些实施例中,如图2B所示,室内机12还包括室内风扇123。室内风扇123靠近室内换热器121设置,且被配置为:向室内换热器121输送室内空气的气流,以促使在第一端口和第二端口之间的传热管中流动的冷媒与室外空气的热交换。
例如,室内机12还包括室内风扇马达,室内风扇马达被配置为驱动室内风扇123转动,以及调节室内风扇123的转速。
在一些实施例中,冷媒在多联机空调系统的冷媒回路中循环流动,以使多联机空调系统实现制冷或制热模式。冷媒回路包括依序连接的压缩机131、冷凝器、膨胀阀111和蒸发器。
例如,当多联机空调系统运行制热模式时,冷媒在冷媒回路中循环的过程包括:压缩机131将经蒸发器蒸发后的低温低压的气态冷媒吸入压缩机腔,压缩成高温高压的气态冷媒,并输送至冷凝器。高温高压气态的气态冷媒在冷凝器中冷凝成高温高压的液态冷媒,之后,经过节流装置11(如膨胀阀111)后,变成低温低压的液态冷媒。接下来,低温低压的液态冷媒进入蒸发器,并被蒸发,再回到压缩机131内,以进入下一轮的制热循环。
可以理解的是,制热模式下的室外换热器132作为蒸发器使用,室内换热器121作为冷凝器使用。制冷模式下的室外换热器132作为冷凝器使用,室内换热器121作为蒸发器使用。
图2C为根据一些实施例的一种多联机空调系统的室内换热器、管路和传感器的结构图。
在一些实施例中,如图2A和图2C所示,多联机空调系统10还包括多个第一温度传感器101和控制器50。多个第一温度传感器101与控制器50通讯连接。
多个第一温度传感器101与多个室内机12相对应,多个第一温度传感器101中的任一个第一温度传感器101设置于对应的室内机12与室外机13之间的气管15上,且被配置为检测气管15的温度值,并将检测到的气管15的温度值发送至控制器50。
例如,多个第一温度传感器101可以检测多个室内机12与室外机13之间的多个气管15的温度,并将多个气管15的温度值发送至控制器50。
在一些实施例中,控制器50被配置为控制压缩机131和膨胀阀111工作,以使得多联机空调系统10运行实现多联机空调系统的各预定功能。在一些实施例中,控制器50还被配置为获取到压缩机131在每个时刻下的运行频率和每个时刻下的工作电流值。
在一些实施例中,如图2A和图2C所示,多联机空调系统10还包括多个第二温度传感器102。多个第二温度传感器102与控制器50通讯连接。
多个第二温度传感器102与多个室内机12相对应,多个第二温度传感器102中的任一个第二温度传感器102设置于对应的室内机12与室外机13之间的液管16上,且被配置为检测液管的温度值,并将检测到的液管的温度值发送至控制器50。
在一些实施例中,如图2A所示,多联机空调系统10还包括多个第三温度传感器103,多个第三温度传感器103均与控制器50通讯连接。多个第三温度传感器103中的任一个第三温度传感器设置于室内机的出风口处,且被配置为检测室内机的出风温度,并发送至控制器50。
例如,多个第三温度传感器103与多个室内机12相对应,且任一个第三温度传感器被配置为检测对应的室内机12的出风温度,并发送至控制器50。
在一些实施例中,如图2A所示,多联机空调系统10还包括多个第四温度传感器104,多个第四温度传感器104均与控制器50通讯连接。多个第四温度传感器104中的任一个第四温度传感器104设置于室内机的进风口(即回风口)处,且被配置为检测室内机的进风温度(即回风温度),并发送至控制器50。
例如,多个第四温度传感器104与多个室内机12相对应,且任一个第四温度传感器104被配置为检测对应的室内机12的进风温度,并发送至控制器50。
在一些实施例中,如图2A所示,多联机空调系统10还包括第五温度传感器105,第五温度传感器105与控制器50通讯连接。第五温度传感器105设置于压缩机的吸气口处,且被配置为检测压缩机的吸气温度值,并将检测到的吸气温度值发送至控制器50。
在一些实施例中,如图2A所示,多联机空调系统10还包括第六温度传感器106,第六温度传感器106与控制器50通讯连接。第六温度传感器106设置于压缩机的排气口处,且被配置为检测压缩机的排气温度值,并将检测到的排气温度值发送至控制器50。
在一些实施例中,如图2A所示,多联机空调系统10还包括第一压力传感器107。第一压力传感器107与控制器50通讯连接。第一压力传感器107设置于压缩机的排气口处,且被配置为检测压缩机的排气压力值,并将检测到的排气压力值发送至控制器50。
在一些实施例中,如图2A所示,多联机空调系统10还包括第二压力传感器108,第二压力传感器108与控制器50通讯连接。第二压力传感器108设置于压缩机的吸气口处,且被配置为检测压缩机的吸气压力值,并将检测到的吸气压力值发送至控制器50。
需要说明的是,本公开的一些实施例中的控制器50是指:可以根据指令操作码和时序信号,产生操作控制信号,以指示多联机空调系统10执行控制指令的装置。
例如,控制器50包括中央处理器(Central processing unit,CPU)、通用处理器网络处理器(Network processor,NP)、数字信号处理器(Digital signal processing,DSP)、微处理器、微控制器或可编程逻辑器件(Programmable logic device,PLD)中的至少一者。
在一些实施例中,控制器还可以是其它具有处理功能的装置,例如电路、器件或软件模块等,本公开对此不做限定。
在一些实施例中,多联机空调系统10还包括遥控器,遥控器被配置为通过红外线或其他通信方式与控制器50进行通信。这样,用户可以通过遥控器,实现对多联机空调系统的控制(如控制多联机空调系统10执行制热模式等),从而实现了用户与多联机空调系统10之间的交互。
在一些实施例中,控制器50包括通信器,通信器被配置为与其他网络实体(如遥控器或终端设备等)建立通讯连接。
例如,通信器包括射频(Radio-frequency,RF)装置,RF装置被配置为接收和发送信号。例如,RF装置可以将接收到的信息发送给控制器50处理,或者,将控制器生成的信号发送出去。
例如,RF装置可以包括天线、至少一个放大器、收发信机、耦合器、低噪声放大器(Low noise amplifier,LNA)、双工器等。
可以理解的是,控制器50可以通过通信器接收用户的终端设备发出的控制指令,并根据所述控制指令,控制多联机空调系统10执行相应的处理,从而可以实现用户与多联机空调系统10之间的交互。
图3为根据一些实施例的一种多联机空调系统的控制器与终端设备的结构图。
如图3所示,终端设备300可以与控制器50建立通讯连接。例如,可使用多种网络通信协议,来建立终端设备300与控制器50之间的通讯连接。
例如,多种网络通信协议可以以太网、通用串行总线(Universal serial bus,USB)、火线(FIREWIRE)、蜂窝网通信协议(如3G/4G/5G)、蓝牙、无线保真(Wireless fidelity,Wi-Fi)、NFC等。
需要说明的是,图3所示的终端设备300仅是终端设备的一个示例。本公开中的终端设备300可以为遥控器、手机、平板电脑等。
图4为根据一些实施例的一种控制器的框图。
在一些实施例中,如图4所示,控制器50包括室外控制装置501和室内控制装置502。室外控制装置501包括第一存储器5011,室内控制装置502包括第二存储器5021。
室内控制装置502通过有线或无线通信的方式与室外控制装置501连接。室外控制装置501可以安装于室外机13中,也可以独立于室外机13以外。室外控制装置501被配置为控制室外机13执行相关操作。室内控制装置502可以安装于室内机12中,也可以独立于室内机12以外。室内控制装置502被配置为控制室内机12的部件以及节流装置11执行相关操作。
需要说明的是,以上装置的划分仅为功能性的划分,例如,室外控制装置501和室内控制装置502也可以集成在一个装置中。例如,第一存储器5011和第二存储器5021也可以集成为一个存储器。
在一些实施例中,第一存储器5011被配置为存储室外机13相关的应用程序以及数据,室外控制装置501通过运行存储在第一存储器5011的应用程序以及数据,执行多联机空调系统的各种功能以及数据处理。
第一存储器5011包括存储程序区以及存储数据区。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(比如室外机风扇开启功能、室外测温功能等)。存储数据区可以存储根据使用多联机空调系统所创建的数据(比如室外温度、各个膨胀阀的开度等)。此外,第一存储器5011还包括高速随机存取存储器,或非易失存储器,例如磁盘存储器件、闪存器件或其他易失性固态存储器件等。
在一些实施例中,第二存储器5021被配置为存储多个室内机12以及多个膨胀阀111相关的应用程序以及数据,室内控制装置502通过运行存储在存储器5021的应用程序以及数据,执行多联机空调系统的各种功能以及数据处理。
第二存储器5021包括存储程序区以及存储数据区。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(比如室内测温功能)。存储数据区可以存储根据使用多联机空调系统所创建的数据(比如室内温度等)。
在一些实施例中,第二存储器5021还被配置为存储室内机12的地址与膨胀阀111的地址的对应关系。
在一些实施例中,室外控制装置501与室外机13通讯连接,且被配置为根据用户指令或系统默认指令,控制室外机13执行相关操作。
例如,室外控制装置501可以根据用户所选择的空调运行模式控制室外风扇的转速。例如,室外控制装置501还可以根据用户指令或系统指令获取室外温度,并将所获取的室外温度储存至第一存储器5011。例如,室外控制装置501还可以根据用户所选择的空调运行模式控制室外机13内的四通阀134转动,以实现制冷或制热模式的选择。例如,室外控制装置501还可以在地址纠正过程中对室外机13的运行模式、压缩机频率等进行控制。
在一些实施例中,室内控制装置502与室内机12通讯连接,且被配置为根据用户指令或系统默认指令控制室内机12执行相关操作。例如,室内控制装置502还可以根据用户指令控制室内机开启室内温度传感器,检测室内温度。
在一些实施例中,室内控制装置502与多个膨胀阀111通讯连接,且被配置为根据用户指令或系统默认指令控制多个膨胀阀111执行相关操作。例如,室内控制装置502可以根据用户指令或系统指令控制各个膨胀阀111的开度。
可以理解的是,图2A中示出的多联机空调系统的硬件结构,并不构成对多联机空调系统的限定。在一些实施例中,多联机空调系统可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置。
本公开的一些实施例还提供了一种多联机空调系统的控制方法,该控制方法可以将多联机空调系统的特征数据输入多个故障识别模型中,得到多个识别结果,且可以排除运行数据中的无关数据,从而有助于提高对多联机空调系统中故障识别的准确率。以下,将结合附图,对多联机空调系统的控制方法进行详细介绍。
需要说明的是,多联机空调系统的控制方法由控制器执行。该控制器可以是上述任一实施例中所述的控制器50,也可以是其他控制器,本公开对此不做限定。
图5为根据一些实施例的一种多联机空调系统的控制方法的流程图。
在一些实施例中,如图5所示,多联机空调系统的控制方法包括步骤S101和步骤S102。
在步骤S101,在确定多联机空调系统发生故障的情况下,根据多联机空调系统的特征数据和多个基于支持向量机的故障识别模型,确定多个故障识别结果。
例如,多联机空调系统的存储器中预先存储有多个已训练完成的基于支持向量机的故障识别模型。在确定多联机空调系统发生故障的情况下,控制器50可以将多联机空调系统的特征数据输入到多个基于支持向量机的故障识别模型中。
需要说明的是,多联机空调系统的特征数据是对多联机空调系统的运行数据进行关联性分析后得到的,所述特征数据是将多联机空调系统的运行数据中去除与故障无关的数据后,保留下来的与故障有关联的数据。
可以理解的是,将多联机空调系统的运行数据进行关联性分析,去除掉与故障无关的数据,可以排 除无关数据对于故障识别的精准率和效率的影响,从而能够提高对多联机空调系统故障识别的准确率和效率。
关于对多联机空调系统的运行数据进行关联性分析,以得到多联机空调系统的特征数据的方法,可以参照下述步骤S301至步骤S302,在此不予赘述。
将多联机空调系统的特征数据输入多个故障识别模型中,一个故障识别模型对应一种故障类型,一个故障识别模型输出的故障识别结果被配置为指示多联机空调系统发生该故障识别模型对应的故障类型的概率。
可以理解的是,一种故障识别模型被配置为识别一种故障类型,一种故障识别模型对多联机空调系统进行故障识别时,只识别该多联机空调系统发生该故障识别模型对应的故障类型的概率,不会在故障识别时受其他故障类型的影响。根据多联机空调系统的运行数据和多个基于支持向量机的故障识别模型,确定多个故障识别结果,也即得到该多联机空调系统发生每种故障识别模型对应的故障类型的概率。
例如,多联机空调系统的故障类型包括:冷媒充注量异常、室外换热器脏堵、室内换热器脏堵、压缩机磨损以及膨胀阀故障。
在一些实施例中,多联机空调系统的特征数据包括压缩机的运行频率、压缩机的排气压力值、压缩机的吸气压力值、压缩机的吸气温度值、压缩机的排气温度值、压缩机的排气过热度、压缩机的吸气过热度、室外风扇档位膨胀阀的开度、每个室内机的出风温度、每个室内机的回风温度、气管15的温度值以及液管16的温度值中的至少一项。
在一些实施例中,支持向量机是一种二分类模型,支持向量机的基本模型是定义在特征空间上的间隔最大的线性分类器。支持向量机还包括核技巧,这使得支持向量机成为实质上的非线性分类器。支持向量机是建立在统计学习理论的VC维理论(Vapnik-Chervonenkis Dimension)和结构风险最小原理的基础上的,根据有限的样本信息在模型的复杂性(即对特定训练样本的学习精度)和学习能力(即无错误地识别任意样本的能力)之间寻求最佳折中,以期获得较好的推广能力。
在一些实施例中,控制器50可以基于多联机空调系统的历史运行数据训练多个基于支持向量机的故障识别模型,并将训练完成的多个故障识别模型存储在存储器中,以便于在执行故障识别功能时,控制器50能够根据训练完成的故障识别模型及时识别出多联机空调系统发生的故障类型。例如,多联机空调系统的历史运行数据包括多联机空调系统在正常运行过程中的正常运行数据和在异常运行过程的异常运行数据(也可以称作历史故障数据)。
在一些实施例中,故障识别模型的训练过程包括:建立数据回归直线、回归平面和超平面进行拟合,并通过损失函数、设定偏差值、松弛变量,调节拟合的精度和范围。
在一些实施例中,控制器50还被配置为在故障识别模型训练完成后,进行模型测试。故障识别模型的测试结果可以通过混淆矩阵和诊断时序图进行诊断结果的可视化,并引入三个模型评价指标:平均几何精度(Geometric mean accuracy,GMA)、虚警率(False alarm rate,FAR)和漏警率(Miss alarm rate,MAR)进行评价。例如,GMA指标表示每个分类类别精度的几何平均值,并且在取得真实结果后,进行判断,如果精度未达到要求,将启动参数更新和调优装置,进行自我优化。
在步骤S102,将多个故障识别结果中最大概率的故障识别结果对应的故障类型作为多联机空调系统的目标故障类型。
可以理解的是,一种故障识别模型对应一种故障类型,一个故障识别结果指示的故障概率越大,代表该多联机空调系统发生该故障识别结果对应的故障类型的概率越高,故可以将多个故障识别结果中最大概率的故障识别结果对应的故障类型作为多联机空调系统的目标故障类型。
示例性的,故障识别模型包括A1、B1和C1,A1对应A故障类型,B1对应B故障类型,C1对应C故障类型。在多联机空调系统确定发生故障的情况下,将多联机空调系统的特征数据输入至三个故障识别模型A1、B1和C1后,得到三个故障识别模型的故障识别结果。在此情况下,若A1输出的故障识别结果指示了多联机空调系统发生A故障类型的概率为50%,B1输出的故障识别结果指示了多联机空调系统发生B故障类型的概率为80%,C1输出的故障识别结果指示了多联机空调系统发生C故障类型的概率为30%,则可以将B故障类型作为多联机空调系统的目标故障类型。
可以理解的是,本公开的一些实施例提供的多联机空调系统的控制方法,在确定多联机空调系统发生故障后,将多联机空调系统的特征数据分别输入多个故障识别模型中,从而得到多个识别结果。由于多联机空调系统的特征数据是基于多联机空调系统的运行数据进行关联性分析后得到的,因此,多个识 别结果排除了运行数据中无关数据对故障识别精准度的影响。在此情况下,将多个故障识别结果中最大概率的故障识别结果对应的故障类型作为多联机空调系统的目标故障类型,从而有利于提高对多联机空调系统中故障识别的准确率。
图6为根据一些实施例的另一种多联机空调系统的控制方法的流程图。
在一些实施例中,如图6所示,在确认多联机空调系统的目标故障类型后(即在步骤S102之后),该方法还包括步骤S201至步骤S202。
在步骤S201,根据所述多联机空调系统的特征数据和与所述目标故障类型对应的故障等级识别模型,确定故障等级识别结果。
可以理解的是,在多联机空调系统发生故障的情况下,不同的故障等级对于多联机空调系统的运行造成的影响不同。在故障等级为轻微的情况下,可以理解为当前故障可能不会对多联机空调系统的运行造成过多影响,可以暂时不进行检修。而在故障等级为严重的情况下,可能会导致多联机空调系统无法运行,需要进行检修。因此,在确定了多联机空调系统的目标故障类型后,还需要根据多联机空调系统的特征数据,得到故障等级识别结果,以此来判断是否要对多联机空调系统进行检修。
在一些实施例中,多联机空调系统的存储器中预先存储有多个故障等级识别模型,一种故障等级识别模型被配置为识别一种故障类型的故障等级。
因此,在确定多联机空调系统的目标故障类型后,可以将多联机空调系统的特征数据输入至目标故障类型对应的故障等级识别模型中,得到故障等级识别结果,故障等级识别结果即代表目标故障类型对多联机空调系统的影响程度。
在一些实施例中,故障等级识别模型可以是基于机器学习算法的故障等级识别模型。
例如,故障等级识别结果包括:故障等级1、故障等级2、故障等级3、故障等级4和故障等级5。若对故障等级识别结果为故障等级1或故障等级2,代表需要引起用户注意,并建议用户关注检查。若对故障等级识别结果为故障等级3,代表需要用户注意,并建议近期检修。若对故障等级识别结果为故障等级4,代表需要引起用户足够注意,并建议及时检修。若对故障等级识别结果为故障等级5,代表需要引起用户高度重视,并建议立即检修。
在步骤S202,在故障等级识别结果指示的故障等级在预设故障等级以上时,发出告警信息。
可以理解的是,在故障等级识别结果指示的故障等级在预设故障等级以上时,代表当前目标故障类型对应的故障等级较高,可能会导致多联机空调系统无法正常运行。为了保证多联机空调系统可以正常运行,可以发出告警信息以提示维修人员对多联机空调系统进行检修。
在一些实施例中,告警信息包括目标故障类型,以便于维修人员可以基于目标故障类型有针对性的对多联机空调系统进行检修,有助于提升对于多联机空调系统的故障修复效率。
例如,预设故障等级可以是多联机空调系统出厂时预先设置的。
图7为根据一些实施例的一种故障等级对多联机空调系统影响程度示意图。
示例性的,如图7所示,多联机空调系统处于故障等级5及以下,代表多联机空调系统发生的故障轻微,故障等级5以下的情况下对多联机空调系统的影响程度较小。多联机空调系统处于故障等级5以上,代表多联机空调系统发生的故障严重,也即故障等级5以上的情况下对多联机空调系统的影响程度较大。
图8为根据一些实施例的一种多联机空调系统故障等级预警示意图。
示例性的,如图8所示,为了避免多联机空调系统发生的轻微故障发展成为严重故障,可以将预设故障等级为故障等级2,也就是说,在确定多联机空调系统的故障等级在故障等级2以上时,控制器发出告警信息,提醒维修人员进行检修,以避免多联机空调系统发生的轻微故障发展成为严重故障。例如避免多联机空调系统的故障等级由故障等级2发展至故障等级5。
在一些实施例中,控制器50可以通过多种方式发出告警信息。例如,多种方式包括方式1、方式2和方式3。
方式1包括:控制器控制室内机的显示器显示告警信息。
例如,当多联机空调系统的目标故障类型为室外换热器脏堵时,告警信息的内容可以是“室外换热器脏堵严重,建议立即检修!”。
在一些实施例中,为了便于用户及时了解到多联机空调系统发生严重故障,控制器可以控制多联机空调系统中的每个室内机的显示器显示上述告警信息。
方式2包括:控制器通过通信器向终端设备发送告警信息。
例如,当多联机空调系统的目标故障类型为室外换热器脏堵时,终端设备接收到控制器50通过Wi-Fi网络或蓝牙发送的告警信息的内容可以是“室外换热器脏堵严重,建议立即检修!”。
方式3包括:控制器通过语音提示装置向终端设备发送告警信息。
在一些实施例中,室内机还包括语音装置,语音提示装置可以是扬声器等,控制器可以控制语音装置播报告警信息,引起用户注意,提醒用户进行检修。
图9为根据一些实施例的又一种多联机空调系统的控制方法的流程图。
在一些实施例中,如图9所示,在步骤101之前,该方法还包括步骤S301至步骤S303。
在步骤S301,在确定多联机空调系统发生故障之前,获取多联机空调系统的运行数据。
可以理解的,在确定多联机空调系统发生故障之后,才可以进一步进行故障类型的识别。所以在确定多联机空调系统发生故障之前,可以获取多联机空调系统的运行数据来判断多联机空调系统是否发生故障。
图10为根据一些实施例的又一种多联机空调系统的控制方法的流程图。在一些实施例中,如图10所示,步骤S301包括步骤S3011至步骤S3012。
在步骤S3011,获取多联机空调系统的原始运行数据。
例如,在多联机空调系统处于运行状态下,控制器可以获取多联机空调系统的各部件在运行过程中所产生的原始运行数据。
在步骤S3012,对多联机空调系统的原始运行数据进行预处理,以得到多联机空调系统的运行数据。
在一些实施例中,所述预处理包括异常值剔除处理和平滑处理。
例如,所述异常值剔除处理包括:在控制器获取原始运行数据的过程中,将与其他运行数据相比,具有更高离散程度的异常运行数据进行剔除。
可以理解的是,若不对多联机空调系统的原始运行数据进行异常值剔除,在后续进行故障诊断时,异常运行数据可能会对故障诊断结果的精度造成影响。因此,在获取到多联机空调系统的原始运行数据后,可以对多联机空调系统的原始运行数据进行异常值剔除处理,从而可以提高对故障针对的精度。
例如,所述平滑处理包括:在对多联机空调系统的原始运行数据进行剔除异常值处理后,利用平滑算法对异常值剔除处理后的原始运行数据进行最小二乘曲线拟合,用拟合的数据代替被剔除的数据。最小二乘拟合是一种数学上的近似和优化方法,根据已知的数据在坐标系中得到一条直线或者曲线,使拟合点与已知数据之间的距离的平方和最小。
例如,所述平滑算法包括Savitzky-Golay算法。
在一些实施例中,对多联机空调系统的原始运行数据进行数据平滑处理还可以包括:将异常值剔除处理后的原始运行数据输入至生成式网络对抗模型中,得到多联机空调系统的运行数据。
需要说明的是,生成式对抗网络模型是一种深度学习模型,模型通过框架包括生成模型和判别模型。生成模型被配置为生成拟合数据,判别模型被配置为对拟合的数据进行判断。例如,判别模型可以判断数据是否平滑。生成模型和判别模型互相博弈,从而得到经过平滑处理后的数据。
在一些实施例中,多联机空调系统的运行数据可以包括:多联机空调系统中室外机在运行过程中的压缩机电流值、压缩机的运行频率、压缩机的排气压力值、压缩机的吸气压力值、压缩机的吸气温度值、压缩机的排气温度值、压缩机的排气过热度、压缩机的吸气过热度、室外风扇档位、膨胀阀的开度、每个室内机的出风温度、每个室内机的回风温度、气管的温度值、液管的温度值、室外机冷媒排出管处的排出压力值和排出温度值中的至少一项。
需要说明的是,以上示出的多联机空调系统的运行数据仅仅是示例性的,多联机空调系统的运行数据还可以包括其他数据,在此不再赘述。
在步骤S302,基于最大信息系数法对多联机空调系统的运行数据进行关联性分析,从多联机空调系统的运行数据中提取出多联机空调系统的特征数据。
可以理解的,多联机空调系统的运行数据中存在大量对于故障诊断无用的冗余数据,冗余数据会影响到故障诊断的效率和精准度。因此,为避免多联机空调系统的运行数据中冗余数据影响故障诊断的效率和精准度,可以基于最大信息系数法对多联机空调系统的运行数据进行关联性分析,从多联机空调系统的运行数据中提取出多联机空调系统的特征数据。
所述最大信息系数法是一种特征选择算法,用于衡量两个变量之间的关联程度。通过最大信息系数 法可以衡量各种故障类型与多联机空调系统的运行数据之间的相关程度,并根据运行数据与故障类型的相关程度对运行数据进行分析和筛选。
与故障类型相关程度较低的运行数据代表该运行数据与故障类型之间关联性较小,因此,可以将该运行数据作为冗余数据,相反的,与故障相关程度较高的运行数据代表该运行数据与故障类型之间的关联性较大,可以将该运行数据作为特征数据。
在一些实施例中,在基于最大信息系数法对多联机空调系统的运行数据进行关联性分析,从多联机空调系统的运行数据中提取出多联机空调系统的特征数据之前(即在步骤S302之前),还可以根据基尼变量重要度以及关联规则算法计算不同运行数据对于不同故障类型的重要程度,并根据重要程度将运行数据进行排序。
所述基尼变量重要度是根据基尼指数衡量变量重要程度的方法。所述基尼指数表示样本集合中一个随机选中的样本被分错的概率,基尼指数越小表示集合被选中的样本被参错的概率越小,即集合的纯度越高。一个特征数据的基尼指数越小,代表该特征数据越重要。
在步骤S303,基于多联机空调系统的特征数据,确定多联机空调系统是否发生故障。
由步骤S302可知,多联机空调系统的特征数据是通过对多联机空调系统的运行数据进行相关性分析,并从多联机空调系统的运行数据中提取出的,多联机空调系统的特征数据能够反映出多联机空调系统的运行情况。而在多联机空调系统发生故障的情况下,多联机空调系统的特征数据也会出现波动。
示例性的,冷媒经过室内机的节流阀后,开始蒸发和吸热的过程,当室内机连接的膨胀阀正常(即不存在故障)时,与室内机连接的气管的温度值和液管的温度值应相等,也就是说,液管的温度值与气管的温度值之间的温度差值大致为0。而当膨胀阀发生故障时,例如,由于膨胀阀故障导致膨胀阀的开度过小时,会导致冷媒流量不足,导致冷媒在蒸发吸热的过程中,过热度过高,进而导致与室内机连接的液管的温度值与气管的温度值之间的温度差值变大。因此,根据特征数据(如气管的温度值和液管的温度值)可以确定膨胀阀是否故障。
图11为根据一些实施例的又一种多联机空调系统的控制方法的流程图。
在一些实施例中,如图11所示,步骤S303包括步骤S3031至步骤S3032。
在步骤S3031,根据所述多联机空调系统的特征数据和故障诊断模型,确定故障诊断结果。
在一些实施例中,多联机空调系统的存储器中预先存储有训练完成的故障诊断模型,在对多联机空调系统进行故障诊断时,可以将多联机空调系统的特征数据输入至训练完成的故障诊断模型中,得到故障诊断结果,故障诊断结果指示了多联机空调系统是否发生故障。
在一些实施例中,故障诊断模型可以是基于支持向量机的故障诊断模型。
在一些实施例中,故障诊断模型训练过程包括:针对每种故障类型设置梯度性的多联机空调系统模拟实验,收集每种故障类型的实验数据并将实验数据根据多联机空调系统正常和异常进行分类,以用于训练故障诊断模型。
示例性的,以冷媒充注量的模拟实验为例,从冷媒充注量120%(过充)至冷媒充注量50%(欠充)依次以10%递减设置多个模拟实验,并收集每个模拟实验的实验数据。
可以理解的是,在模拟实验中,当多联机空调系统的性能下降,并达到第一预设阈值时,则可以认为多联机空调系统出现异常,在此情况下,该次模拟实验的实验数据均被标记为异常。当多联机空调系统的性能下降没有达到第一预设阈值,则认为多联机空调系统正常,该次模拟实验的实验数据均被标记为正常。
在步骤S3032,在故障诊断结果为是的情况下,确定多联机空调系统发生故障。
在一些实施例中,在故障诊断结果为否的情况下,确定多联机空调系统未发生故障。
可以理解的是,本公开的一些实施例提供的控制方法,可以基于最大信息系数法对多联机空调系统的运行数据进行关联性分析,从多联机空调系统的运行数据中提取出特征数据,以便于后续可以基于数据量小、特征代表性强的特征数据来进行故障诊断、故障识别以及故障等级识别,从而提升了故障诊断、故障识别以及故障等级识别的效率以及精准度。
在一些实施例中,本公开实施例提供的一种多联机空调系统的控制方法还包括对故障等级识别模型的训练过程。所述故障等级识别模型的训练过程包括步骤A1至步骤A4。
在步骤A1,执行数据采集。
在一些实施例中,所述数据采集包括:采集用于故障等级识别模型训练的数据。例如,可以针对每 种故障类型设置梯度性的多联机空调系统模拟实验,收集每种故障类型的实验数据,将实验数据根据多联机空调系统的故障等级进行分类,以用于训练故障诊断模型。
需要说明的是,模拟实验与数据采集的具体步骤,已在上文中进行详细介绍,此处不再赘述。
在步骤A2,执行数据预处理。
在一些实施例中,在采集完成被配置为故障等级识别模型训练的实验数据后,需要对采集的实验数据进行预处理,以剔除异常的实验数据,对实验数据进行数据平滑处理。需要说明的是,数据预处理的具体步骤,已在上文中进行详细介绍,此处不再赘述。
在步骤A3,执行重要特征数据选择。
在一些实施例中,在实验数据预处理完成后,根据基尼变量重要度以及关联规则算法计算不同运行数据对于不同故障类型的重要程度,并根据重要程度将运行数据进行排序。对实验数据通过最大信息系数法进行关联性分析,去除实验数据中与故障无关的冗余数据。
需要说明的是,基尼变量重要度与最大信息系数法已在上文中进行详细介绍,此处不再赘述。
在一些实施例中,重要特征数据选择还包括:对故障进行解耦。
解耦是指使含有多个变量的数学方程变成能够用单个变量表示的方程组,即变量不再同时共同直接影响一个方程的结果,从而简化分析计算。在多联机空调系统中,故障与故障之间可能存在关联,导致在多联机空调系统发生单一故障时,引发其他故障。对故障进行解耦即是在分析实验数据与某一故障之间的关联性时,排除其他故障对该故障的影响。
在一些实施例中,重要特征数据选择还包括:结合专家知识体系对现有实验数据进行分析。在对实验数据根据重要程度将运行数据进行排序以及通过最大信息系数法进行关联性分析后,还可以与专家知识体系结合选取重要特征数据。根据多联机空调系统的工作原理,构建专家知识体系,对经过重要度排序和通过最大信息系数法进行关联性分析后的实验数据进行全面分析,选择重要特征数据。
在步骤A4,执行模型训练。
在一些实施例中,在确定重要特征数据后,基于支持向量机模型训练故障等级识别模型,在训练完成后对故障等级识别模型进行评价,如果故障等级识别模型的精度未达到要求,将启动参数更新和调优模型,进行自我优化。
需要说明的是,模型训练与优化的方法已在上文中进行详细介绍,此处不再赘述。
图12为根据一些实施例的一种终端设备的管理界面示意图。
在一些实施例中,如图12所示,终端设备300还被配置为显示多联机空调系统的管理界面301,这样,用户可以通过终端设备300设置多联机空调系统的运行模式。
例如,管理界面301包括第一按键302。终端设备300被配置为:当检测到用户点击管理界面301中的第一按键302时,在管理界面301弹出下拉选择框303。终端设备300还被配置为:当检测到用户在下拉选择框303中选取了指令,并确定该指令后,将用户确定的指令发送给多联机空调系统,以完成运行模式的设置。
例如,用户可以在下拉选择框303中选择制冷模式指令。
图13为根据一些实施例的另一种终端设备的管理界面示意图。
在一些实施例中,如图13所示,管理界面301还包括第二按键304。第二按键304被配置为当受到用户的点击时,在关闭状态和打开状态之间切换。终端设备300还被配置为:当第二按键切换至打开状态时,将开启故障检测的指令传送给多联机空调系统的控制器,使多联机空调系统进入故障检测模式。这样,用户可以通过终端设备300的管理界面开启故障检测功能,从而有利于提高用户与多联机空调系统之间的交互效率。
图14为根据一些实施例的又一种终端设备的管理界面示意图。
在一些实施例中,控制器50还被配置为:在检测到多联机空调系统中存在膨胀阀故障后,通过通信器向终端设备300发送代表多联机空调系统存在故障的指令。
如图14所示,管理界面301还被配置为:在终端设备300接收到代表多联机空调系统存在故障的指令后,显示“检测到多联机空调系统存在膨胀阀故障,是否立即进行故障定位?”的提示信息,以提示用户选择是否开启故障定位功能。在此情况下,若用户选择点击“确定”按钮,则代表用户选择立即进行故障定位。终端设备300响应于用户的确定指令,将确定指令(即故障定位指令)发送至控制器50。控制器50还被配置为在接收到故障定位指令后,开启故障定位模式。若用户选择点击“取消”按钮, 则代表用户选择暂不进行故障定位。
在一些实施例中,如图14所示,管理界面301还包括第三按键305。第三按键305被配置为当受到用户的点击时,在关闭状态和打开状态之间切换。终端设备300还被配置为:当第三按键305切换至打开状态时,向控制器50发送所述故障定位指令。
图15为根据一些实施例的一种多联机空调系统的又一种控制方法的流程图。
本公开的一些实施例还提供了另一种多联机空调系统的控制方法。该另一种多联机空调系统的控制方法由控制器执行。该控制器可以是上述任一实施例中所述的控制器50,也可以是其他控制器。
如图15所示,该方法包括步骤S401至步骤S404。
在步骤S401,获取多联机空调系统的实时运行数据。
可以理解的是,当多联机空调系统的膨胀阀出现故障时,需要对多联机空调系统中的所有膨胀阀进行故障检测,以定位故障的膨胀阀。因此,通过获取多联机空调系统的实时运行数据,从而可以对膨胀阀进行故障检测及定位。
在一些实施例中,控制器还被配置为:在多联机空调系统启动后,以第一预设时长为一个周期,获取多联机空调系统的实时运行数据。这样,控制器可以周期性地对多联机空调系统进行故障检测,从而有利于提高多联机空调系统运行的稳定性和可靠性。
需要说明的是,第一预设时长是多联机空调系统在出厂时已预设在存储器中的数据,第一预设时长的数值可以根据实际使用需求进行设置,本公开对此不做限定。
在一些实施例中,多联机空调系统的实时运行数据包括室外机的运行数据和各个室内机的运行数据。
例如,室外机的运行数据包括:压缩机频率、压力值、压顶温度值、排气过热度值、化霜温度值以及环境温度值。
例如,室内机的运行数据包括:变频散热度值、液管温度值、气管温度值、回风温度值以及出风温度值。
在步骤S402,通过预设图注意力模型对实时运行数据进行故障识别,以得到故障识别结果。
需要说明的是,图注意力模型(Graph Attention Networks,GAT):是一种使用了自注意力(Self attention)机制的图神经网络模型,该网络使用类似神经网络模型里的自注意力的方式,计算图里面任一个节点相对于每个邻接节点的注意力,将该任一个节点本身的特征和注意力特征起来作为该节点的特征,在此基础上进行节点的分类等任务。
在一些实施例中,图注意力模型包括故障检测模型。故障检测模型被配置为检测多个膨胀阀中的任一个膨胀阀是否处于故障运行状态。所述故障识别结果包括所述任一个膨胀阀处于故障运行状态或正常运行状态。
因此,当控制器获取到多联机空调系统的实时运行数据后,通过将实时运行数据输入至预设图注意力模型,从而可以对多个膨胀阀进行故障识别,并得到故障识别结果。
在一些实施例中,预设图注意力模型可以为GAT模型中的故障检测模型。
在步骤S403,判断故障识别结果是否为故障运行状态,若是,则执行步骤S404,若否,则重新执行步骤S401。
可以理解的是,若控制器识别到多个膨胀阀中的任一个膨胀阀处于故障运行状态,则需要继续执行步骤S404,以对该任一个膨胀阀进行定位。若多个膨胀阀均处于正常运行状态,则不需要执行故障定位,在此情况下,控制器重新执行步骤S401。
在一些实施例中,步骤S403包括:当故障识别结果为多联机空调系统中的膨胀阀处于正常运行状态时,经过第二预设时长后,重新执行步骤S401。
需要说明的是,第二预设时长是多联机空调系统在出厂时已预设在存储器中的数据,第二预设时长的数值可以根据实际使用需求进行设置,本公开对此不做限定。
在步骤S404,通过预设图注意力模型对膨胀阀进行故障定位,以确定膨胀阀的内机序号。
在一些实施例中,图注意力模型还包括故障定位模型,所述故障定位模型被配置为定位处于故障运行状态的膨胀阀的内机序号。
例如,当故障识别结果为多联机空调系统中的膨胀阀处于故障运行状态时,将每个原始节点特征向量(将在下文进行详细介绍)输入GAT模型中的故障定位模型中,从而可以定位处于故障运行状态时 的膨胀阀的内机序号。
在一些实施例中,预设图注意力模型可以为图注意力模型中的故障定位模型。
可以理解的是,本公开的一些实施例提供的多联机空调系统的另一种控制方法,通过将获取到的多联机空调系统的实时运行数据输入至预设图注意力模型,以得到多联机空调系统中膨胀阀的故障识别结果,从而有利于提高对膨胀阀的故障检测的效率。另外,在确定膨胀阀处于故障运行状态时,通过预设图注意力模型对该膨胀阀进行定位,并获取该第一膨胀阀的内机序号,从而可以减少数据流预处理流程,有利于提高对膨胀阀的故障定位的准确性。
图16为根据一些实施例的一种多联机空调系统的图注意力模型的训练方法的流程图。
在一些实施例中,GAT模型可以通过控制器训练得到。GAT模型的训练方法如图16所示,该方法由控制器执行,且包括步骤S11至步骤S12。
在步骤S11,获取多联机空调系统的正常运行数据和故障运行数据。
需要说明的是,正常运行数据为膨胀阀处于正常运行状态时,多联机空调系统的运行数据。故障运行数据为膨胀阀处于故障运行状态时,多联机空调系统的运行数据。
例如,控制器可以将多联机空调系统的正常运行数据和故障运行数据输入至GAT模型进行训练,以使GAT模型获取膨胀阀在正常运行状态时的运行数据特征,以及膨胀阀在故障运行状态时的运行数据特征。从而,能更准确的识别多联机空调系统的实时运行数据中是否存在故障运行数据。
在一些实施例中,GAT模型的训练原理可以基于图神经网络模型(Graph neural networks,GNN)。图神经网络模型是一种连接模型,通过网络中节点之间的信息传递的方式来获取图中的依存关系,GNN通过从节点任意深度的邻居来更新该节点状态,这个状态能够表示状态信息。
在步骤S12,根据正常运行数据和故障运行数据,对初始图注意力模型进行训练,得到训练完成后的预设图注意力模型。
在一些实施例中,在控制器将正常运行数据和故障运行数据输入至初始图注意力模型中,得到训练完成后的预设图注意力模型之前,控制器还可以通过GNN模型将正常运行数据和故障运行数据转换为图结构,对该图结构进行节点聚合操作后,迭代更新GAT模型参数,最终输出膨胀阀的故障检测与定位结果。
图17为根据一些实施例的一种多联机空调系统的另一种图注意力模型的训练方法的流程图。如图17所示,该方法包括步骤S21。
在步骤S21,通过预设图神经网络模型将正常运行数据和故障运行数据转换为图结构。
在一些实施例中,在控制器根据正常运行数据和故障运行数据,对初始图注意力模型进行训练之前,控制器通过预设图神经网络模型将正常运行数据和故障运行数据转换为图结构。
例如,图结构包括原始节点特征向量和原始节点特征向量之间的连接关系。原始特征向量为正常运行数据和故障运行数据的向量表现形式。
在一些实施例中,原始节点特征向量之间的连接关系可以以边的形式展现,边以邻接矩阵的形式表示。
在一些实施例中,将两个原始节点特征向量之间的不同数据信息进行皮尔逊相关系数计算。若皮尔逊相关系数大于第二预设阈值,则两个原始节点特征向量之间以边连接,即两个原始节点特征向量之间相关;若皮尔逊相关系数小于第二预设阈值,则两个原始节点特征向量之间不以边连接,即两个原始节点特征向量之间不相关。
在一些实施例中,第二预设阈值为0.5。
例如,若皮尔逊相关系数A大于第二预设阈值,即A>0.5时,两个原始节点特征向量之间以边连接。若A<0.5,则两个原始节点特征向量之间不以边连接。
示例性的,图结构可以表示为公式(1)所示出的形式:
AM=[S1,T1],[S2,T2],[S3,T3],...,[Sn,Tn]]   公式(1)
在公式(1)中,AM为邻接矩阵,S、T为不同运行数据,n为运行数据所在位置。
在一些实施例中,在控制器将正常运行数据和故障运行数据转换为图结构后,根据图结构,控制器将所述原始节点特征向量转换为目标节点特征向量,并为所述目标节点特征向量分配注意力。
在一些实施例中,在控制器将正常运行数据和故障运行数据转换为图结构后,控制器将原始节点特征向量输入注意力层经过线性变化,得到目标节点特征向量。
在一些实施例中,可以通过自注意力机制,对目标节点特征向量分配注意力系数。如公式(2)和公式(3)所示:
x={x1,x1,...,xn}     公式(2)
x'={x'1,x'2,...,x'n}       公式(3)
在公式(2)和公式(3)中,x为原始节点特征向量,x'为目标节点特征向量。
需要说明的是,自注意力是神经网络模型中的一种重要机制,用于对输入序列中的每个元素进行自注意力计算,并得到每个元素的自注意力表示。
在一些实施例中,目标节点特征向量的范围矩阵W满足的关系和注意力系数eij线性变化的方式如公式(4)和公式(5)所示:
W∈RF′*F          公式(4)
在公式(4)和公式(5)中,R为目标节点特征向量的特征空间,F'为目标节点特征向量维度,F为原始节点特征向量的维度,也即目标节点特征向量i对目标节点特征向量j的影响力系数,a表示单层前馈神经网络,输出为一个数值。
在一些实施例中,当注意力系数确定后,根据注意力系数,对目标节点特征向量进行聚合操作。
例如,将与目标节点特征向量Vi周边有关联的节点{Va,Vb,...,Vn}加权至Vi,作为一次目标节点特征向量的聚合。
需要说明的是,在本公开实施例中,可以对所有目标节点特征向量进行聚合操作,聚合方式如公式(6)所示:
Mi=G({wj*xj,j∈Ni})    公式(6)
在公式(6)中,G()为聚合函数,wj为权重,xj为目标节点特征向量,Ni为与目标节点特征向量相连的节点特征向量集。
在一些实施例中,当目标节点特征向量的聚合操作完成后,通过预设图神经网络模型的迭代,对预设图注意力模型进行更新,控制器确定原始节点特征向量是否达到预设收敛条件。
在一些实施例中,当控制器确定原始节点特征向量未达到预设收敛条件时,更新注意力系数,得到原始节点特征向量间的影响力关系。
在一些实施例中,注意力系数的更新方式如公式(7)所示:
Lt+1=Fw(Lt,x)        公式(7)
在公式(7)中,L为原始节点特征向量,Fw为压缩映射。
在一些实施例中,当控制器确定原始节点特征向量未达到预设收敛条件时,停止对初始图注意力模型的训练,以得到训练完成后的预设图注意力模型。
在一些实施例中,原始节点特征向量x的状态向量是否达到收敛条件的判断方式如公式(8)所示:
||xt-xt-1|<εF        公式(8)
在一些实施例中,当GAT模型停止更新后,控制器将多联机空调系统的实时运行数据输入至GAT模型,输出实时结果。对比实时结果与模型结果中的膨胀阀的运行状态和内机序号,确认GAT模型是否训练成功。
例如,若实时结果中的膨胀阀的运行状态与模型结果中的膨胀阀的运行状态相匹配,且实时结果中的内机序号与模型结果中的内机序号相匹配,确认GAT模型训练成功。
例如,若实时结果中的膨胀阀的运行状态与模型结果中的膨胀阀的运行状态相匹配,但实时结果中的内机序号与模型结果中的内机序号不匹配,对GAT模型进行参数更新。
例如,若实时结果中的膨胀阀的运行状态与模型结果中的膨胀阀的运行状态不匹配,且实时结果中的内机序号与模型结果中的内机序号也不匹配,对GAT模型进行参数更新。
在一些实施例中,当GAT模型停止更新后,将多联机空调系统的实时运行数据输入GAT模型中的故障检测模型,经反向传播参数更新后,得到故障识别结果。
在一些实施例中,控制器通过多个阶段的多联机空调系统的实际运行数据及状态和其他机组的实际运行数据及状态,来构成多联机空调系统的维护信息,从而持续更新GAT模型。
图18为根据一些实施例的一种多联机空调系统的又一种控制方法的流程图。
在一些实施例中,所述控制方法包括步骤S1至步骤S8。
在步骤S1,获取多联机空调系统的正常运行数据和故障运行数据。
需要说明的是,多联机空调系统的正常运行数据和故障运行数据所包含的内容与上述的实时运行数据一致,此处不再赘述。
例如,正常运行数据为膨胀阀处于正常运行状态时,多联机空调系统的运行数据;故障运行数据为膨胀阀处于故障运行状态时,多联机空调系统的运行数据。
在步骤S2,将正常运行数据和故障运行数据输入至初始GAT模型。
在一些实施例中,初始GAT模型通过GNN模型进行训练。GNN模型对初始GAT模型的训练方式如上述步骤S21所述,此处不再赘述。
在一些实施例中,控制器先将正常运行数据和故障运行数据输入至初始GAT模型的故障检测模型中,通过GNN模型将正常运行数据和故障运行数据转换为图结构,根据图结构确定多联机空调系统的膨胀阀是否处于故障运行状态。
例如,当控制器确定多联机空调系统的膨胀阀处于故障运行状态时,控制器将正常运行数据和故障运行数据输入至初始GAT模型的故障定位模型中,定位处于故障运行状态下的膨胀阀的内机序号。
在步骤S3,判断初始GAT模型输出的结果是否满足预设条件,若是,执行步骤S5,若否,则执行步骤S4。
例如,所述预设条件包括:通过初始GAT模型输出的膨胀阀故障状态和处于故障运行状态下的膨胀阀的内机序号均正确。
在步骤S4,更新初始GAT模型的参数。
例如,当通过初始GAT模型输出的膨胀阀故障状态不正确,或,通过GAT模型输出的膨胀阀故障状态正确但处于故障运行状态下的膨胀阀的内机序号不正确时,控制器更新初始GAT模型的参数。
在步骤S5,确定初始GAT模型成功训练为预设GAT模型。
在步骤S6,获取多联机空调的实时运行数据,并将实时运行数据输入至预设GAT模型。
在一些实施例中,控制器先将实时运行数据输入至预设GAT模型的故障检测模型中,通过GNN模型将实时运行数据转换为图结构,根据图结构确定多联机空调系统的膨胀阀是否处于故障运行状态。
例如,当控制器确定多联机空调系统的膨胀阀处于故障运行状态时,控制器将实时运行数据输入至预设GAT模型的故障定位模型中,定位处于故障运行状态下的膨胀阀的内机序号。
在步骤S7,判断初始GAT模型输出的结果是否满足预设条件,若是,执行步骤S8,若否,则执行步骤S4。
在步骤S8,控制预设GAT模型根据多联机空调的实时运行数据,进行学习和改进。
例如,当通过初始GAT模型输出的膨胀阀故障状态不正确,或,通过GAT模型输出的膨胀阀故障状态正确但处于故障运行状态下的膨胀阀的内机序号均不正确时,控制器控制预设GAT模型根据多联机空调的实时运行数据,进行学习和改进。
本领域的技术人员将会理解,本发明的公开范围不限于上述具体实施例,并且可以在不脱离本公开的精神的情况下对实施例的某些要素进行修改和替换。本公开的范围受所附权利要求的限制。

Claims (20)

  1. 一种多联机空调系统,包括:
    室外机,包括压缩机和室外换热器;所述压缩机连接所述室外换热器;
    至少一个室内机,所述至少一个室内机中的任一个室内机包括室内换热器;
    膨胀阀,所述室内换热器通过所述膨胀阀连接所述室外换热器;其中,冷媒在所述压缩机、所述室外换热器、所述膨胀阀和所述室内换热器中循环流动,以形成冷媒回路;以及
    控制器,被配置为:
    在确定所述多联机空调系统发生故障的情况下,根据所述多联机空调系统的特征数据和多个基于支持向量机的故障识别模型,确定多个故障识别结果;其中,所述多个故障识别模型中的任一个故障识别模型被配置为识别一种故障类型,且所述任一个故障识别模型输出的故障识别结果被配置为指示所述多联机空调系统发生所述任一个故障识别模型对应的所述故障类型的概率;和
    将所述多个故障识别结果中的最大概率的故障识别结果对应的故障类型作为所述多联机空调系统的目标故障类型。
  2. 根据权利要求1所述的多联机空调系统,其中,所述控制器还被配置为:
    在将所述多个故障识别结果中的所述最大概率的故障识别结果对应的故障类型作为所述多联机空调系统的所述目标故障类型之后,根据所述多联机空调系统的特征数据和与所述目标故障类型对应的故障等级识别模型,确定故障等级识别结果;以及
    当所述故障等级识别结果指示的故障等级在预设故障等级以上时,发出告警信息;其中,所述告警信息包括所述目标故障类型,所述告警信息被配置为提示对所述多联机空调系统进行检修。
  3. 根据权利要求2所述的多联机空调系统,其中,所述控制器还被配置为:
    在确定所述多联机空调系统发生故障之前,获取所述多联机空调系统的运行数据;
    基于最大信息系数法对所述多联机空调系统的运行数据进行关联性分析,从所述多联机空调系统的运行数据中提取出所述多联机空调系统的特征数据;以及
    基于所述多联机空调系统的特征数据,确定所述多联机空调系统是否发生故障。
  4. 根据权利要求3所述的多联机空调系统,其中,所述基于所述多联机空调系统的特征数据,确定所述多联机空调系统是否发生故障,包括:
    根据所述多联机空调系统的特征数据和故障诊断模型,确定故障诊断结果;其中,所述故障诊断结果被配置为指示所述多联机空调系统是否发生故障;以及
    在所述故障诊断结果为是的情况下,确定所述多联机空调系统发生故障。
  5. 根据权利要求3所述的多联机空调系统,其中,所述获取所述多联机空调系统的运行数据,包括:
    获取所述多联机空调系统的原始运行数据;以及
    对所述多联机空调系统的原始运行数据进行预处理,以得到所述多联机空调系统的运行数据;其中,所述预处理包括异常值剔除处理和平滑处理。
  6. 根据权利要求1至5中任一项所述的多联机空调系统,还包括液管和气管,所述室外机通过所述液管和所述气管连接所述至少一个室内机;
    其中,所述多联机空调系统的特征数据包括:所述压缩机的运行频率、所述压缩机的排气压力值、所述压缩机的吸气压力值、所述压缩机的吸气温度值、所述压缩机的排气温度值、所述压缩机的排气过热度、所述压缩机的吸气过热度、室外风扇档位、所述膨胀阀的开度、所述室内机的出风温度、所述室内机的回风温度、所述气管的温度值以及所述液管的温度值中的至少一者。
  7. 一种多联机空调系统的控制方法,其中,所述多联机空调系统包括室外机、至少一个室内机和膨胀阀;所述室外机包括压缩机和室外换热器;所述至少一个室内机中的任一个室内机包括室内换热器;其中,冷媒在所述压缩机、所述室外换热器、所述膨胀阀和所述室内换热器中循环流动,以形成冷媒回路;
    所述方法包括:
    在确定所述多联机空调系统发生故障的情况下,根据所述多联机空调系统的特征数据和多个基于支持向量机的故障识别模型,确定多个故障识别结果;其中,所述多个故障识别模型中的任一个故障识别模型被配置为识别一种故障类型,且所述任一个故障识别模型输出的故障识别结果被配置为指示所述多联机空调系统发生所述任一个故障识别模型对应的所述故障类型的概率;以及
    将所述多个故障识别结果中的最大概率的故障识别结果对应的故障类型作为所述多联机空调系统的目标故障类型。
  8. 根据权利要求7所述的方法,其中,所述方法还包括:
    在将所述多个故障识别结果中的所述最大概率的故障识别结果对应的故障类型作为所述多联机空调系统的所述目标故障类型之后,根据所述多联机空调系统的特征数据和与所述目标故障类型对应的故障等级识别模型,确定故障等级识别结果;以及
    当所述故障等级识别结果指示的故障等级在预设故障等级以上时,发出告警信息;其中,所述告警信息包括所述目标故障类型,所述告警信息被配置为提示对所述多联机空调系统进行检修。
  9. 根据权利要求8所述的方法,其中,所述方法还包括:
    在确定所述多联机空调系统发生故障之前,获取所述多联机空调系统的运行数据;
    基于最大信息系数法对所述多联机空调系统的运行数据进行关联性分析,从所述多联机空调系统的运行数据中提取出所述多联机空调系统的特征数据;以及
    基于所述多联机空调系统的特征数据,确定所述多联机空调系统是否发生故障。
  10. 根据权利要求9所述的方法,其中,所述基于所述多联机空调系统的特征数据,确定所述多联机空调系统是否发生故障,包括:
    根据所述多联机空调系统的特征数据和故障诊断模型,确定故障诊断结果;其中,所述故障诊断结果被配置为指示所述多联机空调系统是否发生故障;以及
    在所述故障诊断结果为是的情况下,确定所述多联机空调系统发生故障。
  11. 根据权利要求9所述的方法,其中,所述获取所述多联机空调系统的运行数据,包括:
    获取所述多联机空调系统的原始运行数据;以及
    对所述多联机空调系统的原始运行数据进行预处理,以得到所述多联机空调系统的运行数据;其中,所述预处理包括异常值剔除处理和平滑处理。
  12. 一种多联机空调系统,包括:
    室外机;
    至少一个室内机,与所述室外机相连接;
    至少一个膨胀阀,与所述至少一个室内机相对应;所述至少一个膨胀阀中的任一个膨胀阀设置在对应的室内机与所述室外机之间的管路上;以及
    控制器,被配置为:
    获取所述多联机空调系统的实时运行数据;
    通过预设图注意力模型对所述实时运行数据进行故障识别,以得到故障识别结果;其中,所述故障识别结果包括所述多联机空调系统中的所述任一个膨胀阀处于故障运行状态或正常运行状态;以及
    在所述任一个膨胀阀处于故障运行状态的情况下,通过所述预设图注意力模型对所述任一个膨胀阀进行故障定位,以确定所述任一个膨胀阀的内机序号。
  13. 根据权利要求12所述的多联机空调系统,其中,所述控制器还被配置为:
    获取所述多联机空调系统的正常运行数据和故障运行数据;其中,所述正常运行数据为所述膨胀阀处于正常运行状态时,所述多联机空调系统的运行数据;所述故障运行数据为所述膨胀阀处于故障运行状态时,所述多联机空调系统的运行数据;以及
    根据所述正常运行数据和所述故障运行数据,对初始图注意力模型进行训练,以得到训练完成后的预设图注意力模型。
  14. 根据权利要求13所述的多联机空调系统,其中,所述控制器还被配置为:
    在根据所述正常运行数据和所述故障运行数据,对所述初始图注意力模型进行训练之前,通过预设图神经网络模型将所述正常运行数据和所述故障运行数据转换为图结构;其中,所述图结构包括多个原始节点特征向量和所述多个原始节点特征向量之间的连接关系;所述原始节点特征向量为所述正常运行数据和所述故障运行数据的向量表现形式。
  15. 根据权利要求14所述的多联机空调系统,其中,所述控制器还被配置为:将所述多个原始节点特征向量中的两个原始节点特征向量之间的不同数据信息进行皮尔逊相关系数计算;
    其中,在所述皮尔逊相关系数大于预设阈值的情况下,所述两个原始节点特征向量之间以边连接,且所述两个原始节点特征向量之间相关;在所述皮尔逊相关系数小于所述预设阈值的情况下,所述两个 所述原始节点特征向量之间不以边连接,且所述两个原始节点特征向量之间不相关。
  16. 根据权利要求14所述的多联机空调系统,其中,所述根据所述正常运行数据和所述故障运行数据,对所述初始图注意力模型进行训练,包括:
    将所述原始节点特征向量转换为目标节点特征向量,并为所述目标节点特征向量分配注意力系数;
    根据所述注意力系数,对所述目标节点特征向量进行聚合操作;
    通过所述预设图神经网络模型的迭代,对所述预设图注意力模型进行更新,以确定所述原始节点特征向量是否达到预设收敛条件;
    在所述原始节点特征向量未达到所述预设收敛条件的情况下,更新所述注意力系数;以及
    在所述原始节点特征向量达到所述预设收敛条件的情况下,停止对所述初始图注意力模型的训练,以得到训练完成后的所述预设图注意力模型。
  17. 根据权利要求12至16中任一项所述的多联机空调系统,其中,所述实时运行数据包括室外机的实时运行数据和室内机的实时运行数据;
    所述室外机的运行实时数据包括压缩机频率、压力值、压顶温度值、排气过热度值、化霜温度值以及环境温度值;
    所述室内机的实时运行数据包括变频散热度值、液管温度值、气管温度值、回风温度值以及出风温度值。
  18. 一种多联机空调系统的控制方法,其中,所述多联机空调系统包括室外机、至少一个室内机和至少一个膨胀阀;所述至少一个膨胀阀与所述至少一个室内机相对应;所述至少一个膨胀阀中的任一个膨胀阀设置在对应的室内机与所述室外机之间的管路上;
    所述方法包括:
    获取所述多联机空调系统的实时运行数据;
    通过预设图注意力模型对所述实时运行数据进行故障识别,以得到故障识别结果;其中,所述故障识别结果包括所述多联机空调系统中的所述任一个膨胀阀处于故障运行状态或正常运行状态;以及
    在所述任一个膨胀阀处于故障运行状态的情况下,通过所述预设图注意力模型对所述任一个膨胀阀进行故障定位,以确定所述任一个膨胀阀的内机序号。
  19. 根据权利要求18所述的方法,还包括:
    获取所述多联机空调系统的正常运行数据和故障运行数据;其中,所述正常运行数据为所述膨胀阀处于正常运行状态时,所述多联机空调系统的运行数据;所述故障运行数据为所述膨胀阀处于故障运行状态时,所述多联机空调系统的运行数据;以及
    根据所述正常运行数据和所述故障运行数据,对初始图注意力模型进行训练,以得到训练完成后的预设图注意力模型。
  20. 根据权利要求19所述的方法,其中,所述根据所述正常运行数据和所述故障运行数据,对所述初始图注意力模型进行训练,包括:
    将所述原始节点特征向量转换为目标节点特征向量,并为所述目标节点特征向量分配注意力系数;
    根据所述注意力系数,对所述目标节点特征向量进行聚合操作;
    通过所述预设图神经网络模型的迭代,对所述预设图注意力模型进行更新,以确定所述原始节点特征向量是否达到预设收敛条件;
    在所述原始节点特征向量未达到所述预设收敛条件的情况下,更新所述注意力系数;以及
    在所述原始节点特征向量达到所述预设收敛条件的情况下,停止对所述初始图注意力模型的训练,以得到训练完成后的所述预设图注意力模型。
PCT/CN2023/134965 2022-12-02 2023-11-29 多联机空调系统及其控制方法 WO2024114675A1 (zh)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN202211542019.X 2022-12-02
CN202211542019.XA CN115950045A (zh) 2022-12-02 2022-12-02 一种多联机空调系统及控制方法
CN202310432299.7A CN116697523A (zh) 2023-04-20 2023-04-20 一种多联机空调系统及故障检测方法
CN202310432299.7 2023-04-20

Publications (1)

Publication Number Publication Date
WO2024114675A1 true WO2024114675A1 (zh) 2024-06-06

Family

ID=91323015

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/134965 WO2024114675A1 (zh) 2022-12-02 2023-11-29 多联机空调系统及其控制方法

Country Status (1)

Country Link
WO (1) WO2024114675A1 (zh)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3002653A1 (fr) * 2014-09-30 2016-04-06 Compagnie Industrielle D'Applications Thermiques Dispositif et procédé de surveillance du fonctionnement d'un système cvca, ensemble comprenant un système cvca et un tel dispositif de surveillance, et produit programme d'ordinateur associé
US20190196460A1 (en) * 2016-09-16 2019-06-27 Siemens Aktiengesellschaft Failure models for embedded analytics and diagnostic/prognostic reasoning
CN112766327A (zh) * 2021-01-05 2021-05-07 格力电器(武汉)有限公司 空调故障预测方法、电子设备和储存介质
CN113203589A (zh) * 2021-04-29 2021-08-03 华中科技大学 一种用于多联机空调系统的分布式故障诊断方法及系统
CN114221857A (zh) * 2020-09-04 2022-03-22 中兴通讯股份有限公司 故障定位的方法、电子设备及存储介质
CN114754413A (zh) * 2022-04-11 2022-07-15 青岛海信日立空调系统有限公司 一种多联机空调系统及故障定位方法
CN115950045A (zh) * 2022-12-02 2023-04-11 青岛海信日立空调系统有限公司 一种多联机空调系统及控制方法
CN116697523A (zh) * 2023-04-20 2023-09-05 青岛海信日立空调系统有限公司 一种多联机空调系统及故障检测方法

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3002653A1 (fr) * 2014-09-30 2016-04-06 Compagnie Industrielle D'Applications Thermiques Dispositif et procédé de surveillance du fonctionnement d'un système cvca, ensemble comprenant un système cvca et un tel dispositif de surveillance, et produit programme d'ordinateur associé
US20190196460A1 (en) * 2016-09-16 2019-06-27 Siemens Aktiengesellschaft Failure models for embedded analytics and diagnostic/prognostic reasoning
CN114221857A (zh) * 2020-09-04 2022-03-22 中兴通讯股份有限公司 故障定位的方法、电子设备及存储介质
CN112766327A (zh) * 2021-01-05 2021-05-07 格力电器(武汉)有限公司 空调故障预测方法、电子设备和储存介质
CN113203589A (zh) * 2021-04-29 2021-08-03 华中科技大学 一种用于多联机空调系统的分布式故障诊断方法及系统
CN114754413A (zh) * 2022-04-11 2022-07-15 青岛海信日立空调系统有限公司 一种多联机空调系统及故障定位方法
CN115950045A (zh) * 2022-12-02 2023-04-11 青岛海信日立空调系统有限公司 一种多联机空调系统及控制方法
CN116697523A (zh) * 2023-04-20 2023-09-05 青岛海信日立空调系统有限公司 一种多联机空调系统及故障检测方法

Similar Documents

Publication Publication Date Title
Rogers et al. A review of fault detection and diagnosis methods for residential air conditioning systems
Guo et al. An expert rule-based fault diagnosis strategy for variable refrigerant flow air conditioning systems
Kim et al. A review of fault detection and diagnostics methods for building systems
Wang et al. Fault detection and diagnosis of chillers using Bayesian network merged distance rejection and multi-source non-sensor information
Guo et al. Optimized neural network-based fault diagnosis strategy for VRF system in heating mode using data mining
Hu et al. A machine learning bayesian network for refrigerant charge faults of variable refrigerant flow air conditioning system
US7444251B2 (en) Detecting and diagnosing faults in HVAC equipment
JP6359423B2 (ja) 空調システムの制御装置、空調システム、及び空調システムの制御装置の異常判定方法
Liu et al. A refrigerant charge fault detection method for variable refrigerant flow (VRF) air-conditioning systems
Kim et al. Development and evaluation of virtual refrigerant mass flow sensors for fault detection and diagnostics
CN114754413B (zh) 一种多联机空调系统及故障定位方法
AU2018423601B2 (en) Failure diagnosis system
CN113654182A (zh) 检测冷媒泄漏的方法和计算机可读存储介质以及空调器
Guo et al. Modularized PCA method combined with expert-based multivariate decoupling for FDD in VRF systems including indoor unit faults
WO2024119723A1 (zh) 空调设备及其故障检测方法
JP2005301582A (ja) プロセス管理装置
KR20070017269A (ko) 멀티 에어컨시스템의 배관점검운전방법 및 배관점검방법
CN114877488A (zh) 一种空调系统及其脏堵确定方法
WO2024114675A1 (zh) 多联机空调系统及其控制方法
AU2018404247B2 (en) State analyzer system and state analysis device
CN115950045A (zh) 一种多联机空调系统及控制方法
CN116697523A (zh) 一种多联机空调系统及故障检测方法
CN115095953B (zh) 一种故障诊断模型的训练方法及装置
Ejenakevwe et al. Review of fault detection and diagnosis studies on residential HVAC systems
CN110926544B (zh) 一种换热机组用检测设备及其在线自动检测方法