Refrigerant leak detection device and method

Abstract

Improves the accuracy of refrigerant leak detection. [Solution] One embodiment of the refrigerant leak detection device of the present disclosure is a refrigerant leak detection device (10) that detects refrigerant leaks in refrigeration and air conditioning equipment that has a refrigeration cycle in which refrigerant circulates in a refrigerant circuit in which a compressor, a condenser, an expansion valve, and an evaporator are connected by piping, and the refrigerant leak detection device includes a control unit (1001) and a prediction model (1000), the explanatory variables of the prediction model include measured values ​​and target values ​​of parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment, and the objective variable of the prediction model is a refrigerant quantity index value corrected for fluctuations in the parameters, and the control unit inputs the measured values ​​and target values ​​of the parameters into the prediction model and outputs the refrigerant quantity index value, and uses the refrigerant quantity index value to detect refrigerant leaks in the refrigerant circuit.

Description

[Technical Field]

[0001] FIELD OF THE DISCLOSURE The present disclosure relates to refrigerant leak detection devices and methods. [Background technology]

[0002] Conventionally, it has been known to predict values ​​that serve as indicators of the amount of refrigerant in a refrigeration and air conditioning equipment (hereinafter also referred to as refrigerant amount indicator values, for example, expansion valve opening, degree of subcooling, degree of intake superheat, degree of discharge superheat, etc.) from the operating data of the refrigeration and air conditioning equipment, and detect refrigerant leaks in the refrigeration and air conditioning equipment. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-156528 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the refrigerant quantity index value fluctuates not only due to the refrigerant quantity but also due to environmental conditions such as outside temperature and air conditioning load. Therefore, to accurately determine the refrigerant quantity, it is necessary to correct for fluctuations due to environmental conditions. For example, when a chilled water chiller supplies chilled water at a constant temperature (i.e., the supply water temperature is controlled to a constant temperature), the evaporation temperature is controlled to a constant temperature, so fluctuations in the low-pressure side of the refrigeration cycle are small. In this case, highly accurate detection of refrigerant leaks is possible by correcting for fluctuations in the condensing temperature on the high-pressure side due to outside temperature and load fluctuations using the outside temperature and compressor speed. However, in chilled water chillers that control the supply water temperature to save energy, the evaporation temperature fluctuates due to the control of the supply water temperature, so the accuracy of refrigerant leak detection is reduced by simply correcting for outside temperature and load fluctuations on the high-pressure side. A similar problem occurs when the condensing temperature fluctuates due to supply water temperature control when using heat for heating or hot water supply.

[0005] In this way, when controlling the usage side of the refrigeration and air conditioning equipment (the low-pressure side when using cold energy, and the high-pressure side when using warm energy) to control the capacity of the refrigeration and air conditioning equipment (for example, controlling the water supply temperature of a chiller), the accuracy of refrigerant leak detection decreases due to fluctuations in the refrigeration cycle parameters caused by controlling the usage side of the refrigeration and air conditioning equipment.

[0006] Furthermore, fluctuations in refrigeration cycle parameters caused by capacity control of refrigeration and air conditioning equipment often occur at shorter intervals than fluctuations in outdoor air temperature. Therefore, when capacity control is performed, the amount of operational data for transient states, in which parameters are fluctuating, increases, while the amount of operational data for steady states, in which parameters are stable, decreases. In transient states, even if the outdoor air temperature and compressor speed are the same, the refrigerant quantity index may differ depending on the operating conditions at the time. Therefore, to accurately determine refrigerant leaks, it is preferable to use steady-state operational data. However, when capacity control is actively performed, the steady-state data required for the determination is insufficient. Therefore, transient data must also be used to make the determination, resulting in a decrease in the accuracy of refrigerant leak detection.

[0007] The present disclosure aims to improve the accuracy of refrigerant leak detection in refrigeration and air conditioning equipment that actively controls the state of the refrigeration cycle on the user side for capacity control, particularly when the state quantities on the user side of the refrigeration cycle are transiently fluctuating due to capacity control. [Means for solving the problem]

[0008] A refrigerant leak detection device according to a first aspect of the present disclosure includes: A refrigerant leakage detection device (10) for detecting refrigerant leakage in a refrigeration and air conditioning device having a refrigeration cycle in which a refrigerant circulates in a refrigerant circuit in which a compressor, a condenser, an expansion valve, and an evaporator are connected by piping, comprising: The refrigerant leak detection device comprises a control unit (1001) and a prediction model (1000), an explanatory variable of the prediction model includes a measured value and a target value of a parameter used to control a refrigeration cycle on a user side of the refrigeration and air conditioning equipment, and a response variable of the prediction model is a refrigerant amount index value corrected for fluctuations of the parameter; The control unit inputting the measured values ​​and target values ​​of the parameters into the prediction model and outputting the refrigerant amount index value; The refrigerant amount index value is used to detect refrigerant leakage in the refrigerant circuit.

[0009] According to the first aspect of the present disclosure, both the measured values ​​and target values ​​of parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment are used, thereby improving the accuracy of predicting the refrigerant quantity index value for operating data including transient states that occur due to capacity control of the refrigeration cycle on the user side.

[0010] A second aspect of the present disclosure is the refrigerant leak detection device according to the first aspect, the evaporator cools air or a secondary heat medium; The parameters used to control the refrigeration cycle are parameters used to control the refrigeration cycle from the outlet of the expansion valve to the inlet of the compressor.

[0011] According to the second aspect of the present disclosure, it is possible to improve the accuracy of prediction of the refrigerant amount index value when cooling the air or the secondary-side heat medium.

[0012] A third aspect of the present disclosure is the refrigerant leak detection device according to the second aspect, The parameter used to control the refrigeration cycle is at least one of the evaporation temperature, evaporation pressure, evaporator blowout air temperature, and evaporator outlet temperature of the secondary-side heat medium.

[0013] According to the third aspect of the present disclosure, it is possible to predict a refrigerant quantity index value in which fluctuations in at least one of the evaporation temperature, evaporation pressure, evaporator blown air temperature, and evaporator outlet temperature of the secondary side heat medium are corrected.

[0014] A fourth aspect of the present disclosure is the refrigerant leak detection device according to the first aspect, the condenser heats air or a secondary heat medium; The parameters used to control the refrigeration cycle are parameters used to control the refrigeration cycle from the outlet of the compressor to the inlet of the expansion valve.

[0015] According to the fourth aspect of the present disclosure, it is possible to improve the accuracy of prediction of the refrigerant amount index value when heating the air or the secondary-side heat medium.

[0016] A fifth aspect of the present disclosure is the refrigerant leak detection device according to the fourth aspect, The parameter used to control the refrigeration cycle is at least one of the condensation temperature, the condensation pressure, the condenser blowout air temperature, and the condenser outlet temperature of the secondary-side heat medium.

[0017] According to the fifth aspect of the present disclosure, it is possible to predict a refrigerant quantity index value in which fluctuations in at least one of the condensation temperature, the condensation pressure, the condenser discharge air temperature, and the condenser outlet temperature of the secondary side heat medium are corrected.

[0018] A sixth aspect of the present disclosure is a refrigerant leakage detection device according to any one of the first to fifth aspects, The refrigerant quantity index value is at least one of the expansion valve opening, the degree of subcooling, the degree of suction superheating, the degree of discharge superheating, and a calculated value of any of the expansion valve opening, the degree of subcooling, the degree of suction superheating, and the degree of discharge superheating.

[0019] According to the sixth aspect of the present disclosure, various values ​​can be appropriately selected and used as an index of the amount of refrigerant depending on the specifications and usage conditions of the refrigeration and air conditioning equipment.

[0020] A seventh aspect of the present disclosure is a refrigerant leakage detection device according to any one of the first to sixth aspects, the explanatory variables of the prediction model further include values ​​of parameters used to correct fluctuations in a refrigeration cycle other than that on the user side of the refrigeration and air conditioning equipment; The control unit The prediction model is input with measured values ​​and target values ​​of parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment, and values ​​of parameters used to correct fluctuations in the refrigeration cycle on the other side of the refrigeration and air conditioning equipment, and outputs the refrigerant quantity index value.

[0021] According to the seventh aspect of the present disclosure, for example, it is possible to correct fluctuations on the heat source side of the refrigeration cycle due to fluctuations in environmental conditions such as outside air temperature and air conditioning load.

[0022] A method according to an eighth aspect of the present disclosure comprises: A method performed by a refrigerant leakage detection device (10) for detecting refrigerant leakage in a refrigeration and air conditioning device having a refrigeration cycle in which a refrigerant circulates in a refrigerant circuit in which a compressor, a condenser, an expansion valve, and an evaporator are connected by piping, comprising: The refrigerant leak detection device comprises a control unit (1001) and a prediction model (1000), an explanatory variable of the prediction model includes a measured value and a target value of a parameter used to control a refrigeration cycle on a user side of the refrigeration and air conditioning equipment, and a response variable of the prediction model is a refrigerant amount index value corrected for fluctuations of the parameter; The control unit inputting the measured values ​​and target values ​​of the parameters into the prediction model and outputting the refrigerant amount index value; The refrigerant amount index value is used to detect refrigerant leakage in the refrigerant circuit. [Brief explanation of the drawings]

[0023] [Figure 1] FIG. 2 is a pH diagram of a refrigeration cycle during cooling according to an embodiment of the present disclosure. [Figure 2] FIG. 2 is a pH diagram of a refrigeration cycle during heating according to an embodiment of the present disclosure. [Figure 3] FIG. 10 is a diagram for explaining fluctuations in evaporation temperature according to an embodiment of the present disclosure. [Figure 4] FIG. 10 is a diagram for explaining the reason for using both the measured value and the target value of a parameter used to control the refrigeration cycle of the user side of the refrigeration and air conditioning equipment. [Figure 5] FIG. 10 is a diagram for explaining the reason for using both the measured value and the target value of a parameter used to control the refrigeration cycle of the user side of the refrigeration and air conditioning equipment. [Figure 6] FIG. 1 is a diagram for explaining a direct expansion refrigeration and air conditioning device (for cooling) according to an embodiment of the present disclosure. [Figure 7] FIG. 1 is a diagram for explaining an indirect expansion refrigeration and air conditioning device (for cooling) according to an embodiment of the present disclosure. [Figure 8] FIG. 1 is a diagram for explaining a direct expansion refrigeration and air conditioning device (for heating) according to an embodiment of the present disclosure. [Figure 9] FIG. 1 is a diagram for explaining an indirect expansion refrigeration and air conditioning device (for heating) according to an embodiment of the present disclosure. [Figure 10] FIG. 1 is a diagram illustrating an overall configuration according to an embodiment of the present disclosure. [Figure 11] 1 is a diagram illustrating the hardware configuration of a refrigerant leak detection device and a learning device according to an embodiment of the present disclosure. [Figure 12] 1 is a diagram illustrating a functional configuration of a refrigerant leakage detection device according to an embodiment of the present disclosure. [Figure 13] FIG. 1 is a diagram illustrating a functional configuration of a learning device according to an embodiment of the present disclosure. [Figure 14] 4 is a flowchart of a refrigerant leakage detection process according to an embodiment of the present disclosure. [Figure 15] 10 is a flowchart of a learning process according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0024] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0025] <Summary> An overview of the present disclosure will be described below with reference to Figures 1 to 5. In the present disclosure, refrigerant leaks are detected using a prediction model in which measured values ​​and target values ​​of parameters such as the evaporation temperature (Te) of the refrigerant circulating through the refrigerant circuit of a refrigeration and air conditioning equipment are explanatory variables, and a refrigerant amount index value is a target variable. Note that the measured values ​​are actually measured values, and the target values ​​are control command values ​​calculated and set by the control logic built into the refrigeration and air conditioning equipment based on desired values ​​for room temperature and water supply temperature input by the user using a remote controller or the like for the refrigeration and air conditioning equipment (in other words, the refrigeration and air conditioning equipment operates so that the actual measured values ​​of parameters such as the evaporation temperature approach the target values, which are control command values).

[0026] FIG. 1 is a pH diagram of a refrigeration cycle during cooling (e.g., air conditioning) of air or a secondary heat medium according to an embodiment of the present disclosure. The left side of FIG. 1 is a pH diagram during standard cooling conditions, and the right side of FIG. 1 is a pH diagram during partial load operation at the same outdoor temperature (35°C) as during standard cooling operation. In this example, the evaporation temperature of the refrigeration and air conditioning equipment during cooling (e.g., air conditioning) of air or a secondary heat medium is not constant but fluctuates depending on the load. In this case, the refrigerant amount index fluctuates due to fluctuations in the evaporation temperature. If the evaporation temperature fluctuates stepwise, as shown in A of FIG. 3, and a sufficient amount of stable operating data can be obtained for the fluctuating evaporation temperature, the measured evaporation temperature can be added to the explanatory variables of the prediction model.

[0027] FIG. 2 is a pH diagram of a refrigeration cycle during heating (e.g., heating) of air or a secondary heat medium according to an embodiment of the present disclosure. The left side of FIG. 2 is a pH diagram during standard heating conditions, and the right side of FIG. 2 is a pH diagram during partial load operation at the same outdoor temperature (7°C) as during standard heating operation. In this example, the condensing temperature of the refrigeration and air conditioning equipment during heating (e.g., heating) of the air or secondary heat medium is not constant but fluctuates depending on the load. In this case, the refrigerant amount index fluctuates due to fluctuations in condensing temperature. If the condensing temperature fluctuates stepwise as shown in A of FIG. 3 and a sufficient amount of stable operating data can be obtained for the fluctuating condensing temperature, the measured value of the condensing temperature can be added to the explanatory variables of the prediction model.

[0028] In this way, if the evaporation temperature and condensation temperature are data like A in Figure 3 (steady state data > transient data), it is sufficient to add only the measured values ​​of the evaporation temperature and condensation temperature to the explanatory variables of the prediction model. However, in reality, as will be described in detail with reference to Figure 3, the evaporation temperature and condensation temperature fluctuate as shown in B and C in Figure 3, so it is not sufficient to add only the measured values ​​of the evaporation temperature and condensation temperature to the explanatory variables of the prediction model.

[0029] FIG. 3 is a diagram for explaining fluctuations in evaporation temperature according to an embodiment of the present disclosure.

[0030] In the case of A in Figure 3, when machine learning a prediction model and when making predictions using the prediction model (i.e., during operation), it is possible to use only long-term steady-state data, even if the evaporation temperature value fluctuates. Therefore, even if the evaporation temperature fluctuates, fluctuations in the refrigerant amount index value due to parameters such as evaporation temperature can be corrected simply by adding the measured value of the evaporation temperature or an equivalent parameter to the explanatory variables. The same applies when the condensing temperature value fluctuates during heating.

[0031] However, it is difficult to use only steady-state data during actual operation, and cases where steady-state data is available only for a short period of time, as in B in Figure 3, or a quasi-steady state including a transient from an unsteady state to a steady state, as in C, are used. For this reason, in this disclosure, not only are the measured values ​​of parameters such as the evaporating temperature added as explanatory variables, but both the measured values ​​and the target values ​​are also added as explanatory variables to correct fluctuations in the refrigerant amount index value due to fluctuations in the evaporating temperature.

[0032] Hereinafter, with reference to FIGS. 4 and 5, the reason for using both the measured values ​​and the target values ​​of the parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment will be described.

[0033] Figure 4 is a scatter plot of the target value (horizontal axis) of the water supply temperature of a chiller in operation and the measured value (vertical axis) of the water supply temperature.

[0034] If the water supply temperature is ideally controlled, the measured value of the water supply temperature should match the target value, and all points on the graph should be plotted on the y=x axis. In this case, the two parameters are multicollinear. If both parameters are used as explanatory variables in the prediction model, there is a concern that the accuracy of the prediction model may decrease or become unstable, so only the measured value of the water supply temperature should be used as an explanatory variable.

[0035] In the scatter diagram of the target value of the water supply temperature and the measured value of the water supply temperature during actual operation, the two parameters are positively correlated, but are distributed over a wide range. The regression equation based on linear regression is close to y=x, but the coefficient of determination R, which is a measure of the strength of the correlation, is 2 Since the correlation coefficient is below 0.5, which is generally considered to be the standard for determining high correlation, the two parameters are not multicollinear. In this case, using the two parameters as explanatory variables in the prediction model will improve the accuracy of the prediction model.

[0036] Figure 5 is a time series graph of the target value of the chiller's water supply temperature and the measured value of the water supply temperature during operation. At each of points A, B, and C, the measured value of the water supply temperature is the same temperature T2, but the target value of the water supply temperature is different.

[0037] A: The target value of the water supply temperature has been changed from T3 to T1, so the water supply temperature is in an unsteady state. B: The target value of the water supply temperature has been changed from T1 to T3, so the water supply temperature is rising. C: The water temperature has reached a steady state and is maintained at the target value T2.

[0038] As described above, the water supply temperature conditions at points A, B, and C are different, so by adding the measured water supply temperature value and the target water supply temperature value to the explanatory variables, the expressive power of the prediction model is improved, and the prediction accuracy is also improved.

[0039] <Refrigerating and air conditioning equipment> Hereinafter, a refrigeration and air conditioning equipment will be described with reference to Figs. 6 to 9. The refrigeration and air conditioning equipment has a refrigeration cycle in which a refrigerant circulates in a refrigerant circuit in which a compressor 101, a condenser 102, an expansion valve 103, and an evaporator 104 are connected by piping. For example, the refrigeration and air conditioning equipment is an equipment that controls the evaporation temperature when cooling the air or secondary-side heat medium (e.g., cooling) and the condensation temperature when heating the air or secondary-side heat medium (e.g., heating) during partial load operation to save energy. Note that instead of the evaporation temperature when cooling the secondary-side heat medium or the condensation temperature when heating, the liquid supply temperature of the secondary-side heat medium (e.g., the water supply temperature when the secondary-side medium is water) may be controlled.

[0040] As the refrigerant quantity index value of the refrigeration and air conditioning equipment, at least one of the expansion valve opening, the degree of subcooling, the degree of intake superheating, the degree of discharge superheating, and a calculated value calculated using either the expansion valve opening, the degree of subcooling, the degree of intake superheating, or the degree of discharge superheating, or a combination thereof, can be used.

[0041] The expansion valve opening (EV opening) is the opening of the expansion valve (EV) 103.

[0042] The degree of subcooling is the difference between the condenser outlet temperature Tb and the condensation temperature Tc.

[0043] The suction superheat is the difference between the compressor suction temperature Ts and the evaporation temperature Te.

[0044] The discharge superheat is the difference between the compressor discharge temperature Td and the condensation temperature Tc.

[0045] 6 is a diagram illustrating a direct expansion refrigeration and air conditioning device (for cooling) according to an embodiment of the present disclosure. For example, the refrigeration and air conditioning device is a direct expansion type that performs cooling by directly exchanging heat between a low-temperature refrigerant and the air in the space to be air-conditioned.

[0046] When the evaporator 104 cools air, the parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment are parameters used to control the refrigeration cycle from the outlet of the expansion valve 103 to the inlet of the compressor 101. For example, the parameters used to control the refrigeration cycle from the outlet of the expansion valve 103 to the inlet of the compressor 101 are at least one of the evaporation temperature, the evaporation pressure, and the evaporator blow-out air temperature.

[0047] 7 is a diagram for explaining an indirect expansion type refrigeration and air conditioning equipment (in the case of cooling) according to one embodiment of the present disclosure. For example, the refrigeration and air conditioning equipment is of an indirect expansion type that cools a low-temperature refrigerant by heat exchange with a secondary heat medium (for example, water) and supplies the cooled refrigerant to the user side.

[0048] When the evaporator 104 cools a secondary heat medium (for example, water), the parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment are parameters used to control the refrigeration cycle from the outlet of the expansion valve 103 to the inlet of the compressor 101. For example, the parameters used to control the refrigeration cycle from the outlet of the expansion valve 103 to the inlet of the compressor 101 are at least one of the evaporation temperature, the evaporation pressure, and the evaporator outlet temperature of the secondary heat medium (for example, water).

[0049] 8 is a diagram illustrating a direct expansion refrigeration and air conditioning device (for heating) according to an embodiment of the present disclosure. For example, the refrigeration and air conditioning device is a direct expansion type that heats a high-temperature refrigerant by directly exchanging heat with the air in the space to be air-conditioned.

[0050] When the condenser 102 heats air, the parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment are parameters used to control the refrigeration cycle from the outlet of the compressor 101 to the inlet of the expansion valve 103. For example, the parameters used to control the refrigeration cycle from the outlet of the compressor 101 to the inlet of the expansion valve 103 are at least one of the condensing temperature, the condensing pressure, and the condenser discharge air temperature.

[0051] 9 is a diagram for explaining an indirect expansion type refrigeration and air conditioning equipment (for heating) according to an embodiment of the present disclosure. For example, the refrigeration and air conditioning equipment is an indirect expansion type that heats a high-temperature refrigerant by heat exchange with a secondary heat medium (for example, water) and supplies the heated refrigerant to the user side.

[0052] When the condenser 102 heats a secondary-side heat medium (for example, water), the parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment are parameters used to control the refrigeration cycle from the outlet of the compressor 101 to the inlet of the expansion valve 103. For example, the parameters used to control the refrigeration cycle from the outlet of the compressor 101 to the inlet of the expansion valve 103 are at least one of the condensation temperature, the condensation pressure, and the condenser outlet temperature of the secondary-side heat medium (for example, water).

[0053] <Overall composition> Fig. 10 is a diagram showing the overall configuration according to one embodiment of the present disclosure. The refrigerant leak detection system 1 can include a refrigerant leak detection device 10 and a learning device 20. Although Fig. 10 shows the refrigerant leak detection device 10 and the learning device 20 as separate devices, the refrigerant leak detection device 10 and the learning device 20 may also be combined into a single device. Each will be described below.

[0054] <<Refrigerant Leak Detection System>> The refrigerant leakage detection system 1 is a system that detects refrigerant leakage from a refrigeration and air conditioning device 30.

[0055] <<Refrigerant leak detection device>> The refrigerant leak detection device 10 inputs measured values ​​and target values ​​of parameters used to control the refrigeration cycle on the user side (low-pressure side during cooling and high-pressure side during heating) of the refrigeration and air conditioning equipment 30 into the prediction model generated by the learning device 20, and outputs a refrigerant amount index value (specifically, a refrigerant amount index value corrected for fluctuations in the parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment 30) to detect a refrigerant leak in the refrigeration and air conditioning equipment 30. In addition to the measured values ​​and target values ​​of the parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment 30, any operating data of the refrigeration and air conditioning equipment 30 may also be input to the prediction model. For example, to correct for fluctuations in environmental conditions on the heat source side (high-pressure side during cooling and low-pressure side during heating) of the refrigeration and air conditioning equipment 30, related heat source side parameters (outdoor air temperature, compressor rotation speed, etc.) may also be input. The refrigerant leak detection device 10 is composed of one or more computers.

[0056] <<Learning device>> The learning device 20 is a device that generates a prediction model. The explanatory variables of the prediction model include measured values ​​and target values ​​of parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment 30 (the low-pressure side when cooling and the high-pressure side when heating), and the objective variable of the prediction model is a refrigerant amount index value (specifically, a refrigerant amount index value corrected for fluctuations in the parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment 30). Note that the explanatory variables of the prediction model may include any operating data of the refrigeration and air conditioning equipment 30 in addition to the measured values ​​and target values ​​of the parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment 30. For example, to correct fluctuations in environmental conditions on the heat source side of the refrigeration and air conditioning equipment 30 (the high-pressure side when cooling and the low-pressure side when heating), related heat source parameters (outdoor air temperature, compressor rotation speed, etc.) may also be included. The learning device 20 is configured with one or more computers.

[0057] <<Refrigerating and air conditioning equipment>> The refrigeration and air conditioning equipment 30 includes a refrigeration cycle in which a refrigerant circulates in a refrigerant circuit in which a compressor, a condenser, an expansion valve, and an evaporator are connected by piping. For example, the refrigeration and air conditioning equipment 30 is the refrigeration and air conditioning equipment described with reference to Figs. 6 to 9.

[0058] <Hardware configuration> 11 is a diagram showing the hardware configuration of the refrigerant leak detection device 10 and the learning device 20 according to an embodiment of the present disclosure. The refrigerant leak detection device 10 and the learning device 20 can include a control unit 1001, a main memory unit 1002, an auxiliary memory unit 1003, an input unit 1004, an output unit 1005, and an interface unit 1006. Each of these will be described below.

[0059] The control unit 1001 is a processor (for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), etc.) that executes various programs installed in the auxiliary storage unit 1003.

[0060] The main memory unit 1002 includes a non-volatile memory (Read Only Memory (ROM)) and a volatile memory (Random Access Memory (RAM)). The ROM stores various programs, data, etc. required for the control unit 1001 to execute various programs installed in the auxiliary memory unit 1003. The RAM provides a working area into which the various programs installed in the auxiliary memory unit 1003 are expanded when executed by the control unit 1001.

[0061] The auxiliary storage unit 1003 is an auxiliary storage device that stores various programs and information used when the various programs are executed.

[0062] The input unit 1004 is an input device through which the operator of the refrigerant leak detection device 10 and the learning device 20 inputs various instructions to the refrigerant leak detection device 10 and the learning device 20 .

[0063] The output unit 1005 is an output device that outputs the internal states of the refrigerant leak detection device 10 and the learning device 20, etc.

[0064] The interface unit 1006 is a communication device for connecting to a network and communicating with other devices.

[0065] <Functional configuration> 12 is a diagram showing the functional configuration of a refrigerant leak detection device 10 according to an embodiment of the present disclosure. A control unit 1001 of the refrigerant leak detection device 10 includes an operating data acquisition unit 111, a prediction unit 112, a calculation unit 113, and a refrigerant leak detection unit 114. Moreover, the control unit 1001 of the refrigerant leak detection device 10 executes a program to function as the operating data acquisition unit 111, the prediction unit 112, the calculation unit 113, and the refrigerant leak detection unit 114. A prediction model 1000 generated by a learning device 20 is stored in the refrigerant leak detection device 10.

[0066] The operating data acquisition unit 111 acquires operating data of the refrigeration and air conditioning equipment 30 in operation (i.e., the refrigeration and air conditioning equipment that is the target of refrigerant leakage detection). Specifically, the operating data acquisition unit 111 acquires, from the refrigeration and air conditioning equipment 30, measured values ​​and target values ​​of parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment 30 (for example, measured values ​​and target values ​​of the evaporation temperature).

[0067] For example, in addition to the measured values ​​and target values ​​of parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment 30, the operating data acquisition unit 111 also acquires measured values ​​of parameters (e.g., outside air temperature and compressor rotation speed) on the heat source side (high-pressure side when cooling, low-pressure side when heating) of the refrigeration and air conditioning equipment 30 in order to correct for fluctuations in environmental conditions.

[0068] The prediction unit 112 predicts a refrigerant amount index value (for example, the expansion valve opening, the degree of subcooling, the degree of intake superheat, the degree of discharge superheat, etc. under normal conditions) using the prediction model 1000. Specifically, the prediction unit 112 inputs all parameters acquired by the operation data acquisition unit 111 into the prediction model 1000, and acquires a predicted value of the refrigerant amount index value as an output of the prediction model 1000.

[0069] The calculation unit 113 calculates the measured value of the refrigerant amount index value (i.e., the actually measured value). Specifically, the calculation unit 113 calculates the measured value of the refrigerant amount index value using the operating data acquired by the operating data acquisition unit 111.

[0070] The refrigerant leak detection unit 114 detects a refrigerant leak. For example, the refrigerant leak detection unit 114 determines that a refrigerant leak has occurred if the difference between the predicted refrigerant amount index value acquired by the prediction unit 112 and the measured refrigerant amount index value calculated by the calculation unit 113 is equal to or greater than a threshold, and determines that a refrigerant leak has not occurred if the difference between the predicted refrigerant amount index value acquired by the prediction unit 112 and the measured refrigerant amount index value calculated by the calculation unit 113 is less than the threshold. If a refrigerant leak has occurred, the refrigerant leak detection unit 114 can notify any device that a refrigerant leak has occurred.

[0071] Prediction model 1000 is a model in which explanatory variables include measured values ​​and target values ​​of parameters used to control the refrigeration cycle on the user side of refrigeration and air conditioning equipment 30, and dependent variables are refrigerant amount index values ​​(specifically, refrigerant amount index values ​​corrected for fluctuations in the parameters used to control the refrigeration cycle on the user side of refrigeration and air conditioning equipment 30). Note that the explanatory variables of prediction model 1000 can include, in addition to the measured values ​​and target values ​​of parameters used to control the refrigeration cycle on the user side of refrigeration and air conditioning equipment 30, measured values ​​of parameters (e.g., outside air temperature and compressor rotation speed) used to correct fluctuations in the refrigeration cycle on the heat source side (high-pressure side during cooling, low-pressure side during heating) of refrigeration and air conditioning equipment 30.

[0072] 13 is a diagram illustrating the functional configuration of a learning device 20 according to an embodiment of the present disclosure. A control unit 2001 of the learning device 20 includes a teacher data acquisition unit 211 and a learning unit 212. Furthermore, the control unit 2001 of the learning device 20 executes a program to function as the teacher data acquisition unit 211 and the learning unit 212.

[0073] The training data acquisition unit 211 acquires training data used when generating the prediction model 1000.

[0074] For example, the training data is obtained by extracting parameters corresponding to the objective variable and the explanatory variables of the prediction model 1000 from data obtained during normal operation of the refrigeration and air conditioning equipment 30, in which no refrigerant leaks or other malfunctions are detected, from past operational data acquired during operation of the refrigeration and air conditioning equipment 30. Specifically, when cold energy is used, the objective variables include the expansion valve opening, the degree of subcooling, the degree of intake superheat, the degree of discharge superheat, etc. Furthermore, the explanatory variables may include not only measured values ​​and target values ​​of parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment 30, but also measured values ​​of parameters (e.g., outside air temperature and compressor rotation speed) used to correct fluctuations in the refrigeration cycle on the heat source side (high-pressure side during cooling and low-pressure side during heating) of the refrigeration and air conditioning equipment 30.

[0075] The learning unit 212 generates the prediction model 1000 using the teacher data acquired by the teacher data acquisition unit 211. For example, the learning unit 212 performs machine learning to generate the prediction model 1000 so that the predicted value of the refrigerant amount index value output when the measured values ​​and target values ​​of the parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment 30, which are explanatory variables of the teacher data, are input to the prediction model 1000, approaches the measured value of the refrigerant amount index value, which is the objective variable of the teacher data.

[0076] For example, the learning unit 212 performs machine learning to generate the prediction model 1000 so that the predicted value of the refrigerant quantity index value output when the measured values ​​and target values ​​of the parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment 30, which are explanatory variables of the training data, and the measured values ​​of the parameters (e.g., outside air temperature and compressor rotation speed) used to correct fluctuations in the refrigeration cycle on the heat source side (high-pressure side when cooling, low-pressure side when heating) of the refrigeration and air conditioning equipment 30, approach the measured value of the refrigerant quantity index value, which is the objective variable of the training data.

[0077] For example, prediction model 1000 is a model that, when input with measured values ​​and target values ​​of parameters used to control the refrigeration cycle on the user side of refrigeration and air conditioning equipment 30 in operating data during operation, outputs a predicted value of the refrigerant amount index value when refrigeration and air conditioning equipment 30 is normal. For example, prediction model 1000 is a model that, when input with measured values ​​and target values ​​of parameters used to control the refrigeration cycle on the user side of refrigeration and air conditioning equipment 30 in operating data during operation, and measured values ​​of parameters (e.g., outside air temperature and compressor rotation speed) used to correct fluctuations in the refrigeration cycle on the heat source side (high-pressure side during cooling, low-pressure side during heating) of refrigeration and air conditioning equipment 30, outputs a predicted value of the refrigerant amount index value when refrigeration and air conditioning equipment 30 is normal.

[0078] <Processing method> FIG. 14 is a flowchart of a refrigerant leakage detection process according to an embodiment of the present disclosure.

[0079] In step 101 (S101), the control unit 1001 of the refrigerant leak detection device 10 acquires, from the refrigeration and air conditioning equipment 30, measured values ​​and target values ​​of parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment 30. For example, the control unit 1001 of the refrigerant leak detection device 10 acquires, in addition to the measured values ​​and target values ​​of parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment 30, measured values ​​of parameters (e.g., outside air temperature and compressor rotation speed) used to correct fluctuations in the refrigeration cycle on the heat source side (high-pressure side when cooling, low-pressure side when heating) of the refrigeration and air conditioning equipment 30.

[0080] Specifically, in step 111 (S111), the control unit 1001 of the refrigerant leak detection device 10 acquires measured values ​​and target values ​​of parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment 30. In step 112 (S112), the control unit 1001 of the refrigerant leak detection device 10 determines whether or not to correct the fluctuations in the refrigeration cycle on the heat source side of the refrigeration and air conditioning equipment 30. If the fluctuations in the refrigeration cycle on the heat source side of the refrigeration and air conditioning equipment 30 are to be corrected, the process proceeds to S113, and if not, the process proceeds to S102. In step 113 (S113), the control unit 1001 of the refrigerant leak detection device 10 acquires measured values ​​of parameters used to correct the fluctuations in the refrigeration cycle on the heat source side of the refrigeration and air conditioning equipment 30.

[0081] In step 102 (S102), the control unit 1001 of the refrigerant leak detection device 10 inputs the measured values ​​and target values ​​of the parameters acquired in S101 to the prediction model 1000, and outputs a predicted value of the refrigerant amount index value under normal conditions. For example, the control unit 1001 of the refrigerant leak detection device 10 inputs the measured values ​​and target values ​​of the parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment 30, and the measured values ​​of parameters (e.g., outside air temperature and compressor rotation speed) used to correct fluctuations in the refrigeration cycle on the heat source side (high-pressure side during cooling and low-pressure side during heating) of the refrigeration and air conditioning equipment 30, and outputs a predicted value of the refrigerant amount index value under normal conditions.

[0082] In step 103 (S103), the control unit 1001 of the refrigerant leakage detection device 10 calculates a measurement value of the refrigerant amount index value (for example, an actually measured value or a calculated value of these values).

[0083] In step 104 (S104), the control unit 1001 of the refrigerant leak detection device 10 detects a refrigerant leak. For example, the control unit 1001 of the refrigerant leak detection device 10 determines that a refrigerant leak has occurred if the difference between the predicted value of the refrigerant amount index value in S102 and the measured value of the refrigerant amount index value in S103 is equal to or greater than a threshold, and determines that a refrigerant leak has not occurred if the difference between the predicted value of the refrigerant amount index value in S102 and the measured value of the refrigerant amount index value in S103 is less than the threshold.

[0084] FIG. 15 is a flowchart of a learning process according to an embodiment of the present disclosure.

[0085] In step 201 (S201), the control unit 2001 of the learning device 20 acquires past operating data of the refrigeration and air conditioning equipment 30.

[0086] In step 202 (S202), the control unit 2001 of the learning device 20 extracts normal data in which no equipment failure or refrigerant leakage has occurred from the past operation data of the refrigeration and air conditioning equipment 30 acquired in S201.

[0087] In step 203 (S203), the control unit 2001 of the learning device 20 acquires only parameters related to the objective variable and explanatory variable of the prediction model 1000 from the past normal operation data of the refrigeration and air conditioning equipment 30 acquired in S202 as training data to be used when generating the prediction model 1000.

[0088] In step 204 (S204), the control unit 2001 of the learning device 20 generates the prediction model 1000 using the training data acquired in S203. For example, the control unit 2001 of the learning device 20 performs machine learning to generate the prediction model 1000 so that the predicted value of the refrigerant amount index value output when the measured values ​​and target values ​​of the parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment 30, which are the training data, are input to the prediction model 1000 approaches the measured value of the refrigerant amount index value, which is the training data. For example, the control unit 2001 of the learning device 20 performs machine learning to generate the prediction model 1000 so that the predicted value of the refrigerant quantity index value output when the measured values ​​and target values ​​of the parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment 30, which are training data, and the measured values ​​of the parameters (e.g., outside air temperature and compressor rotation speed) used to correct fluctuations in the refrigeration cycle on the heat source side (high-pressure side when cooling, low-pressure side when heating) of the refrigeration and air conditioning equipment 30, approach the measured value of the refrigerant quantity index value, which is the training data.

[0089] As described above, according to the embodiment of the present disclosure, there is provided a refrigerant leak detection device (10) that detects refrigerant leaks in refrigeration and air conditioning equipment having a refrigeration cycle in which refrigerant circulates in a refrigerant circuit in which a compressor, a condenser, an expansion valve, and an evaporator are connected by piping, the refrigerant leak detection device having a control unit (1001) and a prediction model (1000), explanatory variables of the prediction model include measured values ​​and target values ​​of parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment, and the objective variable of the prediction model is a refrigerant quantity index value corrected for parameter fluctuations, and the control unit inputs the measured values ​​and target values ​​of the parameters to the prediction model and outputs the refrigerant quantity index value, and a refrigerant leak detection device that detects refrigerant leaks in the refrigerant circuit using the refrigerant quantity index value can be provided.

[0090] This allows for the use of both the measured values ​​and the target values ​​of the parameters used to control the refrigeration cycle of the refrigeration and air conditioning equipment on the user side, thereby improving the accuracy of prediction of the refrigerant amount index value.

[0091] Preferably, the evaporator cools the air or the secondary-side heat medium, and the parameters used to control the refrigeration cycle are parameters used to control the refrigeration cycle from the outlet of the expansion valve to the inlet of the compressor, thereby improving the accuracy of prediction of the refrigerant amount index value when cooling the air or the secondary-side heat medium.

[0092] Preferably, the parameter used to control the refrigeration cycle is at least one of the evaporation temperature, evaporation pressure, evaporator blow-out air temperature, and evaporator outlet temperature of the secondary heat medium, thereby making it possible to predict a refrigerant amount index value in which fluctuations in at least one of the evaporation temperature, evaporation pressure, evaporator blow-out air temperature, and evaporator outlet temperature of the secondary heat medium are corrected.

[0093] Preferably, the condenser heats the air or the secondary-side heat medium, and the parameters used to control the refrigeration cycle are parameters used to control the refrigeration cycle from the outlet of the compressor to the inlet of the expansion valve, thereby improving the accuracy of prediction of the refrigerant amount index value when heating the air or the secondary-side heat medium.

[0094] Preferably, the parameter used to control the refrigeration cycle is at least one of the condensing temperature, the condensing pressure, the condenser discharge air temperature, and the condenser outlet temperature of the secondary heat medium, thereby making it possible to predict a refrigerant amount index value in which fluctuations in at least one of the condensing temperature, the condensing pressure, the condenser discharge air temperature, and the condenser outlet temperature of the secondary heat medium are corrected.

[0095] Preferably, the refrigerant amount index value is at least one of the expansion valve opening, the degree of subcooling, the degree of suction superheat, the degree of discharge superheat, and a calculated value of any of the expansion valve opening, the degree of subcooling, the degree of suction superheat, and the degree of discharge superheat, thereby enabling various values ​​to be used as the refrigerant amount index.

[0096] Preferably, the explanatory variables of the prediction model (1000) further include values ​​of parameters used to correct fluctuations in the refrigeration cycle on the user side of the refrigeration and air conditioning equipment. The control unit (1001) inputs measured values ​​and target values ​​of parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment and values ​​of parameters used to correct fluctuations in the refrigeration cycle on the user side of the refrigeration and air conditioning equipment to the prediction model (1000), and outputs a refrigerant amount index value. This makes it possible to correct fluctuations due to environmental conditions such as outside air temperature and air conditioning load, as well as fluctuations due to other factors. Furthermore, if a transient response occurs in the refrigeration cycle on the heat source side due to sudden fluctuations due to the environmental conditions, the explanatory variables of the prediction model (1000) are added to correct the excessive response, for example, by adding the measured value and target value of the condensing temperature when cold energy is used, or the measured value and target value of the evaporating temperature when hot energy is used.

[0097] According to an embodiment of the present disclosure, there is provided a method executed by a refrigerant leak detection device (10) for detecting a refrigerant leak in a refrigeration and air conditioning equipment having a refrigeration cycle in which a refrigerant circulates in a refrigerant circuit in which a compressor, a condenser, an expansion valve, and an evaporator are connected by piping, the refrigerant leak detection device comprising a control unit (1001) and a prediction model (1000), explanatory variables of the prediction model include measured values ​​of parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment, and a target variable of the prediction model is a refrigerant quantity index value corrected for parameter fluctuations, the control unit inputs the measured values ​​and target values ​​of the parameters to the prediction model and outputs the refrigerant quantity index value, and a method can be provided for detecting a refrigerant leak in the refrigerant circuit using the refrigerant quantity index value.

[0098] Although the embodiments have been described above, it will be understood that various changes in form and details can be made without departing from the spirit and scope of the claims. [Explanation of symbols]

[0099] 1. Refrigerant leak detection system 10 Refrigerant leak detection device 20 Learning Device 30 Refrigeration and air conditioning equipment 101 Compressor 102 Condenser 103 Expansion valve 104 Evaporator 111 Operation data acquisition unit 112 Prediction Department 113 Calculation Unit 114 Refrigerant leak detection unit 211 Teacher Data Acquisition Department 212 Learning Department 1000 predictive models 1001 control section 1002 Main memory 1003 Auxiliary storage unit 1004 Input section 1005 Output section 1006 Interface section

Claims

1. A refrigerant leakage detection device (10) for detecting refrigerant leakage in a refrigeration and air conditioning device having a refrigeration cycle in which a refrigerant circulates in a refrigerant circuit in which a compressor, a condenser, an expansion valve, and an evaporator are connected by piping, The refrigerant leakage detection device comprises a control unit (1001) and a prediction model (1000), an explanatory variable of the prediction model includes a measured value and a target value of a parameter used to control a refrigeration cycle on a user side of the refrigeration and air conditioning equipment, and a response variable of the prediction model is a refrigerant amount index value corrected for fluctuations of the parameter; The control unit inputting the measured values ​​and target values ​​of the parameters into the prediction model and outputting the refrigerant amount index value; A refrigerant leakage detection device that detects refrigerant leakage in the refrigerant circuit using the refrigerant amount index value.

2. the evaporator cools air or a secondary heat medium; 2. The refrigerant leakage detection device according to claim 1, wherein the parameter used to control the refrigeration cycle is a parameter used to control the refrigeration cycle from the outlet of the expansion valve to the inlet of the compressor.

3. 3. The refrigerant leak detection device according to claim 2, wherein the parameters used to control the refrigeration cycle are at least one of an evaporation temperature, an evaporation pressure, an evaporator blow-out air temperature, and an evaporator outlet temperature of the secondary-side heat medium.

4. the condenser heats air or a secondary heat medium; 2. The refrigerant leakage detection device according to claim 1, wherein the parameter used to control the refrigeration cycle is a parameter used to control the refrigeration cycle from the outlet of the compressor to the inlet of the expansion valve.

5. 5. The refrigerant leak detection device according to claim 4, wherein the parameter used to control the refrigeration cycle is at least one of a condensation temperature, a condensation pressure, a condenser blowout air temperature, and a condenser outlet temperature of the secondary side heat medium.

6. 6. A refrigerant leak detection device as described in any one of claims 1 to 5, wherein the refrigerant quantity index value is at least one of an expansion valve opening degree, a degree of subcooling, a degree of intake superheat, a degree of discharge superheat, and a calculated value of any of the expansion valve opening degree, the degree of subcooling, the degree of intake superheat, and the degree of discharge superheat.

7. the explanatory variables of the prediction model further include values ​​of parameters used to correct fluctuations in a refrigeration cycle other than that on the user side of the refrigeration and air conditioning equipment; The control unit 2. The refrigerant leak detection device of claim 1, wherein the prediction model is input with measured values ​​and target values ​​of parameters used to control the refrigeration cycle on the user side of the refrigeration and air conditioning equipment, and values ​​of parameters used to correct fluctuations in the refrigeration cycle on the other side than the user side of the refrigeration and air conditioning equipment, and outputs the refrigerant quantity index value.

8. A method executed by a refrigerant leak detection device (10) for detecting refrigerant leaks in a refrigeration and air conditioning device having a refrigeration cycle in which a refrigerant circulates in a refrigerant circuit in which a compressor, a condenser, an expansion valve, and an evaporator are connected by piping, comprising: The refrigerant leakage detection device comprises a control unit (1001) and a prediction model (1000), an explanatory variable of the prediction model includes a measured value and a target value of a parameter used to control a refrigeration cycle on a user side of the refrigeration and air conditioning equipment, and a response variable of the prediction model is a refrigerant amount index value corrected for fluctuations of the parameter; The control unit inputting the measured values ​​and target values ​​of the parameters into the prediction model and outputting the refrigerant amount index value; The refrigerant quantity indicator value is used to detect a refrigerant leak in the refrigerant circuit.

Images