Air conditioning system, processing device, and method for determining the operating state of an air conditioner

Abstract

An air conditioning system (100) comprises: a monitoring unit (12) that monitors an electrical characteristic value which is state information of each of a plurality of components disposed on a control substrate (10); a storage unit (14) that stores, as a first electrical characteristic value, the rated value of an electrical characteristic of each of the components, that stores, as a second electrical characteristic value, an electrical characteristic value of each of the components before an air conditioner (1) is broken, and that stores, as a third electrical characteristic value, an electrical characteristic value in the determination transmitted from the monitoring unit (12); a learning unit (22) that generates a learning model on the basis of the first and second electrical characteristic values; a storage unit (23) that stores the learning model; an inference unit (13) that performs inference calculation for determining normality or abnormality of the control substrate (10) on the basis of the third electrical characteristic value and the learning model; and a display unit (15) that displays information relating to the operation state of the air conditioner (1) on the basis of a result of the inference calculation.

Description

[Technical Field]

[0001] The present disclosure relates to an air conditioning system including at least one air conditioner having a control board for controlling air conditioning, a processing device configured to be able to communicate with the air conditioner, and a method for determining the operating state of the air conditioner. [Background technology]

[0002] A conventional air conditioning system for determining whether an air conditioner is malfunctioning is, for example, that shown in Patent Document 1. Patent Document 1 discloses a method for determining whether an air conditioner is malfunctioning by using a refrigeration cycle diagram that shows the refrigeration cycle, which indicates changes in the state of the refrigerant, on a pH diagram. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2019 / 146035 Summary of the Invention [Problem to be solved by the invention]

[0004] The prior art typified by Patent Document 1 aims to allow the user to easily diagnose the cause and severity of an abnormality when an abnormality occurs in an air conditioner. For this reason, when an abnormality occurs in an air conditioner, it is possible to compare the state with when the air conditioner is normal, but there is a problem in that it is difficult to notify the user in advance that the air conditioner may break down.

[0005] The present disclosure has been made in consideration of the above, and aims to provide an air conditioning system that can notify information about the operating status of an air conditioner before the air conditioner breaks down. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the object, an air conditioning system according to the present disclosure is an air conditioning system including at least one air conditioner having a control board for controlling air conditioning, and a processing device configured to be able to communicate with the air conditioner. The air conditioning system includes a monitoring unit, a characteristic value storage unit, a learning unit, a learning model storage unit, an inference unit, and a display unit. The monitoring unit monitors electrical characteristic values, which are status information for each of a plurality of components arranged on the control board. The characteristic value storage unit stores rated values ​​of the electrical characteristics of each component as first electrical characteristic values, stores electrical characteristic values ​​of each component before the air conditioner failed based on the electrical characteristic values ​​transmitted from the monitoring unit as second electrical characteristic values, and stores the electrical characteristic values ​​at the time of determination transmitted from the monitoring unit as third electrical characteristic values. The learning unit generates a learning model, which is a trained model, based on the first and second electrical characteristic values. The learning model storage unit stores the learning model. The inference unit performs an inference calculation to determine whether the control board is normal or abnormal based on the third electrical characteristic value and the learning model. The display unit displays information about the operating state of the air conditioner based on the result of the inference calculation. [Effects of the Invention]

[0007] The air conditioning system according to the present disclosure has the advantage of being able to notify information relating to the operating status of an air conditioner before the air conditioner breaks down. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing a configuration example of an air conditioning system according to a first embodiment. [Figure 2] FIG. 1 is a diagram showing another example of the system configuration of the air conditioning system according to the first embodiment. [Figure 3] FIG. 1 is a diagram showing an example of the configuration of an inference unit provided on a control board of an air conditioner according to Embodiment 1. [Figure 4] 1 is a flowchart illustrating an operation in a utilization phase according to the first embodiment; [Figure 5] FIG. 1 is a diagram showing a configuration example of a learning unit provided in a cloud server according to a first embodiment; [Figure 6] 1 is a flowchart illustrating the operation of the learning phase according to the first embodiment; [Figure 7] FIG. 10 is a diagram illustrating the operation of the learning phase in more detail according to the first embodiment. [Figure 8] FIG. 1 is a diagram showing a configuration example of an air conditioning system according to a modified example of the first embodiment. [Figure 9] FIG. 10 is a diagram showing a configuration example of an air conditioning system according to a second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] An air conditioning system, a processing device, and an air conditioner operating state determination method according to embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0010] Embodiment 1 FIG. 1 is a diagram showing an example of the configuration of an air conditioning system 100 according to the first embodiment. FIG. 2 is a diagram showing another example of the system configuration of the air conditioning system 100 according to the first embodiment. The air conditioning system 100 according to the first embodiment includes an air conditioner 1 having a control board for controlling air conditioning, and a cloud server 2 which is an example of a processing device configured to be able to communicate with the air conditioner 1. While FIG. 1 shows one air conditioner 1 as an example, as shown in FIG. 2, there may be multiple air conditioners 1. Therefore, the cloud server 2 is configured to be able to communicate with at least one air conditioner 1. The air conditioner 1 may be a separate-type air conditioner in which an outdoor unit and an indoor unit (not shown) are separated, or may be an integrated-type air conditioner in which a compressor, an indoor heat exchanger, an outdoor heat exchanger, etc. (not shown) are provided in a single housing.

[0011] Next, the configurations of the air conditioner 1 and the cloud server 2, and the functions of the air conditioner 1 and the cloud server 2 will be described.

[0012] The air conditioner 1 has a control board 10 and a display unit 15. The control board 10 has a communication unit 11, a monitoring unit 12, an inference unit 13, and a memory unit 14. The control board 10 may be the same board as the control board for performing air conditioning control, or may be a different board from the control board for performing air conditioning control.

[0013] The monitoring unit 12 monitors the electrical characteristic values, which are status information of each of the multiple components arranged on the control board 10. The electrical characteristic values ​​may be any value that can determine the status of the component. For example, if the component is a resistor, the electrical characteristic value is the resistance value, and if the component is a capacitor, the electrical characteristic value is the capacitance.

[0014] The memory unit 14 stores the rated value of the electrical characteristic of each component as a first electrical characteristic value. Furthermore, the memory unit 14 stores the electrical characteristic value of each component before the air conditioner 1 failed as a second electrical characteristic value, based on the electrical characteristic value transmitted from the monitoring unit 12. Furthermore, the memory unit 14 stores the electrical characteristic value at the time of determination transmitted from the monitoring unit 12 as a third electrical characteristic value. In this document, the memory unit 14 is appropriately referred to as a "characteristic value memory unit." An example of the memory unit 14 is a nonvolatile memory. The memory unit 14 may be any storage medium or storage device that can retain the first to third electrical characteristic values ​​in a nonvolatile manner.

[0015] The inference unit 13 performs an inference calculation to determine whether the control board 10 is normal or abnormal based on the third electrical characteristic value and a learning model described later. The inference result, which is the result of the inference calculation inferred by the inference unit 13, is stored in the storage unit 14.

[0016] The display unit 15 refers to the inference results stored in the memory unit 14 or displays information about the operating state of the air conditioner 1 based on the inference results received from the inference unit 13. Information about the operating state includes a normal state and an abnormal state. If the inference calculation determines that the control board 10 is normal, a determination result that the air conditioner 1 is in a normal state is displayed. If the inference calculation determines that the control board 10 is abnormal, a determination result that the air conditioner 1 is in an abnormal state is displayed. A determination result that the air conditioner 1 is in an abnormal state means that even if the air conditioner 1 is not malfunctioning at the time of the determination, there is a high possibility that it will malfunction in the future.

[0017] Communication unit 11 is configured to be able to communicate with cloud server 2. Communication unit 11 may be either a communication circuit implemented on control board 10 or a communication adapter. Communication unit 11 transmits information required for processing by cloud server 2 to cloud server 2, receives information transmitted from cloud server 2, and stores it in memory unit 14.

[0018] The functions of the communication unit 11, monitoring unit 12, and inference unit 13 in the control board 10 can be realized by processing means such as a microcomputer. The processing means referred to here includes those called microprocessors, microcomputers, microcontrollers, CPUs (Central Processing Units), or DSPs (Digital Signal Processors). The processing means executes the above-mentioned processes by calling up control programs stored in the storage unit 14. The processing means may also be realized by a single circuit, a composite circuit, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a circuit that combines these.

[0019] The cloud server 2 has a communication unit 21, a learning unit 22, and a memory unit 23. The communication unit 21 is realized by a communication device, a communication circuit, a communication adapter, or the like. The communication unit 21 receives information transmitted from the air conditioner 1 and stores it in the memory unit 23. The information transmitted from the air conditioner 1 includes the first to third electrical characteristic values ​​described above. The learning unit 22 generates a learning model, which is a trained model, based on the first to third electrical characteristic values ​​stored in the memory unit 23. The memory unit 23 stores the learning model generated by the learning unit 22. In this document, the memory unit 23 will be referred to as the "learning model memory unit" as appropriate.

[0020] Next, the operation of the utilization phase when utilizing the learning model according to embodiment 1 will be described with reference to Fig. 3 and Fig. 4. Fig. 3 is a diagram showing an example of the configuration of the inference unit 13 provided on the control board 10 of the air conditioner 1 according to embodiment 1. Fig. 4 is a flowchart explaining the operation of the utilization phase according to embodiment 1.

[0021] 3, the inference unit 13 includes a data acquisition unit 131 and an inference calculation unit 132. The data acquisition unit 131 acquires a third electrical characteristic value from the monitoring unit 12 (step S11). The data acquisition unit 131 passes the third electrical characteristic value acquired in step S11 to the inference calculation unit 132 (step S12). The inference calculation unit 132 reads a learning model from the storage unit 14 (step S13). The inference calculation unit 132 performs an inference calculation to determine whether the control board 10 is normal or abnormal based on the third electrical characteristic value and the learning model (step S14).

[0022] The inference unit 13 determines whether or not there is an abnormality in the control board 10 based on the result of the inference calculation (step S15). If it is determined that the control board 10 is abnormal (step S15, Yes), the inference unit 13 outputs a determination result that the air conditioner 1 is in an abnormal state as information regarding the operating state of the air conditioner 1 (step S16). If it is determined that the control board 10 is not abnormal, i.e., is normal (step S15, No), the inference unit 13 outputs a determination result that the air conditioner 1 is in a normal state as information regarding the operating state of the air conditioner 1 (step S17). The display unit 15 receives the determination results from steps S16 and S17 and notifies the user by displaying the received determination result (step S18). When the processing of step S18 is completed, the process returns to step S11, and the processing from step S11 is repeated.

[0023] Next, the operation of the learning phase when generating a learning model according to the first embodiment will be described with reference to Fig. 5 and Fig. 6. Fig. 5 is a diagram showing an example of the configuration of the learning unit 22 provided in the cloud server 2 according to the first embodiment. Fig. 6 is a flowchart illustrating the operation of the learning phase according to the first embodiment.

[0024] 5, the learning unit 22 includes a data acquisition unit 221 and a learning model generation unit 222. The data acquisition unit 221 acquires first and second electrical characteristic values ​​from the air conditioner 1 as learning data (step S21). The data acquisition unit 221 passes the first and second electrical characteristic values ​​acquired in step S21 to the learning model generation unit 222 (step S22).

[0025] The learning model generation unit 222 generates a learning model for inferring the operating state of each air conditioner 1 based on learning data created based on a combination of the first and second electrical characteristic values ​​(step S23). Here, the learning data is data in which the first and second electrical characteristic values ​​are associated with each other. The learning model generated in step S23 is stored in the memory unit 23 (step S24).

[0026] The learning algorithm used by the learning unit 22 can be any known algorithm such as supervised learning, unsupervised learning, or reinforcement learning. Here, we will explain the case where unsupervised learning is applied. Unsupervised learning is a method of learning features in learning data that does not include results by providing the learning unit 22 with the learning data.

[0027] Fig. 7 is a diagram for explaining the operation of the learning phase in more detail according to embodiment 1. Fig. 7 shows the concept of operation when k-means, which is an example of unsupervised learning, is applied. The k-means is a non-hierarchical clustering algorithm, and is a method for classifying a given number of clusters into k clusters using the mean of the clusters.

[0028] First, the learning model generation unit 222 calculates the difference between the second electrical characteristic value and the first electrical characteristic value as difference data (step a). The learning model generation unit 222 randomly assigns clusters 603 to the difference data 601 and calculates the centroid 602 of each cluster 603 based on the assigned difference data 601 (step b). Next, the learning model generation unit 222 calculates the distance between each difference data 601 and each centroid 602, and reassigns each difference data 601 to the cluster 603 having the centroid 602 with the closest distance (step c). Then, if the assignment of clusters 603 to all difference data 601 remains unchanged or if the amount of change falls below a predetermined threshold in the above process, the learning model generation unit 222 determines that the learning process has converged and terminates the learning process (step d).

[0029] The learning model generation unit 222 executes the above-mentioned learning process and stores the optimized difference data 601 and the information on the optimized centroids 602 and clusters 603 as learning model data in the storage unit 23. The subsequent processes are as described above.

[0030] In the air conditioning system 100 according to the first embodiment, a configuration in which the air conditioner 1 has an inference unit 13 is illustrated as shown in Fig. 1, but it may also be configured as shown in Fig. 8. Fig. 8 is a diagram showing an example configuration of an air conditioning system 100A according to a modified example of the first embodiment.

[0031] Comparing the configuration in Fig. 8 with Fig. 1, the air conditioner 1 has been replaced with an air conditioner 1A, the control board 10 has been replaced with a control board 10A, and the cloud server 2 has been replaced with a cloud server 2A. Furthermore, the inference unit 13 has been removed from the control board 10, and an inference unit 24 has been provided in the cloud server 2A. That is, the inference unit 13 that was provided on the control board 10 has been moved to the cloud server 2A as the inference unit 24. The other configurations are the same as or equivalent to the configuration in Fig. 1, and the same or equivalent components are denoted by the same reference numerals, and duplicate explanations will be omitted.

[0032] In the air conditioning system 100A configured as shown in Figure 8, the inference unit 24 provided in the cloud server 2A performs the above-mentioned inference calculations on multiple control boards 10A provided in multiple air conditioners 1A. According to the air conditioning system 100A, it is possible to suppress an increase in functionality on the air conditioner 1A side, which has the effect of suppressing the cost of modifying the air conditioner 1A side.

[0033] 8 in which the inference unit 24 is provided in the cloud server 2A, the first to third electrical characteristic values ​​transmitted from the air conditioner 1A may be periodically received and stored in the storage unit 23 of the cloud server 2A, regardless of whether the learning process is being executed in the cloud server 2A. In this way, the processing time in the inference unit 24 can be shortened.

[0034] As described above, the air conditioning system according to the first embodiment includes at least one air conditioner having a control board for controlling the air conditioning, and a processing device configured to be able to communicate with the air conditioner. The air conditioning system includes a monitoring unit, a characteristic value storage unit, a learning unit, a learning model storage unit, an inference unit, and a display unit. The monitoring unit monitors electrical characteristic values, which are status information for each of a plurality of components arranged on the control board. The characteristic value storage unit stores the rated values ​​of the electrical characteristics of each component as first electrical characteristic values, stores the electrical characteristic values ​​of each component before the air conditioner failed based on the electrical characteristic values ​​transmitted from the monitoring unit as second electrical characteristic values, and stores the electrical characteristic values ​​at the time of determination transmitted from the monitoring unit as third electrical characteristic values. The learning unit generates a learning model, which is a trained model, based on the first and second electrical characteristic values, and the learning model storage unit stores the learning model. The inference unit performs inference calculations to determine whether the control board is normal or abnormal based on the third electrical characteristic value and the learning model. The display unit displays information about the operating status of the air conditioner based on the results of the inference calculation. By using an air conditioning system configured in this manner, it is possible to output information about the operating status of the air conditioner before the air conditioner breaks down, and therefore it is possible to notify the user in advance that the air conditioner may break down.

[0035] The processing device according to the first embodiment is configured to be able to communicate with at least one air conditioner having a control board for controlling air conditioning. The control board of the air conditioner stores electrical characteristic values, which are status information for each of a plurality of components arranged on the control board. The processing device includes a memory unit, a learning unit, an inference unit, and a display unit. The memory unit stores rated values ​​of the electrical characteristics of each component in the air conditioner as first electrical characteristic values, receives electrical characteristic values ​​transmitted from the air conditioner, retains electrical characteristic values ​​of each component before the air conditioner failed based on the electrical characteristic values ​​transmitted from the air conditioner as second electrical characteristic values, and stores electrical characteristic values ​​transmitted from the air conditioner at the time of determination as third electrical characteristic values. The learning unit generates a learning model, which is a trained model, based on the first and second electrical characteristic values ​​and stores it in the memory unit. The inference unit performs an inference calculation to determine whether the control board is normal or abnormal based on the third electrical characteristic value and the learning model. The display unit displays information regarding the operating status of the air conditioner based on the results of the inference calculation. By using a processing device configured in this manner, information regarding the operating status of the air conditioner can be output before the air conditioner breaks down, so that the user can be notified in advance that there is a possibility that the air conditioner will break down.

[0036] Furthermore, the air conditioner operating state determination method according to the first embodiment is applied to a processing device configured to be able to communicate with at least one air conditioner in which electrical characteristic values, which are status information for each of a plurality of components arranged on a control board for controlling the air conditioning, are stored on the control board, and is a method for determining the operating state of the air conditioner in order to notify the user of a possible abnormality in the air conditioner before the air conditioner breaks down. This operating state determination method includes the following first to fifth steps. The first step is a step of storing the rated values ​​of the electrical characteristics of each component in the air conditioner as first electrical characteristic values. The second step is a step of storing the electrical characteristic values ​​of each component before the air conditioner broke down as second electrical characteristic values ​​based on the electrical characteristic values ​​transmitted from the air conditioner. The third step is a step of storing the electrical characteristic values ​​at the time of determination transmitted from the air conditioner as third electrical characteristic values. The fourth step is a step of performing an inference calculation to determine whether the control board is normal or abnormal based on a learning model, which is a trained model generated based on the first and second electrical characteristic values, and the third electrical characteristic value. The fifth step is to output information about the operating status of the air conditioner based on the result of the inference calculation. By having a computer execute these steps, it is possible to output information about the operating status of the air conditioner before the air conditioner breaks down, and to notify the user in advance that the air conditioner may break down.

[0037] Embodiment 2 FIG. 9 is a diagram showing an example of the configuration of an air conditioning system 100B according to embodiment 2. Comparing the configuration of FIG. 9 with FIG. 1, the air conditioning system 100B shown in FIG. 9 is provided with an information processing terminal 3 configured to be able to communicate with the air conditioner 1 and the cloud server 2. The information processing terminal 3 has a communication unit 30, a storage unit 31, and a display unit 32. The other configuration is the same as or equivalent to the configuration of FIG. 1, and the same or equivalent components are denoted by the same reference numerals, and duplicate explanations will be omitted. Note that although the configuration related to a variation of embodiment 2 is not shown, the cloud server 2 may also be provided with an inference unit 24, as in FIG. 8.

[0038] The communication unit 30 is configured to be able to communicate with the air conditioner 1 and the cloud server 2. The communication unit 30 is realized by a communication device, a communication circuit, a communication adapter, or the like. The communication unit 30 receives information sent from the air conditioner 1 and the cloud server 2 and stores it in the memory unit 31. The display unit 32 receives the result of the inference calculation from either the air conditioner 1 or the cloud server 2, and displays information related to the operating status of the air conditioner 1.

[0039] In the case of the air conditioning system 100B according to the second embodiment, the information processing terminal 3 is provided, and therefore it is possible to more visually display the results of the inference calculation and information relating to the operating state of the air conditioner 1. This makes it possible to provide more accurate and suitable information to the user.

[0040] As described above, the air conditioning system according to the second embodiment further includes an information processing terminal configured to be able to communicate with the air conditioner and the processing device. The information processing terminal receives the result of the inference calculation from either the air conditioner or the processing device and displays information relating to the operating status of the air conditioner. This allows the air conditioning system according to the second embodiment to enjoy the effects of the first embodiment while also achieving the effect of being able to provide more accurate and appropriate information to the user.

[0041] The configurations shown in the above embodiments are merely examples, and may be combined with other known technologies, or different embodiments may be combined with each other. It is also possible to omit or modify parts of the configurations as long as they do not deviate from the gist of the invention. [Explanation of symbols]

[0042] 1,1A Air conditioner, 2,2A Cloud server, 3 Information processing terminal, 10,10A Control board, 11,21,30 Communication unit, 12 Monitoring unit, 13,24 Inference unit, 14,23,31 Memory unit, 15,32 Display unit, 22 Learning unit, 100,100A,100B Air conditioning system, 131,221 Data acquisition unit, 132 Inference calculation unit, 222 Learning model generation unit, 601 Differential data, 602 Center of gravity, 603 Cluster.

Claims

1. An air conditioning system including at least one air conditioner having a control board for controlling air conditioning, and a processing device configured to be able to communicate with the air conditioner, a monitoring unit that monitors electrical characteristic values, which are status information of each of the plurality of components arranged on the control board; a characteristic value storage unit that stores the rated value of the electrical characteristic of each of the components as a first electrical characteristic value, stores the electrical characteristic value of each of the components before the air conditioner failed based on the electrical characteristic value transmitted from the monitoring unit as a second electrical characteristic value, and stores the electrical characteristic value at the time of determination transmitted from the monitoring unit as a third electrical characteristic value; a learning unit that generates a learning model that is a trained model based on the first and second electrical characteristic values; a learning model storage unit that stores the learning model; an inference unit that performs an inference calculation to determine whether the control board is normal or abnormal based on the third electrical characteristic value and the learning model; a display unit that displays information about the operating state of the air conditioner based on the result of the inference calculation; An air conditioning system comprising:

2. The learning unit a data acquisition unit that acquires the first and second electrical characteristic values ​​from at least one of the air conditioners as learning data; a learning model generation unit that generates the learning model for inferring the operating state of each of the air conditioners based on the learning data; The air conditioning system of claim 1 .

3. The inference unit a data acquisition unit that acquires the third electrical characteristic value; an inference calculation unit that performs an inference calculation to determine whether the control board is normal or abnormal based on the third electrical characteristic value and the learning model; Equipped with outputting information about the operating state of the air conditioner based on the result of the inference calculation; The air conditioning system of claim 1 .

4. The air conditioner includes the monitoring unit, the characteristic value storage unit, the inference unit, and the display unit, The processing device includes the learning unit and the learning model storage unit. The air conditioning system of claim 1 .

5. The air conditioner includes the monitoring unit, the characteristic value storage unit, and the display unit, The processing device includes the learning unit, the learning model storage unit, and the inference unit. The air conditioning system of claim 1 .

6. The air conditioner includes the monitoring unit and the display unit, the processing device includes the learning unit, the learning model storage unit, and the inference unit, The learning model storage unit stores the first to third electrical characteristic values ​​transmitted from the air conditioner. The air conditioning system of claim 1 .

7. the air conditioning system includes an information processing terminal configured to be able to communicate with the air conditioner and the processing device, The information processing terminal receives the result of the inference calculation from either the air conditioner or the processing device and displays information about the operating state of the air conditioner. The air conditioning system of claim 1 .

8. the air conditioning system includes an information processing terminal configured to be able to communicate with the air conditioner and the processing device, The air conditioner includes the monitoring unit, the processing device includes the learning unit, the characteristic value storage unit, the learning model storage unit, and the inference unit, The information processing terminal includes the display unit. The air conditioning system of claim 1 .

9. the air conditioning system includes an information processing terminal configured to be able to communicate with the air conditioner and the processing device, The air conditioner includes the monitoring unit, the processing device includes the learning unit, the characteristic value storage unit, and the learning model storage unit; The information processing terminal includes the characteristic value storage unit and the display unit. The air conditioning system of claim 1 .

10. The processing device is a cloud server.

10. An air conditioning system according to any one of claims 1 to 9.

11. A processing device having a control board for controlling air conditioning and configured to be able to communicate with at least one air conditioner, The control board stores electrical characteristic values ​​that are status information of each of the plurality of components arranged on the control board, The processing device includes a storage unit that stores the rated values ​​of the electrical characteristics of each of the components in the air conditioner as first electrical characteristic values, receives the electrical characteristic values ​​transmitted from the air conditioner, stores the electrical characteristic values ​​of each of the components before the air conditioner failed as second electrical characteristic values ​​based on the electrical characteristic values ​​transmitted from the air conditioner, and stores the electrical characteristic values ​​transmitted from the air conditioner at the time of determination as third electrical characteristic values; a learning unit that generates a learned model that is a learned model based on the first and second electrical characteristic values ​​and stores the model in the storage unit; an inference unit that performs an inference calculation to determine whether the control board is normal or abnormal based on the third electrical characteristic value and the learning model; Equipped with The processing device outputs information about the operating state of the air conditioner based on the result of the inference calculation. Processing equipment.

12. The learning unit acquires the first and second electrical characteristic values ​​from at least one of the air conditioners as learning data, and generates the learning model for inferring the operating state of each of the air conditioners based on the learning data. The processing device of claim 11 .

13. the inference unit acquires the third electrical characteristic value from the air conditioner, and performs an inference calculation to determine whether the control board is normal or abnormal based on the acquired third electrical characteristic value and the learning model; outputting information about the operating state of the air conditioner based on the result of the inference calculation; The processing device of claim 11 .

14. The processing device is a cloud server.

14. The processing device according to any one of claims 11 to 13.

15. 1. A method for determining the operational status of an air conditioner, the method being applied to a processing device configured to be able to communicate with at least one air conditioner in which electrical characteristic values, which are status information of each of a plurality of components arranged on a control board for controlling air conditioning, are stored on the control board, and the method notifies the user of a possible abnormality in the air conditioner before the air conditioner breaks down, a first step of storing a rated value of an electrical characteristic of each of the components in the air conditioner as a first electrical characteristic value; a second step of storing, as second electrical characteristic values, electrical characteristic values ​​of each of the components before the air conditioner failed based on the electrical characteristic values ​​transmitted from the air conditioner; a third step of storing the electrical characteristic value at the time of determination transmitted from the air conditioner as a third electrical characteristic value; a fourth step of performing an inference calculation to determine whether the control board is normal or abnormal based on a learned model, which is a learned model generated based on the first and second electrical characteristic values, and the third electrical characteristic value; a fifth step of outputting information about the operating state of the air conditioner based on the result of the inference calculation; A method for determining the operating state of an air conditioner, comprising:

16. The learning model is generated based on the first and second electrical characteristic values. The method for determining the operating state of an air conditioner according to claim 15.

Images