Assistance system

Abstract

An assistance system (100) assists an operator in adjustment operation for adjusting the loaded amount of a refrigerant in an air conditioner (50). The assistance system (100) comprises a calculation device (101) and an input interface (103). The input interface (103) receives refrigeration cycle information and information indicating an appropriate loaded amount of the refrigerant. The calculation device (101): acquires information indicating a pre-loaded amount of the refrigerant by using the refrigeration cycle information; acquires information indicating an adjustment amount by calculating the difference between the appropriate loaded amount and the pre-loaded amount; acquires, on the basis of the adjustment amount, information indicating a waiting time; and outputs, to a display device (106), a display signal for displaying the waiting time.

Description

Support System

[0001] The present disclosure relates to an assistance system, and more particularly to an assistance system that assists in an operation to adjust the amount of refrigerant charged in an air conditioner.

[0002] Japanese Patent Application Laid-Open No. 2012-132598 (Patent Document 1) describes an air conditioner that assists an operator by displaying the time remaining until the completion of refrigerant filling after the start of refrigerant filling.

[0003] JP 2012-132598 A

[0004] However, after refrigerant charging begins, there can be a large discrepancy between the calculated refrigerant shortage and the actual shortage. One factor that can cause this is the slow rate of change in the refrigeration cycle of the air conditioner. When the rate of change in the refrigeration cycle of the air conditioner is slow, the calculations show a refrigerant shortage even though the actual refrigerant charge has reached the appropriate level. In this case, continuing to charge the air conditioner with refrigerant can lead to overcharging.

[0005] In view of the above circumstances, the present disclosure aims to provide a support system capable of supporting the operation of adjusting the amount of refrigerant charged in an air conditioner to an appropriate amount.

[0006] The present disclosure provides a support system for supporting adjustment work to adjust the amount of refrigerant filled in an air conditioner, the support system comprising a computing device and an input interface for accepting input of information, wherein the input interface accepts refrigeration cycle information indicating changes in the refrigeration cycle of the air conditioner and information indicating the appropriate amount of refrigerant filled in the air conditioner, the computing device uses the refrigeration cycle information to obtain information indicating the pre-fill amount of refrigerant, obtains information indicating the adjustment amount by calculating the difference between the appropriate amount and the pre-fill amount, obtains information indicating the waiting time based on the adjustment amount, and outputs a display signal to the display device for displaying the waiting time, wherein the pre-fill amount is the amount of refrigerant filled in the air conditioner before the adjustment work, and the waiting time is the time from when adjustment of the adjustment amount of refrigerant is started until the responsiveness of the air conditioner's refrigeration cycle stabilizes.

[0007] According to the present disclosure, it is possible to provide a support system capable of supporting the operation of adjusting the amount of refrigerant charged in an air conditioner to an appropriate amount.

[0008] FIG. 1 is a block diagram showing the configuration of a support system according to a first embodiment. FIG. 2 is a diagram showing an example of an air conditioner. FIG. 3 is a graph showing an example in which refrigerant overfilling occurs due to a response delay in a refrigeration cycle. FIG. 4 is a diagram for explaining an example of the relationship between a pre-fill amount and an adjustment amount. FIG. 5 is a diagram for explaining an overview of the refrigerant amount adjustment work. FIG. 6 is a block diagram for explaining machine learning of a first inference model. FIG. 7 is a block diagram for explaining machine learning of a second inference model. FIG. 8 is a block diagram for explaining the processing of the support system. FIG. 9 is a flowchart for explaining the processing of a calculation device included in the support system. FIG. 10 is a diagram showing an example of a screen displayed on a display device. FIG. 11 is a block diagram for explaining the configuration of a support system according to a second embodiment.

[0009] Each embodiment will be described in detail below with reference to the drawings. The same or corresponding parts in the drawings are designated by the same reference numerals, and the description thereof will not be repeated. It is assumed that the embodiments and modifications in this disclosure can be combined with each other.

[0010] Embodiment 1. [Support System 100] Fig. 1 is a block diagram showing the configuration of a support system 100 according to Embodiment 1. The support system 100 is connected to an air conditioner 50 by wire or wirelessly. The air conditioner 50 is installed, for example, by a contractor in a building or the like where the air conditioner 50 is required. In many cases, the air conditioner 50 installed by the contractor is pre-filled with a refrigerant. For example, a worker performing maintenance work on the air conditioner 50 adjusts the amount of refrigerant charged so that the air conditioner 50 installed in the building is filled with an appropriate amount of refrigerant. The worker uses the support system 100 when adjusting the amount of refrigerant charged.

[0011] The present disclosure also assumes a case where the air conditioner 50 installed by the contractor is not filled with refrigerant. Even in this case, the worker uses the support system 100 to adjust the amount of refrigerant charged so that the air conditioner 50 is filled with the appropriate amount of refrigerant. Hereinafter, the person who performs the refrigerant amount adjustment work will also be referred to as the "worker."

[0012] The assistance system 100 is realized by, for example, a tablet computer. The assistance system 100 includes a computing device 101, a storage device 102, an input interface 103, an output interface 104, an input device 105, and a display device 106. The assistance system 100 may be configured as a notebook personal computer or a desktop personal computer. The assistance system 100 may be configured such that the display device 106 and the input device 105 are independent from the main body. The assistance system 100 does not need to include the display device 106. In this case, the assistance system 100 only needs to have a function of outputting a display signal to a display device connected to the assistance system.

[0013] The arithmetic device 101 is a computing entity that executes various processes according to various programs. The arithmetic device 101 includes a processor, which is an example of a control circuit. The arithmetic device 101 includes, for example, at least one of a central processing unit (CPU), a field programmable gate array (FPGA), a graphics processing unit (GPU), and a multi-processing unit (MPU). Furthermore, the arithmetic device 101 may include volatile memory such as dynamic random access memory (DRAM) and static random access memory (SRAM), and non-volatile memory such as read-only memory (ROM) and flash memory. The arithmetic device 101 may be configured with a processing circuitry. The arithmetic device 101 may be a collection of multiple arithmetic devices or a single arithmetic device.

[0014] The storage device 102 includes non-volatile memory such as a hard disk drive (HDD) and a solid state drive (SSD). The storage device 102 stores various programs and data. The storage device 102 stores at least a first inference model 110, a second inference model 120, and an inference program 130. Each of the first inference model 110 and the second inference model 120 is a model trained by machine learning. The arithmetic device 101 executes inference processing using the first inference model 110 and the second inference model 120. The arithmetic device 101 executes inference processing according to the inference program 130. The arithmetic device 101 may execute various processes using dedicated hardware (electronic circuits) rather than using software.

[0015] The input interface 103 communicates with the air conditioner 50 and receives information relating to the refrigeration cycle of the air conditioner 50 from the air conditioner 50. The input interface 103 transmits the received information to the arithmetic device 101. The output interface 104 outputs a display signal based on an instruction from the arithmetic device 101 to the display device 106. The display device 106 includes a liquid crystal display or the like. The display device 106 displays an image based on the display signal.

[0016] The input device 10 is configured by, for example, a keyboard, a mouse, a microphone, etc. The input device 10 receives an operation from an operator and transmits an operation signal to the arithmetic device 101.

[0017] Here, the flow of the refrigerant amount adjustment work using the assistance system 100 will be outlined. An operator performs a test run of the air conditioner 50 to adjust the refrigerant amount. During the test run, the assistance system 100 calculates the amount of refrigerant already charged in the air conditioner 50. The assistance system 100 obtains the "adjustment amount" of refrigerant by calculating the difference between the calculated refrigerant amount and a known appropriate amount. The assistance system 100 calculates the time required for the air conditioner 50 to be charged with the appropriate amount of refrigerant when refrigerant equivalent to the "adjustment amount" is added to the air conditioner 50. The assistance system 100 displays the calculated adjustment amount and time on the display device 106.

[0018] The worker performs the work of filling the air conditioner 50 with the "adjustment amount" of refrigerant displayed on the display device 106, and waits until the time displayed on the display device 106 has elapsed. The worker finishes the work of adjusting the amount of refrigerant when the time displayed on the display device 106 has elapsed.

[0019] In this embodiment, the operation of the support system 100 will be described using as an example a case where an installed air conditioner 50 is filled with an amount of refrigerant that is less than the appropriate amount. However, this disclosure does not exclude a case where an installed air conditioner 50 is not filled with refrigerant at all. Therefore, when an installed air conditioner 50 is not filled with refrigerant at all, the amount of refrigerant filled by an operator to adjust the amount of refrigerant in the air conditioner 50 to the appropriate amount also falls under the category of "adjustment amount."

[0020] Furthermore, the present disclosure does not exclude cases where an installed air conditioner 50 is filled with more than the appropriate amount of refrigerant. Therefore, when an installed air conditioner 50 is filled with more than the appropriate amount of refrigerant, the amount of refrigerant discharged by an operator to adjust the amount of refrigerant in the air conditioner 50 to the appropriate amount also falls under the category of "adjustment amount." In this case, the operator performs the work of discharging the "adjustment amount" displayed on the display device 106 from the air conditioner 50 and waits until the time displayed on the display device 106 has elapsed. The operator completes the refrigerant amount adjustment work when the time displayed on the display device 106 has elapsed.

[0021] [Air Conditioner 50] FIG. 2 is a diagram showing an example of an air conditioner 50. The air conditioner 50 includes an outdoor unit 51 and an indoor unit 52. The outdoor unit 51 includes a compressor 1, an outdoor heat exchanger (condenser) 2, and a control device 53. A pressure sensor 8 is provided on the discharge side of the compressor 1. A pressure sensor 9 is provided on the suction side of the compressor 1. The pressure sensor 8 detects the pressure on the discharge side of the compressor 1. The pressure sensor 9 detects the pressure on the suction side of the compressor 1. The outdoor unit 51 also includes a temperature sensor 14. The temperature sensor 14 detects the outside air temperature. The outside air temperature is the temperature outside the air-conditioned space of the air conditioner 50. The pressure sensors 8 and 9 and the temperature sensor 14 each transmit their detected values ​​to the control device 53. The control device 53 receives the detected values ​​of the pressure sensors 8 and 9 and the temperature sensor 14.

[0022] The indoor unit 52 includes an indoor heat exchanger (evaporator) 3 and an expansion valve 4. The outdoor unit 51 and the indoor unit 52 include a refrigerant circuit capable of circulating refrigerant. The refrigerant circuit includes a compressor 1, an outdoor heat exchanger 2, an indoor heat exchanger 3, and an expansion valve 4.

[0023] The outdoor unit 51 includes a bypass circuit 15. The bypass circuit 15 is provided with an on-off valve 5. The bypass circuit 15 branches off from the refrigerant circuit on the discharge side of the compressor 1 and reaches the suction side of the compressor 1 via the on-off valve 5. The bypass circuit 15 further includes a filling port 7 and an on-off valve 6. An operator injects refrigerant into the filling port 7 with the on-off valve 6 open. This causes the air conditioner 50 to be filled with refrigerant.

[0024] The control device 53 is provided, for example, on a board included in the outdoor unit 51. The control device 53 communicates with the support system 100 wirelessly or via a wired connection, and transmits information and the like related to the refrigeration cycle of the air conditioner 50 to the support system 100. The information and the like related to the refrigeration cycle include the pressure on the discharge side of the compressor 1, the pressure on the suction side of the compressor 1, and the outdoor air temperature. The control device 53 may transmit, as the information and the like related to the refrigeration cycle, the refrigerant temperature on the discharge side of the compressor 1, the refrigerant temperatures at the outlet and inlet of the outdoor heat exchanger 2, and the refrigerant temperatures at the outlet and inlet of the indoor heat exchanger 3 to the support system 100. The control device 53 may be provided in the indoor unit 52 instead of the outdoor unit 51.

[0025] 2 merely illustrates an air conditioner 50 having a basic configuration. The refrigerant circuit of the air conditioner 50 may include a four-way valve that switches the state of the refrigerant circuit between a first state and a second state. In the first state, the discharge side of the compressor 1 is connected to the outdoor heat exchanger 2, and the suction side of the compressor 1 is connected to the indoor heat exchanger 3. In the second state, the discharge side of the compressor 1 is connected to the indoor heat exchanger 3, and the suction side of the compressor 1 is connected to the outdoor heat exchanger 2.

[0026] [Background Description] Fig. 3 is a graph showing an example of refrigerant overcharging caused by a response delay in the refrigeration cycle. Fig. 4 is a diagram for explaining an example of the relationship between the pre-charging amount and the adjustment amount. Before describing the operation of the assistance system 100, the background that led to the proposal of the assistance system 100 in this disclosure will be explained using Figs. 3 and 4. Fig. 3 shows problems of related art that should be compared with this disclosure.

[0027] As the air conditioner 50 begins to be filled with refrigerant, the amount of refrigerant in the air conditioner 50 gradually increases. However, after the start of refrigerant filling, a large discrepancy may occur between the "determined refrigerant amount" calculated using related technology and the "actual amount filled." Figure 3 shows the relationship between the "determined refrigerant amount" and the "actual amount filled." The "actual amount filled" increases as the amount of refrigerant injected increases. The "actual amount filled" reaches the appropriate amount at time t1.

[0028] However, the "refrigerant amount determined" by the calculation using the related technology is less than the appropriate amount at time t1 because the response delay of the refrigeration cycle is not taken into account. In other words, the related technology determines that the refrigerant amount is insufficient at time t1. Therefore, even though the refrigerant amount actually reaches the appropriate amount at time t1, the related technology continues to inject refrigerant. Thereafter, the related technology determines that the refrigerant amount is appropriate at time t2. As a result, the related technology results in overfilling of refrigerant. Therefore, the operator cannot rely on the related technology to adjust the refrigerant amount.

[0029] It is desirable to enable an operator to determine the exact timing when the air conditioner 50 will be charged with the appropriate amount of refrigerant. To do this, the operator needs to identify the amount of refrigerant to be charged into the air conditioner 50 and the time required to charge the identified amount of refrigerant.

[0030] The amount of refrigerant to be charged into an air conditioner 50 that does not contain refrigerant can be calculated based on the performance of the air conditioner 50. For example, the amount of refrigerant to be charged into an air conditioner 50 that does not contain refrigerant can be determined by using performance test results obtained during design. However, an air conditioner 50 that has already been installed may be pre-charged with refrigerant. This "pre-charge amount" of refrigerant is often unknown when workers adjust the amount of refrigerant on-site.

[0031] Here, the relationship between the "pre-charge amount" and the "adjustment amount" will be explained with reference to FIG. 4. When the total amount of refrigerant to be charged into the air conditioner 50 is defined as the "appropriate charge amount," the "appropriate charge amount" is the sum of the "pre-charge amount" and the "adjustment amount" (see FIG. 5). Therefore, as shown in FIG. 4, the "adjustment amount" is obtained by subtracting the "pre-charge amount" from the "appropriate charge amount." The worker must perform the work of charging the air conditioner 50 with the "adjustment amount" of refrigerant.

[0032] However, in this example, it is assumed that the "pre-fill amount" is less than the "appropriate fill amount." Therefore, if the "pre-fill amount" exceeds the "appropriate fill amount," the "adjustment amount" is obtained by subtracting the "appropriate fill amount" from the "pre-fill amount." In this case, the worker must perform work to drain the "adjustment amount" of refrigerant from the air conditioner 50.

[0033] As already explained, while the "appropriate charging amount" can be calculated based on the performance of the air conditioner 50, the "pre-charging amount" is often unknown during test operation. The "pre-charging amount" may be zero, or the "pre-charging amount" may be close to the "appropriate charging amount." For this reason, even if an operator can determine the amount of refrigerant to be charged into an air conditioner 50 that does not contain refrigerant (appropriate charging amount), the operator cannot determine the "adjustment amount." Even if the operator can determine the "adjustment amount," it is difficult for the operator to determine the waiting time during the adjustment work, taking into account the response delay of the refrigeration cycle. Hereinafter, the time the operator must wait from the start of the charging work with the "adjustment amount" of refrigerant until the charging work is completed may be referred to as the "waiting time."

[0034] If the accurate "waiting time" could be presented to the worker, the worker would be able to complete the refrigerant amount adjustment work simply by waiting until the "waiting time" had elapsed after starting the refrigerant filling work.

[0035] Therefore, in this embodiment, we propose a support system 100 that calculates the ``adjustment amount'' and ``waiting time'' using a first inference model 110 and a second inference model 120 that have been trained by machine learning.

[0036] Refrigerant Amount Adjustment Work FIG. 5 is a diagram for explaining an overview of the refrigerant amount adjustment work. The worker starts a test run of the air conditioner 50 and has the support system 100 calculate the adjustment amount and standby time. The support system 100 displays the calculated adjustment amount and standby time on the display device 106. After checking the displayed adjustment amount and standby time, the worker starts the refrigerant amount adjustment work. When the standby time is reached, the worker ends the refrigerant amount adjustment work. At this point, the air conditioner 50 is filled with the appropriate amount of refrigerant.

[0037] [Machine Learning of First Inference Model 110] Figure 6 is a block diagram for explaining machine learning of the first inference model 110. As shown in Figure 6, the first inference model 110 is trained by supervised learning in a training unit 205 of the computer 200. The training unit 205 is configured with hardware and software of the computer 200. The training unit 205 receives the installation conditions, time-series data during trial operation, a first reference value, a second reference value, and a pre-fill amount as learning data used in the machine learning of the first inference model 110. Of these learning data, the pre-fill amount is the correct answer data. The time-series data during trial operation is an example of refrigeration cycle information that indicates changes in the refrigeration cycle of the air conditioner 50.

[0038] The installation conditions include the length of the refrigerant piping included in the air conditioner 50, the difference in elevation between the installation positions of the outdoor unit 51 and the indoor unit 52, and the model name of the air conditioner 50. The time-series data during the test run includes the outside air temperature, the pressure on the discharge side of the compressor 1, and the pressure on the suction side of the compressor 1.

[0039] The first reference value and the second reference value are appropriate refrigerant fill amounts for the air conditioner 50. However, the first reference value is an appropriate fill amount calculated through a performance test at the time of design, and the second reference value is an appropriate fill amount calculated based on the installation conditions. In this way, the information indicating the appropriate fill amount includes information indicating the fill amount calculated through a performance test of the air conditioner 50.

[0040] The pre-fill amount is the amount already filled into the air conditioner 50. The pre-fill amount is identified from the actual filling record. If the workers involved in the refrigerant amount adjustment work are managed by ID, the ID may be added to the learning data so that the adjustment skills of the workers are taken into account in the machine learning.

[0041] Strictly speaking, the appropriate refrigerant charge amount for the air conditioner 50 is determined taking into consideration the outdoor heat exchanger 2, the indoor heat exchanger 3, the refrigerant piping, and the like that make up the refrigerant circuit. However, in this embodiment, the appropriate refrigerant charge amount for the air conditioner 50 is represented by the appropriate refrigerant charge amount for the outdoor heat exchanger (condenser) 2. This is because, in general, the refrigerant amount in the condenser is considered to roughly reflect the refrigerant amount for the entire air conditioner. Therefore, the first reference value, the second reference value, and the appropriate charge amount are each the appropriate refrigerant charge amount for the outdoor heat exchanger 2.

[0042] Typically, during the design stage before an air conditioning system (air conditioner) leaves the factory, the condenser is filled with an amount of refrigerant determined based on the condenser's size. This amount of refrigerant does not take into account disturbance factors such as outside air temperature. For example, whether the outside temperature is -5°C or +35°C, the condenser is filled with a uniform amount of refrigerant that is considered appropriate for the condenser. To correct for disturbance factors, it is necessary to record in a database whether the actual amount of refrigerant filled was correct.

[0043] By comparing the amount of refrigerant filled when the outside air temperature is -5°C with the appropriate amount, a correction value for eliminating the effects of disturbance factors can be identified. The amount of refrigerant filled when the outside air temperature is -5°C is, for example, 20 kg, and the appropriate amount is, for example, 18 kg. In this case, if refrigerant is filled so that the amount of refrigerant in the condenser is the appropriate value of 10 kg at an outside air temperature of -5°C, it can be seen that there will be an overfill of 2 kg. In this case, the amount of refrigerant filled in the condenser should be corrected from 10 kg to 8 kg.

[0044] The training unit 205 receives a large amount of data set consisting of the learning data shown in Figure 6 and trains the first inference model 110. The trained first inference model 110 is stored in the storage device 102 of the assistance system 100.

[0045] In this way, the first inference model 110 is trained to infer the pre-fill amount based on the learning data. More specifically, the first inference model 110 is trained to infer the pre-fill amount based on the learning data including the pre-fill amount and refrigeration cycle information. Note that the learning data of the first inference model 110 does not necessarily have to include the installation conditions. Furthermore, the learning data of the first inference model 110 does not necessarily have to include the first reference value or the second reference value.

[0046] [Machine Learning of Second Inference Model 120] Fig. 7 is a block diagram for explaining machine learning of the second inference model 120. As shown in Fig. 7, the second inference model 120, like the first inference model 110, is trained by supervised learning in the training unit 205 of the computer 200. Note that, like the first inference model 110, the second inference model 120 may be trained in a computer other than the computer 200.

[0047] The training unit 205 accepts the installation conditions, time-series data during trial operation, adjustment amount, and waiting time as learning data used in the machine learning of the second inference model 120. Of these learning data, the waiting time is the correct answer data.

[0048] The installation conditions and the time-series data during trial operation are the same as those described as the learning data for the first inference model 110. The adjustment amount is the amount of refrigerant required for an operator to adjust the amount of refrigerant in the air conditioner 50 to the appropriate amount. For example, if the amount of refrigerant in the air conditioner 50 is less than the appropriate amount, the adjustment amount is the amount of refrigerant that should be added to the air conditioner 50 during trial operation. In this way, the adjustment amount includes the amount of refrigerant that should be charged to the air conditioner 50 during the adjustment work to adjust the amount of refrigerant in the air conditioner 50 to the appropriate charge amount.

[0049] The standby time is the time from when the refrigerant amount in the air conditioner 50 is adjusted with the adjusted amount of refrigerant until the responsiveness of the refrigeration cycle stabilizes. For example, if the amount of refrigerant in the air conditioner 50 is less than the appropriate amount, the standby time is the time from when the adjusted amount of refrigerant is filled into the air conditioner 50 until the responsiveness of the refrigeration cycle stabilizes. In other words, the standby time is the time that the operator who adjusted the refrigerant in the air conditioner 50 with the adjusted amount of refrigerant must wait.

[0050] The training unit 205 receives a large amount of data set consisting of these learning data and trains the second inference model 120. The trained second inference model 120 is stored in the storage device 102 of the assistance system 100.

[0051] In this way, the second inference model 120 is trained to infer the waiting time based on the training data. More specifically, the second inference model 120 is trained to infer the waiting time based on the training data including the waiting time and the adjustment amount. Note that the training data of the second inference model 120 does not necessarily include the installation conditions.

[0052] [Processing of the Support System 100] Figure 8 is a block diagram for explaining the processing of the support system 100. As shown in Figure 8, time-series data during a test run, installation conditions, and a first reference value are input to the first inference model 110. The time-series data during a test run is input periodically or irregularly over time from the air conditioner 50 that has started a test run. The installation conditions and the first reference value are input, for example, from the input device 105 (see Figure 1) based on the operation of an operator. Note that when the support system 100 is connected to a cloud system configured on a network, the installation conditions and the first reference value may be input to the first inference model 110 from the cloud system.

[0053] The first inference model 110 infers the pre-fill amount based on the input information and outputs the pre-fill amount. The adjustment amount is calculated by subtracting the first reference value from the inference result. The calculated adjustment amount, installation conditions, and the first reference value are input to the second inference model 120. The second inference model 120 infers the waiting time based on the input information and outputs the waiting time. The display device 106 displays the adjustment amount and the waiting time. The calculation device 101 performs the above-described processing by controlling the first inference model 110, the second inference model 120, and the display device 106.

[0054] The first inference model 110 may output an inference result even when installation conditions are not input. The first inference model 110 may output an inference result even when a second reference value is input instead of the first reference value. The second inference model 120 may output an inference result even when installation conditions are not input.

[0055] 9 is a flowchart for explaining the processing of the arithmetic device 101 included in the support system 100. Here, the processing of the arithmetic device 101 will be explained in more detail according to the flowchart shown in FIG.

[0056] First, an operator starts a test run of the air conditioner 50. The arithmetic device 101 starts processing to acquire time-series data from the air conditioner 50 during the test run (step S101). Next, the operator uses the input device 105 to input the installation conditions and the first reference value (appropriate filling amount) to the arithmetic device 101. As a result, the arithmetic device 101 acquires the installation conditions and the first reference value (step S102).

[0057] The processing of steps S101 and S102 is executed via the input interface 103 (see FIG. 1 ). That is, the input interface 103 receives refrigeration cycle information indicating a change in the refrigeration cycle of the air conditioner 50 and information indicating the appropriate amount of refrigerant charged to the air conditioner 50.

[0058] Next, the calculation device 101 inputs the installation conditions, the first reference value, and the time-series data into the first inference model 110 (step S103). Next, the calculation device 101 acquires the inference result (pre-fill amount) from the first inference model 110 (step S104). That is, the calculation device 101 acquires information indicating the pre-fill amount using the refrigeration cycle information. More specifically, the calculation device 101 acquires the pre-fill amount from the first inference model 110 by inputting the refrigeration cycle information into the first inference model 110.

[0059] Next, the calculation device 101 calculates the adjustment amount by subtracting the pre-filled amount from the first reference value (appropriate filling amount) (step S105). That is, the calculation device 101 calculates the difference between the appropriate filling amount and the pre-filled amount to obtain information indicating the adjustment amount.

[0060] Next, the calculation device 101 inputs the installation conditions, time-series data, and adjustment amount to the second inference model 120 (step S106). Next, the calculation device 101 acquires the inference result (waiting time) from the second inference model 120 (step S107). That is, the calculation device 101 acquires information indicating the waiting time based on the adjustment amount. More specifically, the calculation device 101 acquires the waiting time from the second inference model 120 by inputting the adjustment amount to the second inference model 120.

[0061] Next, the arithmetic device 101 outputs a display signal for displaying the adjustment amount and the standby time to the display device 106 (step S108). The display device 106 displays the adjustment amount and the standby time based on the display signal. Thereafter, an operator fills the air conditioner 50 with the adjustment amount of refrigerant. Note that if the calculation result in step S105 is a negative value, an operator discharges the adjustment amount of refrigerant from the air conditioner 50.

[0062] [Display Example of Display Device 106] FIG. 10 is a diagram showing an example of a screen 107 displayed on the display device 106. As shown in FIG. 10, the screen 107 displays, for example, an adjustment amount, a waiting time, and an OK button. The worker fills the air conditioner 50 with the adjusted amount of refrigerant and clicks the OK button. The waiting time then counts down as time passes. After clicking the OK button, the worker waits for the waiting time on the screen 107 to reach zero. When the waiting time on the screen 107 reaches zero, the refrigerant amount adjustment operation is completed. At this point, the air conditioner 50 is filled with the appropriate amount of refrigerant. According to this embodiment, the worker can fill the air conditioner 50 with the appropriate amount of refrigerant by simply performing the refrigerant amount adjustment operation once.

[0063] Second Embodiment Fig. 11 is a block diagram illustrating the configuration of a support system 100A according to a second embodiment. The support system 100A includes a server device 400 constituting a cloud system or the like, and a communication device 300. The communication device 300 and the server device 400 are communicatively connected via a network 90 such as the Internet. The communication device 300 is, for example, a mobile terminal such as a smartphone carried by a worker performing the work of adjusting the amount of refrigerant. The communication device 300 may be configured as a desktop personal computer (PC), a laptop PC, a smartwatch, a wearable device, a tablet PC, or the like.

[0064] The server device 400 includes a computing device 101 and a storage device 102, similar to the assistance system 100. The storage device 102 stores the first inference model 110, the second inference model 120, and the inference program 130 shown in Figure 1. The server device 400 further includes a communication interface 115 that enables communication between the communication device 300 and the computing device 101.

[0065] The communication device 300 includes a display device 20, an input interface 103, an input device 105, and a communication interface 116. The communication device 300 is connected to a network 90 via the communication interface 116.

[0066] The communication device 300 acquires time-series data during the test run from the air conditioner 50 via the input interface 103. The communication device 300 acquires the installation conditions and the first reference value via the input device 105 operated by an operator. The communication device 300 transmits the time-series data during the test run, the installation conditions, and the first reference value to the server device 400 via the network 90.

[0067] Server device 400 calculates the adjustment amount and standby time based on the information received from communication device 300, similarly to support system 100, and transmits information indicating the adjustment amount and standby time to communication device 300. Communication device 300 displays the adjustment amount and standby time on display device 20 based on the information received from server device 400. Screen 107 shown in FIG. 10 is displayed on display device 20. Note that server device 400 may acquire the installation conditions and the first reference value via various cloud systems. Using the adjustment amount and standby time displayed on display device 20, the worker performs the refrigerant adjustment work in the same procedure as in embodiment 1.

[0068] (Summary) The present embodiment will be summarized below.

[0069] (1) The present disclosure provides a support system (100, 100A) that supports adjustment work to adjust the amount of refrigerant charged in an air conditioner, the support system including a calculation device (101) and an input interface (103) that accepts input of information. The input interface accepts refrigeration cycle information indicating changes in the refrigeration cycle of the air conditioner and information indicating an appropriate amount of refrigerant charged to the air conditioner (steps S101 and S102). The calculation device uses the refrigeration cycle information to obtain information indicating the pre-charge amount of refrigerant (step S104). The calculation device calculates the difference between the appropriate amount and the pre-charge amount to obtain information indicating the adjustment amount (step S105). The calculation device obtains information indicating a waiting time based on the adjustment amount (step S107). The calculation device outputs a display signal to a display device (106) to display the waiting time (step S108). The pre-charge amount is the amount of refrigerant charged in the air conditioner before the adjustment work. The waiting time is the time from when the adjustment of the adjustment amount of refrigerant is started until the responsiveness of the refrigeration cycle of the air conditioner stabilizes.

[0070] (2) The support system of paragraph 1 further includes a memory device (102), which is configured to store a first inference model (110) for inferring the pre-filling amount, and the first inference model is trained to infer the pre-filling amount based on learning data including the pre-filling amount and refrigeration cycle information, and the calculation device obtains the pre-filling amount from the first inference model by inputting the refrigeration cycle information into the first inference model (steps S103, S104).

[0071] (3) In the support system of paragraph 2, the input interface further accepts information regarding the installation conditions of the air conditioner (step S102), the first inference model is trained to infer the pre-fill amount based on learning data that further includes information regarding the installation conditions, and the calculation device obtains the pre-fill amount from the first inference model by inputting refrigeration cycle information and information regarding the installation conditions into the first inference model.

[0072] (4) In the assistance system of paragraph 2, the storage device is configured to store a second inference model (120) for inferring waiting time, the second inference model is trained to infer waiting time based on learning data including waiting time and an adjustment amount, and the calculation device obtains the waiting time from the second inference model by inputting the adjustment amount into the second inference model (steps S106 and S107).

[0073] (5) In the support system of paragraph 4, the input interface further accepts information regarding the installation conditions of the air conditioner (step S102), the second inference model is trained to infer the waiting time based on learning data that further includes information regarding the installation conditions, and the calculation device obtains the waiting time from the second inference model by inputting information regarding the adjustment amount and the installation conditions into the second inference model (steps S106, S107).

[0074] (6) In the support system according to any one of paragraphs 1 to 5, the information indicating the appropriate filling amount includes information indicating the filling amount calculated through a performance test of the air conditioner.

[0075] (7) In the support system of any one of paragraphs 1 to 6, the refrigeration cycle information includes an outside air temperature, a pressure on the discharge side of a compressor included in the air conditioner, and a pressure on the suction side of the compressor.

[0076] (8) In the support system of any one of paragraphs 1 to 7, the adjustment amount is the amount of refrigerant to be charged into the air conditioner in the adjustment work to adjust the amount of refrigerant in the air conditioner to the appropriate charging amount, and the calculation device calculates the adjustment amount by subtracting the pre-charging amount from the appropriate charging amount (step S105).

[0077] The embodiments disclosed herein should be considered to be illustrative in all respects and not restrictive. The scope of the present disclosure is defined by the claims, not by the description of the above embodiments, and is intended to include all modifications within the meaning and scope of the claims.

[0078] 1 Compressor, 2 Outdoor heat exchanger (condenser), 3 Indoor heat exchanger (evaporator), 4 Expansion valve, 5, 6 Opening / closing valve, 7 Filling port, 8, 9 Pressure sensor, 14 Temperature sensor, 15 Bypass circuit, 50 Air conditioner, 51 Outdoor unit, 52 Indoor unit, 53 Control device, 90 Network, 100, 100A Support system, 101 Arithmetic device, 102 Storage device, 103 Input interface, 104 Output interface, 105 Input device, 106 Display device, 107 Screen, 110 First inference model, 115, 116 Communication interface, 120 Second inference model, 130 Inference program, 200 Computer, 205 Inference unit, 300 Communication device, 400 Server device.

Claims

1. A support system for supporting adjustment work to adjust the amount of refrigerant charged in an air conditioner, comprising: a calculation device; and an input interface for receiving input of information, wherein the input interface receives refrigeration cycle information indicating changes in the refrigeration cycle of the air conditioner and information indicating an appropriate amount of refrigerant charged to the air conditioner, wherein the calculation device uses the refrigeration cycle information to obtain information indicating a pre-charge amount of refrigerant, obtains information indicating an adjustment amount by calculating the difference between the appropriate charge amount and the pre-charge amount, obtains information indicating a waiting time based on the adjustment amount, and outputs a display signal to a display device to display the waiting time, wherein the pre-charge amount is the amount of refrigerant charged in the air conditioner before the adjustment work, and the waiting time is the time from when adjustment of the adjustment amount of refrigerant is started until the responsiveness of the refrigeration cycle of the air conditioner stabilizes.

2. The assistance system of claim 1, further comprising a memory device configured to store a first inference model for inferring the pre-filling amount, the first inference model being trained to infer the pre-filling amount based on learning data including the pre-filling amount and the refrigeration cycle information, and the computing device obtaining the pre-filling amount from the first inference model by inputting the refrigeration cycle information into the first inference model.

3. The assistance system described in claim 2, wherein the input interface further accepts information regarding the installation conditions of the air conditioner, the first inference model is trained to infer the pre-fill amount based on learning data further including information regarding the installation conditions, and the calculation device obtains the pre-fill amount from the first inference model by inputting the refrigeration cycle information and information regarding the installation conditions into the first inference model.

4. The assistance system of claim 2, wherein the storage device is configured to store a second inference model for inferring the waiting time, the second inference model is trained to infer the waiting time based on learning data including the waiting time and the adjustment amount, and the computing device obtains the waiting time from the second inference model by inputting the adjustment amount into the second inference model.

5. The assistance system described in claim 4, wherein the input interface further accepts information regarding the installation conditions of the air conditioner, the second inference model is trained to infer the waiting time based on learning data further including information regarding the installation conditions, and the computing device obtains the waiting time from the second inference model by inputting the adjustment amount and information regarding the installation conditions into the second inference model.

6. An assistance system according to any one of claims 1 to 5, wherein the information indicating the appropriate filling amount includes information indicating the filling amount calculated through a performance test of the air conditioner.

7. An assistance system according to any one of claims 1 to 6, wherein the refrigeration cycle information includes the outside air temperature, the pressure on the discharge side of a compressor included in the air conditioner, and the pressure on the suction side of the compressor.

8. The assistance system described in any one of claims 1 to 7, wherein the adjustment amount is the amount of refrigerant to be charged into the air conditioner in the adjustment work in order to adjust the amount of refrigerant in the air conditioner to the appropriate charging amount, and the calculation device calculates the adjustment amount by subtracting the pre-charging amount from the appropriate charging amount.

Images