Diagnosis device, air conditioning device, and diagnosis method

Abstract

A diagnosis device (400) comprises: a refrigeration cycle control information acquisition unit (401) that acquires refrigeration cycle control information of a refrigeration cycle including a refrigerant compressor (211) that, by being driven by a motor (232), performs refrigerant compression; a motor control information acquisition unit (402) that acquires motor control information of the motor; a first physical quantity calculation unit (403) that calculates a first physical quantity of the refrigerant compression on the basis of the refrigeration cycle control information; a second physical quantity calculation unit (404) that calculates a second physical quantity of the refrigerant compression on the basis of the motor control information; a relationship information calculation unit (405) that calculates relationship information indicating the relationship between the first physical quantity and the second physical quantity; and a diagnosis unit (407) that diagnoses the deterioration state of the refrigerant compressor on the basis of the relationship information. The relationship information calculation unit calculates the relationship information on the basis of the distribution on a plane of the first physical quantity and the second physical quantity when the first physical quantity and the second physical quantity are plotted on the plane. The diagnosis unit diagnoses the deterioration state of the refrigerant compressor on the basis of the relationship information.

Description

Diagnostic device, air conditioning device, and diagnostic method

[0001] This disclosure relates to a diagnostic device, an air conditioning system, and a diagnostic method for diagnosing a refrigerant compressor.

[0002] In recent years, there has been a growing need for diagnostic technologies that enable timely maintenance of air conditioning systems. The refrigerant compressor is a critical component of air conditioning systems, and its deterioration can directly lead to the shutdown of the entire air conditioning system. Therefore, the need for diagnostic technologies for refrigerant compressors is particularly high.

[0003] The air conditioning system described in Patent Document 1 estimates the degree of deterioration of the refrigerant compressor by comparing the time change of the current value or power value of the refrigerant compressor, estimated from the refrigerant temperature and refrigerant pressure, with the time change of the current value or power value actually detected.

[0004] International Publication No. 2021 / 166020

[0005] However, the current or power flowing through the refrigerant compressor is affected by factors other than the deterioration of the refrigerant compressor. Therefore, in the technology described in Patent Document 1, depending on the motor control state, the current or power flowing through the refrigerant compressor may include components that do not contribute to refrigerant compression. For this reason, the technology described in Patent Document 1 had the problem of sometimes falsely detecting deterioration of the refrigerant compressor.

[0006] This disclosure has been made in view of the above, and aims to provide a diagnostic device that can accurately diagnose the deterioration of a refrigerant compressor regardless of the motor control state.

[0007] To solve the above-mentioned problems and achieve the objective, the diagnostic device of this disclosure comprises a refrigeration cycle control information acquisition unit that acquires refrigeration cycle control information, which is control information for a refrigeration cycle including a refrigerant compressor that performs refrigerant compression by driving a motor, and a motor control information acquisition unit that acquires motor control information, which is control information for a motor. The diagnostic device of this disclosure also comprises a first physical quantity calculation unit that calculates a first physical quantity related to refrigerant compression based on the refrigeration cycle control information, and a second physical quantity calculation unit that calculates a second physical quantity related to refrigerant compression based on the motor control information. The diagnostic device of this disclosure also comprises a relationship information calculation unit that calculates relationship information showing the relationship between the first physical quantity and the second physical quantity, and a diagnostic unit that diagnoses the deterioration state of the refrigerant compressor based on the relationship information. The relationship information calculation unit calculates relationship information based on the distribution of the first physical quantity and the second physical quantity on a plane when the first physical quantity and the second physical quantity are plotted on a plane, and the diagnostic unit diagnoses the deterioration state of the refrigerant compressor based on the relationship information.

[0008] The diagnostic device described herein has the effect of being able to accurately diagnose the deterioration of the refrigerant compressor regardless of the motor control state.

[0009] A diagram showing the configuration of an air conditioning system equipped with a diagnostic device according to Embodiment 1. A flowchart showing the processing procedure of the refrigerant compressor diagnostic process performed by the diagnostic device according to Embodiment 1. A diagram explaining the relationship information calculated by the diagnostic device according to Embodiment 1. A flowchart showing the processing procedure of the deterioration state determination process performed by the diagnostic device according to Embodiment 1. A diagram showing the configuration of a diagnostic device according to Embodiment 2. A flowchart showing the processing procedure of the learning process performed by the diagnostic device according to Embodiment 2. A flowchart showing the processing procedure of the diagnostic process performed by the diagnostic device according to Embodiment 2. A diagram showing an example of the configuration of a processing circuit when the processing circuit of the diagnostic device according to Embodiments 1 and 2 is implemented with a processor and memory. A diagram showing an example of the configuration of a processing circuit when the processing circuit of the diagnostic device according to Embodiments 1 and 2 is configured with dedicated hardware.

[0010] The diagnostic device, air conditioning device, and diagnostic method according to embodiments of this disclosure will be described in detail below with reference to the drawings.

[0011] Embodiment 1. Figure 1 shows the configuration of an air conditioning system equipped with a diagnostic device according to Embodiment 1. The air conditioning system 200 is a device that performs air conditioning by heating or cooling a room by transferring heat between the outside air and the indoor air via a refrigerant.

[0012] The air conditioning system 200 of Embodiment 1 includes an indoor unit 220, an outdoor unit 210, and a remote controller 300. In the air conditioning system 200, the components of the outdoor unit 210 and the components of the indoor unit 220 constitute a refrigeration cycle system.

[0013] The outdoor unit 210 includes a diagnostic device 400 for the refrigerant compressor 211, an electric motor drive unit 100, a compressor current detection unit 217, an outdoor unit control unit 101, and an outdoor temperature detection unit 218. The outdoor unit 210 also includes a refrigerant compressor 211, a refrigerant storage unit 215, a four-way valve 213, a heat exchanger 212, a pressure reducing unit 214, and an outdoor unit fan 216. The electric motor drive unit 100 is connected to the outdoor unit control unit 101, and the outdoor unit control unit 101 is connected to the outdoor temperature detection unit 218.

[0014] The indoor unit 220 includes an indoor unit control unit 201, an indoor temperature detection unit 202, a heat exchanger 221, and an indoor unit fan 222. The indoor unit control unit 201 is connected to the indoor temperature detection unit 202 and the outdoor unit control unit 101. The indoor unit control unit 201 can also be connected to the remote controller 300 via wireless communication.

[0015] The outdoor unit control unit 101 controls the motor drive unit 100, refrigerant storage unit 215, four-way valve 213, heat exchanger 212, pressure reducing unit 214, and outdoor unit fan 216. The motor drive unit 100 controls and drives the refrigerant compressor 211. The indoor unit control unit 201 controls the heat exchanger 221 and indoor unit fan 222.

[0016] The outdoor temperature detection unit 218 detects the outdoor temperature and transmits the detected outdoor temperature to the outdoor unit control unit 101. The outdoor unit control unit 101 transmits the outdoor temperature received from the outdoor temperature detection unit 218 to the indoor unit control unit 201.

[0017] The refrigerant compressor 211 comprises a compression mechanism 231 for compressing the refrigerant and a motor 232 for operating the compression mechanism 231. The heat exchanger 212 comprises a temperature detection unit 219. The temperature detection unit 219 detects the temperature of the heat exchanger 212 located on the outdoor unit 210 and transmits the detected temperature, the outdoor heat exchanger temperature, to the outdoor unit control unit 101. The outdoor unit control unit 101 transmits the outdoor heat exchanger temperature received from the temperature detection unit 219 to the indoor unit control unit 201. Note that the illustration omits the connection wires between the temperature detection unit 219 and the outdoor unit control unit 101.

[0018] The indoor temperature detection unit 202 detects the indoor temperature and transmits the detected indoor temperature to the indoor unit control unit 201. The indoor unit control unit 201 transmits the indoor temperature received from the indoor temperature detection unit 202 to the outdoor unit control unit 101.

[0019] The heat exchanger 221 is equipped with a temperature detection unit 223. The temperature detection unit 223 detects the temperature of the heat exchanger 221 located in the indoor unit 220 and transmits the detected temperature, the indoor heat exchanger temperature, to the indoor unit control unit 201. The indoor unit control unit 201 transmits the indoor heat exchanger temperature received from the temperature detection unit 223 to the outdoor unit control unit 101. Note that the illustration of the connection wires between the temperature detection unit 223 and the indoor unit control unit 201 is omitted.

[0020] In the air conditioning system 200, the outdoor unit 210 and the indoor unit 220 are connected by refrigerant piping, forming a refrigerant circuit through which the refrigerant circulates. Of the refrigerant piping, the piping through which the gas phase refrigerant flows is the gas piping 340, and the piping through which the liquid phase refrigerant flows is the liquid piping 350. Note that two-phase gas-liquid refrigerant may flow through the liquid piping 350.

[0021] In the refrigerant piping, the refrigerant compressor 211 is connected to the refrigerant storage unit 215, which is connected to the heat exchanger 212 via a four-way valve 213. The heat exchanger 212 is connected to the pressure reducing unit 214, which is connected to the heat exchanger 221. The heat exchanger 221 is also connected to the refrigerant compressor 211 via a four-way valve 213.

[0022] The compression mechanism 231 compresses the refrigerant drawn in from the refrigerant piping and discharges it to the refrigerant storage unit 215 or the heat exchanger 221. The refrigerant storage unit 215 stores the refrigerant. The four-way valve 213 switches the flow of refrigerant between cooling operation and heating operation based on instructions from the outdoor unit control unit 101. Note that the illustration of the connecting wires between the four-way valve 213 and the outdoor unit control unit 101 is omitted.

[0023] The heat exchanger 212, located on the outdoor side, performs heat exchange between the refrigerant and the outdoor air. During heating operation, the heat exchanger 212 acts as an evaporator, exchanging heat between the low-pressure refrigerant flowing in from the liquid piping 350 and the outdoor air, causing the refrigerant to evaporate and vaporize. During cooling operation, the heat exchanger 212 acts as a condenser, exchanging heat between the refrigerant, which has been compressed by the compression mechanism 231 flowing in from the four-way valve 213 side, and the outdoor air, causing the refrigerant to condense and liquefy.

[0024] The heat exchanger 212 is equipped with an outdoor unit fan 216 to improve the efficiency of heat exchange between the refrigerant and the outdoor air. The pressure reducing unit 214 adjusts the refrigerant pressure by changing its opening. The pressure reducing unit 214 is configured to include, for example, an electronic expansion valve.

[0025] The heat exchanger 221, which is the load-side heat exchanger, performs heat exchange between the refrigerant and the indoor air. During heating operation, the heat exchanger 221 acts as a condenser, exchanging heat between the refrigerant flowing in from the gas piping 340 and the indoor air, condensing the refrigerant into liquefaction and releasing it to the liquid piping 350 side. During cooling operation, the heat exchanger 221 acts as an evaporator, exchanging heat between the refrigerant, which has been reduced in pressure by the pressure reduction unit 214, and the indoor air, causing the refrigerant to absorb heat from the air, vaporizing it, and releasing it to the gas piping 340 side. The indoor unit fan 222 adjusts the airflow during heat exchange by the heat exchanger 221.

[0026] The air conditioning system 200 determines the operating mode and heat exchange amount required for the refrigeration cycle in response to user operations on the remote controller 300, etc. At this time, in response to operations on the remote controller 300, the outdoor unit 210 determines the rotational speed of the compression mechanism 231, the operation of the four-way valve 213, and the rotational speed of the outdoor unit fan 216, while the indoor unit 220 determines the rotational speed of the indoor unit fan 222. The rotational speed of the compression mechanism 231 is determined by the motor drive unit 100 based on a command from the outdoor unit control unit 101.

[0027] The diagnostic device 400 calculates a first physical quantity from refrigeration cycle control information, which is information used when controlling the refrigeration cycle, and calculates a second physical quantity from motor control information, which is information used when controlling the motor 232. The diagnostic device 400 calculates relationship information, which is information showing the relationship (distribution of correspondence) between the first physical quantity and the second physical quantity, and determines the deterioration state (degree of deterioration) of the refrigerant compressor 211 based on this relationship information.

[0028] The first and second physical quantities are of the same type, and their units are the same. The first and second physical quantities are torque (Nm), electric current (A), or work (W). The following explanation focuses on the case where the first and second physical quantities are primarily torques.

[0029] The diagnostic device 400 comprises a refrigeration cycle control information acquisition unit 401, a motor control information acquisition unit 402, a first physical quantity calculation unit 403, a second physical quantity calculation unit 404, a related information calculation unit 405, a storage unit 406, a diagnostic unit 407, and an output unit 408.

[0030] The refrigeration cycle control information acquisition unit 401 is connected to the outdoor unit control unit 101 and the first physical quantity calculation unit 403. The motor control information acquisition unit 402 is connected to the motor drive unit 100 and the second physical quantity calculation unit 404.

[0031] Furthermore, the related information calculation unit 405 is connected to the first physical quantity calculation unit 403, the second physical quantity calculation unit 404, the storage unit 406, and the diagnostic unit 407. The diagnostic unit 407 is connected to the storage unit 406 and the output unit 408.

[0032] The refrigeration cycle control information acquisition unit 401 acquires refrigeration cycle control information, which is information used when controlling the refrigeration cycle from the outdoor unit control unit 101. The refrigeration cycle control information is information such as the state of the refrigerant compressor 211, such as the discharge temperature of the refrigerant compressor 211. Details of the refrigeration cycle control information will be described later. The refrigeration cycle control information acquisition unit 401 transmits the refrigeration cycle control information to the first physical quantity calculation unit 403.

[0033] The motor control information acquisition unit 402 acquires motor control information, which is information used when controlling the motor 232 from the motor drive device 100. The motor control information is information such as the state of the motor 232, such as the motor current. Details of the motor control information will be described later. The motor control information acquisition unit 402 transmits the motor control information to the second physical quantity calculation unit 404.

[0034] The first physical quantity calculation unit 403 calculates a first physical quantity based on the refrigeration cycle control information. The first physical quantity is a physical quantity when the refrigeration cycle is controlled. For example, when the refrigeration cycle control information includes the suction temperature and the discharge temperature, the first physical quantity calculation unit 403 calculates the suction pressure and the discharge pressure based on the suction temperature and the discharge temperature, and uses the suction pressure and the discharge pressure to calculate the first physical quantity, torque (torque T1 described later).

[0035] The suction temperature is the refrigerant temperature on the suction side of the refrigerant compressor 211, and the discharge temperature is the refrigerant temperature on the discharge side of the refrigerant compressor 211. The suction pressure is the refrigerant pressure on the suction side of the refrigerant compressor 2, and the discharge pressure is the refrigerant pressure on the discharge side of the refrigerant compressor 211. The first physical quantity calculation unit 403 transmits the first physical quantity to the relationship information calculation unit 405.

[0036] The second physical quantity calculation unit 404 calculates a second physical quantity based on the motor control information. The second physical quantity is a physical quantity when the motor 232 is controlled. When calculating the second physical quantity, the second physical quantity calculation unit 404 removes components that do not contribute to refrigerant compression based on the magnetic pole position of the motor 232 and calculates the second physical quantity. For example, when the motor control information includes motor current, number of pole pairs, induced voltage constant, and inductance, the second physical quantity calculation unit 404 uses the motor current, number of pole pairs, induced voltage constant, and inductance to calculate the second physical quantity, torque (torque T2 described later). The number of pole pairs, induced voltage constant, and inductance are motor parameters determined for each motor 232. The second physical quantity calculation unit 404 transmits the second physical quantity to the relationship information calculation unit 405.

[0037] The relationship information calculation unit 405 calculates relationship information indicating the relationship between the first physical quantity and the second physical quantity. The relationship information calculation unit 405 calculates, as the relationship information, information indicating the distribution on a plane of a plurality of sets of combinations of the first physical quantity and the second physical quantity. Specifically, the relationship information calculation unit 405 uses one of the x-axis and the y-axis as the first physical quantity and the other as the second physical quantity, and calculates, as the relationship information, information indicating the distribution on the xy plane of the combinations of the first physical quantity and the second physical quantity when the combinations of the first physical quantity and the second physical quantity are plotted on the xy plane.

[0038] The combination of the first physical quantity and the second physical quantity used for calculating the relationship information is a combination of the first physical quantity and the second physical quantity obtained at substantially the same timing. The relationship information calculation unit 405 calculates relationship information indicating the distribution on a plane of the sets of the first physical quantity and the second physical quantity obtained at substantially the same timing.

[0039] The distribution on the plane of the combination of the first physical quantity and the second physical quantity indicated by the relationship information changes according to the deterioration state of the refrigerant compressor 211. That is, the distribution on the plane of the relationship between the first physical quantity and the second physical quantity changes according to the deterioration state of the refrigerant compressor 211. The relationship information calculation unit 405 calculates relationship information that quantifies the tendency of the distribution on the plane of the combination of the first physical quantity and the second physical quantity.

[0040] The relational information calculation unit 405 calculates, for example, the covariance between the first physical quantity and the second physical quantity as relational information. The relational information calculation unit 405 also calculates, for example, the difference between the average of the first physical quantity and the average of the second physical quantity (hereinafter sometimes referred to as the average difference) as relational information.

[0041] The memory unit 406 stores a first reference value used to determine whether or not to start determining the deterioration state of the refrigerant compressor 211. The memory unit 406 also stores second to fourth reference values ​​used to determine the deterioration state of the refrigerant compressor 211. The first to fourth reference values ​​are set in advance and stored in the memory unit 406. The third reference value is a value greater than the fourth reference value.

[0042] The diagnostic unit 407 uses a first reference value to determine whether or not to start determining the deterioration state of the refrigerant compressor 211. The first reference value is a value that is compared with the number of time-series data points (refrigeration cycle control information and motor control information) used to calculate the distribution of related information on a plane.

[0043] If the number of time-series data points is less than or equal to the first reference value, the diagnostic unit 407 determines that the refrigerant compressor 211 is normal and does not perform a deterioration status determination, taking into consideration that the number of time-series data points is small and susceptible to detection noise, etc., in order to prevent false detection. If the number of time-series data points is greater than the first reference value, the diagnostic unit 407 performs a deterioration status determination.

[0044] The second reference value is a value compared to the covariance between the first physical quantity and the second physical quantity. If the covariance is less than or equal to the second reference value, the diagnostic unit 407 determines that the refrigerant compressor 211 is in the final stages of deterioration.

[0045] The third and fourth reference values ​​are values ​​compared with the average difference. The diagnostic unit 407 determines that the refrigerant compressor 211 is in the middle stage of deterioration if the average difference is greater than or equal to the third reference value. The diagnostic unit 407 determines that the refrigerant compressor 211 is in the early stage of deterioration if the average difference is greater than or equal to the fourth reference value. The diagnostic unit 407 determines that the refrigerant compressor 211 is normal if the average difference is less than the fourth reference value. The output unit 408 outputs the deterioration status determination result from the diagnostic unit 407 to an external device such as a display device.

[0046] The output unit 408 may also output the relationship information calculated by the relationship information calculation unit 405 to an external device such as a display device. In this case, the output unit 408 either acquires the relationship information from the relationship information calculation unit 405 via the diagnostic unit 407 and outputs it, or acquires the relationship information from the relationship information calculation unit 405 and outputs it. When the output unit 408 acquires the relationship information from the relationship information calculation unit 405, the output unit 408 and the relationship information calculation unit 405 are connected.

[0047] The air conditioning system 200 sets, for example, a target temperature (hereinafter referred to as the set temperature) based on the user's operation of the remote controller 300 or the like. The air conditioning system 200 also determines the amount of heat exchange required by the heat exchanger 221 of the indoor unit 220 according to the set temperature and the indoor temperature detected by the indoor temperature detection unit 202. The air conditioning system 200 also determines the rotation speed of the refrigerant compressor 211, the operation of the four-way valve 213, the opening degree of the pressure reducing unit 214, the rotation speed of the outdoor unit fan 216, and the rotation speed of the indoor unit fan 222, respectively, according to the set temperature and the indoor temperature.

[0048] The four-way valve 213, the pressure reducing unit 214, and the outdoor unit fan 216 are controlled by the outdoor unit control unit 101, and the indoor unit fan 222 is controlled by the indoor unit control unit 201. Both the outdoor unit control unit 101 and the indoor unit control unit 201 can use known control methods. In this way, the outdoor unit control unit 101 determines the rotation speed of the refrigerant compressor 211, the operation of the four-way valve 213, the opening degree of the pressure reducing unit 214, and the rotation speed of the outdoor unit fan 216 based on the set temperature and the indoor temperature, and controls the refrigerant compressor 211, the four-way valve 213, the pressure reducing unit 214, and the outdoor unit fan 216. The indoor unit control unit 201 also determines the rotation speed of the indoor unit fan 222 based on the set temperature and the indoor temperature, and controls the indoor unit fan 222.

[0049] The outdoor unit control unit 101 transmits refrigeration cycle control information to the refrigeration cycle control information acquisition unit 401. The refrigeration cycle control information includes at least one of the following: the discharge temperature of the refrigerant compressor 211, the suction temperature of the refrigerant compressor 211, the stroke volume of the refrigerant compressor 211, and the polytrope index of the refrigerant compressor 211.

[0050] The compressor current detection unit 217 is located on the connection line between the refrigerant compressor 211 and the motor drive unit 100, and detects the current output by the motor drive unit 100 to the refrigerant compressor 211. The compressor current detection unit 217 transmits the detected current value to the motor drive unit 100.

[0051] The refrigerant compressor 211 is controlled by the motor drive unit 100. The motor drive unit 100 controls the position sensorless motor 232 of the refrigerant compressor 211 while estimating the magnetic pole position of the motor 232 based on the current value detected by the compressor current detection unit 217. The motor drive unit 100 can use known techniques for estimating the magnetic pole position and controlling the motor.

[0052] The motor drive unit 100 transmits motor control information to the motor control information acquisition unit 402. The motor control information includes, for example, the motor speed, the motor current detected by the compressor current detection unit 217, the motor voltage, the motor constants, and the magnetic pole position.

[0053] Next, the processing procedure of the diagnostic device 400 will be described. Figure 2 is a flowchart showing the processing procedure of the refrigerant compressor diagnostic process performed by the diagnostic device according to Embodiment 1.

[0054] The diagnostic device 400 starts a diagnostic process for the refrigerant compressor 211 at a specific interval. The refrigeration cycle control information acquisition unit 401 of the diagnostic device 400 acquires refrigeration cycle control information used when controlling the refrigeration cycle from the outdoor unit control unit 101 (step S10). The refrigeration cycle control information acquisition unit 401 acquires, for example, the discharge temperature of the refrigerant compressor 211, the suction temperature of the refrigerant compressor 211, the stroke volume of the refrigerant compressor 211, and the polytrope index of the refrigerant compressor 211 as refrigeration cycle control information.

[0055] Alternatively, the refrigeration cycle control information acquisition unit 401 may acquire the outdoor heat exchanger temperature detected by the temperature detection unit 219 located on the heat exchanger 212 of the outdoor unit 210 from the outdoor unit control unit 101, instead of the discharge temperature of the refrigerant compressor 211.

[0056] Alternatively, the refrigeration cycle control information acquisition unit 401 may acquire the indoor heat exchanger temperature detected by the temperature detection unit 223 located on the heat exchanger 221 of the indoor unit 220 from the indoor unit control unit 201, instead of the suction temperature of the refrigerant compressor 211. In this case, the indoor unit control unit 201 transmits the indoor heat exchanger temperature to the outdoor unit control unit 101, and the outdoor unit control unit 101 transmits the indoor heat exchanger temperature to the refrigeration cycle control information acquisition unit 401.

[0057] Furthermore, the refrigeration cycle control information acquisition unit 401 may acquire an estimated value of the polytrope index corresponding to the control of the refrigeration cycle. In this case, the outdoor unit control unit 101 estimates the polytrope index corresponding to the control of the refrigeration cycle. Alternatively, the refrigeration cycle control information acquisition unit 401 may estimate the polytrope index.

[0058] Furthermore, the motor control information acquisition unit 402 of the diagnostic device 400 acquires motor control information used when controlling the motor 232 from the motor drive unit 100 (step S20). The motor control information acquisition unit 402 acquires motor control information such as motor speed, motor current, motor voltage, motor constants, and magnetic pole position. Motor constants are, for example, the number of pole pairs, inductance, resistance, and induced voltage constant, and are stored in a memory device (not shown) of the motor drive unit 100.

[0059] The motor control information acquisition unit 402 may acquire an estimated value of the magnetic pole position corresponding to the control of the motor 232. In this case, the motor drive unit 100 estimates the magnetic pole position according to the control of the motor 232. Alternatively, the motor control information acquisition unit 402 may estimate the magnetic pole position.

[0060] After the processing in step S10, the first physical quantity calculation unit 403 calculates a first physical quantity based on the refrigeration cycle control information (step S30). The first physical quantity calculation unit 403 calculates the intake pressure from the intake temperature included in the refrigeration cycle control information, and calculates the discharge pressure from the discharge temperature included in the refrigeration cycle control information. The first physical quantity calculation unit 403 may calculate at least one of the intake pressure and discharge pressure using a table, or it may calculate at least one of the intake pressure and discharge pressure using polynomial approximation.

[0061] The table used to calculate the intake pressure is a table that associates intake temperature with intake pressure. When the first physical quantity calculation unit 403 calculates the intake pressure using the table, it selects the intake pressure corresponding to the intake temperature from within the table. Based on the table that associates intake temperature with intake pressure and the intake temperature included in the refrigeration cycle control information, the first physical quantity calculation unit 403 calculates the intake pressure corresponding to the intake temperature.

[0062] The table used to calculate the discharge pressure is a table that associates discharge temperature with discharge pressure. When the first physical quantity calculation unit 403 calculates the discharge pressure using the table, it selects the discharge pressure corresponding to the discharge temperature from within the table. Based on the table that associates discharge temperature with discharge pressure and the discharge temperature included in the refrigeration cycle control information, the first physical quantity calculation unit 403 calculates the discharge pressure corresponding to the discharge temperature.

[0063] Furthermore, the first physical quantity calculation unit 403 calculates torque T1 (Nm) as a first physical quantity based on the calculated suction pressure and discharge pressure, the stroke volume and polytropic index of the refrigerant compressor 211, and the motor rotation speed (here, motor rotation speed N) acquired as motor control information by the motor control information acquisition unit 402. In this case, the first physical quantity calculation unit 403 and the motor control information acquisition unit 402 are connected, and the motor control information acquisition unit 402 transmits the motor rotation speed N to the first physical quantity calculation unit 403. The first physical quantity calculation unit 403 calculates torque T1 using, for example, the following equation (1).

[0064]

[0065] In equation (1), P s This is the suction pressure (Pa), and P d V is the discharge pressure (Pa). st is the stroke volume (cc), n is the polytropic index, and N is the motor rotational speed.

[0066] f(N) is a function that outputs a value of 1 or greater, and the output increases as the motor rotation speed N increases. Since the friction loss in the refrigerant compressor 211 depends on the motor rotation speed N, it is desirable to consider the friction loss when calculating the torque T1 in order to accurately determine the torque T1. If it is difficult to define the friction loss in advance, the value of f(N) may be set to a fixed value regardless of N.

[0067] After the processing of step S20, the second physical quantity calculation unit 404 calculates the second physical quantity based on the motor control information (step S40). For example, the second physical quantity calculation unit 404 calculates the motor current in the rotating coordinates from the motor current and the magnetic pole position included in the motor control information. In this case, the second physical quantity calculation unit 404 performs coordinate conversion of the motor current using the magnetic pole position and calculates the motor current in the rotating coordinates. The second physical quantity calculation unit 404 calculates the motor current in the rotating coordinates using, for example, the following equation (2).

[0068]

[0069] In equation (2), I u , I v , I w are the motor phase currents of each of the uvw phases, and I<00OO007>, I q are the motor currents in the rotating coordinates.<00001 (61>

[0070] Further, the second physical quantity calculation unit 404 calculates the torque T2 (Nm) as the second physical quantity based on the motor current in the rotating coordinates (the d-axis motor current and the q-axis motor current) calculated as the second physical quantity, the number of pole pairs, the induced voltage constant, and the inductances (d-axis inductance and q-axis inductance) acquired by the motor control information acquisition unit 402 as the motor control information. The second physical quantity calculation unit 404 calculates the torque T2 using, for example, the following equation (I 3).[[ID=2o]]

[0071] ​​​​​​​​​​​​​​This is the q-axis inductance. In this way, the second physical quantity calculation unit 404 uses the magnetic pole position to calculate the second physical quantity, torque T2. The torque T2 calculated by the second physical quantity calculation unit 404 is the component of the motor 232's torque that contributes to refrigerant compression. In other words, the second physical quantity calculation unit 404 separates the motor 232's torque into a component that contributes to refrigerant compression and a component that does not, and calculates the component that contributes to refrigerant compression as torque T2.

[0073] Here, we will explain why the diagnostic device 400 calculates the torque T2 using the motor current in the rotating coordinates, rather than directly using the motor current detected by the compressor current detection unit 217. As can be seen from equation (3), the motor current I in the rotating coordinates d , I q The torque generated varies depending on the motor current I q It can be seen that torque T2 is generated by this.

[0074] Furthermore, the motor current I in the rotating coordinate system d , I q To calculate the torque, the magnetic pole position is required. Generally, the motor 232 used in refrigerant compressors is a position sensorless motor 232, and is driven while the magnetic pole position is estimated. From this, it can be seen that the torque T2 can be calculated by combining the compressor current detection unit 217 and the motor control information of the motor drive unit 100.

[0075] Note that the processes in step S10 and step S20 may be executed in any order. Also, the processes in step S30 and step S40 may be executed in any order. Furthermore, the process in step S30 may be performed after the process in step S10, and the processes in step S30 and step S20 may be executed in any order. Also, the process in step S40 may be performed after the process in step S20, and the processes in step S40 and step S10 may be executed in any order. The diagnostic device 400 may, for example, execute the processes in steps S10 and S20 simultaneously, and then execute the processes in steps S30 and S40 simultaneously.

[0076] After the processing in steps S30 and S40, the relationship information calculation unit 405 calculates relationship information, which is information indicating the relationship between the first physical quantity and the second physical quantity (step S50). In Embodiment 1, when quantifying the trend of the plane distribution of the first and second physical quantities, the relationship information calculation unit 405 calculates the mean of the first physical quantity, the variance of the first physical quantity, the mean of the second physical quantity, the variance of the second physical quantity, and the covariance between the first and second physical quantities as parameters of a two-dimensional normal distribution. In this way, by expressing the relationship information as parameters of a two-dimensional normal distribution, the relationship information calculation unit 405 does not need to retain all time-series data, and it is possible to reduce the storage capacity of the memory (not shown) of the diagnostic device 400.

[0077] The details of the relationship information, which is the correspondence between the first physical quantity and the second physical quantity, will be explained. Figure 3 is a diagram illustrating the relationship information calculated by the diagnostic device according to Embodiment 1. In each graph shown in Figure 3, the horizontal axis represents the first physical quantity, and the vertical axis represents the second physical quantity.

[0078] In Figure 3, the x-axis (horizontal axis) represents the first physical quantity, and the y-axis (vertical axis) represents the second physical quantity. The physical quantities (first and second physical quantities) calculated by the diagnostic device 400 in steps S30 and S40 are plotted in pairs for a certain time series period.

[0079] The dotted line L1 shown in each graph is a straight line with a slope of 1 and an intercept of 0. Experiments by the inventors have revealed that the distribution of the first and second physical quantities on a plane changes in the order of phase P1, phase P3, and phase P4 in Figure 3, with phase P1 being the initial phase, as the refrigerant compressor 211 deteriorates. In other words, when the air conditioning system 200 operates using the refrigerant compressor 211, the distribution of the combination of the first and second physical quantities on a plane changes in the order of phase P1, phase P2, phase P3, and phase P4 as the refrigerant compressor 211 deteriorates.

[0080] The planar distribution of the combinations of the first and second physical quantities in phase P1 represents the initial planar data distribution of the refrigerant compressor 211. As shown in phase P1 of Figure 3, if no deterioration occurs in the refrigerant compressor 211, the combinations of the first and second physical quantities are distributed in the region close to the dotted line L1.

[0081] In phase P2, the distribution of the combination of the first and second physical quantities shifts in the positive direction of the y-axis compared to phase P1. This suggests that the second physical quantity, namely the torque T2 of the motor 232, increases due to an action other than refrigerant compression, causing frictional deterioration of the mechanical parts of the refrigerant compressor 211.

[0082] In phase P3, compared to phase P2, the distribution of combinations of the first and second physical quantities has shifted in the negative direction of the x-axis. This suggests that the friction of the mechanical parts of the refrigerant compressor 211 has exceeded a certain level, resulting in a deterioration of the function of compressing the refrigerant.

[0083] In phase P4, the distribution of the combination of the first and second physical quantities shifts further in the negative x-axis and y-axis directions. This suggests that the function of the refrigerant compressor 211 in performing refrigerant compression has deteriorated significantly. In this way, the diagnostic device 400 can diagnose the deterioration of the refrigerant compressor 211 by observing the changes in the distribution on a plane of the combination of the first and second physical quantities, which is the distribution of pairs of physical quantities plotted on a plane.

[0084] The diagnostic unit 407 performs a deterioration state determination process for the refrigerant compressor 211 based on the relational information calculated by the relational information calculation unit 405 in step S50 (step S60). That is, the diagnostic unit 407 quantifies the plane distribution of combinations of the first physical quantity and the second physical quantity that change in response to changes in the relational information, and determines the deterioration state by comparing the quantified distribution information with the judgment reference values ​​(second to fourth reference values).

[0085] The diagnostic unit 407 may also quantify the change from the initial value of the relationship between the first physical quantity and the second physical quantity calculated by the relationship information calculation unit 405 in step S50, and determine the deterioration state by comparing the amount of change from the initial value with a threshold for the amount of change.

[0086] As explained in Figure 3, the trend of the distribution of the combination of the first and second physical quantities on a plane changes depending on the deterioration state of the refrigerant compressor 211. Therefore, the diagnostic unit 407 determines the deterioration state based on the parameters of the distribution on the plane.

[0087] In this way, the diagnostic unit 407 determines whether or not the refrigerant compressor 211 is degraded based on the relevant information and the judgment criteria value (step S70). If the diagnostic unit 407 determines that the refrigerant compressor 211 is degraded (step S70, Yes), it outputs a degradation determination result indicating that the refrigerant compressor 211 is degraded from the output unit 408 to an external device of the diagnostic device 400 (such as a display device not shown, a user terminal not shown, or a remote controller 300) (step S80).

[0088] The output unit 408 outputs the deterioration judgment result by notification via an alert or the like. When the output unit 408 outputs the deterioration judgment result, the diagnostic processing of the refrigerant compressor 211 by the diagnostic device 400 is completed.

[0089] On the other hand, if the diagnostic unit 407 determines that the refrigerant compressor 211 is not deteriorated (step S70, No), the diagnostic process of the refrigerant compressor 211 by the diagnostic device 400 ends without outputting the determination result. In the diagnostic device 400, the processes of steps S10 to S80 are repeated at a specific cycle.

[0090] The diagnostic device 400 enables timely maintenance by notifying the user only when it determines that the refrigerant compressor 211 is deteriorating. When the diagnostic device 400 determines that the refrigerant compressor 211 is deteriorating, it may output to the outside, along with the deterioration determination result, at least one of the deterioration status of the refrigerant compressor 211 and the related information calculated by the related information calculation unit 405. This allows the person performing maintenance on the refrigerant compressor 211 to visually understand the actual condition of the refrigerant compressor 211.

[0091] Next, we will explain the details of the deterioration state determination process performed by the diagnostic unit 407, as described in step S60 of Figure 2. Figure 4 is a flowchart showing the processing procedure of the deterioration state determination process performed by the diagnostic device according to Embodiment 1. The first to fourth reference values ​​are stored in the storage unit 406 in advance.

[0092] The diagnostic unit 407 determines whether the number of time-series data used to calculate the distribution of relational information on a plane showing the relationship between the first physical quantity and the second physical quantity is less than or equal to a first reference value (step S110). That is, the diagnostic unit 407 determines whether the number of times the refrigeration cycle control information used in the calculation of the first physical quantity or the number of times the motor control information used in the calculation of the second physical quantity is less than or equal to a first reference value.

[0093] If the number of time-series data points used to calculate the distribution of related information on a plane is less than or equal to the first reference value (step S110, Yes), the diagnostic unit 407 determines that the refrigerant compressor 211 is normal (step S120) and terminates the deterioration state determination process.

[0094] On the other hand, if the number of time-series data points used to calculate the distribution of relational information on a plane is greater than the first reference value (step S110, No), the diagnostic unit 407 determines whether the covariance between the first physical quantity and the second physical quantity is less than or equal to the second reference value (step S130). This determination process corresponds to determining whether or not the state of phase P4 shown in Figure 3 is in place.

[0095] If the diagnostic unit 407 determines that the covariance is below the second reference value (step S130, Yes), that is, that the state is Phase P4 as shown in Figure 3, it determines that the refrigerant compressor 211 is in the final stage of deterioration (step S140), and terminates the deterioration state determination process.

[0096] On the other hand, if the covariance is greater than the second reference value (step S130, No), the diagnostic unit 407 determines the deterioration state using the average of the first physical quantity and the average of the second physical quantity. Specifically, the diagnostic unit 407 determines whether the difference (average difference) between the average of the first physical quantity and the average of the second physical quantity is greater than or equal to the third reference value (step S150). This determination process corresponds to determining whether or not the state is that of phase P3 shown in Figure 3.

[0097] If the average difference is greater than or equal to the third reference value (step S150, Yes), the diagnostic unit 407 determines that the refrigerant compressor 211 is in the middle stage of deterioration (step S160), and terminates the deterioration state determination process.

[0098] On the other hand, if the average difference is smaller than the third reference value (step S150, No), the diagnostic unit 407 determines whether the difference between the average of the first physical quantity and the average of the second physical quantity (average difference) is greater than or equal to the fourth reference value (step S170). This determination process corresponds to determining whether or not the state of phase P2 shown in Figure 3 is in effect.

[0099] If the average difference is greater than or equal to the fourth reference value (step S170, Yes), the diagnostic unit 407 determines that the refrigerant compressor 211 is in the early stages of deterioration (step S180), and terminates the deterioration state determination process.

[0100] On the other hand, if the average difference is smaller than the fourth reference value (step S170, No), the diagnostic unit 407 determines that the refrigerant compressor 211 is normal (step S190) and terminates the deterioration state determination process. When the average difference is smaller than the fourth reference value, it corresponds to the state of phase P1 shown in Figure 3.

[0101] The diagnostic unit 407 may also determine the state of deterioration using different criteria than those used in steps S130, S150, and S170 described above. For example, in step S130, the diagnostic unit 407 may combine a determination of whether the average of the first physical quantity is below a fifth reference value (first additional determination) and a determination of whether the average of the second physical quantity is below a sixth reference value (second additional determination) to determine whether the deterioration is at its final stage.

[0102] Furthermore, in step S130, the diagnostic unit 407 may determine whether or not the device is in the final stages of deterioration by combining the determination of whether or not the variance of the first physical quantity is below the seventh reference value (third additional determination) and the determination of whether or not the variance of the second physical quantity is below the eighth reference value (fourth additional determination). Alternatively, in step S130, the diagnostic unit 407 may determine whether or not the device is in the final stages of deterioration by combining the first to fourth additional determinations.

[0103] In Embodiment 1, the diagnostic device 400 was described as determining the degree of deterioration based on the parameters of a two-dimensional normal distribution (mean of the first physical quantity, variance of the first physical quantity, mean of the second physical quantity, variance of the second physical quantity, and covariance between the first and second physical quantities). However, the deterioration state may also be determined based on other information. For example, the diagnostic device 400 may determine the distance from a predefined normal distribution corresponding to phases P1 to P4 in Figure 3 (for example, L 2 The deterioration state may be determined based on distance (Kullback-Leibler distance). Alternatively, the diagnostic device 400 may obtain a probability ellipse from the parameters of a two-dimensional normal distribution and determine the deterioration state based on the parameters of the probability ellipse (e.g., center, semi-major axis, semi-minor axis, slope).

[0104] Furthermore, the second to fourth reference values ​​stored in the memory unit 406 may be pre-designed values ​​or values ​​obtained from the initial operating data of the refrigerant compressor 211. In the latter case, the second to fourth reference values ​​are calculated based on the operating data up to a specific time, which represents the cumulative operating time since the refrigerant compressor 211 started operation, and the diagnostic unit 407 does not diagnose the refrigerant compressor 211 while the second to fourth reference values ​​are being calculated.

[0105] If the reference value stored in the memory unit 406 is a value obtained from the initial operating data of the refrigerant compressor 211, the reference value is set by adding a specific offset to the relational information obtained by the relational information calculation unit 405 based on the initial operating data of the refrigerant compressor 211.

[0106] In this way, by using actual operating data to generate the reference value, it becomes possible to prevent misjudgments due to manufacturing variations of the refrigerant compressor 211, etc. The reference value may be set by the diagnostic device 400, or by a device other than the diagnostic device 400.

[0107] In Embodiment 1, instead of the diagnostic device 400 calculating the first and second physical quantities, the outdoor unit control unit 101 may calculate the first and second physical quantities. In other words, any device may be used to calculate the first and second physical quantities, and the device performing the calculation is not limited.

[0108] Furthermore, although the diagnostic device 400 of Embodiment 1 calculated the first physical quantity using the discharge temperature or suction temperature, the first physical quantity may also be calculated using the suction pressure or discharge pressure of the refrigerant compressor 211 instead of the discharge temperature or suction temperature.

[0109] The diagnostic device 400 may also calculate the first physical quantity using all of the discharge temperature, intake temperature, intake pressure, and discharge pressure. The diagnostic device 400 calculates the first physical quantity using at least one of the discharge temperature, intake temperature, intake pressure, and discharge pressure.

[0110] When using either the suction pressure or the discharge pressure, the diagnostic device 400 eliminates the need to perform approximate calculations to convert temperature to pressure. Furthermore, when using all of the discharge temperature, suction temperature, suction pressure, and discharge pressure, the diagnostic device 400 can determine the polytropic index, enabling the calculation of the first physical quantity with even greater accuracy.

[0111] Furthermore, while Embodiment 1 described the case where the first and second physical quantities are torque (Nm), the first and second physical quantities may also be the current (A) flowing through the motor 232 or the work done by the motor 232 (W). In other words, the first and second physical quantities may be any physical quantities related to the refrigerant compression of the refrigerant compressor 211. The refrigeration cycle control information and motor control information when the first and second physical quantities are the current (A) flowing through the motor 232 or the work done by the motor 232 (W) are the same as the refrigeration cycle control information and motor control information when the first and second physical quantities are torque.

[0112] Of the current flowing through the motor 232, the current used to hold the magnet is a component that does not contribute to refrigerant compression, while the current used to rotate the motor 232 is a component that contributes to refrigerant compression. Even when the second physical quantity is current, the second physical quantity calculation unit 404 calculates the component of the current that contributes to refrigerant compression based on the magnetic pole position. Specifically, the second physical quantity calculation unit 404 calculates the torque T2 based on the magnetic pole position and calculates the current flowing through the motor 232 based on the torque T2, thereby calculating the component of the current that contributes to refrigerant compression.

[0113] Of the work done by the motor 232, the work done to hold the magnet is a component that does not contribute to refrigerant compression, while the work done to rotate the motor 232 is a component that contributes to refrigerant compression. Even when the second physical quantity is work, the second physical quantity calculation unit 404 calculates the component of work that contributes to refrigerant compression based on the magnetic pole position. Specifically, the second physical quantity calculation unit 404 calculates the torque T2 based on the magnetic pole position and calculates the work done by the motor 232 based on the torque T2, thereby calculating the component of work that contributes to refrigerant compression.

[0114] Furthermore, while Embodiment 1 described a configuration in which the diagnostic device 400 is located inside the outdoor unit 210, the indoor unit 220 or the remote controller 300 may also be equipped with the diagnostic device 400, or an external device (not shown) may be equipped with the diagnostic device 400.

[0115] As described above, the diagnostic device 400 determines the deterioration state based on the planar distribution of two physical quantities (first physical quantity and second physical quantity) that focus on refrigerant compression, making it possible to diagnose the deterioration of the refrigerant compressor 211 regardless of the operating conditions of the refrigerant compressor 211.

[0116] Thus, the diagnostic device 400 determines the deterioration state of the refrigerant compressor 211 using a first physical quantity and a second physical quantity that contribute to refrigerant compression and correspond to the deterioration of the refrigerant compressor 211. On the other hand, the air conditioning system described in Patent Document 1 determines the deterioration state of the refrigerant compressor based on information other than the deterioration of the refrigerant compressor (current or power flowing to the refrigerant compressor). For example, when the refrigerant compressor is operated at high speed, flux weakening control may be used. Flux weakening control is a control that achieves high-speed operation by flowing a large amount of current that does not contribute to refrigerant compression. Therefore, depending on the state of motor control, the current or power flowing to the refrigerant compressor may include components that do not contribute to refrigerant compression, so in the case of the air conditioning system described in Patent Document 1, there is a concern that this may lead to a false detection of the deterioration state of the refrigerant compressor.

[0117] Furthermore, as an example of a diagnostic device 400, there is an internal state estimation device that sets a steady-state torque from temperature or pressure information of the refrigerant system and estimates the internal state of the refrigerant compressor based on a comparison of this steady-state torque with the detected motor torque.

[0118] Generally, the operation of air conditioning systems varies depending on the user's set temperature, the room temperature, and the installation environment (outside temperature), and the control state of the refrigerant compressor also differs accordingly. Furthermore, in environments where windows or doors are frequently opened and closed, and the room temperature is unstable, the rotational speed and load torque of the refrigerant compressor fluctuate frequently. Therefore, the rotational speed and load torque of the refrigerant compressor vary greatly, including the amount of fluctuation, depending on the installation environment and how the system is used by the user.

[0119] Therefore, if the internal state of the refrigerant compressor is estimated based on motor torque, as in the comparative example's internal state estimation device, the estimation error becomes large, making it impossible to accurately determine the deterioration state of the refrigerant compressor. While it is conceivable to fix the operating conditions of the comparative example's internal state estimation device to a fixed set of conditions in order to accurately determine the deterioration state of the refrigerant compressor, this raises concerns about user discomfort, such as the room not heating or cooling properly.

[0120] The diagnostic device 400 of Embodiment 1 determines the deterioration state of the refrigerant compressor 211 using a first physical quantity and a second physical quantity corresponding to the deterioration of the refrigerant compressor 211. Therefore, it can accurately determine the deterioration state regardless of the operating conditions of the refrigerant compressor 211, the motor control state, and the operating environment. In other words, the diagnostic device 400 can diagnose the occurrence of deterioration of the refrigerant compressor 211, regardless of the rotational speed, load torque, and control state of the refrigerant compressor 211.

[0121] As described above, the diagnostic device 400 of Embodiment 1 calculates a first physical quantity related to refrigerant compression based on refrigeration cycle control information and a second physical quantity related to refrigerant compression based on motor control information. The diagnostic device 400 then calculates relational information based on the distribution of the first and second physical quantities on a plane when the first and second physical quantities are plotted on a plane, and diagnoses the deterioration state of the refrigerant compressor 211 based on the relational information. Therefore, the diagnostic device 400 can accurately diagnose the deterioration of the refrigerant compressor 211 regardless of the motor control state.

[0122] Embodiment 2. Next, Embodiment 2 will be described with reference to Figures 5 to 7. The diagnostic device 400 of Embodiment 1 performed a rule-based diagnosis of the deterioration state based on the distribution of the first physical quantity and the second physical quantity on a plane, but the diagnostic device of Embodiment 2 (diagnostic device 400A, described later) performs a diagnosis of the deterioration state using machine learning. Details common to Embodiment 1 will be omitted from the explanation.

[0123] Figure 5 shows the configuration of the diagnostic device according to Embodiment 2. Among the components in Figure 5, components that achieve the same function as the diagnostic device 400 of Embodiment 1 shown in Figure 1 are denoted by the same reference numerals, and redundant explanations are omitted.

[0124] The diagnostic device 400A includes a refrigeration cycle control information acquisition unit 401, a motor control information acquisition unit 402, a first physical quantity calculation unit 403, a second physical quantity calculation unit 404, a storage unit 406, an output unit 408, a model generation unit 409, and an inference unit 410. In other words, compared to the diagnostic device 400, the diagnostic device 400A includes a model generation unit 409 and an inference unit 410 instead of a relational information calculation unit 405 and a diagnostic unit 407.

[0125] The model generation unit 409 is connected to the first physical quantity calculation unit 403, the second physical quantity calculation unit 404, the storage unit 406, and the inference unit 410. The inference unit 410 is connected to the first physical quantity calculation unit 403, the second physical quantity calculation unit 404, the storage unit 406, and the output unit 408.

[0126] The model generation unit 409 performs a learning process for the deterioration state of the refrigerant compressor 211 using the first physical quantity and the second physical quantity. Specifically, the model generation unit 409 learns the deterioration state based on training data created based on the combination of the first physical quantity and the second physical quantity received from the first physical quantity calculation unit 403 and the second physical quantity calculation unit 404. That is, it generates a trained model that can infer the deterioration state from the combination of the first physical quantity and the second physical quantity. Here, the training data is data that associates the combination of the first physical quantity and the second physical quantity with the deterioration state. The model generation unit 409 generates the trained model using a learning algorithm such as unsupervised learning. The model generation unit 409 stores the trained model in the storage unit 406.

[0127] The inference unit 410 diagnoses the deterioration state of the refrigerant compressor 211 by inferring the deterioration state using a trained model. The inference unit 410 inputs a first physical quantity and a second physical quantity to the trained model and diagnoses the deterioration state by having the trained model output a deterioration state corresponding to the combination of the first physical quantity and the second physical quantity. The inference unit 410 transmits the deterioration state of the refrigerant compressor 211 to the output unit 408. The output unit 408 outputs the deterioration state of the refrigerant compressor 211 to an external device.

[0128] Next, the processing procedure of the diagnostic device 400A will be described. Figure 6 is a flowchart showing the processing procedure of the learning process performed by the diagnostic device according to Embodiment 2. Of the steps in Figure 6, steps that perform the same processing as the diagnostic device 400 of Embodiment 1 shown in Figure 2 are given the same step number, and redundant explanations are omitted.

[0129] The diagnostic device 400A performs the processing in steps S10 to S40 in the same manner as the diagnostic device 400. After processing in step S30, the first physical quantity calculation unit 403 transmits the first physical quantity to the model generation unit 409. After processing in step S40, the second physical quantity calculation unit 404 transmits the second physical quantity to the model generation unit 409.

[0130] After the processing in steps S30 and S40, the model generation unit 409 performs a learning process for the degradation state using the first physical quantity and the second physical quantity (step S51). That is, the model generation unit 409 takes the first physical quantity calculated by the first physical quantity calculation unit 403 and the second physical quantity calculated by the second physical quantity calculation unit 404 as input and learns the classification of the degradation state as output.

[0131] The model generation unit 409 can use known learning algorithms such as supervised learning, unsupervised learning, and reinforcement learning. As an example, the case in which the k-means clustering method, which is an unsupervised learning method, is applied to the model generation unit 409 will be described. Unsupervised learning is a method of learning features in training data by providing training data that does not contain results (labels). The model generation unit 409 performs unsupervised learning using training data of a refrigerant compressor 211 in a normal state.

[0132] The model generation unit 409 learns to classify the degradation state by so-called unsupervised learning, for example, according to a grouping method using the K-means method. The K-means method is a non-hierarchical clustering algorithm that uses the mean of the clusters to classify a given number of clusters into k groups.

[0133] Specifically, the K-means algorithm is processed in the following manner. First, the model generation unit 409 randomly assigns a cluster to each data point xi. Next, the model generation unit 409 calculates the center Vj of each cluster based on the assigned data points xi. Then, the model generation unit 409 calculates the distance between each data point xi and each center Vj, and reassigns the data point xi to the cluster with the nearest center Vj. Finally, the model generation unit 409 determines that convergence has occurred and terminates processing if the cluster assignments for all data points xi have not changed after the above process, or if the amount of change falls below a predetermined threshold.

[0134] In Embodiment 2, the model generation unit 409 learns the classification of degradation states by so-called unsupervised learning, according to training data created based on a combination of the first physical quantity and the second physical quantity.

[0135] The model generation unit 409 generates and outputs a trained model by performing the learning described above. The model generation unit 409 transmits the generated trained model to the storage unit 406. As a result, the storage unit 406 stores the trained model received from the model generation unit 409 (step S61). Once the storage unit 406 stores the trained model, the diagnostic device 400A terminates the learning process.

[0136] Next, the operation during diagnosis will be explained using the flowchart in Figure 7. Figure 7 is a flowchart showing the processing steps of the diagnostic process performed by the diagnostic device according to Embodiment 2. Among the steps in Figure 7, steps that perform the same processing as the diagnostic device 400 of Embodiment 1 shown in Figure 2 are given the same step number, and redundant explanations are omitted.

[0137] The diagnostic device 400A generates a trained model and then performs diagnostic processing. The inference unit 410 of the diagnostic device 400 diagnoses the degradation state by inferring the degradation state using the trained model.

[0138] The diagnostic device 400A executes the processes in steps S11, S21, S31, and S41, which are the same as the processes in steps S10, S20, S30, and S40. The processes in steps S10, S20, S30, and S40, as explained in Figure 6, are processes for generating a trained model, while the processes in steps S11, S21, S31, and S41, as shown in Figure 7, are processes for diagnosing the deterioration state of the refrigerant compressor 211 by inferring the deterioration state of the refrigerant compressor 211.

[0139] After processing in step S31, the first physical quantity calculation unit 403 transmits the first physical quantity to the inference unit 410. After processing in step S41, the second physical quantity calculation unit 404 transmits the second physical quantity to the inference unit 410.

[0140] After the processing in steps S31 and S41, the inference unit 410 inputs the first physical quantity and the second physical quantity into the trained model stored in the memory unit 406 (step S52). As a result, the trained model infers and outputs the degradation state corresponding to the combination of the first physical quantity and the second physical quantity, so the inference unit 410 obtains a degradation determination result indicating the degradation state from the trained model. In other words, the inference unit 410 diagnoses the degradation state of the refrigerant compressor 211 by inferring the degradation state of the refrigerant compressor 211.

[0141] The inference unit 410 outputs the degradation determination result from the output unit 408 to an external device (such as a display device not shown, a user terminal not shown, or a remote controller 300) outside the diagnostic device 400A (step S80). As a result, the output unit 408 outputs the degradation diagnosis result, which is the inference result, to an external device. The output from the output unit 408 is a notification by an alert, etc.

[0142] If the data (first physical quantity and second physical quantity) input to the trained model belongs to any cluster that indicates it is not in a degraded state, the trained model outputs information indicating it is in a normal state, and the inference unit 410 infers that it is in a normal state. In other words, if the data input to the trained model belongs to any cluster that indicates it is in a normal state, the inference unit 410 infers that it is in a normal state.

[0143] Furthermore, if the data input to the trained model does not belong to any cluster that indicates it is not in a degraded state, the trained model outputs information indicating that degradation has occurred, and the inference unit 410 infers that degradation has occurred. In other words, if the data input to the trained model belongs to any cluster that indicates it is in a degraded state, the inference unit 410 infers that it is in a degraded state.

[0144] For example, if the model generation unit 409 performs unsupervised learning using only training data in which the refrigerant compressor 211 is in a normal state, the inference unit 410 infers that the data input to the trained model is in a normal state if it belongs to any cluster indicating a normal state. On the other hand, if the data input to the trained model does not belong to any cluster indicating a normal state, the inference unit 410 infers that it is in a degraded state.

[0145] In Embodiment 2, the case in which unsupervised learning is applied to the learning algorithm used by the model generation unit 409 was described. However, the learning algorithm used by the model generation unit 409 is not limited to unsupervised learning; reinforcement learning, supervised learning, or semi-supervised learning can also be applied.

[0146] Furthermore, the learning algorithm used in the model generation unit 409 can also be deep learning, which learns to extract the features themselves. Other known methods may also be used as the learning algorithm in the model generation unit 409.

[0147] When implementing unsupervised learning in Embodiment 2, the model generation unit 409 may perform other known clustering methods, not limited to the non-hierarchical clustering using the K-means method described above. For example, the clustering performed by the model generation unit 409 may be a hierarchical clustering method such as the shortest distance method.

[0148] The model generation unit 409 may, for example, learn the degradation state by so-called supervised learning according to a neural network model. Here, supervised learning is a method in which the model generation unit 409 is given pairs of input and result (label) data, learns features in the training data, and infers the result from the input.

[0149] Furthermore, when the model generation unit 409 generates a trained model using supervised learning, it learns the degradation state based on training data created from a combination of data consisting of pairs of first and second physical quantities received from the first physical quantity calculation unit 403 and the second physical quantity calculation unit 404, and the degradation state corresponding to this pair. In other words, the model generation unit 409 generates a trained model that infers the optimal degradation state from pairs of first and second physical quantities and the degradation state. Here, the training data is data that associates pairs of first and second physical quantities and the degradation state with each other.

[0150] A neural network consists of an input layer made up of multiple neurons, an intermediate layer (hidden layer) made up of multiple neurons, and an output layer made up of multiple neurons. The intermediate layer may consist of one or more layers.

[0151] For example, in a three-layer neural network, when multiple inputs are input to the input layer, their values ​​are multiplied by weights and input to the hidden layer, and the result is further multiplied by weights and output from the output layer. This output result varies depending on the value of each weight.

[0152] When the model generation unit 409 uses a neural network model, the neural network learns the degradation state through so-called supervised learning, according to training data created based on combinations of a first physical quantity and a second physical quantity and the degradation state.

[0153] In other words, a neural network learns by inputting a first physical quantity and a second physical quantity into the input layer and adjusting the weights so that the result output from the output layer approaches the degraded state.

[0154] In Embodiment 2, at least one of the model generation unit 409 and the inference unit 410 may be configured to be connected to the diagnostic device 400A via a network, for example.

[0155] As described above, the diagnostic device 400A performs learning and inference using machine learning, enabling it to perform diagnoses that can respond to more complex data changes compared to rule-based diagnoses.

[0156] As described above, the diagnostic device 400A of Embodiment 2 generates a trained model that infers the deterioration state of the refrigerant compressor 211 from a first physical quantity and a second physical quantity corresponding to the deterioration of the refrigerant compressor 211, and uses the trained model to infer the deterioration state of the refrigerant compressor 211 from the first physical quantity and the second physical quantity. As a result, the diagnostic device 400A can accurately determine the deterioration state regardless of the motor control state and operating environment.

[0157] Next, the hardware configuration of the diagnostic devices 400 and 400A will be described. The diagnostic devices 400 and 400A are implemented by a processing circuit. The processing circuit may be a processor and memory that execute a program stored in memory, or it may be dedicated hardware.

[0158] Figure 8 shows an example of the configuration of a processing circuit when the processing circuit of the diagnostic device according to Embodiments 1 and 2 is implemented using a processor and memory. Since the diagnostic devices 400 and 400A have similar hardware configurations, the hardware configuration of the diagnostic device 400 will be described here.

[0159] The processing circuit 90 shown in Figure 8 comprises a processor 91 and a memory 92. When the processing circuit 90 consists of a processor 91 and a memory 92, each function of the processing circuit 90 is realized by software, firmware, or a combination of software and firmware. The software or firmware is written as a degradation diagnosis program and stored in the memory 92. In the processing circuit 90, each function is realized by the processor 91 reading and executing the degradation diagnosis program stored in the memory 92. In other words, the processing circuit 90 includes a memory 92 for storing the degradation diagnosis program, which will ultimately be executed by the processing of the diagnostic device 400. This degradation diagnosis program can also be said to be a program that causes the diagnostic device 400 to execute each function realized by the processing circuit 90. This degradation diagnosis program may be provided on a computer-readable recording medium on which the degradation diagnosis program is recorded, or it may be provided by other means such as a communication medium.

[0160] In the case of the diagnostic device 400 of Embodiment 1, the degradation diagnostic program can also be described as a program that causes the diagnostic device 400 to execute the processes of steps S10 to S80 in Figure 2. In the case of the diagnostic device 400, the degradation diagnostic program causes the diagnostic device 400 to execute the processes of steps S110 to S190 in Figure 4 as the process of step S60 in Figure 2.

[0161] Furthermore, in the case of the diagnostic device 400A of Embodiment 2, the degradation diagnostic program includes a model generation program for executing the functions of the model generation unit 409 and an inference program for executing the functions of the inference unit 410. The model generation program and the inference program may be separate programs.

[0162] In the case of the diagnostic device 400A of Embodiment 2, the deterioration diagnosis program can also be described as a program that causes the diagnostic device 400A to execute the processes of steps S10 to S40, S51, and S61 in Figure 6, and the processes of steps S11 to S41, S52, and S80 in Figure 7.

[0163] If the model generation program and the inference program are separate programs, the model generation program causes the diagnostic device 400A to execute the processes in steps S10 to S40, S51, and S61 in Figure 6. The inference program causes the diagnostic device 400A to execute the processes in steps S11 to S41, S52, and S80 in Figure 7.

[0164] Here, the processor 91 is, for example, a CPU (Central Processing Unit), processing unit, arithmetic unit, microprocessor, microcomputer, or DSP (Digital Signal Processor). The memory 92 is, for example, a non-volatile or volatile semiconductor memory such as RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable ROM), EEPROM (Registered Trademark) (Electrically EPROM), magnetic disk, flexible disk, optical disk, compact disk, minidisc, or DVD (Digital Versatile Disc).

[0165] Figure 9 shows an example of the configuration of a processing circuit when the processing circuit of the diagnostic device according to Embodiments 1 and 2 is configured with dedicated hardware. The processing circuit 93 shown in Figure 9 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination thereof. The processing circuit 93 may be partially implemented with dedicated hardware and partially implemented with software or firmware. In this way, the processing circuit 93 can realize the above-mentioned functions with dedicated hardware, software, firmware, or a combination thereof.

[0166] The configurations shown in the above embodiments are examples only, and can be combined with other known technologies, or the embodiments can be combined with each other. It is also possible to omit or modify parts of the configuration without departing from the gist of the invention.

[0167] 90, 93 Processing circuit, 91 Processor, 92 Memory, 100 Motor drive unit, 101 Outdoor unit control unit, 200 Air conditioning unit, 201 Indoor unit control unit, 202 Indoor temperature detection unit, 210 Outdoor unit, 211 Refrigerant compressor, 212, 221 Heat exchanger, 213 Four-way valve, 214 Pressure reducing unit, 215 Refrigerant storage unit, 216 Outdoor unit fan, 217 Compressor current detection unit, 218 Outdoor temperature detection unit, 219, 223 Temperature detection unit, 220 Indoor unit, 222 Indoor unit fan, 231 Compression mechanism, 232 Motor, 300 Remote controller, 340 Gas piping, 350 Liquid piping, 400, 400A Diagnostic device, 401 Refrigeration cycle control information acquisition unit, 402 Motor control information acquisition unit, 403 404 First physical quantity calculation unit, 405 Second physical quantity calculation unit, 406 Relationship information calculation unit, 406 Memory unit, 407 Diagnostic unit, 408 Output unit, 409 Model generation unit, 410 Inference unit.

Claims

1. A diagnostic device comprising: a refrigeration cycle control information acquisition unit that acquires refrigeration cycle control information, which is control information for a refrigeration cycle including a refrigerant compressor that performs refrigerant compression by driving a motor; a motor control information acquisition unit that acquires motor control information, which is control information for the motor; a first physical quantity calculation unit that calculates a first physical quantity related to the refrigerant compression based on the refrigeration cycle control information; a second physical quantity calculation unit that calculates a second physical quantity related to the refrigerant compression based on the motor control information; a relationship information calculation unit that calculates relationship information showing the relationship between the first physical quantity and the second physical quantity; and a diagnostic unit that diagnoses the deterioration state of the refrigerant compressor based on the relationship information, wherein the relationship information calculation unit calculates the relationship information based on the distribution of the first physical quantity and the second physical quantity on a plane when the first physical quantity and the second physical quantity are plotted on a plane; and the diagnostic unit diagnoses the deterioration state of the refrigerant compressor based on the relationship information.

2. A diagnostic device comprising: a refrigeration cycle control information acquisition unit that acquires refrigeration cycle control information, which is control information for a refrigeration cycle including a refrigerant compressor that performs refrigerant compression by driving a motor; a motor control information acquisition unit that acquires motor control information, which is control information for the motor; a first physical quantity calculation unit that calculates a first physical quantity related to the refrigerant compression based on the refrigeration cycle control information; a second physical quantity calculation unit that calculates a second physical quantity related to the refrigerant compression based on the motor control information; a model generation unit that generates a trained model for inferring the deterioration state of the refrigerant compressor from the first physical quantity and the second physical quantity using training data including the first physical quantity and the second physical quantity; and an inference unit that diagnoses the deterioration state of the refrigerant compressor by inferring the deterioration state of the refrigerant compressor from the first physical quantity and the second physical quantity using the trained model.

3. The diagnostic device according to claim 1 or 2, wherein the units of the first physical quantity and the second physical quantity are the same, and the first physical quantity and the second physical quantity are torque, current, or work.

4. The diagnostic device according to any one of claims 1 to 3, wherein the second physical quantity calculation unit calculates the second physical quantity based on the magnetic pole position of the motor, with components that do not contribute to the compression of the refrigerant removed.

5. The diagnostic device according to claim 4, wherein the second physical quantity calculation unit calculates the second physical quantity by removing components that do not contribute to the refrigerant compression, based on the current flowing through the motor, the magnetic pole position of the motor, and the motor parameter values ​​of the motor.

6. The diagnostic device according to claim 5, wherein the motor is a motor without a position sensor, and the magnetic pole position is an estimated value.

7. The diagnostic device according to claim 1, wherein the relational information calculation unit expresses the relational information as parameters of a two-dimensional normal distribution.

8. The diagnostic device according to claim 1 or 7, wherein the diagnostic unit diagnoses the deterioration state of the refrigerant compressor when the number of time-series data used in calculating the relational information is greater than a first reference value.

9. The diagnostic device according to any one of claims 1, 7, or 8, wherein the relational information calculation unit calculates the covariance between the first physical quantity and the second physical quantity, and the average difference which is the difference between the average of the first physical quantity and the average of the second physical quantity, as relational information; the diagnostic unit diagnoses that the refrigerant compressor is in a first deterioration state if the covariance is less than or equal to a second reference value; diagnoses that the refrigerant compressor is in a second deterioration state if the covariance is greater than the second reference value and the average difference is greater than or equal to a third reference value; and diagnoses that the refrigerant compressor is in a third deterioration state if the covariance is greater than the second reference value and the average difference is less than the third reference value and greater than or equal to a fourth reference value.

10. The diagnostic device according to claim 9, wherein the second reference value, the third reference value, and the fourth reference value are calculated based on operating data up to a specific time, and the diagnostic unit does not diagnose the refrigerant compressor while the second reference value, the third reference value, and the fourth reference value are being calculated.

11. The diagnostic device according to any one of claims 1 to 10, wherein the first physical quantity calculation unit calculates the first physical quantity based on the suction temperature, which is the refrigerant temperature on the suction side of the refrigerant compressor, and the discharge temperature, which is the refrigerant temperature on the discharge side.

12. The diagnostic device according to any one of claims 1 to 11, further comprising an output unit for outputting the diagnostic results of the diagnosis performed by the diagnostic unit to the outside.

13. An air conditioning system having a diagnostic device according to any one of claims 1 to 12.

14. A diagnostic method comprising: a refrigeration cycle control information acquisition step in which a diagnostic device acquires refrigeration cycle control information, which is control information for a refrigeration cycle including a refrigerant compressor that performs refrigerant compression by driving a motor; a motor control information acquisition step in which the diagnostic device acquires motor control information, which is control information for the motor; a first physical quantity calculation step in which the diagnostic device calculates a first physical quantity relating to the refrigerant compression based on the refrigeration cycle control information; a second physical quantity calculation step in which the diagnostic device calculates a second physical quantity relating to the refrigerant compression based on the motor control information; a relationship information calculation step in which the diagnostic device calculates relationship information showing the relationship between the first physical quantity and the second physical quantity; and a diagnostic step in which the diagnostic device diagnoses the deterioration state of the refrigerant compressor based on the relationship information, wherein in the relationship information calculation step, the diagnostic device calculates the relationship information based on the distribution of the first physical quantity and the second physical quantity on a plane when the first physical quantity and the second physical quantity are plotted on a plane; and in the diagnostic step, the diagnostic device diagnoses the deterioration state of the refrigerant compressor based on the relationship information.

15. A diagnostic device acquires a first refrigeration cycle control information acquisition step, in which the diagnostic device acquires refrigeration cycle control information, which is control information for a refrigeration cycle including a refrigerant compressor that performs refrigerant compression by driving a motor; a diagnostic device acquires a first motor control information acquisition step, in which the diagnostic device acquires motor control information, which is control information for the motor; a first physical quantity calculation step, in which the diagnostic device calculates a first physical quantity relating to the refrigerant compression based on the refrigeration cycle control information; a first second physical quantity calculation step, in which the diagnostic device calculates a second physical quantity relating to the refrigerant compression based on the motor control information; a model generation step, in which the diagnostic device generates a trained model for inferring the deterioration state of the refrigerant compressor from the first physical quantity and the second physical quantity using training data including the first physical quantity and the second physical quantity; a second refrigeration cycle control information acquisition step, in which the diagnostic device acquires refrigeration cycle control information, which is control information for a refrigeration cycle including a refrigerant compressor that performs refrigerant compression by driving a motor; and a second motor control information acquisition step, in which the diagnostic device acquires motor control information, A diagnostic method comprising: a second first physical quantity calculation step in which the diagnostic device calculates a first physical quantity relating to the refrigerant compression based on the refrigeration cycle control information; a second second physical quantity calculation step in which the diagnostic device calculates a second physical quantity relating to the refrigerant compression based on the motor control information; and an inference step in which the diagnostic device diagnoses the deterioration state of the refrigerant compressor by inferring the deterioration state of the refrigerant compressor from the first physical quantity calculated in the second first physical quantity calculation step and the second physical quantity calculated in the second second physical quantity calculation step using the learned model.

Images