WO2023197711A1 - 多联机空调系统、故障定位方法及故障诊断模型训练方法 - Google Patents

多联机空调系统、故障定位方法及故障诊断模型训练方法 Download PDF

Info

Publication number
WO2023197711A1
WO2023197711A1 PCT/CN2023/071431 CN2023071431W WO2023197711A1 WO 2023197711 A1 WO2023197711 A1 WO 2023197711A1 CN 2023071431 W CN2023071431 W CN 2023071431W WO 2023197711 A1 WO2023197711 A1 WO 2023197711A1
Authority
WO
WIPO (PCT)
Prior art keywords
conditioning system
air conditioning
electronic expansion
fault
expansion valve
Prior art date
Application number
PCT/CN2023/071431
Other languages
English (en)
French (fr)
Inventor
石靖峰
任兆亭
张佳舒
阮岱玮
夏兴祥
盛凯
陈焕新
苟伟
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 CN202210386517.3A external-priority patent/CN114754413B/zh
Priority claimed from CN202210682549.8A external-priority patent/CN115095953B/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 WO2023197711A1 publication Critical patent/WO2023197711A1/zh

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F1/00—Room units for air-conditioning, e.g. separate or self-contained units or units receiving primary air from a central station
    • F24F1/0003—Room units for air-conditioning, e.g. separate or self-contained units or units receiving primary air from a central station characterised by a split arrangement, wherein parts of the air-conditioning system, e.g. evaporator and condenser, are in separately located units
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
    • F24F11/32—Responding to malfunctions or emergencies
    • F24F11/38—Failure diagnosis
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/50—Control or safety arrangements characterised by user interfaces or communication
    • F24F11/54—Control or safety arrangements characterised by user interfaces or communication using one central controller connected to several sub-controllers
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/70—Control systems characterised by their outputs; Constructional details thereof
    • F24F11/80—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air
    • F24F11/83—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling the supply of heat-exchange fluids to heat-exchangers
    • F24F11/84—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling the supply of heat-exchange fluids to heat-exchangers using valves
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/89—Arrangement or mounting of control or safety devices
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/10—Temperature
    • F24F2110/12—Temperature of the outside air
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/50—Air quality properties
    • F24F2110/64—Airborne particle content

Definitions

  • the present disclosure relates to the field of air conditioning technology, and in particular to a multi-connected air conditioning system, a fault location method and a fault diagnosis model training method.
  • the multi-split air conditioning system includes an outdoor unit and multiple indoor units, thereby regulating the temperatures of multiple indoor spaces where the multiple indoor units are located. Since there are a large number of components in the multi-split air conditioning system, when a fault occurs in the multi-split air conditioning system, it is difficult to quickly locate the faulty component, resulting in low fault location efficiency of the multi-split air conditioning system.
  • a multi-split air conditioning system includes an outdoor unit, multiple indoor units, multiple electronic expansion valves, and a controller.
  • Each indoor unit among the plurality of indoor units is connected with a gas pipe and a liquid pipe, so as to communicate with the outdoor unit through the gas pipe and the liquid pipe.
  • Multiple electronic expansion valves correspond to multiple indoor units.
  • a plurality of electronic expansion valves are respectively provided in liquid pipes connected to corresponding indoor units, and are configured to control the refrigerant output or refrigerant input of the corresponding indoor units.
  • the controller is configured to: acquire characteristic data of each of the plurality of indoor units in the event of an electronic expansion valve failure in the multi-split air conditioning system.
  • the characteristic data of each indoor unit includes the temperature difference between the temperature value of the liquid pipe correspondingly connected to the indoor unit and the temperature value of the air pipe correspondingly connected to the indoor unit.
  • an abnormal indoor unit among the plurality of indoor units is determined.
  • the electronic expansion valve corresponding to the abnormal indoor unit is determined to be the faulty electronic expansion valve.
  • the multi-split air conditioning system includes an outdoor unit, multiple indoor units and multiple electronic expansion valves.
  • Each indoor unit among the plurality of indoor units is connected with a gas pipe and a liquid pipe, so as to communicate with the outdoor unit through the gas pipe and the liquid pipe.
  • Multiple electronic expansion valves correspond to multiple indoor units.
  • a plurality of electronic expansion valves are respectively provided in liquid pipes connected to corresponding indoor units, and are configured to control the refrigerant output or refrigerant input of the corresponding indoor units.
  • the method includes: when an electronic expansion valve failure occurs in a multi-split air conditioning system, obtaining characteristic data of each indoor unit in a plurality of indoor units.
  • the characteristic data of each indoor unit includes the temperature difference between the temperature value of the liquid pipe correspondingly connected to the indoor unit and the temperature value of the air pipe correspondingly connected to the indoor unit.
  • an abnormal indoor unit among the plurality of indoor units is determined.
  • the electronic expansion valve corresponding to the abnormal indoor unit is determined to be the faulty electronic expansion valve.
  • some embodiments of the present disclosure provide a fault diagnosis model training method for a multi-connected air conditioning system.
  • the training method includes: obtaining normal values and fault values of multiple operating data of the first multi-connected air conditioning system. Based on the normal values and fault values of the plurality of operating data of the first multi-split air conditioning system, a first characteristic offset space of the first multi-split air conditioning system is determined.
  • the first characteristic offset space includes a difference between a fault value and a normal value of each operating data of the plurality of operating data of the first multi-connected air conditioning system.
  • the first feature offset space is corrected to obtain the second multi-connected air conditioning system.
  • the second characteristic of the air conditioning system is the offset space.
  • the fault values of the plurality of operating data of the second multi-connected air conditioning system are determined.
  • the fault diagnosis model is trained based on the normal values and fault values of multiple operating data of the second multi-split air conditioning system.
  • Figure 1 is a structural diagram of a multi-split air conditioning system according to some embodiments
  • Figure 2 is another structural diagram of a multi-split air conditioning system according to some embodiments.
  • Figure 3 is a block diagram of a controller according to some embodiments.
  • Figure 4 is a diagram of the interaction between the controller and the terminal device according to some embodiments.
  • Figure 5 is an interface diagram of a terminal device according to some embodiments.
  • Figure 6 is a flow chart of a fault location method of a multi-split air conditioning system according to some embodiments
  • Figure 7 is another interface diagram of a terminal device according to some embodiments.
  • Figure 8 is another interface diagram of a terminal device according to some embodiments.
  • Figure 9 is a location diagram of a first temperature sensor and a second temperature sensor according to some embodiments.
  • Figure 10 is another flow chart of a fault location method of a multi-split air conditioning system according to some embodiments.
  • Figure 11 is another flowchart of a fault location method of a multi-split air conditioning system according to some embodiments.
  • Figure 12 is another interface diagram of a terminal device according to some embodiments.
  • Figure 13 is a flow chart of a fault diagnosis model training method for a multi-split air conditioning system according to some embodiments
  • Figure 14 is another flowchart of a fault diagnosis model training method for a multi-split air conditioning system according to some embodiments
  • Figure 15 is a structural diagram of a fault diagnosis model according to some embodiments.
  • Figure 16 is another flowchart of a fault diagnosis model training method for a multi-split air conditioning system according to some embodiments
  • Figure 17 is another flowchart of a fault diagnosis model training method for a multi-split air conditioning system according to some embodiments.
  • Figure 18 is a structural diagram of an autoencoding model according to some embodiments.
  • first and second are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of indicated technical features. Therefore, features defined as “first” and “second” may explicitly or implicitly include one or more of these features. In the description of the embodiments of the present disclosure, unless otherwise specified, "plurality" means two or more.
  • connection should be understood in a broad sense.
  • connection can be a fixed connection, a detachable connection, or an integrated connection; it can be a direct connection or an indirect connection through an intermediate medium.
  • coupled indicates, for example, that two or more components are in direct physical or electrical contact.
  • coupled or “communicatively coupled” may also refer to two or more components that are not in direct contact with each other but still cooperate or interact with each other.
  • the embodiments disclosed herein are not necessarily limited by the content herein.
  • a and/or B includes the following three combinations: A only, B only, and a combination of A and B.
  • the multi-split air conditioning system 10 includes an outdoor unit 11, a plurality of electronic expansion valves 12, a plurality of indoor units 13 and a controller 14 (not shown in Figure 1).
  • the outdoor unit 11 may be, for example, a device in the multi-split air conditioning system 10 installed on the outside of a wall or on a roof of a house.
  • the outdoor unit 11 is mainly used to compress the refrigerant and drive the refrigerant to circulate in the multi-split air conditioning system 10 .
  • Refrigerant is a substance that easily absorbs heat and becomes a gas, and also releases heat and becomes a liquid.
  • the indoor unit 13 may be, for example, a device installed indoors in the multi-split air conditioning system 10 .
  • the indoor unit 13 is mainly used to transmit cold air or hot air to the indoor space where the indoor unit 13 is located, so as to adjust the temperature of the indoor space.
  • each indoor unit among the plurality of indoor units 13 is connected with an air pipe 15 and a liquid pipe 16 correspondingly, so as to communicate with the outdoor unit 11 through the air pipe 15 and the liquid pipe 16 .
  • the gas pipe 15 is configured to transmit gaseous refrigerant or two-phase refrigerant (a refrigerant in which gaseous and liquid phases coexist) between the outdoor unit 11 and the indoor unit 13
  • the liquid pipe 16 is configured to transmit liquid between the outdoor unit 11 and the indoor unit 13 Refrigerant or two-phase refrigerant.
  • the air pipe 15 and the liquid pipe 16 may be collectively referred to as a pipe.
  • the plurality of electronic expansion valves 12 correspond to the plurality of indoor units 13 .
  • the plurality of electronic expansion valves 12 are respectively provided in the liquid pipes 16 connected to the corresponding indoor units 13, and are configured to control the refrigerant output amount or the refrigerant input amount of the corresponding indoor units 13.
  • the plurality of electronic expansion valves 12 may be provided independently of the plurality of indoor units 13 (as shown in FIG. 1 ), or may be provided subordinate to the plurality of indoor units 13. In subsequent embodiments, a plurality of electronic expansion valves 12 are provided independently of a plurality of indoor units 13 as an example for illustrative description.
  • the outdoor unit 11 includes a compressor 111 , an outdoor heat exchanger 112 , a gas-liquid separator 113 , a four-way valve 114 and an outdoor fan 115 .
  • the exhaust port of the compressor 111 is connected to the D end of the four-way valve 114, and the suction port of the compressor 111 is connected to the exhaust port of the gas-liquid separator 113.
  • the suction port of the gas-liquid separator 113 is connected to the S end of the four-way valve 114.
  • the C end of the four-way valve 114 is connected to the first end of the outdoor heat exchanger 112 , and the E end of the four-way valve 114 is connected to each air pipe 15 .
  • the second end of the outdoor heat exchanger 112 is connected to each liquid pipe 16 .
  • each of the plurality of indoor units 13 includes an indoor heat exchanger 131 , an indoor fan 132 , an air outlet 133 and a return air outlet 134 .
  • the first end of the indoor heat exchanger 131 is connected to the corresponding air pipe 15
  • the second end of the indoor heat exchanger 131 is connected to the corresponding liquid pipe 16 .
  • the air outlet 133 and the return air outlet 134 are connected to the indoor heat exchanger 131 through the air outlet duct and the return air duct respectively.
  • the structure shown in FIG. 1 is an exemplary structure of the multi-split air conditioning system 10
  • the multi-split air conditioning system 10 may include more, fewer, or different components than those shown in FIG. 1 .
  • the outdoor unit 11 may further include an outdoor fan motor for driving the outdoor fan 115 to operate
  • the indoor unit 13 may further include a display and an indoor fan motor for driving the indoor fan 132 to operate.
  • the display may be configured to display the temperature of the indoor space where the indoor unit 13 is located, and/or be configured to display the working status of the multi-split air conditioning system 10 , etc.
  • the controller 14 is coupled to the compressor 111 , the four-way valve 114 and the outdoor fan 115 in the outdoor unit 11 , to a plurality of electronic expansion valves 12 , and to a plurality of electronic expansion valves 12 .
  • the indoor fan 132 in the indoor unit 13 is coupled.
  • the controller 14 is configured to control the operating status of each component coupled to the controller 14 .
  • the controller 14 is also coupled with multiple temperature sensors and multiple pressure sensors to obtain temperature values and pressure values of multiple components in the multi-connected air conditioning system 10 .
  • the arrangement manner of the plurality of temperature sensors and the plurality of pressure sensors will be described in subsequent embodiments.
  • the controller 14 is also coupled to the communicator 109 to establish a communication connection with other devices (such as terminal devices) through the communicator 109 to send and receive communication signals.
  • the communicator 109 may include a radio frequency (Radio Frequency, RF) device, a cellular device, a wireless network communication technology (Wi-Fi) device, a global positioning system (Global Positioning System, GPS) device, etc.
  • RF Radio Frequency
  • Wi-Fi wireless network communication technology
  • GPS Global Positioning System
  • the controller 14 refers to a device that can generate an operation control signal according to the instruction operation code and the timing signal, thereby instructing the multi-split air conditioning system 10 to execute the control instruction.
  • the controller 14 can be a central processing unit (Central Processing Unit, CPU), a general-purpose processor, a network processor (Network Processor, NP), a digital signal processor (Digital Signal Processing, DSP), a microprocessor, Microcontroller, Programmable Logic Device (PLD) or any combination thereof.
  • the controller 14 may also be other devices with processing functions, such as circuits, devices or software modules, which are not limited in the embodiments of the present disclosure.
  • the controller 14 includes an outdoor controller 141 and an indoor controller 142 .
  • the outdoor controller 141 includes a first memory 1411 and is configured to control the outdoor unit 11 to perform relevant operations;
  • the indoor controller 142 includes a second memory 1421 and is configured to control a plurality of indoor units 13 and a plurality of electronic expansion valves 12 to perform operations.
  • the outdoor controller 141 and the indoor controller 142 may be attached to the outdoor unit 11 and the indoor unit 13 respectively, or may be installed independently of the outdoor unit 11 and the indoor unit 13 .
  • the structure of the controller 14 shown in FIG. 3 is an exemplary structure of the controller 14.
  • the outdoor controller 141 and the indoor controller 142 can also be integrated into one controller.
  • the first memory 1411 and the second memory 1421 may also be integrated into one memory.
  • the first memory 1411 and the second memory 1421 are configured to store application programs and data, and the outdoor controller 141 and the indoor controller 142 respectively execute the applications stored in the first memory 1411 and the second memory 1421.
  • the programs and data execute various functions and data processing of the multi-split air conditioning system 10 .
  • the first memory 1411 and the second memory 1421 may include high-speed random access memory, and may also include non-volatile memory.
  • the first memory 1411 and the second memory 1421 are, for example, disk storage devices, flash memory devices, or the like.
  • the user can control the working status of the multi-split air conditioning system 10 through a device that has established a communication connection with the controller 14 .
  • a communication connection between the controller 14 and the user's terminal device 300 .
  • the communication connection can be implemented using various wired or wireless communication technologies, such as Ethernet, Universal Serial Bus (USB), FireWire, any cellular network communication technology (such as 3G/4G/5G), Bluetooth, Wi-Fi, Near Field Communication (NFC) or any other suitable communication technology.
  • the terminal device 300 may be, for example, a remote control, a mobile phone, a tablet, a personal computer (PC), a personal digital assistant (Personal Digital Assistant, PDA), a smart watch, a wearable electronic device, or augmented reality technology (Augmented Reality, AR). ) equipment, virtual reality (VR) equipment, robots, etc., Figure 4 and subsequent embodiments take the terminal device 300 as a mobile phone as an example for illustrative description. This disclosure does not limit the specific form of the terminal device 300.
  • the management interface 301 of the multi-split air conditioning system 10 is displayed on the terminal device 300 .
  • the management interface 301 includes a first button 302 for managing the working status of the multi-split air conditioning system 10 .
  • the terminal device 300 pops up the working status drop-down selection box 303 in the management interface 301.
  • the terminal device 300 sends a work instruction corresponding to the selection operation to the multi-split air conditioning system 10, so that the multi-split air conditioning system 10 works according to the user's selection. status running.
  • the above-mentioned multi-split air conditioning system 10 works in a cooling operating state to reduce the temperature of the indoor space.
  • the controller 14 controls the compressor 111 to start working, and controls the D end of the four-way valve 114 to communicate with the C end, and the S end with the E end.
  • the compressor 111 starts to compress the refrigerant, so that the refrigerant circulates in the multi-split air conditioning system 10 .
  • the compressor 111 compresses the gaseous refrigerant into a high-temperature, high-pressure gaseous refrigerant, and drives the compressed refrigerant to pass through the D end and C end of the four-way valve 114 to the first end of the outdoor heat exchanger 112, so as to Enter the outdoor heat exchanger 112.
  • the high-temperature and high-pressure gaseous refrigerant After the high-temperature and high-pressure gaseous refrigerant is liquefied into low-temperature and low-pressure liquid refrigerant in the outdoor heat exchanger 112, it passes through the second end of the outdoor heat exchanger 112, the liquid pipe 16 and the multiple electronic expansion valves 12 to reach multiple indoor exchangers.
  • the second end of the heat exchanger 131 enters the plurality of indoor heat exchangers 131 .
  • the low-temperature, low-pressure liquid refrigerant is vaporized into a gaseous refrigerant in the indoor heat exchanger 131 of the indoor unit, thereby absorbing the heat around the indoor heat exchanger 131.
  • the temperature of the gas inside the indoor unit is lowered, and the cooled gas is transported to the outside of the indoor unit through the air outlet 133 of the indoor unit, thereby achieving the effect of lowering the temperature of the indoor space.
  • the vaporized gaseous refrigerant reaches the four-way valve 114 through the first end of the indoor heat exchanger 131 and the air pipe 15, and reaches the suction port of the gas-liquid separator 113 through the E and S ends of the four-way valve 114.
  • the gaseous refrigerant may be condensed to produce liquid during the transmission from the indoor heat exchanger 131 to the gas-liquid separator 113. After the gas-liquid separator 113 separates the liquid, the gaseous refrigerant is input into the compressor 111 to realize the refrigerant. Recycling.
  • the above-mentioned multi-split air conditioning system 10 works in a heating operating state to increase the temperature of the indoor space. Different from the above refrigeration working state, in the heating working state, the controller 14 controls the D end of the four-way valve 114 to communicate with the E end, and the S end with the C end.
  • the high-temperature and high-pressure gaseous refrigerant obtained after compression processing by the compressor 111 passes through the D end and E end of the four-way valve 114 and is input from the gas pipe 15 into the plurality of indoor heat exchangers 131 .
  • the high-temperature, high-pressure gaseous refrigerant is liquefied into a low-temperature, low-pressure liquid refrigerant in the indoor heat exchanger 131 of the indoor unit, and is thereby supplied to the indoor heat exchanger 131 .
  • the low-temperature, low-pressure liquid refrigerant flows out of the indoor heat exchanger 131 from the second end of the indoor heat exchanger 131 and enters the outdoor heat exchanger 112 through a plurality of electronic expansion valves 12 and liquid pipes 16 .
  • the low-temperature, low-pressure liquid refrigerant is vaporized into gaseous refrigerant in the outdoor heat exchanger 112, and then transmitted to the gas-liquid separator 113 through the C and S ends of the four-way valve 114, and then returned to the compressor 111.
  • the outdoor fan 115 is configured to start working under the control of the controller 14 to discharge the heat generated by the liquefied refrigerant or the cold generated by the vaporized refrigerant by the outdoor heat exchanger 112
  • the outdoor unit 11; the indoor fan 132 is configured to start working under the control of the controller 14 to discharge the cold generated by the vaporized refrigerant or the heat generated by the liquefied refrigerant by the indoor heat exchanger 131 to the indoor unit 13 to regulate the indoor temperature.
  • the return air port 134 of the indoor unit 13 is configured to transport the gas outside the indoor unit 13 to the inside of the indoor unit 13, so that the gas is reduced or reduced inside the indoor unit 13 through the indoor heat exchanger 131. After the temperature is raised, it is delivered to the outside of the indoor unit 13 through the air outlet 133 . In this way, the gas in the indoor space where the indoor unit 13 is located can be circulated to cool down or heat up, thereby improving the cooling efficiency or heating efficiency of the multi-split air conditioning system 10 .
  • the outdoor heat exchanger 112 when the multi-split air conditioning system 10 is working in the cooling working state, the outdoor heat exchanger 112 can also be called a condenser, and the indoor heat exchanger 131 can also be called an evaporator; when the multi-split air conditioning system 10 is in When operating in the heating working state, the outdoor heat exchanger 112 can also be called an evaporator, and the indoor heat exchanger 131 can also be called a condenser.
  • the pressure value at the exhaust port of the compressor 111 can be called the exhaust pressure value, and can also be called the condensation pressure value or the high pressure pressure value; the pressure value at the suction port of the compressor 111 can be called the suction pressure. value, which can also be called evaporation pressure value or low pressure pressure value.
  • the electronic expansion valve 12 has the function of expanding and decompressing the refrigerant flowing through the electronic expansion valve 12, thereby regulating the flow rate of the refrigerant in the pipeline. If the opening (degree of opening) of the electronic expansion valve 12 decreases, the refrigerant flow rate passing through the electronic expansion valve 12 decreases. When the opening degree of the electronic expansion valve 12 increases, the refrigerant flow rate passing through the electronic expansion valve 12 increases. For example, if the multi-split air conditioning system 10 is in the cooling operating state, the plurality of electronic expansion valves 12 are respectively located on the refrigerant input side of the corresponding indoor unit 13. Therefore, at this time, the plurality of electronic expansion valves 12 respectively control the corresponding indoor units.
  • the inventor of the present disclosure found through research that when multiple electronic expansion valves 12 work normally, the temperature value of the liquid pipe 16 connected to any indoor unit and the temperature value of the liquid pipe 16 connected to the indoor unit.
  • the temperature difference between the temperature values of the air pipe 15 is less than a certain threshold.
  • the temperature value of the liquid pipe 16 connected to the indoor unit 13 corresponding to the faulty electronic expansion valve and the temperature value of the liquid pipe 16 connected to the indoor unit 13
  • the temperature difference between the temperature values of the air pipe 15 is greater than the above-mentioned certain threshold. Therefore, by monitoring the characteristic data of multiple indoor units 13 during operation (for example, the temperature values of the liquid pipe 16 and the gas pipe 15 connected to the same indoor unit 13), it can be determined whether the multiple electronic expansion valves 12 have malfunctioned.
  • some embodiments of the present disclosure provide a multi-split air conditioning system 10.
  • the controller 14 in the multi-split air conditioning system 10 can obtain the multi-split air conditioning system 10 when an electronic expansion valve failure occurs in the multi-split air conditioning system 10.
  • Characteristic data of multiple indoor units 13 in 10 and identify abnormal indoor units among multiple indoor units 13 based on the characteristic data, and then determine the electronic expansion valve 12 corresponding to the abnormal indoor unit as a faulty electronic expansion valve to complete Positioning of faulty electronic expansion valve.
  • the faulty electronic expansion valve can be located without the need for professional maintenance personnel to manually identify multiple electronic expansion valves 12 based on personal experience, thereby improving the maintenance of the multi-split air conditioning system. 10
  • the degree of automation of fault location is improved, and the efficiency of locating the faulty electronic expansion valve in the multi-split air conditioning system 10 is improved.
  • the controller 14 is configured to perform steps S101 to S103 described below.
  • the characteristic data of each indoor unit includes the temperature difference between the temperature value of the liquid pipe 16 correspondingly connected to the indoor unit and the temperature value of the air pipe 15 correspondingly connected to the indoor unit.
  • the above-mentioned temperature difference may be a value obtained by subtracting the temperature value of the gas pipe 15 correspondingly connected to the indoor unit from the temperature value of the liquid pipe 16 correspondingly connected to the indoor unit.
  • the temperature difference may be a value obtained by subtracting the temperature value of the liquid pipe 16 correspondingly connected to the indoor unit from the temperature value of the air pipe 15 connected to the indoor unit.
  • the user can instruct the multi-split air conditioning system 10 to turn on the fault detection function and fault locating function through a device that has established a communication connection with the controller 14, so that the controller 14 starts to detect whether an electronic expansion valve fault occurs and locate the fault. Faulty electronic expansion valve. It should be noted that the method by which the controller 14 detects whether an electronic expansion valve failure occurs will be described in subsequent embodiments.
  • the management interface 301 of the terminal device 300 includes a second button 304 for turning on or off the fault detection function of the multi-split air conditioning system 10, and a The third button 306 turns on or off the fault locating function of the multi-split air conditioning system 10 .
  • the second button 304 When the fault detection function (or fault locating function) of the multi-line air conditioning system 10 is in a closed state, the second button 304 (or the third button 306) is in the first display state 3041 (or the third display state 3061); When the fault detection function (or fault locating function) of the air conditioning system 10 is on, the second button 304 (or the third button 306) is in the second display state 3042 (or the fourth display state 3062).
  • the terminal device 300 may send an instruction to the controller 14 to instruct the controller 14 to turn on the fault detection function.
  • the controller 14 After the fault detection function is turned on, the controller 14 may send an instruction to the terminal device 300 to instruct the terminal device 300 to switch the display state of the second button 304 to the second display state 3042.
  • the controller 14 can send an instruction to the terminal device 300 through the communicator 109, so that the terminal device 300 displays the prompt box as shown in Figure 8 305.
  • the prompt information in prompt box 305 is "It is detected that there is an electronic expansion valve failure in the multi-split air conditioning system. Do you want to locate the fault immediately?" to prompt the user to choose whether to turn on the fault locating function.
  • the terminal device 300 may send an instruction to the controller 14 to instruct the controller 14 to enable the fault location function.
  • the controller 14 may send an instruction to the terminal device 300 to instruct the terminal device 300 to switch the display state of the third button 306 from the third display state 3061 to the fourth display state 3062.
  • the multi-split air conditioning system 10 can automatically turn on the fault detection function and fault location function after working for a preset period of time.
  • the preset time period may be preset by the user or the manufacturer.
  • the controller 14 After the fault locating function is turned on, the controller 14 begins to obtain characteristic data of multiple indoor units.
  • the multi-split air conditioning system 10 includes a plurality of first temperature sensors 101 and a plurality of second temperature sensors 102 to respectively detect the temperature values of the liquid pipes 16 connected to the plurality of indoor units 13 and the temperature values of the air pipes 15 connected to the plurality of indoor units 13 .
  • the plurality of first temperature sensors 101 correspond to the indoor heat exchangers 131 of the plurality of indoor units 13 and are disposed in the air pipes 15 connected to the corresponding indoor heat exchangers 131 to detect the corresponding air pipes. temperature value of 15.
  • the plurality of second temperature sensors 102 correspond to the indoor heat exchangers 131 of the plurality of indoor units 13 and are arranged in the liquid pipes 16 connected to the corresponding indoor heat exchangers 131 to detect the temperature value of the corresponding liquid pipe 16 .
  • the controller 14 is coupled to a plurality of first temperature sensors 101 and a plurality of second temperature sensors 102 to obtain the temperature value of the liquid pipe 16 correspondingly connected to each of the plurality of indoor units 13 and the temperature value of the liquid pipe 16 connected to the indoor unit. Corresponding to the temperature difference between the temperature values of the connected air pipes 15.
  • the characteristic data of each indoor unit may also include at least one of the following: the discharge pressure value of the compressor 111, the suction pressure value of the compressor 111, the discharge temperature value of the compressor 111, the compressor 111, the outlet air temperature value of the air outlet 133 of the indoor unit, or the return air temperature value of the return air outlet 134 of the indoor unit.
  • the multi-connected air conditioning system 10 in addition to the plurality of first temperature sensors 101 and the plurality of second temperature sensors 102, includes a plurality of other temperature sensors and a plurality of pressure sensors to detect the above-mentioned respective characteristic data. .
  • the multi-split air conditioning system 10 includes a first pressure sensor 107 and a second pressure sensor 108 .
  • the first pressure sensor 107 is disposed at the exhaust port of the compressor 111 and is configured to detect the exhaust pressure value of the compressor 111;
  • the second pressure sensor 108 is disposed at the suction port of the compressor 111 and is configured to The suction pressure value of the compressor 111 is detected.
  • the controller 14 is coupled with the first pressure sensor 107 and the second pressure sensor 108 to obtain exhaust pressure values and suction pressure values.
  • the multi-split air conditioning system 10 includes a third temperature sensor 103 , a fourth temperature sensor 104 , a plurality of fifth temperature sensors 105 and a plurality of sixth temperature sensors 106 .
  • the third temperature sensor 103 is disposed at the exhaust port of the compressor 111 and is configured to detect the exhaust temperature value of the compressor 111;
  • the fourth temperature sensor 104 is disposed at the suction port of the compressor 111 and is configured to The suction air temperature value of the compressor 111 is detected.
  • the plurality of fifth temperature sensors 105 correspond to the plurality of indoor units 13 and are arranged at the air outlet 133 of the corresponding indoor unit 13 to detect the air outlet temperature value of the air outlet 133; the plurality of sixth temperature sensors 106 are connected to a plurality of The indoor units 13 correspond to each other and are arranged at the return air outlet 134 of the corresponding indoor unit 13 to detect the return air temperature value of the return air outlet 134 .
  • the controller 14 is coupled to the third temperature sensor 103, the fourth temperature sensor 104, a plurality of fifth temperature sensors 105 and a plurality of sixth temperature sensors 106 to obtain the exhaust gas temperature value, the suction air temperature value, and the outlet air temperature value. and return air temperature value.
  • the above-mentioned abnormal indoor unit refers to the indoor unit 13 in an abnormal operating state, that is, the indoor unit 13 whose corresponding electronic expansion valve 12 is a faulty electronic expansion valve. Similarly, when the electronic expansion valve 12 corresponding to the indoor unit 13 is not a faulty electronic expansion valve, it can be understood that the indoor unit 13 is in a normal operating state.
  • a failure of the electronic expansion valve in the multi-split air conditioning system 10 will cause the characteristic data of the multiple indoor units 13 to change.
  • the temperature difference between the temperature value of the liquid pipe 16 correspondingly connected to any indoor unit and the temperature value of the air pipe 15 correspondingly connected to the indoor unit is less than a certain threshold. If a certain electronic expansion valve 12 fails and the electronic expansion valve 12 cannot be opened normally, the amount of refrigerant in the indoor unit 13 corresponding to the electronic expansion valve 12 will be insufficient, resulting in the indoor unit 13 not being able to evaporate or condense the refrigerant normally.
  • the refrigerant is further embodied as the temperature difference between the temperature value of the liquid pipe 16 connected to the indoor unit 13 and the temperature value of the air pipe 15 connected to the indoor unit 13 increases to exceed the certain threshold. Therefore, the controller 14 can determine whether the indoor unit is an abnormal indoor unit based on the characteristic data of any indoor unit.
  • any operating data such as the above exhaust pressure value, suction pressure value, exhaust temperature value, suction temperature value, indoor unit outlet air temperature value, and indoor unit return air temperature value can also be used as the indoor unit's operating data. Feature data.
  • the controller 14 may input the characteristic data of each indoor unit in the plurality of indoor units into a fault identification model based on deep neural networks (Deep Neural Networks, DNN) to obtain a fault identification result.
  • Deep neural network DNN is a technology in the field of Machine Learning (ML). Since the fault identification model based on the deep neural network DNN can output multiple labels, the fault identification result can indicate whether each of the plurality of indoor units 13 is an abnormal indoor unit. In this way, the controller 14 can determine the abnormal indoor unit among the plurality of indoor units 13 based on the fault identification result.
  • a fault identification model based on a deep neural network DNN is pre-stored in the memory of the controller 14.
  • the controller 14 or other devices with processing capabilities can train a deep neural network-based system based on historical feature data sets of multiple indoor units 13 in normal operating states and historical feature data sets in abnormal operating states.
  • the fault identification model is used to obtain a trained fault identification model based on the deep neural network DNN, and the trained fault identification model is stored in the memory of the controller 14 .
  • the controller 14 can determine one or more abnormal indoor units from the plurality of indoor units 13, and then determine one or more electronic expansion valves 12 corresponding to the one or more abnormal indoor units. Faulty electronic expansion valve.
  • the multi-split air conditioning system 10 provided by the embodiment of the present disclosure can obtain the characteristic data of multiple indoor units 13 in the multi-split air conditioning system 10 when an electronic expansion valve failure occurs in the multi-split air conditioning system 10 , and then based on the multiple indoor units The characteristic data of the unit 13 determines an abnormal indoor unit among the plurality of indoor units 13, and determines the electronic expansion valve 12 corresponding to the abnormal indoor unit as a faulty electronic expansion valve.
  • the faulty electronic expansion valve in the multi-split air conditioning system 10 can be accurately located, without the need for professional maintenance personnel to spend a lot of time observing and analyzing the faulty electronic expansion valve based on personal experience, thereby improving the accuracy of the multi-split air conditioning system 10
  • the accuracy and degree of automation of positioning the faulty electronic expansion valve in the multi-split air conditioning system 10 can be improved, thereby improving the fault positioning efficiency of the multi-split air conditioning system 10 .
  • the controller 14 can determine whether an electronic expansion valve failure has occurred in the multi-split air conditioning system 10 by executing steps S201 to S203.
  • the above operating data is parameter information generated during the operation of the multi-split air conditioning system 10 .
  • the operating data includes, for example, at least one of the following: the operating current value of the compressor 111, the exhaust pressure value of the compressor 111, the exhaust temperature value of the compressor 111, and the air outlet temperature values of the air outlets 133 of the plurality of indoor units 13. and the return air temperature values of the return air inlets 134 of the multiple indoor units 13 .
  • the controller 14 can obtain the operating data of the multi-split air conditioning system 10 .
  • characteristic data and the above-mentioned operating data in the embodiments of the present disclosure are exemplary.
  • the characteristic data and the operating data may also include other data related to the operation of the multi-connected air conditioning system 10.
  • I won’t go into details one by one.
  • the controller 14 may input the operating data of the multi-split air conditioning system 10 into a fault diagnosis model based on a Support Vector Machine (SVM) to obtain a fault diagnosis result, which indicates Whether the electronic expansion valve of the multi-split air conditioning system 10 has failed.
  • SVM Support Vector Machine
  • the controller 14 can determine whether an electronic expansion valve failure has occurred in the multi-split air conditioning system 10 based on the fault diagnosis result.
  • the support vector machine SVM is a generalized linear classifier that performs binary classification of data according to a supervised learning method. The binary classification performance of the support vector machine SVM is better. Therefore, through the fault diagnosis model based on the support vector machine SVM, The accuracy of determining whether the electronic expansion valve failure occurs in the multi-split air conditioning system 10 can be improved.
  • a fault diagnosis model based on a support vector machine is pre-stored in the memory of the controller 14 .
  • the controller 14 or other devices with processing capabilities may be based on the historical operating data set of the multi-split air conditioning system 10 when no electronic expansion valve failure occurs and the historical operating data when the electronic expansion valve failure occurs. Set, train the fault diagnosis model based on the support vector machine SVM to obtain the trained fault diagnosis model based on the support vector machine SVM, and store the trained fault diagnosis model in the memory of the controller 14 .
  • the controller 14 determines that the multi-split air conditioning system 10 has an electronic expansion valve failure, the controller 14 executes the above steps S101 to S103.
  • the controller 14 determines that the electronic expansion valve failure does not occur in the multi-split air conditioning system 10, the controller 14 executes the following step S203.
  • the above-mentioned first prompt information is used to prompt that the electronic expansion valve failure does not occur in the multi-split air conditioning system 10 .
  • the first prompt information may be text, pictures, and other information displayed through the displays.
  • the indoor unit 13 includes a speaker
  • the first prompt information may be sound information emitted through the speaker.
  • the multi-split air conditioning system 10 is connected to the user's terminal device for communication
  • the first prompt information may be text, pictures, sounds, vibrations and other information sent through the terminal device.
  • the first prompt information can also be other forms of information, such as lighting information, etc., and the present disclosure does not limit this.
  • the controller 14 may send a second prompt message to remind that the faulty electronic expansion valve has failed.
  • the controller 14 issues the second prompt information by executing the following steps S301 to S303.
  • the controller 14 adjusts the refrigerant input amount or the refrigerant output amount of the indoor unit 13 corresponding to the electronic expansion valve 12 by adjusting the opening degree of the electronic expansion valve 12 . Therefore, an abnormal working state of an abnormal indoor unit is usually caused by an abnormal opening of the electronic expansion valve corresponding to the abnormal indoor unit. Moreover, the opening of the electronic expansion valve can represent the degree of failure of the electronic expansion valve.
  • the controller 14 may determine the fault level of the faulty electronic expansion valve according to the first correspondence between the opening of the faulty electronic expansion valve and the fault level.
  • the first correspondence relationship may be stored in the memory of the controller 14 in advance.
  • the normal opening degrees of the multiple electronic expansion valves 12 are related to the working status of the multi-split air conditioning system 10 .
  • the normal opening of the multiple electronic expansion valves 12 should be 100% (that is, the multiple electronic expansion valves 12 should be fully open).
  • the first corresponding relationship between the opening of the faulty electronic expansion valve and the fault level is as shown in Table 1 below.
  • the controller 14 may determine that the fault level of the faulty electronic expansion valve is level one. If the opening of the faulty electronic expansion valve is within the range of 50% to 74%, the controller 14 may determine that the fault level of the faulty electronic expansion valve is level two. If the opening of the faulty electronic expansion valve is within the range of 24% to 49%, the controller 14 may determine that the fault level of the faulty electronic expansion valve is level three. If the opening of the faulty electronic expansion valve is below 23%, the controller 14 may determine that the fault level of the faulty electronic expansion valve is level four. It should be noted that from “level one”, “level two", “level three” to "level four", the fault level of the faulty electronic expansion valve increases in sequence, and the urgency of repairing the faulty electronic expansion valve also increases. rise in sequence.
  • the normal opening of the plurality of electronic expansion valves 12 should be 12% to 13%.
  • the opening of the faulty electronic expansion valve is greater than 13%, the larger the opening of the faulty electronic expansion valve, the higher the fault level of the faulty electronic expansion valve, and the greater the need to repair the faulty electronic expansion valve.
  • Expansion valve for maintenance For example, when the multi-split air conditioning system 10 is in the cooling working state, the first corresponding relationship between the opening of the faulty electronic expansion valve and the fault level is as shown in Table 2 below.
  • the controller 14 may determine that the fault level of the faulty electronic expansion valve is level four. If the opening of the faulty electronic expansion valve is within the range of 50% to 74%, the controller 14 may determine that the fault level of the faulty electronic expansion valve is level three. If the opening of the faulty electronic expansion valve is within the range of 25% to 49%, the controller 14 may determine that the fault level of the faulty electronic expansion valve is level two. If the opening of the faulty electronic expansion valve is within the range of 14% to 24%, or below 12%, the controller 14 may determine that the fault level of the faulty electronic expansion valve is level one.
  • the above second prompt information is used to prompt the fault level of the faulty electronic expansion valve.
  • the controller 14 can issue the second prompt information through the display, speaker, terminal device, etc. of the indoor unit 13 (for example, the abnormal indoor unit).
  • the second prompt information may be, for example, "Electronic expansion valve numbered as 001" A serious malfunction has occurred, it is recommended to repair it immediately!” This text message.
  • the faulty electronic expansion valve can be determined based on the first corresponding relationship between the opening of the faulty electronic expansion valve and the fault level.
  • the fault level of the faulty electronic expansion valve is determined, and a second prompt message corresponding to the fault level of the faulty electronic expansion valve is sent, so as to prompt the user to reasonably arrange the maintenance work of the faulty electronic expansion valve according to the fault level of the faulty electronic expansion valve, to avoid
  • the failure of the electronic expansion valve causes the cooling or heating effect of the multi-split air conditioning system 10 to decrease.
  • Some embodiments of the present disclosure also provide a fault location method for a multi-split air conditioning system.
  • the multi-split air conditioning system may be, for example, the above-mentioned multi-split air conditioning system 10 , and the method may, for example, include various steps executed by the above-mentioned controller 14 .
  • the beneficial effects of this method include at least the beneficial effects of the multi-split air conditioning system 10 mentioned above, which will not be described again here.
  • this fault diagnosis model training method will lead to a long establishment period of the fault diagnosis model, which will lead to the use of this fault diagnosis model to analyze the multi-split air conditioning systems. Troubleshooting is less efficient.
  • some embodiments of the present disclosure also provide a fault diagnosis model training method for a multi-connected air conditioning system.
  • This method can construct the first multi-split air-conditioning system based on the values of the operating data under normal operating conditions (i.e., the normal values of the operating data) and the values of the operating data when various faults occur (i.e., the fault values of the operating data).
  • a first characteristic offset space of a multi-split air conditioner system and based on the difference between the normal value of the operating data of the first multi-split air conditioner and the normal value of the operating data of the second multi-split air conditioner, the first characteristic offset space Correction is made to obtain the second characteristic offset space of the second multi-split air conditioner, so that the operation of the second multi-split air conditioner system can be obtained based on the second characteristic offset space and the normal value of the operating data of the second multi-split air conditioner system.
  • the fault value of the data is used to establish the fault diagnosis model of the second multi-split air conditioning system.
  • the above fault diagnosis model training method of the multi-split air conditioning system includes the following steps S401 to S405.
  • the execution subject of this method may be the above-mentioned controller 14, or may be other equipment with processing capabilities, such as a server.
  • the subsequent embodiments take the controller 14 executing the method as an example for illustrative description.
  • the structure and working principle of the multi-split air conditioning system can be referred to the multi-split air conditioning system 10 in the previous embodiment, and will not be described again here.
  • the first multi-spread air conditioning system may be called an experimental multi-spread air conditioning system.
  • the memory of the first multi-split air conditioning system stores historical operating data generated when the first multi-split air conditioning system operates under various operating conditions.
  • the above operating data includes, for example, the suction temperature value of the compressor 111 , the discharge temperature value of the compressor 111 , the suction pressure value of the compressor 111 , the discharge pressure value of the compressor 111 , and the opening degrees of the plurality of electronic expansion valves 12 , the operating current value of the compressor 111, the ambient temperature value of the outdoor unit 11, the average value of the ambient temperature values of multiple indoor units, the suction superheat of the compressor 111, and the exhaust superheat of the compressor 111 , the operating temperature value of the outdoor unit 11 and the operating temperature values of the multiple indoor units 13 .
  • the suction superheat degree refers to the difference between the suction temperature value of the compressor 111 and the saturation temperature of the refrigerant at the suction pressure value;
  • the exhaust superheat degree refers to the exhaust gas temperature value of the compressor 111 and The difference between the saturation temperatures of the refrigerant at the exhaust pressure value.
  • the operating temperature value of the outdoor unit 11 may be, for example, the operating temperature value of the outdoor heat exchanger 112 .
  • the operating temperature value of a certain indoor unit 13 among the plurality of indoor units 13 may be, for example, the operating temperature value of the indoor heat exchanger 131 of the certain indoor unit 13 .
  • step S101 may be specifically implemented as the following steps S4011 and S4012.
  • the historical operation data includes normal operation data generated by the first multi-split air conditioning system under normal operating conditions during the historical period and various fault operation data generated by the first multi-split air conditioning system when various faults occur. It should be noted that this disclosure does not limit the length of the historical period.
  • the controller 14 can analyze the historical operating data of the multi-line air conditioning system and distinguish the multiple operating data. Multiple operating data generated by the online air conditioning system in normal operation and multiple operating data generated by the multi-online air conditioning system when a fault occurs, and then the normal value and fault of each operating data in the multiple operating data are obtained value.
  • possible failures in the multi-split air conditioning system include refrigerant leakage, excessive refrigerant participating in the cycle, or abnormal opening of the electronic expansion valve 12, etc.
  • the controller 14 may analyze the historical operating data according to the preset value ranges corresponding to the plurality of operating data. If the value of any one of the multiple operating data is within the corresponding preset value range, the value of the operating data is determined to be a normal value. If the value of any operating data is outside the corresponding preset value range, the value of the operating data is determined to be a fault value.
  • the preset value range may be preset by a staff member or manufacturer, for example.
  • the controller 14 may correspond the fault value of the first multi-split air conditioning system with the fault that occurred in the first multi-split air conditioner system.
  • the first multi-split air conditioning system can be constructed based on the offset between the fault value and the normal value of multiple operating data.
  • the first characteristic offset space includes an offset of each of the plurality of operating data of the first multi-split air conditioning system.
  • a space composed of normal values of multiple operating data of the multi-split air conditioning system may be called a characteristic space of the multi-split air conditioning system.
  • the first feature space of the first multi-split air conditioning system can be expressed as the following matrix:
  • x j is a column vector of a certain operating data, and the value of j is 1 to n; n is an integer greater than 1.
  • the first characteristic offset space of the first multi-split air conditioning system can be expressed as:
  • ⁇ xi [ ⁇ xi 1 ⁇ xi 2 ... ⁇ xi n-1 ⁇ xi n ]
  • ⁇ xi j is the offset of a certain operating data, and the value of j is from 1 to n; n is an integer greater than 1.
  • the machine of the first multi-connected air conditioning system is there are differences between models with second multi-split air conditioning systems.
  • the first multi-split air conditioning system is a single-cooling type
  • the second multi-split air conditioning system is a heat pump type.
  • multi-split air conditioning systems of different models usually have similar characteristic offset spaces. Therefore, based on the difference between the model of the first multi-split air-conditioning system and the model of the second multi-split air-conditioning system, the first characteristic offset space can be corrected to obtain the second characteristic of the second multi-split air-conditioning system. offset space.
  • the memory of the controller 14 pre-stores the second correspondence between the model of the multi-connected air conditioning system and the correction coefficient.
  • the correction coefficient is, for example, a ratio between the characteristic offset space of other multi-split air-conditioning systems and the first characteristic deviation space of the first multi-split air-conditioning system.
  • model determine the model of the second multi-split air conditioning system, so that the correction coefficient of the second characteristic offset space relative to the first characteristic offset space can be determined according to the model of the second multi-split air conditioning system and the second corresponding relationship. , and then correct the first feature offset space according to the correction coefficient, and obtain the second feature offset space. For example, the controller 14 multiplies the correction coefficient with the first feature offset space to obtain the second feature offset space.
  • the above second corresponding relationship can be obtained through experiments or simulations.
  • the controller 14 may analyze the historical operating data of the second multi-split air conditioning system in normal operation within the historical period, and determine the normal values of the plurality of operating data of the second multi-split air conditioning system, Thereby, the fault values of the multiple operating data of the second multi-connected air conditioning system are obtained based on the normal values of the multiple operating data of the second multi-connected air conditioning system and the second characteristic offset space.
  • the controller 14 may add the normal values of the plurality of operating data of the second multi-connected air conditioning system and the second characteristic offset space to obtain the fault value of the plurality of operating data of the second multi-connected air conditioning system.
  • S405 Train the fault diagnosis model based on the normal values and fault values of multiple operating data of the second multi-online air conditioning system.
  • the controller 14 may use the normal values and fault values of multiple operating data of the second multi-connected air conditioning system as a sample set to train the fault diagnosis model.
  • the above fault diagnosis model is a fault diagnosis model based on one-dimensional convolutional neural networks (Convolutional Neural Networks, CNN).
  • the convolutional neural network is a multi-layer perceptron.
  • the working principle of convolutional neural networks mainly involves three basic concepts: local receptive field, pooling and shared weights.
  • One-dimensional convolutional neural network is a convolutional neural network with one-dimensional input data and has classification capabilities. Therefore, one-dimensional convolutional neural network can be used for fault detection and diagnosis of multi-split air conditioning systems.
  • Fault detection is the process of detecting whether a system fault occurs
  • fault diagnosis is the acquisition of detailed information such as the fault type and fault severity.
  • the fault diagnosis model may include: an input layer, a convolution layer, a pooling layer, a fully connected layer, and an output layer.
  • the convolutional layer is the key structure in the convolutional neural network.
  • the function of the convolutional layer is to use a series of filters to convolve the input data from the input layer to form a series of feature maps of the original input data and output it.
  • a filter convolves the input data of a convolutional layer
  • a local receptive field moves repeatedly over the input data.
  • the data in the local receptive field will perform a dot product operation with the weight matrix in the filter, and after adding a fixed offset value, an output matrix will be formed.
  • the output matrix is a feature map of the original input data.
  • the convolution operation of the filter on the input has the characteristic of shared weights, that is, the weight matrix and bias used by a filter for the data in the local receptive field are the same.
  • an activation function (such as a ReLU activation function) can be applied to the output of the convolution layer to perform delinearization, thereby improving the nonlinear fitting ability of the convolution layer.
  • the ReLU activation function can be expressed as the following formula (1):
  • the output a i of the i-th convolutional layer can be expressed as the following formula (2):
  • ⁇ is the ReLU activation function
  • b i is the bias value
  • w i is the weight matrix
  • the output of the convolutional layer can be fed into the pooling layer.
  • the pooling layer divides the input data into multiple pooling areas, and summarizes each pooling area to form an output.
  • the output of the pooling layer is a generalized and reduced feature map of its input.
  • the fully connected layer plays the role of a "classifier" in the entire convolutional neural network and can map distributed features into the sample label space. That is to say, the fully connected layer is used to integrate the output of the pooling layer to obtain the output of the fully connected layer, and input the output of the fully connected layer into the output layer.
  • a classification network (softmax) layer can be used as the output layer of the convolutional neural network.
  • the classification result of the input data of the softmax layer can be determined according to the dimension where the maximum value of the probability vector in the softmax layer output is located.
  • the fault diagnosis model training method of the multi-split air conditioning system can obtain multiple parameters used to characterize the first multi-split air conditioning system based on the normal values and fault values of the multiple operating data of the first multi-split air conditioning system.
  • the first characteristic offset space of the offset between the normal value of the operating data and the multiple fault values, and based on the difference between the model of the second multi-split air-conditioning system and the model of the first multi-split air-conditioning system The first characteristic offset space is corrected to obtain the second characteristic offset space of the second multi-split air conditioning system.
  • the fault values of the multiple operating data of the second multi-connected air conditioning system can be obtained based on the second characteristic offset space and the normal values of the multiple operating data of the second multi-connected air conditioning system.
  • the fault diagnosis model can be trained using the fault values and normal values of multiple operating data of the second multi-split air-conditioning system to obtain a trained fault diagnosis model suitable for the second multi-split air-conditioning system.
  • the fault diagnosis model of the second multi-split air-conditioning system can be established without collecting the fault values of multiple operating data when various faults occur in the second multi-split air-conditioning system in actual working conditions, thereby shortening the establishment of the fault diagnosis model. cycle, thereby improving the efficiency of fault diagnosis of the second multi-split air conditioning system using this fault diagnosis model.
  • step S405 may be specifically implemented as the following steps S501 and S502.
  • the multiple operating data of the second multi-split air conditioning system may be mixed with some redundant operating data that is irrelevant to training the fault diagnosis model.
  • the multiple operating data need to be processed. Data filtering.
  • the above-mentioned at least one first operating data is operating data common to multi-split air conditioning systems of different models and highly relevant to the training fault diagnosis model.
  • the controller 14 may calculate the difference between the normal value and the fault value of each of the plurality of operating data of the second multi-connected air conditioning system, and determine the difference among the plurality of differences that is greater than the preset threshold.
  • the operating data corresponding to the difference is used as alternative operating data, and then at least one operating data common to various types of multi-split air conditioning systems is extracted from the alternative operating data as first operating data.
  • the preset threshold can be set in advance by the staff or the manufacturer.
  • the first operating data of the detection model is helpful to improve the accuracy of fault detection by the trained fault detection model.
  • the fault diagnosis model training method of the multi-split air conditioning system in the above embodiment can extract at least one of the plurality of operational data of the second multi-split air conditioning system by filtering the data. A first operating data, and then using the normal value and fault value of the at least one first operating data to train the fault diagnosis model. Since the training sample set of the fault diagnosis model is simplified, the training speed of the fault diagnosis model can be increased, thereby improving the efficiency of fault diagnosis of the multi-split air conditioning system using the fault diagnosis model.
  • step S502 can be specifically implemented as the following steps S601 to step S603.
  • the autoencoder model is an unsupervised learning model.
  • the autoencoder includes an encoder and a decoder.
  • the encoder is configured to encode high-dimensional input data (i.e., original feature data) into low-dimensional latent variables (i.e., compressed data), allowing the autoencoder model to learn more informative data.
  • the decoder is configured to reduce the low-dimensional latent variables to the original dimensions of the high-dimensional input data.
  • the process in which the original feature data is encoded by the encoder and then decoded by the decoder is the data reconstruction process of the original feature data.
  • the process of training an autoencoder model may include the following steps 1 to 4.
  • X 1 , X 2 ,..., X n represent the normal value and fault value of the at least one first operating data.
  • Step 2 The encoder compresses the original feature data into the hidden layer as shown in the following formula (3).
  • ⁇ e is the Sigmoid function
  • X is the original feature data set
  • W e is the encoder weight parameter
  • B e is the encoder bias
  • H is the mapping of the original feature data in the hidden layer.
  • Step 3 The decoder reconstructs the original feature data and outputs the reconstructed feature data in the manner shown in the following formula (4).
  • ⁇ d is the Sigmoid function
  • W d is the weight parameter of the decoder
  • B d is the deviation of the decoder
  • Step 4 Train the autoencoder model to reduce the reconstruction error and obtain the corresponding We e , W d and
  • S602. Input the normal value and fault value of at least one first operating data of the second multi-connected air-conditioning system into the trained autoencoder model to obtain the data repetition of at least one first operating data of the second multi-connected air-conditioning system. Construct normal values and data reconstruct fault values.
  • the fault diagnosis model training method of the multi-connected air conditioning system in the above embodiment uses the autoencoder to reconstruct the normal value and fault value of at least one first operating data of the second multi-connected air conditioning system, which can reduce the at least one Data noise (i.e., random errors in the data caused by measurement and other reasons) of the normal value and fault value of the first operating data, thereby removing the normal value and fault value of the at least one first operating data, which is misleading for training the fault detection model
  • the data used thereby improves the accuracy of fault detection using the fault detection model.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computing Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Human Computer Interaction (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

本公开一些实施例提供了一种多联机空调系统、故障定位方法及故障诊断模型训练方法。多联机空调系统包括室外机、多个室内机、多个电子膨胀阀以及控制器。多个室内机中的每个室内机对应连接有气管和液管。多个电子膨胀阀分别设置在对应的室内机所连接的液管中。控制器被配置为：在多联机空调系统发生电子膨胀阀故障的情况下，获取多个室内机中的每个室内机的特征数据。每个室内机的特征数据包括与该室内机对应连接的液管的温度值和与该室内机对应连接的气管的温度值之间的温度差值。根据多个室内机中的每个室内机的特征数据，确定多个室内机中的异常室内机。将与异常室内机对应的电子膨胀阀确定为故障电子膨胀阀。

Description

多联机空调系统、故障定位方法及故障诊断模型训练方法
本申请要求于2022年04月11日提交的、申请号为202210386517.3的中国专利申请的优先权，以及于2022年06月16日提交的、申请号为202210682549.8的中国专利申请的优先权；其全部内容通过引用结合在本申请中。
技术领域
本公开涉及空调技术领域，尤其涉及一种多联机空调系统、故障定位方法及故障诊断模型训练方法。
背景技术
多联机空调系统包括室外机和多个室内机，从而调节该多个室内机所在的多个室内空间的温度。由于多联机空调系统中的部件数量较多，因此，当该多联机空调系统发生故障时，难以快速定位出发生故障的部件，从而导致该多联机空调系统的故障定位效率较低。
发明内容
一方面，本公开一些实施例提供一种多联机空调系统。多联机空调系统包括室外机、多个室内机、多个电子膨胀阀以及控制器。多个室内机中的每个室内机对应连接有气管和液管，以通过该气管和该液管与室外机连通。多个电子膨胀阀与多个室内机对应。多个电子膨胀阀分别设置在对应的室内机所连接的液管中，且被配置为控制对应的室内机的冷媒输出量或冷媒输入量。
控制器被配置为：在多联机空调系统发生电子膨胀阀故障的情况下，获取多个室内机中的每个室内机的特征数据。每个室内机的特征数据包括与该室内机对应连接的液管的温度值和与该室内机对应连接的气管的温度值之间的温度差值。根据多个室内机中的每个室内机的特征数据，确定该多个室内机中的异常室内机。将与异常室内机对应的电子膨胀阀确定为故障电子膨胀阀。
另一方面，本公开一些实施例提供一种多联机空调系统的故障定位方法。其中，多联机空调系统包括室外机、多个室内机以及多个电子膨胀阀。多个室内机中的每个室内机对应连接有气管和液管，以通过该气管和该液管与室外机连通。多个电子膨胀阀与多个室内机对应。多个电子膨胀阀分别设置在对应的室内机所连接的液管中，且被配置为控制对应的室内机的冷媒输出量或冷媒输入量。
该方法包括：在多联机空调系统发生电子膨胀阀故障的情况下，获取多个室内机中的每个室内机的特征数据。每个室内机的特征数据包括与该室内机对应连接的液管的温度值和与该室内机对应连接的气管的温度值之间的温度差值。根据多个室内机中的每个室内机的特征数据，确定该多个室内机中的异常室内机。将与异常室内机对应的电子膨胀阀确定为故障电子膨胀阀。
再一方面，本公开一些实施例提供一种多联机空调系统的故障诊断模型训练方法。该训练方法包括：获取第一多联机空调系统的多个运行数据的正常值和故障值。基于第一多联机空调系统的多个运行数据的正常值和故障值，确定第一多联机空调系统的第一特征偏移空间。第一特征偏移空间包括第一多联机空调系统的多个运行数据中的、各个运行数据的故障值与正常值之间的差值。基于第一多联机空调系统的多个运行数据的正常值与第二多联机空调系统的多个运行数据的正常值之间的差异，对第一特征偏移空间进行修正，得到第二多联机空调系统的第二特征偏移空间。基于第二多联机空调系统的多个运行数据的正常值以及第二特征偏移空间，确定第二多联机空调系统的多个运行数据的故障值。基于第二多联机空调系统的多个运行数据的正常值和故障值，对故障诊断模型进行训练。
附图说明
为了更清楚地说明本公开中的技术方案，下面将对本公开一些实施例中所需要使用的附图作简单地介绍，然而，下面描述中的附图仅仅是本公开的一些实施例的附图，对于本领域普通技术人员来讲，还可以根据这些附图获得其他的附图。此外，以下描 述中的附图可以视作示意图，并非对本公开实施例所涉及的产品的实际尺寸、方法的实际流程、信号的实际时序等的限制。
图1为根据一些实施例的多联机空调系统的一个结构图；
图2为根据一些实施例的多联机空调系统的另一个结构图；
图3为根据一些实施例的控制器的结构图；
图4为根据一些实施例的控制器与终端设备之间的交互方式图；
图5为根据一些实施例的终端设备的一个界面图；
图6为根据一些实施例的多联机空调系统的故障定位方法的一个流程图；
图7为根据一些实施例的终端设备的另一个界面图；
图8为根据一些实施例的终端设备的又一个界面图；
图9为根据一些实施例的第一温度传感器和第二温度传感器的位置图；
图10为根据一些实施例的多联机空调系统的故障定位方法的另一个流程图；
图11为根据一些实施例的多联机空调系统的故障定位方法的又一个流程图；
图12为根据一些实施例的终端设备的又一个界面图；
图13为根据一些实施例的多联机空调系统的故障诊断模型训练方法的一个流程图；
图14为根据一些实施例的多联机空调系统的故障诊断模型训练方法的另一个流程图；
图15为根据一些实施例的故障诊断模型的结构图；
图16为根据一些实施例的多联机空调系统的故障诊断模型训练方法的又一个流程图；
图17为根据一些实施例的多联机空调系统的故障诊断模型训练方法的又一个流程图；
图18为根据一些实施例的自编码模型的结构图。
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(oneembodiment)”、“一些实施例(someembodiments)”、“示例性实施例(exemplaryembodiments)”、“示例(example)”、“特定示例(specificexample)”或“一些示例(someexamples)”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“耦接”和“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。术语“耦接”例如表明两个或两个以上部件有直接物理接触或电接触。术语“耦接”或“通信耦合(communicatively coupled)”也可能指两个或两个以上部件彼此间并无直接接触，但仍彼此协作或相互作用。这里所公开的实施例并不必然限制于本文内容。
“A和/或B”，包括以下三种组合：仅A，仅B，及A和B的组合。
本文中“被配置为”的使用意味着开放和包容性的语言，其不排除被配置为执行额外任务或步骤的设备。
另外，“基于”的使用意味着开放和包容性，因为“基于”一个或多个所述条件或值的过程、步骤、计算或其他动作在实践中可以基于额外条件或超出所述的值。
本公开一些实施例提供了一种多联机空调系统10。如图1所示，多联机空调系统10包括室外机11、多个电子膨胀阀12、多个室内机13和控制器14(图1中未示出)。室外机11例如可以为多联机空调系统10中，安装于房屋的墙体外侧或楼顶等区域的设备。室外机11主要用于压缩冷媒，并驱动该冷媒在多联机空调系统10中循环。冷媒为容易吸热变成气体、也容易放热变成液体的物质。室内机13例如可以为多联机空调系统10中，安装于室内的设备。室内机13主要用于向该室内机13所在的室内空间传输冷气或热气，以调节该室内空间的温度。
在一些实施例中，多个室内机13中的每个室内机对应连接有气管15和液管16，以通过气管15和液管16与室外机11连通。气管15被配置为在室外机11和室内机13之间传输气态冷媒或两相态冷媒(气态和液态并存的冷媒)，液管16被配置为在室外机11和室内机13之间传输液态冷媒或两相态冷媒。气管15和液管16可以合称为管道。
在一些示例中，多个电子膨胀阀12与多个室内机13对应。多个电子膨胀阀12分别设置在对应的室内机13所连接的液管16中，且被配置为控制对应的室内机13的冷媒输出量或冷媒输入量。
需要说明的是，多个电子膨胀阀12可以独立于多个室内机13设置(如图1所示)，也可以隶属于多个室内机13设置。后续实施例以多个电子膨胀阀12独立于多个室内机13设置为例，进行示例性说明。
在一些实施例中，室外机11包括压缩机111、室外换热器112、气液分离器113、四通阀114和室外风扇115。压缩机111的排气口与四通阀114的D端连通，压缩机111的吸气口与气液分离器113的排气口连通。气液分离器113的吸气口与四通阀114的S端连通。四通阀114的C端与室外换热器112的第一端连通，四通阀114的E端与各个气管15连通。室外换热器112的第二端与各个液管16连通。
在一些实施例中，多个室内机13中的每个室内机包括室内换热器131、室内风扇132、出风口133和回风口134。室内换热器131的第一端与对应的气管15连通，室内换热器131的第二端与对应的液管16连通。出风口133和回风口134分别通过出风管道和回风管道与室内换热器131连通。
需要说明的是，图1所示的结构为多联机空调系统10的示例性结构，多联机空调系统10可以包括比图1所示的部件更多、更少或不同的部件。例如，室外机11还可以包括用于驱动室外风扇115工作的室外风扇马达，室内机13还可以包括显示器和用于驱动室内风扇132工作的室内风扇马达。当室内机13包括显示器时，该显示器可以被配置为显示室内机13所在的室内空间的温度，和/或被配置为显示多联机空调系统10的工作状态等。
在一些实施例中，如图2所示，控制器14与室外机11中的压缩机111、四通阀114和室外风扇115耦接，与多个电子膨胀阀12耦接，且与多个室内机13中的室内风扇132耦接。控制器14被配置为控制与控制器14耦接的各部件的工作状态。
控制器14还与多个温度传感器和多个压力传感器耦接，以获取多联机空调系统10中多个部件的温度值和压力值。关于该多个温度传感器和该多个压力传感器的设置方式，将在后续实施例中进行说明。
另外，控制器14还与通信器109耦接，以通过通信器109与其他设备(例如终端设备)建立通信连接，从而收发通信信号。示例性地，通信器109可以包括射频(Radio Frequency，RF)装置、蜂窝装置、无线网络通信技术(Wi-Fi)装置、以及全球定位系统(Global Positioning System，GPS)装置等。
在一些示例中，控制器14是指可以根据指令操作码和时序信号产生操作控制信号，从而指示多联机空调系统10执行控制指令的装置。示例性地，控制器14可以为中央处理 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、可编程逻辑器件(Programmable Logic Device，PLD)或它们的任意组合。控制器14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，本公开实施例对此不作限制。
示例性地，如图3所示，控制器14包括室外控制器141和室内控制器142。室外控制器141包括第一存储器1411，且被配置为控制室外机11执行相关操作；室内控制器142包括第二存储器1421，且被配置为控制多个室内机13以及多个电子膨胀阀12执行相关操作。室内控制器142与室外控制器141之间存在有线或无线通信连接。室外控制器141和室内控制器142可以分别隶属于室外机11和室内机13设置，也可以独立于室外机11和室内机13设置。
需要说明的是，图3所示的控制器14的结构为控制器14的示例性结构。例如，室外控制器141和室内控制器142也可以集成为一个控制器。第一存储器1411和第二存储器1421也可以集成为一个存储器。
在一些实施例中，第一存储器1411和第二存储器1421被配置为存储应用程序以及数据，室外控制器141和室内控制器142分别通过运行存储在第一存储器1411和第二存储器1421中的应用程序以及数据，执行多联机空调系统10的各种功能以及数据处理。示例性地，第一存储器1411和第二存储器1421可以包括高速随机存取存储器，还可以包括非易失存储器。第一存储器1411和第二存储器1421例如为磁盘存储器件、闪存器件等。
在一些实施例中，用户可以通过与控制器14建立了通信连接的设备，控制多联机空调系统10的工作状态。示例性地，如图4所示，控制器14与用户的终端设备300之间存在通信连接。该通信连接可以利用各种有线或无线通信技术实现，例如利用以太网、通用串行总线(Universal Serial Bus，USB)、火线(FireWire)、任何蜂窝网通信技术(如3G/4G/5G)、蓝牙、Wi-Fi、近场通信(Near Field Communication，NFC)或任何其他合适的通信技术。
终端设备300例如可以为遥控器、手机、平板电脑、个人计算机(Personal Computer，PC)、个人数字助理(Personal Digital Assistant，PDA)、智能手表、可穿戴电子设备、增强现实技术(Augmented Reality，AR)设备、虚拟现实(Virtual Reality，VR)设备、机器人等，图4及后续实施例以终端设备300为手机为例进行示例性说明，本公开对终端设备300的具体形式不作限制。
在该实施例中，如图5所示，终端设备300上显示多联机空调系统10的管理界面301。管理界面301包括用于管理多联机空调系统10的工作状态的第一按键302。响应于用户对管理界面301中的第一按键302的点击操作，终端设备300在管理界面301弹出工作状态下拉选择框303。响应于用户在工作状态下拉选择框303中进行的工作状态选择操作，终端设备300将与该选择操作对应的工作指令发送给多联机空调系统10，以使多联机空调系统10按照用户选择的工作状态运行。
在一些实施例中，上述多联机空调系统10在制冷工作状态下工作，以降低室内空间的温度。在制冷工作状态下，控制器14控制压缩机111开始工作，并控制四通阀114的D端与C端连通、S端与E端连通。
这样，压缩机111开始压缩冷媒，以使该冷媒在多联机空调系统10中循环。示例性地，压缩机111将气态的冷媒压缩为高温、高压的气态冷媒，并驱动压缩处理后的冷媒经过四通阀114的D端和C端到达室外换热器112的第一端，以进入室外换热器112中。高温、高压的气态冷媒在室外换热器112中被液化为低温、低压的液态冷媒后，经过室外换热器112的第二端、液管16和多个电子膨胀阀12到达多个室内换热器131的第二端，以进入该多个室内换热器131中。对于多个室内机13中的任一个室内机而言，低温、低压的液态冷媒在该室内机的室内换热器131中被汽化为气态冷媒，从而吸收该室内换热器131周围的热量、降低该室内机内部的气体的温度，并通过该室内机的出风口133将降温后的该气体输送至该室内机外部，进而达到降低室内空间的温度的效果。然后，汽化后的气态冷媒经过室内换热器131的第一端和气管15到达四通阀114，并经过四通阀114的 E端和S端到达气液分离器113的吸气口。气态冷媒在从室内换热器131传输至气液分离器113的过程中可能会冷凝产生液体，气液分离器113将该液体分离出去后，将气态冷媒输入压缩机111中，以实现冷媒的循环利用。
在另一些实施例中，上述多联机空调系统10在制热工作状态下工作，以升高室内空间的温度。区别于上述制冷工作状态，在制热工作状态下，控制器14控制四通阀114的D端与E端连通、S端与C端连通。
这样，压缩机111进行压缩处理后得到的高温、高压的气态冷媒经过四通阀114的D端和E端，从气管15输入多个室内换热器131中。针对多个室内机13中的任一个室内机而言，高温、高压的气态冷媒在该室内机的室内换热器131中被液化为低温、低压的液态冷媒，从而向该室内换热器131周围释放热量、升高该室内机内部的气体的温度，并通过该室内机的出风口133将升温后的该气体输送至该室内机外部，进而达到升高室内空间的温度的效果。然后，低温、低压的液态冷媒从室内换热器131的第二端流出该室内换热器131，并经过多个电子膨胀阀12和液管16进入室外换热器112中。低温、低压的液态冷媒在室外换热器112中被汽化为气态冷媒，然后经过四通阀114的C端和S端传输至气液分离器113中，再回到压缩机111中。
在上述制冷工作状态或制热工作状态下，室外风扇115被配置为在控制器14的控制下开始工作，以将室外换热器112液化冷媒所产生的热量或汽化冷媒所产生的冷量排出室外机11；室内风扇132被配置为在控制器14的控制下开始工作，以将室内换热器131汽化冷媒所产生的冷量或液化冷媒所产生的热量排出室内机13，以调节该室内机13所在的室内空间的温度。
在一些实施例中，室内机13的回风口134被配置为将该室内机13外部的气体输送至该室内机13内部，从而使该气体在该室内机13内部经室内换热器131降低或提升温度后，再通过出风口133输送至该室内机13外部。这样，可以使室内机13所在的室内空间中的气体被循环降温或升温，从而提高多联机空调系统10的降温效率或升温效率。
需要说明的是，当多联机空调系统10在制冷工作状态下工作时，室外换热器112也可以称为冷凝器，室内换热器131也可以称为蒸发器；当多联机空调系统10在制热工作状态下工作时，室外换热器112也可以称为蒸发器，室内换热器131也可以称为冷凝器。另外，压缩机111的排气口处的压力值可以称为排气压力值，也可以称为冷凝压力值或高压压力值；压缩机111的吸气口处的压力值可以称为吸气压力值，也可以称为蒸发压力值或低压压力值。
在一些实施例中，电子膨胀阀12具有使流经电子膨胀阀12的冷媒膨胀而减压的功能，可以调节管道内冷媒的流量。若电子膨胀阀12的开度(开启的程度)减小，则通过电子膨胀阀12的冷媒流量减小。若电子膨胀阀12的开度增大，则通过电子膨胀阀12的冷媒流量增大。示例性地，若多联机空调系统10处于制冷工作状态中，则多个电子膨胀阀12分别位于对应的室内机13的冷媒输入侧，因此，此时多个电子膨胀阀12分别控制对应的室内机13的冷媒输入量；若多联机空调系统10处于制热工作状态中，则多个电子膨胀阀12分别位于对应的室内机13的冷媒输出侧，因此，此时多个电子膨胀阀12分别控制对应的室内机13的冷媒输出量。
如背景技术所述，在相关技术中，若多联机空调系统10中出现了电子膨胀阀故障，则需要专业的维修人员对整个多联机空调系统10中的电子膨胀阀12进行观察和分析后，定位出故障电子膨胀阀，再对该故障电子膨胀阀进行维修或更换等，从而排除多联机空调系统10中的电子膨胀阀故障。因此，相关技术中的多联机空调系统10的故障定位效率较低、故障定位的自动化程度较低。
针对相关技术中存在的上述技术问题，本公开的发明人经过研究发现：当多个电子膨胀阀12正常工作时，与任一个室内机连接的液管16的温度值和与该室内机连接的气管15的温度值之间的温度差值小于一定阈值。当多联机空调系统10发生电子膨胀阀故障(例如电子膨胀阀12不能正常开启)时，与故障电子膨胀阀所对应的室内机13连接的液管16的温度值和与该室内机13连接的气管15的温度值之间的温度差值大于上述一定阈 值。因此，可以通过监测多个室内机13在运行过程中的特征数据(例如，与同一室内机13连接的液管16和气管15的温度值)，判断多个电子膨胀阀12是否发生了故障。
基于上述技术构思，本公开一些实施例提供的多联机空调系统10，该多联机空调系统10中的控制器14可以在多联机空调系统10发生电子膨胀阀故障的情况下，获取多联机空调系统10中多个室内机13的特征数据，并根据该特征数据识别出多个室内机13中的异常室内机，进而将与异常室内机对应的电子膨胀阀12确定为故障电子膨胀阀，以完成故障电子膨胀阀的定位。这样，在多联机空调系统10发生电子膨胀阀故障后，无需专业的维修人员基于个人经验对多个电子膨胀阀12进行人工识别即可定位出故障电子膨胀阀，从而可以提高对多联机空调系统10进行故障定位的自动化程度，提高对多联机空调系统10中故障电子膨胀阀的定位效率。
下面主要结合附图，对控制器14执行故障定位方法的过程进行示例性说明。
在一些实施例中，如图6所示，控制器14被配置为执行下述步骤S101至步骤S103。
S101、在多联机空调系统10发生电子膨胀阀故障的情况下，获取多个室内机13中的每个室内机的特征数据。
每个室内机的特征数据包括与该室内机对应连接的液管16的温度值和与该室内机对应连接的气管15的温度值之间的温度差值。
示例性地，上述温度差值可以为与该室内机对应连接的液管16的温度值减去与该室内机对应连接的气管15的温度值得到的值。或者，该温度差值可以为与该室内机对应连接的气管15的温度值减去与该室内机对应连接的液管16的温度值得到的值。
在一些实施例中，用户可以通过与控制器14建立了通信连接的设备指示多联机空调系统10开启故障检测功能和故障定位功能，以使控制器14开始检测是否发生了电子膨胀阀故障以及定位故障电子膨胀阀。需要说明的是，关于控制器14检测是否发生了电子膨胀阀故障的方法，将在后续实施例中进行说明。
以该设备为终端设备300为例，如图7和图8所示，终端设备300的管理界面301包括用于开启或关闭多联机空调系统10的故障检测功能的第二按键304，以及用于开启或关闭多联机空调系统10的故障定位功能的第三按键306。当多联机空调系统10的故障检测功能(或故障定位功能)处于关闭状态时，第二按键304(或第三按键306)处于第一显示状态3041(或第三显示状态3061)；当多联机空调系统10的故障检测功能(或故障定位功能)处于开启状态时，第二按键304(或第三按键306)处于第二显示状态3042(或第四显示状态3062)。例如，在第二按键304处于第一显示状态3041时，响应于用户对第二按键304的点击操作，终端设备300可以向控制器14发送指令，以指示控制器14开启故障检测功能。在故障检测功能开启后，控制器14可以向终端设备300发送指令，以指示终端设备300将第二按键304的显示状态切换至第二显示状态3042。
在一些示例中，若检测到多联机空调系统10中存在电子膨胀阀故障，则控制器14可以通过通信器109向终端设备300发送指令，以使终端设备300显示如图8所示的提示框305。示例性地，提示框305中的提示信息为“检测到多联机空调系统存在电子膨胀阀故障，是否立即进行故障定位？”，以提示用户选择是否开启故障定位功能。例如，响应于用户对提示框305中的“确定”按钮的点击操作，终端设备300可以向控制器14发送指令，以指示控制器14开启故障定位功能。在故障定位功能开启后，控制器14可以向终端设备300发送指令，以指示终端设备300将第三按键306的显示状态从第三显示状态3061切换至第四显示状态3062。
在另一些实施例中，多联机空调系统10可以在工作预设时长后自动开启故障检测功能和故障定位功能。示例性地，该预设时长可以由用户或制造商预先设定。
在故障定位功能开启之后，控制器14开始获取多个室内机的特征数据。
在一些示例中，如图2所示，多联机空调系统10包括多个第一温度传感器101和多个第二温度传感器102，以分别检测与多个室内机13连接的液管16的温度值和与多个室内机13连接的气管15的温度值。如图9所示，该多个第一温度传感器101与多个室内机13的室内换热器131对应，且设置于对应的室内换热器131所连接的气管15中，以检测 对应的气管15的温度值。该多个第二温度传感器102与多个室内机13的室内换热器131对应，且设置于对应的室内换热器131所连接的液管16中，以检测对应的液管16的温度值。控制器14与多个第一温度传感器101和多个第二温度传感器102耦接，以获取与多个室内机13中的每个室内机对应连接的液管16的温度值和与该室内机对应连接的气管15的温度值之间的温度差值。
在一些实施例中，每个室内机的特征数据还可以包括以下至少之一：压缩机111的排气压力值、压缩机111的吸气压力值、压缩机111的排气温度值、压缩机111的吸气温度值、该室内机的出风口133的出风温度值或该室内机的回风口134的回风温度值。在该实施例中，除上述多个第一温度传感器101和多个第二温度传感器102之外，多联机空调系统10包括多个其他的温度传感器和多个压力传感器，以检测上述各个特征数据。
在一些示例中，如图2所示，多联机空调系统10包括第一压力传感器107和第二压力传感器108。第一压力传感器107设置于压缩机111的排气口处，且被配置为检测压缩机111的排气压力值；第二压力传感器108设置于压缩机111的吸气口处，且被配置为检测压缩机111的吸气压力值。控制器14与第一压力传感器107和第二压力传感器108耦接，以获取排气压力值和吸气压力值。
在一些示例中，多联机空调系统10包括第三温度传感器103、第四温度传感器104、多个第五温度传感器105和多个第六温度传感器106。第三温度传感器103设置于压缩机111的排气口处，且被配置为检测压缩机111的排气温度值；第四温度传感器104设置于压缩机111的吸气口处，且被配置为检测压缩机111的吸气温度值。多个第五温度传感器105与多个室内机13对应，且设置于对应的室内机13的出风口133处，以检测出风口133的出风温度值；多个第六温度传感器106与多个室内机13对应，且设置于对应的室内机13的回风口134处，以检测回风口134的回风温度值。控制器14与第三温度传感器103、第四温度传感器104、多个第五温度传感器105和多个第六温度传感器106耦接，以获取排气温度值、吸气温度值、出风温度值和回风温度值。
S102、根据多个室内机13中的每个室内机的特征数据，确定多个室内机13中的异常室内机。
上述异常室内机是指处于异常运行状态下的室内机13，即对应的电子膨胀阀12为故障电子膨胀阀的室内机13。同理，当室内机13对应的电子膨胀阀12不是故障电子膨胀阀时，可以理解为该室内机13处于正常运行状态下。
需要说明的是，多联机空调系统10中的电子膨胀阀故障，会引起多个室内机13的特征数据变化。例如，多联机空调系统10正常运行时，与任一个室内机对应连接的液管16的温度值和与该室内机对应连接的气管15的温度值之间的温度差值小于一定阈值。若某个电子膨胀阀12故障导致该电子膨胀阀12不能正常开启，则会导致与该电子膨胀阀12对应的室内机13中的冷媒量不足，从而导致该室内机13不能正常蒸发冷媒或冷凝冷媒，进而体现为与该室内机13连接的液管16的温度值和与该室内机13连接的气管15的温度值之间的温度差值增大至超过该一定阈值。因此，控制器14可以根据任一个室内机的特征数据，判断该室内机是否为异常室内机。
另外，由于多联机空调系统10中的各个部件相互配合形成一个整体，因此，若多联机空调系统10中存在异常室内机，则整个多联机空调系统10中其他部件处的运行数据也会产生变化。因此，上述排气压力值、吸气压力值、排气温度值、吸气温度值、室内机的出风温度值和室内机的回风温度值等任一运行数据也可以作为该室内机的特征数据。
在一些实施例中，控制器14可以将多个室内机中的每个室内机的特征数据输入至基于深度神经网络(Deep Neural Networks，DNN)的故障识别模型中，以得到故障识别结果。深度神经网络DNN是机器学习(Machine Learning，ML)领域中的一种技术。由于基于深度神经网络DNN的故障识别模型可以对多标签进行输出，因此，该故障识别结果可以指示多个室内机13中的每个室内机是否为异常室内机。这样，控制器14可以根据该故障识别结果确定多个室内机13中的异常室内机。
在一些实施例中，控制器14的存储器中预先存储有基于深度神经网络DNN的故障识 别模型。在一些示例中，控制器14或其他具备处理能力的设备可以根据多个室内机13处于正常运行状态下的历史特征数据集以及处于异常运行状态下的历史特征数据集，训练基于深度神经网络的故障识别模型，以得到训练后的基于深度神经网络DNN的故障识别模型，并将该训练后的故障识别模型存储到控制器14的存储器中。
S103、将与异常室内机对应的电子膨胀阀确定为故障电子膨胀阀。
在一些实施例中，控制器14可以从多个室内机13中确定出一个或多个异常室内机，进而将与该一个或多个异常室内机对应的一个或多个电子膨胀阀12确定为故障电子膨胀阀。
本公开实施例提供的多联机空调系统10，在多联机空调系统10发生电子膨胀阀故障的情况下，可以获取多联机空调系统10中的多个室内机13的特征数据，进而根据多个室内机13的特征数据确定多个室内机13中的异常室内机，并将与该异常室内机对应的电子膨胀阀12确定为故障电子膨胀阀。这样，能够精准地定位出多联机空调系统10中的故障电子膨胀阀，无需专业的维修人员基于个人经验、且耗费大量时间观察和分析出故障电子膨胀阀，从而能够提高对多联机空调系统10中的故障电子膨胀阀进行定位的准确性和自动化程度，进而能够提升多联机空调系统10的故障定位效率。
下面主要结合附图，对控制器14检测多联机空调系统10是否发生了电子膨胀阀故障的方法，进行示例性介绍。如图10所示，控制器14可以通过执行步骤S201至步骤S203，判断多联机空调系统10是否发生了电子膨胀阀故障。
S201、获取多联机空调系统10的运行数据。
上述运行数据为多联机空调系统10在运行过程中产生的参数信息。该运行数据例如包括以下至少之一：压缩机111的工作电流值、压缩机111的排气压力值、压缩机111的排气温度值、多个室内机13的出风口133的出风温度值和多个室内机13的回风口134的回风温度值。
在一些实施例中，如前所述，控制器14开启故障检测功能后，控制器14可以获取多联机空调系统10的运行数据。
需要说明的是，本公开实施例中对上述特征数据和上述运行数据的举例是示例性的，该特征数据和该运行数据还可以包括与多联机空调系统10的运行相关的其他数据，在此不一一赘述。
S202、根据该运行数据，判断多联机空调系统10是否发生电子膨胀阀故障。
在一些实施例中，控制器14可以将多联机空调系统10的运行数据输入至基于支持向量机(Support Vector Machine，SVM)的故障诊断模型中，以得到故障诊断结果，该故障诊断结果指示了多联机空调系统10是否发生了电子膨胀阀故障。这样，控制器14可以根据该故障诊断结果判断多联机空调系统10是否发生了电子膨胀阀故障。示例性地，支持向量机SVM是一种按照监督学习方式对数据进行二元分类的广义线性分类器，支持向量机SVM的二分性能较好，因此，通过基于支持向量机SVM的故障诊断模型，可以提高判断多联机空调系统10是否发生电子膨胀阀故障的准确性。
在一些实施例中，控制器14的存储器中预先存储有基于支持向量机SVM的故障诊断模型。在一些示例中，控制器14或其他具备处理能力的设备可以根据多联机空调系统10未发生电子膨胀阀故障的情况下的历史运行数据集以及发生了电子膨胀阀故障的情况下的历史运行数据集，训练基于支持向量机SVM的故障诊断模型，以得到训练后的基于支持向量机SVM的故障诊断模型，并将该训练后的故障诊断模型存储到控制器14的存储器中。
在一些实施例中，若控制器14判断多联机空调系统10发生了电子膨胀阀故障，则控制器14执行上述步骤S101至步骤S103。
在一些实施例中，若控制器14判断多联机空调系统10未发生电子膨胀阀故障，则控制器14执行下述步骤S203。
S203、发出第一提示信息。
上述第一提示信息用于提示多联机空调系统10未发生电子膨胀阀故障。
示例性地，当多个室内机13包括显示器时，该第一提示信息可以为通过该显示器显示的文字、图片等信息。或者，当室内机13包括扬声器时，该第一提示信息可以为通过该扬声器发出的声音信息。又或者，当多联机空调系统10与用户的终端设备通信连接时，该第一提示信息可以为通过该终端设备发出的文字、图片、声音、震动等信息。需要说明的是，该第一提示信息还可以为其他形式的信息，例如灯光信息等，本公开对此不作限制。
在一些实施例中，在控制器14确定出故障电子膨胀阀之后，即，在上述步骤S103之后，控制器14可以发出第二提示信息，以提示该故障电子膨胀阀发生了故障。在一些示例中，如图11所示，控制器14通过执行下述步骤S301至步骤S303，发出该第二提示信息。
S301、在确定出故障电子膨胀阀之后，获取该故障电子膨胀阀的开度。
如前所述，控制器14通过调节电子膨胀阀12的开度，调节与该电子膨胀阀12对应的室内机13的冷媒输入量或冷媒输出量。因此，异常室内机处于异常工作状态通常是由与该异常室内机对应的电子膨胀阀的开度异常引起的。并且，该电子膨胀阀的开度可以表征该电子膨胀阀的故障程度。
S302、根据该故障电子膨胀阀的开度，确定该故障电子膨胀阀的故障等级。
在一些实施例中，控制器14可以根据故障电子膨胀阀的开度与故障等级之间的第一对应关系，确定故障电子膨胀阀的故障等级。该第一对应关系可以预先存储在控制器14的存储器中。
需要说明的是，多个电子膨胀阀12的正常开度与多联机空调系统10的工作状态有关。
在一些示例中，若多联机空调系统10处于制热工作状态下，则多个电子膨胀阀12的正常开度应该为100％(即多个电子膨胀阀12应该完全开启)。在该示例中，故障电子膨胀阀的开度越小，说明该故障电子膨胀阀的故障等级越高。示例性地，在多联机空调系统10处于制热工作状态下时，故障电子膨胀阀的开度与故障等级的第一对应关系如下述表1所示。
表1
故障电子膨胀阀的开度 故障等级
75％至99％ 一级
50％至74％ 二级
24％至49％ 三级
23％以下 四级
参照表1，若故障电子膨胀阀的开度位于75％至99％的区间范围内，则控制器14可以确定该故障电子膨胀阀的故障等级为一级。若故障电子膨胀阀的开度位于50％至74％的区间范围内，则控制器14可以确定该故障电子膨胀阀的故障等级为二级。若故障电子膨胀阀的开度位于24％至49％的区间范围内，则控制器14可以确定该故障电子膨胀阀的故障等级为三级。若故障电子膨胀阀的开度位于23％以下，则控制器14可以确定该故障电子膨胀阀的故障等级为四级。需要说明的是，从“一级”、“二级”、“三级”到“四级”，故障电子膨胀阀的故障等级依次升高，且对该故障电子膨胀阀进行检修的紧迫性也依次升高。
在另一些示例中，若多联机空调系统10处于制冷工作状态下，则多个电子膨胀阀12的正常开度应该为12％至13％。在该示例中，在故障电子膨胀阀的开度大于13％的情况下，该故障电子膨胀阀的开度越大，说明该故障电子膨胀阀的故障等级越高，从而越急需对该故障电子膨胀阀进行检修。示例性地，多联机空调系统10处于制冷工作状态下时，故障电子膨胀阀的开度与故障等级的第一对应关系如下述表2所示。
表2
故障电子膨胀阀的开度 故障等级
75％-100％ 四级
50％-74％ 三级
25％-49％ 二级
14％-24％ 一级
12％以下 一级
参照表2，若故障电子膨胀阀的开度位于75％至100％的区间范围内，则控制器14可以确定该故障电子膨胀阀的故障等级为四级。若故障电子膨胀阀的开度位于50％至74％的区间范围内，则控制器14可以确定该故障电子膨胀阀的故障等级为三级。若故障电子膨胀阀的开度位于25％至49％的区间范围内，则控制器14可以确定该故障电子膨胀阀的故障等级为二级。若故障电子膨胀阀的开度位于14％至24％的区间范围内、或者位于12％以下，则控制器14可以确定该故障电子膨胀阀的故障等级为一级。
S303、发出第二提示信息。
上述第二提示信息用于提示该故障电子膨胀阀的故障等级。
在一些实施例中，与上述步骤S203中发出第一提示信息的方式类似，控制器14可以通过室内机13(例如异常室内机)的显示器、扬声器、终端设备等发出第二提示信息。示例性地，以故障电子膨胀阀的故障等级为四级、且故障电子膨胀阀的编号为001为例，如图12所示，该第二提示信息例如可以为“编号为001的电子膨胀阀发生严重故障，建议立即检修！”这一文字信息。
上述实施例中的多联机空调系统10，在定位出多联机空调系统10中的故障电子膨胀阀之后，可以根据该故障电子膨胀阀的开度与故障等级之间的第一对应关系，确定该故障电子膨胀阀的故障等级，并发出与该故障电子膨胀阀的故障等级对应的第二提示信息，以便于提示用户根据故障电子膨胀阀的故障等级合理安排该故障电子膨胀阀的检修工作，避免电子膨胀阀故障引起多联机空调系统10的制冷或制热效果下降。
本公开一些实施例还提供一种多联机空调系统的故障定位方法。该多联机空调系统例如可以为上述多联机空调系统10，该方法例如可以包括上述控制器14所执行的各个步骤。该方法所具备的有益效果至少包括上述多联机空调系统10所具备的有益效果，在此不再赘述。
由于不同机型的多联机空调系统的运行数据不同，因此，在相关技术中，需要分别采集各种机型的多联机空调系统在正常运行状态下的运行数据和在异常运行状态(发生故障的运行状态)下的运行数据作为样本集，以建立故障诊断模型。这样，能够使得故障诊断模型可以适用于多种机型的多联机空调系统，从而提高利用该故障诊断模型对多联机空调系统进行故障诊断的适配性和准确性。然而，由于需要采集多种机型的多联机空调系统的运行数据，因此这种故障诊断模型的训练方法会导致故障诊断模型的建立周期过长，进而导致利用该故障诊断模型对多联机空调系统进行故障诊断的效率较低。
基于上述技术问题，本公开一些实施例还提供一种多联机空调系统的故障诊断模型训练方法。该方法可以根据第一多联机空调系统在正常运行状态下的运行数据的值(即运行数据的正常值)和发生各种故障时的运行数据的值(即运行数据的故障值)，构建第一多联机空调系统的第一特征偏移空间，并基于第一多联机空调的运行数据的正常值与第二多联机空调的运行数据的正常值之间的差异，对第一特征偏移空间进行修正，得到第二多联机空调的第二特征偏移空间，从而可以根据该第二特征偏移空间和第二多联机空调系统的运行数据的正常值，得到第二多联机空调系统的运行数据的故障值，以用于建立第二多联机空调系统的故障诊断模型。这样，在建立第二多联机空调系统的故障诊断模型的过程中，无需在实际工况下采集第二多联机空调系统在各种故障运行状态下的运行数据，从而可以缩短该故障诊断模型的建立周期，进而提升利用该故障诊断模型对多联机空调系统进行故障诊断的效率。
如图13所示，上述多联机空调系统的故障诊断模型训练方法包括以下步骤S401至步骤S405。需要说明的是，该方法的执行主体可以为上述控制器14，也可以为其他具备处理能力的设备，例如服务器。后续实施例以控制器14执行该方法为例，进行示例性说明。另外，该多联机空调系统的结构和工作原理可以参照前述实施例中的多联机空调系统10，在此不再赘述。
S401、获取第一多联机空调系统的多个运行数据的正常值和故障值。
在一些实施例中，第一多联机空调系统可以称为实验多联机空调系统。第一多联机空调系统的存储器中存储有该第一多联机空调系统在各种工况下运行时所产生的历史运行数据。
上述运行数据例如包括压缩机111的吸气温度值、压缩机111的排气温度值、压缩机111的吸气压力值、压缩机111的排气压力值、多个电子膨胀阀12的开度、压缩机111的工作电流值、室外机11所处的环境温度值、多个室内机所处的环境温度值的平均值、压缩机111的吸气过热度、压缩机111的排气过热度、室外机11的工作温度值和多个室内机13的工作温度值。
示例性地，吸气过热度是指压缩机111的吸气温度值与冷媒在吸气压力值下的饱和温度之间的差值；排气过热度是指压缩机111的排气温度值与冷媒在排气压力值下的饱和温度之间的差值。室外机11的工作温度值例如可以为室外换热器112的工作温度值。多个室内机13中的某个室内机13的工作温度值例如可以为该某个室内机13的室内换热器131的工作温度值。
在一些示例中，如图14所示，上述步骤S101可以具体实现为以下步骤S4011和步骤S4012。
S4011、获取第一多联机空调系统的历史运行数据。
其中，历史运行数据包括历史时段内，第一多联机空调系统在正常运行状态下产生的正常运行数据以及第一多联机空调系统在发生各种故障时所产生的各种故障运行数据。需要说明的是，本公开不限制历史时段的长短。
S4012、对该历史运行数据进行解析，确定该第一多联机空调系统的多个运行数据在该第一多联机空调系统处于正常运行状态下的正常值和在该第一多联机空调系统发生故障时的故障值。
需要说明的是，多个运行数据中的任一个运行数据的正常值与该运行数据的故障值是不同的，因此控制器14可以对多联机空调系统的历史运行数据进行解析，区分出该多联机空调系统在正常运行状态下所产生的多个运行数据和该多联机空调系统在发生故障时所产生的多个运行数据，进而获取多个运行数据中的每个运行数据的正常值和故障值。示例性地，多联机空调系统可能发生的故障包括冷媒泄漏、参与循环的冷媒过量、或电子膨胀阀12开度异常等。
示例性地，控制器14可以根据多个运行数据所对应的预设取值范围，对历史运行数据进行解析。若多个运行数据中的任一个运行数据的值位于对应的预设取值范围内，则确定该运行数据的该值为正常值。若任一个运行数据的值位于对应的预设取值范围外，则确定该运行数据的该值为故障值。其中，预设取值范围例如可以由工作人员或制造商预先设定。
需要说明的是，当多联机空调系统产生不同故障时，多个运行数据的故障值通常也是不同的。控制器14在对第一多联机空调的历史运行数据进行解析时，可以将该第一多联机空调系统的故障值与该第一多联机空调系统发生的故障进行对应。
S402、基于该第一多联机空调系统的多个运行数据的正常值和故障值，确定该第一多联机空调系统的第一特征偏移空间。
需要说明的是，由于多个运行数据的正常值和故障值之间存在偏差，因此可以根据多个运行数据的故障值与正常值之间的偏移量，构建第一多联机空调系统的第一特征偏移空间。第一特征偏移空间包括第一多联机空调系统的多个运行数据中的各个运行数据的偏移量。
在一些实施例中，多联机空调系统的多个运行数据的正常值组成的空间可以称为该多联机空调系统的特征空间。
示例性地，第一多联机空调系统的第一特征空间例如可以表示为如下矩阵：
X＝[x 1 x 2…x n-1 x n]
其中，x j为某一个运行数据的列向量，j的取值为1至n；n为大于1的整数。
示例性地，某一个故障下，第一多联机空调系统的第一特征偏移空间可以表示为：
Δxi＝[Δxi 1 Δxi 2…Δxi n-1 Δxi n]
其中，Δxi j为某一个运行数据的偏移量，j的取值为1至n；n为大于1的整数。
S403、基于第一多联机空调系统的多个运行数据的正常值与第二多联机空调系统的多个运行数据的正常值之间的差异，对第一特征偏移空间进行修正，得到第二多联机空调系统的第二特征偏移空间。
需要说明的是，第一多联机空调系统的多个运行数据的正常值与第二多联机空调系统的多个运行数据的正常值之间有差异时，可以认为第一多联机空调系统的机型与第二多联机空调系统的机型之间有差异。示例性地，第一多联机空调系统的机型为单冷型，第二多联机空调系统的机型为热泵型。
另外，由于导致各种多联机空调系统产生故障的热物理机理相似，不同机型的多联机空调系统之间通常具有相似的特征偏移空间。因此，可以基于第一多联机空调系统的机型与第二多联机空调系统的机型之间的差异，对第一特征偏移空间进行修正，以得到第二多联机空调系统的第二特征偏移空间。
示例性地，控制器14的存储器中预先存储有多联机空调系统的机型与修正系数之间的第二对应关系。该修正系数例如为其他多联机空调系统的特征偏移空间与第一多联机空调系统的第一特征偏移空间之间的比值。在确定第一多联机空调系统的多个运行数据的正常值与第二多联机空调系统的多个运行数据的正常值之间的差异后，控制器14可以根据第一多联机空调系统的机型，确定第二多联机空调系统的机型，从而可以根据第二多联机空调系统的机型和该第二对应关系，确定第二特征偏移空间相对于第一特征偏移空间的修正系数，进而根据该修正系数对第一特征偏移空间进行修正，并得到第二特征偏移空间。例如，控制器14将该修正系数与第一特征偏移空间相乘，以得到第二特征偏移空间。
示例性地，上述第二对应关系可以通过实验或模拟获得。
S404、基于第二多联机空调系统的多个运行数据的正常值以及第二特征偏移空间，确定第二多联机空调系统的多个运行数据的故障值。
在一些实施例中，控制器14可以对第二多联机空调系统在历史时段内处于正常运行状态下的历史运行数据进行解析，确定出第二多联机空调系统的多个运行数据的正常值，从而根据第二多联机空调系统的多个运行数据的正常值和第二特征偏移空间得到第二多联机空调系统的多个运行数据的故障值。
示例性地，控制器14可以将第二多联机空调系统的多个运行数据的正常值与第二特征偏移空间相加，以得到第二多联机空调系统的多个运行数据的故障值。
S405、基于第二多联机空调系统的多个运行数据的正常值和故障值，对故障诊断模型进行训练。
在一些实施例中，控制器14可以将第二多联机空调系统的多个运行数据的正常值和故障值作为样本集，对故障诊断模型进行训练。
在一些示例中，上述故障诊断模型是基于一维卷积神经网络(Convolutional Neural Networks，CNN)的故障诊断模型。其中，卷积神经网络是一种多层感知器。卷积神经网络的工作原理主要涉及三个基本概念：局部感受野、池化和共享权重。一维卷积神经网络是具有一维输入数据的卷积神经网络，具有分类能力，因此一维卷积神经网络可用于多联机空调系统的故障检测和诊断。故障检测是检测系统是否发生故障的过程，故障诊断是获取故障的故障类型、故障严重性等详细信息。
在一些实施例中，如图15所示，故障诊断模型可以包括：输入层、卷积层、池化层、全连接层以及输出层。
卷积层是卷积神经网络中的关键结构，卷积层的功能为使用一系列滤波器对来自输入层的输入数据进行卷积，以形成一系列原始输入数据的特征映射并输出。当一个滤波器对卷积层的输入数据进行卷积时，一个局部感受野会在该输入数据上反复移动。局部感受野中的数据会与滤波器中的权值矩阵进行点积运算，并在加上一个固定的偏置值后 形成一个输出矩阵，该输出矩阵即是原始输入数据的一个特征映射。滤波器对输入的卷积操作具有共享权重的特点，即一个滤波器对局部感受野中的数据使用的权值矩阵和偏置是相同的。
示例性地，激活函数(例如ReLU激活函数)可以应用于卷积层的输出以进行去线性化，从而提升卷局曾的非线性拟合能力。例如，ReLU激活函数可以表示为下述公式(1)：
Figure PCTCN2023071431-appb-000001
第i个卷积层的输出a i可以表示为下述公式(2)：
Figure PCTCN2023071431-appb-000002
其中，
Figure PCTCN2023071431-appb-000003
为卷积运算，σ为ReLU激活函数，b i为偏置值，w i为权重矩阵。
卷积层的输出可以输入到池化层中。池化层会将输入的数据划分为多个池化区域，并对各个池化区域分别进行概括并形成输出。池化层的输出是其输入的一般化和精简特征映射。
全连接层在整个卷积神经网络中起到“分类器”的作用，可以把分布式特征映射到样本标记空间中。也就是说，全连接层用于将池化层的输出进行整合以得到全连接层的输出，并将全连接层的输出输入至输出层中。
示例性地，可以采用分类网络(softmax)层作为卷积神经网络的输出层。这样，根据softmax层输出中的概率向量最大值所在的维度，即可确定softmax层的输入数据的分类结果。
本公开实施例提供的多联机空调系统的故障诊断模型训练方法，可以根据第一多联机空调系统的多个运行数据的正常值和故障值，得到用于表征第一多联机空调系统的多个运行数据的正常值与多种故障值之间的偏移量的第一特征偏移空间，并根据第二多联机空调系统的机型与第一多联机空调系统的机型之间的差异，对第一特征偏移空间进行修正，以得到第二多联机空调系统的第二特征偏移空间。从而可以根据第二特征偏移空间和第二多联机空调系统的多个运行数据的正常值，得到第二多联机空调系统的多个运行数据的故障值。进而可以使用第二多联机空调系统的多个运行数据的故障值与正常值对故障诊断模型进行训练，以得到训练后的、适用于第二多联机空调系统的故障诊断模型。这样，无需在实际工况中采集第二多联机空调系统发生各种故障时多个运行数据的故障值即可建立第二多联机空调系统的故障诊断模型，从而能够缩短该故障诊断模型的建立周期，进而提升利用该故障诊断模型对第二多联机空调系统进行故障诊断的效率。
在一些实施例中，如图16所示，上述步骤S405可以具体实现为以下步骤S501和步骤S502。
S501、基于第二多联机空调系统的多个运行数据的正常值和故障值，从第二多联机空调系统的多个运行数据中确定出至少一个第一运行数据。
需要说明的是，第二多联机空调系统的多个运行数据中可能掺杂了一些与训练故障诊断模型无关的冗余运行数据，为了提升故障诊断模型的训练速度，需要对多个运行数据进行数据筛选。示例性地，上述至少一个第一运行数据为不同机型的多联机空调系统所共有的、且与训练故障诊断模型相关性较高的运行数据。
示例性地，控制器14可以计算出第二多联机空调系统的多个运行数据中的各个运行数据的正常值与故障值之间的差值，并将多个差值中大于预设阈值的差值所对应的运行数据作为备选运行数据，进而从备选运行数据中提取出至少一个各种机型的多联机空调系统所共有的运行数据作为第一运行数据。其中，预设阈值可以由工作人员或制造商预先设定。
需要说明的是，某个运行数据的正常值与故障值之间的差值越大，说明该运行数据越能反映出第二多联机空调系统发生了故障，因此，将该运行数据作为训练故障检测模型的第一运行数据，有利于提高训练后的故障检测模型检测故障的准确性。
S502、根据第二多联机空调系统的至少一个第一运行数据的正常值和故障值，对故 障诊断模型进行训练。
上述实施例中的多联机空调系统的故障诊断模型训练方法，通过对第二多联机空调系统的多个运行数据进行数据筛选，可以提取出第二多联机空调系统的多个运行数据中的至少一个第一运行数据，进而利用该至少一个第一运行数据的正常值和故障值，对故障诊断模型进行训练。由于精简了故障诊断模型的训练样本集，因此，能够提升故障诊断模型的训练速度，进而提升利用该故障诊断模型对多联机空调系统进行故障诊断的效率。
在一些实施例中，如图17所示，步骤S502可以具体实现为以下步骤S601至步骤S603。
S601、基于第二多联机空调系统的至少一个第一运行数据的正常值和故障值，对自编码器模型进行训练。
自编码器模型是一种无监督式学习模型。示例性地，如图18所示，自编码器包括编码器和解码器。编码器被配置为将高维输入数据(即原始特征数据)编码为低维隐变量(即压缩数据)，从而使自编码器模型学习信息量较高的数据。解码器被配置为将低维隐变量还原为高维输入数据的原始维度。原始特征数据经编码器编码、再经解码器解码的过程即为该原始特征数据的数据重构过程。示例性地，训练自编码器模型的过程可以包括如下步骤1至步骤4。
步骤1、控制器14将至少一个第一运行数据的正常值和故障值转换为特征向量矩阵X＝{X 1,X 2,…,X n}，并将该特征向量矩阵输入自编码器模型。
其中，X 1,X 2,…,X n表示该至少一个第一运行数据的正常值和故障值。
步骤2、编码器通过如下述公式(3)所示的方式将原始特征数据压缩到隐藏层。
H＝σ e(W eX+B e)     公式(3)
其中，σ e为Sigmoid函数，X为原始特征数据集，W e为编码器权重参数，B e为编码器偏差，H为原始特征数据在隐含层的映射。
步骤3、解码器通过如下述公式(4)所示的方式重构原始特征数据并输出重构特征数据。
Figure PCTCN2023071431-appb-000004
其中，σ d为Sigmoid函数，W d是解码器的权重参数，B d是解码器的偏差，
Figure PCTCN2023071431-appb-000005
是重构后的原始特征数据。
步骤4、训练自编码器模型，减小重构误差，得到相应的W e、W d和
Figure PCTCN2023071431-appb-000006
示例性地，重构误差的计算公式如下述公式(5)所示：
Figure PCTCN2023071431-appb-000007
其中，
Figure PCTCN2023071431-appb-000008
为softmax重构误差，X i为原始特征数据，
Figure PCTCN2023071431-appb-000009
为重构特征数据。
S602、将第二多联机空调系统的至少一个第一运行数据的正常值和故障值输入至训练后的自编码器模型中，得到第二多联机空调系统的至少一个第一运行数据的数据重构正常值和数据重构故障值。
S603、基于该数据重构正常值和该数据重构故障值，对故障诊断模型进行训练。
上述实施例中的多联机空调系统的故障诊断模型训练方法，通过自编码器对第二多联机空调系统的至少一个第一运行数据的正常值和故障值进行数据重构，可以降低该至少一个第一运行数据的正常值和故障值的数据噪声(即数据中由于测量等原因引起的随机误差)，从而去除该至少一个第一运行数据的正常值和故障值中对训练故障检测模型具有误导作用的数据，进而提高利用该故障检测模型进行故障检测的准确性。
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申请的精神的情况下对实施例的某些要素进行修改和替换。本申请的范围受所附权利要求的限制。

Claims (17)

  1. 一种多联机空调系统，包括：
    室外机；
    多个室内机，所述多个室内机中的每个室内机对应连接有气管和液管，以通过所述气管和所述液管与所述室外机连通；
    多个电子膨胀阀，与所述多个室内机对应；所述多个电子膨胀阀分别设置在对应的室内机所连接的所述液管中，且被配置为控制所述对应的室内机的冷媒输出量或冷媒输入量；以及
    控制器，被配置为：
    在所述多联机空调系统发生电子膨胀阀故障的情况下，获取所述多个室内机中的每个室内机的特征数据；每个室内机的所述特征数据包括与所述室内机对应连接的所述液管的温度值和与所述室内机对应连接的所述气管的温度值之间的温度差值；
    根据所述多个室内机中的每个室内机的所述特征数据，确定所述多个室内机中的异常室内机；
    将与所述异常室内机对应的电子膨胀阀确定为故障电子膨胀阀。
  2. 根据权利要求1所述的多联机空调系统，其中，
    所述控制器被配置为：
    将所述多个室内机中的每个室内机的所述特征数据输入至基于深度神经网络DNN的故障识别模型中，根据所述故障识别模型的故障识别结果，确定所述多个室内机中的所述异常室内机；
    所述室外机包括压缩机；
    所述多个室内机中的每个室内机包括：出风口和回风口；
    每个室内机的所述特征数据还包括以下至少之一：所述压缩机的排气压力值、所述压缩机的吸气压力值、所述压缩机的排气温度值、所述压缩机的吸气温度值、所述室内机的所述出风口的出风温度值或所述室内机的所述回风口的回风温度值。
  3. 根据权利要求1或2所述的多联机空调系统，其中，
    所述室外机包括压缩机；
    所述多个室内机中的每个室内机包括：出风口和回风口；
    所述控制器还被配置为：
    获取所述多联机空调系统的运行数据，所述运行数据包括以下至少之一：所述压缩机的工作电流值、所述压缩机的排气压力值、所述压缩机的排气温度值、所述多个室内机的所述出风口的出风温度值或所述多个室内机的所述回风口的回风温度值；
    根据所述运行数据，判断所述多联机空调系统是否发生所述电子膨胀阀故障。
  4. 根据权利要求3所述的多联机空调系统，其中，
    所述控制器被配置为：
    将所述运行数据输入至基于支持向量机SVM的故障诊断模型中，根据所述故障诊断模型的故障诊断结果，判断所述多联机空调系统是否发生所述电子膨胀阀故障。
  5. 根据权利要求1至4中任一项所述的多联机空调系统，其中，所述控制器还被配置为：
    在所述多联机空调系统未发生所述电子膨胀阀故障的情况下，发出第一提示信息，所述第一提示信息用于提示所述多联机空调系统未发生所述电子膨胀阀故障。
  6. 根据权利要求1至5中任一项所述的多联机空调系统，其中，所述控制器还被配置为：
    在确定出所述故障电子膨胀阀之后，获取所述故障电子膨胀阀的开度；
    根据所述故障电子膨胀阀的开度，确定所述故障电子膨胀阀的故障等级；
    发出第二提示信息，所述第二提示信息用于提示所述故障电子膨胀阀的所述故障等级。
  7. 一种多联机空调系统的故障定位方法，其中，所述多联机空调系统包括：
    室外机；
    多个室内机，所述多个室内机中的每个室内机对应连接有气管和液管，以通过所述气管和所述液管与所述室外机连通；以及
    多个电子膨胀阀，与所述多个室内机对应；所述多个电子膨胀阀分别设置在对应的室内机所连接的所述液管中，且被配置为控制所述对应的室内机的冷媒输出量或冷媒输入量；
    所述方法包括：
    在所述多联机空调系统发生电子膨胀阀故障的情况下，获取所述多个室内机中的每个室内机的特征数据；每个室内机的所述特征数据包括与所述室内机对应连接的所述液管的温度值和与所述室内机对应连接的所述气管的温度值之间的温度差值；
    根据所述多个室内机中的每个室内机的所述特征数据，确定所述多个室内机中的异常室内机；
    将与所述异常室内机对应的电子膨胀阀确定为故障电子膨胀阀。
  8. 根据权利要求7所述的方法，其中，根据所述多个室内机中的每个室内机的所述特征数据，确定所述多个室内机中的所述异常室内机，包括：
    将所述多个室内机中的每个室内机的所述特征数据输入至基于深度神经网络DNN的故障识别模型中，根据所述故障识别模型的故障识别结果，确定所述多个室内机中的所述异常室内机；
    所述室外机包括压缩机；
    所述多个室内机中的每个室内机包括：出风口和回风口；
    每个室内机的所述特征数据还包括以下至少之一：所述压缩机的排气压力值、所述压缩机的吸气压力值、所述压缩机的排气温度值、所述压缩机的吸气温度值、所述室内机的所述出风口的出风温度值或所述室内机的所述回风口的回风温度值。
  9. 根据权利要求7或8所述的方法，其中，
    所述室外机包括压缩机；
    所述多个室内机中的每个室内机包括：出风口和回风口；
    所述方法还包括：
    获取所述多联机空调系统的运行数据，所述运行数据包括以下至少之一：所述压缩机的工作电流值、所述压缩机的排气压力值、所述压缩机的排气温度值、所述多个室内机的所述出风口的出风温度值或所述多个室内机的所述回风口的回风温度值；
    根据所述运行数据，判断所述多联机空调系统是否发生所述电子膨胀阀故障。
  10. 根据权利要求9所述的方法，其中，根据所述运行数据，判断所述多联机空调系统是否发生所述电子膨胀阀故障，包括：
    将所述运行数据输入至基于支持向量机SVM的故障诊断模型中，根据所述故障诊断模型的故障诊断结果，判断所述多联机空调系统是否发生所述电子膨胀阀故障。
  11. 根据权利要求7至10中任一项所述的方法，还包括：
    在所述多联机空调系统未发生所述电子膨胀阀故障的情况下，发出第一提示信息，所述第一提示信息用于提示所述多联机空调系统未发生所述电子膨胀阀故障。
  12. 根据权利要求7至11中任一项所述的方法，还包括：
    在确定出所述故障电子膨胀阀之后，获取所述故障电子膨胀阀的开度；
    根据所述故障电子膨胀阀的开度，确定所述故障电子膨胀阀的故障等级；
    发出第二提示信息，所述第二提示信息用于提示所述故障电子膨胀阀的所述故障等级。
  13. 一种多联机空调系统的故障诊断模型训练方法，包括：
    获取第一多联机空调系统的多个运行数据的正常值和故障值；
    基于所述第一多联机空调系统的所述多个运行数据的正常值和故障值，确定所述第一多联机空调系统的第一特征偏移空间，所述多个运行数据为所述多联机空调系统在运行过程中产生的参数信息，所述第一特征偏移空间包括所述第一多联机空调系统的所述多个运行数据中的、各个运行数据的故障值与正常值之间的差值；
    基于所述第一多联机空调系统的所述多个运行数据的正常值与第二多联机空调系统的所述多个运行数据的正常值之间的差异，对所述第一特征偏移空间进行修正，得到第二多联机空调系统的第二特征偏移空间；
    基于所述第二多联机空调系统的所述多个运行数据的正常值以及所述第二特征偏移空间，确定所述第二多联机空调系统的所述多个运行数据的故障值；
    基于所述第二多联机空调系统的所述多个运行数据的正常值和故障值，对故障诊断模型进行训练。
  14. 根据权利要求13所述的方法，其中，基于所述第二多联机空调系统的所述多个运行数据的正常值和故障值，对所述故障诊断模型进行训练，包括：
    基于所述第二多联机空调系统的所述多个运行数据的正常值和故障值，从所述第二多联机空调系统的所述多个运行数据中确定出至少一个第一运行数据；
    根据所述第二多联机空调系统的所述至少一个第一运行数据的正常值和故障值，对所述故障诊断模型进行训练。
  15. 根据权利要求14所述的方法，其中，根据所述第二多联机空调系统的所述第一运行数据的正常值和故障值，对所述故障诊断模型进行训练，包括：
    基于所述第二多联机空调系统的所述至少一个第一运行数据的正常值和故障值，对自编码器模型进行训练；
    将所述第二多联机空调系统的所述至少一个第一运行数据的正常值和故障值输入至训练后的自编码器模型中，得到所述第二多联机空调系统的所述至少一个第一运行数据的数据重构正常值和数据重构故障值；
    基于所述数据重构正常值和所述数据重构故障值，对所述故障诊断模型进行训练。
  16. 根据权利要求13至15中任一项所述的方法，其中，所述多联机空调系统包括：
    室外机，且包括：
    压缩机，被配置为压缩冷媒，以使所述冷媒在所述多联机空调系统中循环；
    多个室内机，与所述室外机连通；
    多个电子膨胀阀，与所述多个室内机对应，且被配置为控制对应的室内机的冷媒输出量或冷媒输入量；
    所述多个运行数据包括所述压缩机的吸气温度值、所述压缩机的排气温度值、所述压缩机的吸气压力值、所述压缩机的排气压力值、所述多个电子膨胀阀的开度、所述压缩机的工作电流值、所述室外机所处的环境温度值、所述多个室内机所处的环境温度值的平均值、所述压缩机的吸气过热度、所述压缩机的排气过热度、所述室外机的工作温度值和所述多个室内机的工作温度值。
  17. 根据权利要求13至16中任一项所述的方法，其中，获取所述第一多联机空调系统的所述多个运行数据的正常值和故障值，包括：
    获取所述第一多联机空调系统的历史运行数据；
    对所述历史运行数据进行解析，确定所述第一多联机空调系统的所述多个运行数据在所述第一多联机空调系统处于正常运行状态下的正常值和在所述第一多联机空调系统发生故障时的故障值。
PCT/CN2023/071431 2022-04-11 2023-01-09 多联机空调系统、故障定位方法及故障诊断模型训练方法 WO2023197711A1 (zh)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN202210386517.3A CN114754413B (zh) 2022-04-11 2022-04-11 一种多联机空调系统及故障定位方法
CN202210386517.3 2022-04-11
CN202210682549.8 2022-06-16
CN202210682549.8A CN115095953B (zh) 2022-06-16 2022-06-16 一种故障诊断模型的训练方法及装置

Publications (1)

Publication Number Publication Date
WO2023197711A1 true WO2023197711A1 (zh) 2023-10-19

Family

ID=88328781

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/071431 WO2023197711A1 (zh) 2022-04-11 2023-01-09 多联机空调系统、故障定位方法及故障诊断模型训练方法

Country Status (1)

Country Link
WO (1) WO2023197711A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117948744A (zh) * 2024-02-29 2024-04-30 淮阴工学院 一种基于云网互联的电子膨胀阀健康管理系统

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007333219A (ja) * 2006-06-12 2007-12-27 Mitsubishi Electric Building Techno Service Co Ltd マルチ式空気調和システム
CN105021381A (zh) * 2014-04-30 2015-11-04 广东美的暖通设备有限公司 空调器中电子膨胀阀的故障检测方法和装置
CN106352472A (zh) * 2016-08-19 2017-01-25 广东美的暖通设备有限公司 多联机系统及其联动故障检测方法
CN106500238A (zh) * 2016-09-12 2017-03-15 珠海格力电器股份有限公司 电子膨胀阀故障检测方法、装置及多联机设备系统
CN109282424A (zh) * 2018-09-20 2019-01-29 广东美的暖通设备有限公司 空调器控制方法、空调器控制装置
CN110410936A (zh) * 2019-07-23 2019-11-05 宁波奥克斯电气股份有限公司 一种多联机系统故障检测方法、装置及多联机系统
CN111650917A (zh) * 2020-05-14 2020-09-11 中铁第四勘察设计院集团有限公司 一种设备的多维度状态在线监测方法及系统
CN112283876A (zh) * 2020-10-30 2021-01-29 青岛海尔空调电子有限公司 空调故障预测方法及空调
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
CN112907781A (zh) * 2021-02-07 2021-06-04 中国人民解放军国防科技大学 一种系统故障诊断方法、装置、计算机设备和存储介质
CN113033913A (zh) * 2021-04-16 2021-06-25 上海电气集团股份有限公司 空调故障预测性维护方法、系统、电子设备及存储介质
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
CN115095953A (zh) * 2022-06-16 2022-09-23 青岛海信日立空调系统有限公司 一种故障诊断模型的训练方法及装置

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007333219A (ja) * 2006-06-12 2007-12-27 Mitsubishi Electric Building Techno Service Co Ltd マルチ式空気調和システム
CN105021381A (zh) * 2014-04-30 2015-11-04 广东美的暖通设备有限公司 空调器中电子膨胀阀的故障检测方法和装置
CN106352472A (zh) * 2016-08-19 2017-01-25 广东美的暖通设备有限公司 多联机系统及其联动故障检测方法
CN106500238A (zh) * 2016-09-12 2017-03-15 珠海格力电器股份有限公司 电子膨胀阀故障检测方法、装置及多联机设备系统
CN109282424A (zh) * 2018-09-20 2019-01-29 广东美的暖通设备有限公司 空调器控制方法、空调器控制装置
CN110410936A (zh) * 2019-07-23 2019-11-05 宁波奥克斯电气股份有限公司 一种多联机系统故障检测方法、装置及多联机系统
CN111650917A (zh) * 2020-05-14 2020-09-11 中铁第四勘察设计院集团有限公司 一种设备的多维度状态在线监测方法及系统
CN112283876A (zh) * 2020-10-30 2021-01-29 青岛海尔空调电子有限公司 空调故障预测方法及空调
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
CN112907781A (zh) * 2021-02-07 2021-06-04 中国人民解放军国防科技大学 一种系统故障诊断方法、装置、计算机设备和存储介质
CN113033913A (zh) * 2021-04-16 2021-06-25 上海电气集团股份有限公司 空调故障预测性维护方法、系统、电子设备及存储介质
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
CN115095953A (zh) * 2022-06-16 2022-09-23 青岛海信日立空调系统有限公司 一种故障诊断模型的训练方法及装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117948744A (zh) * 2024-02-29 2024-04-30 淮阴工学院 一种基于云网互联的电子膨胀阀健康管理系统

Similar Documents

Publication Publication Date Title
US10747187B2 (en) Building management system with voting-based fault detection and diagnostics
US11886209B2 (en) HVAC system with data driven user interfaces for equipment commissioning and operation
US10700942B2 (en) Building management system with predictive diagnostics
US11747034B2 (en) Systems and methods for steady state detection
US7496472B2 (en) Method and system for assessing performance of control systems
US12093844B2 (en) Analysis system with machine learning based interpretation
US7031880B1 (en) Method and apparatus for assessing performance of an environmental control system
US20180087790A1 (en) Systems and methods for automatically creating and using adaptive pca models to control building equipment
US10372567B2 (en) Automatic fault detection and diagnosis in complex physical systems
Zhang et al. Fault detection and diagnosis for the screw chillers using multi-region XGBoost model
WO2023197711A1 (zh) 多联机空调系统、故障定位方法及故障诊断模型训练方法
CN108809663A (zh) 具有由以太网供电（PoE）独立供电的通信子系统的建筑物装置
WO2023169519A1 (zh) 多联机空调系统及多联机空调系统的容错控制方法
JP2005301582A (ja) プロセス管理装置
Wang et al. Modeling Variable Refrigerant Flow (VRF) systems in building applications: A comprehensive review
Ghimire et al. Fault diagnosis and augmented reality-based troubleshooting of HVAC systems
US20220333810A1 (en) Model sharing system, model management apparatus, and control apparatus for air conditioning apparatus
CN115307669B (zh) 用于检测被测系统的异常传感器的方法、设备和介质
AU2018348784B2 (en) Systems and a method for maintenance of HVAC systems
CN114659547B (zh) 用于定位异常传感器的方法、设备和介质
CN114484770B (zh) 空调控制系统
WO2024114675A1 (zh) 多联机空调系统及其控制方法
KR20220009052A (ko) 칠러 시스템 및 그 동작 방법
CN115358352B (zh) 用于定位异常传感器的方法、设备和介质
KR102723317B1 (ko) Hvac 시스템의 고장 진단 방법 및 이를 이용한 장치

Legal Events

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

Ref document number: 23787360

Country of ref document: EP

Kind code of ref document: A1