Air conditioning control device

Abstract

The air conditioning control device (3) is an air conditioning control device (3) that controls the operation of an air conditioner (4), and includes: a data collection unit (32) that acquires learning data including data when the air conditioner (4) is started and data when it is stopped; a learning unit (34) that uses the learning data to generate a trained model for estimating a startup standby time from when the air conditioner (4) is started until the indoor temperature reaches a set temperature; a calculation unit (35) that uses the trained model to output the startup standby time from the startup data acquired by the data collection unit (32); and a control unit (36) that causes the air conditioner (4) to start operation the startup standby time before a predetermined set time.

Description

[Technical Field]

[0001] The present disclosure relates to an air conditioning control device that controls the operation of an air conditioner. [Background technology]

[0002] Conventionally, there are technologies for efficiently controlling air conditioners using various information such as room temperature, outdoor temperature, and the heat retention capacity of a building. For example, Patent Document 1 describes optimal startup control that estimates the time required to reach a target temperature using historical data, such as room temperature, target temperature, and information on temperatures when the air conditioner was previously started and the time required to reach the target temperature, and starts operation of the air conditioner before the target time. Patent Document 2 also discloses technology for determining the optimal operating mode based on room temperature, outdoor temperature, and the heat retention capacity of a building. Patent Document 2 also describes estimating the heat retention capacity of a building from the indoor temperature change rate, which is the change in indoor temperature over a certain period of time after the air conditioner is stopped. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2016-061487 [Patent Document 2] Patent Publication No. 2021-508554 Summary of the Invention [Problem to be solved by the invention]

[0004] In air conditioner startup control, the startup standby time, which is the time required to reach the target temperature, is affected not only by the target temperature and room temperature, but also by the performance of the building in which the air conditioner is installed, such as the building's thermal mass. By collecting past performance data and learning the startup standby time as learning data, it is possible to estimate the startup standby time while taking into account the influence of the building's performance. However, because the learning data used to estimate the startup standby time is affected by the building, it must be collected after the air conditioner is installed in the building, which creates an issue of time-consuming collection of learning data. Furthermore, for example, if the building in which the air conditioner is installed is used as an office, the air conditioner starts up at the start of work and stops at the end of work, so startup data can only be obtained once a day, which is one of the reasons why it takes time to collect learning data.

[0005] In order to solve the above-mentioned problems, the present disclosure aims to provide an air conditioning control device that collects the learning data necessary to accurately estimate the startup reserve time of an air conditioner taking into account the performance of the building in a shorter period of time than if only startup data were used. [Means for solving the problem]

[0006] An air conditioning control device according to the present disclosure is an air conditioning control device that controls the operation of an air conditioner, and includes a data collection unit that acquires learning data including data when the air conditioner is started and data when it is stopped, a learning unit that uses the learning data to generate a trained model for inferring a start-up standby time from when the air conditioner is started until the indoor temperature reaches a set temperature, a calculation unit that uses the trained model to output the start-up standby time from the start-up conditions acquired by the data collection unit, and a calculation unit that starts operation of the air conditioner before the start-up standby time from a predetermined set time, A start-up temperature difference, which is the difference between the room temperature and the outside temperature when the air conditioner is started, is calculated, and when the scheduled time for stopping the air conditioner is reached, temperature difference control is performed to control the air conditioner so that the difference between the room temperature and the outside temperature approaches the start-up temperature difference, and operation of the air conditioner is stopped when the difference between the room temperature and the outside temperature and the start-up temperature difference becomes smaller than a threshold value. A control unit is provided. [Effects of the Invention]

[0007] According to the present disclosure, an air conditioning control device can be obtained that collects learning data for accurately estimating the startup standby time of an air conditioner taking into account the performance of the building in a shorter time than when only startup data is used. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a diagram showing an example of the configuration of an air conditioning system including an air conditioning control device according to a first embodiment. [Figure 2] 1 is a block diagram showing a functional configuration of an air conditioning control device according to a first embodiment. [Figure 3] FIG. 3 is a diagram showing an example of a neural network used to infer a startup spare time of the air conditioning control device according to the first embodiment. [Figure 4] 1 is a graph showing changes over time in room temperature and outside temperature; [Figure 5] 4 is a flowchart showing the flow of learning data collection and learning in the air conditioning control device according to the first embodiment. [Figure 6] 4 is a flowchart showing the flow of data acquisition processing at the time of startup of the air conditioning control device according to the first embodiment. [Figure 7] 4 is a flowchart showing the flow of data acquisition processing when the air conditioning control device according to the first embodiment is stopped. [Figure 8] 5 is a flowchart showing the flow of learning of the startup spare time in the air conditioning control device according to the first embodiment. [Figure 9] 4 is a flowchart showing the flow of estimating the startup spare time and controlling the air conditioner in the air conditioning control device according to the first embodiment. [Figure 10] 10 is a graph showing the time changes in room temperature and outside air temperature when a temperature difference control process is performed. [Figure 11] 10 is a flowchart showing the flow of learning data collection and learning in an air conditioning control device according to a second embodiment. [Figure 12] 10 is a flowchart showing the flow of a temperature difference control process in an air conditioning control device according to a second embodiment. [Figure 13]FIG. 10 is a diagram showing an example of the configuration of an air conditioning system including an air conditioning control device according to a third embodiment. [Figure 14] 10 is a graph showing the change in room temperature over time when stop time difference processing is performed. [Figure 15] 10 is a flowchart showing the flow of learning data collection and learning in an air conditioning control device according to a third embodiment. [Figure 16] 10 is a flowchart showing the flow of learning data collection and learning in an air conditioning control device according to a fourth embodiment. [Figure 17] 10 is a flowchart showing the flow of learning of the startup spare time in the air conditioning control device according to the fourth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] The following description will discuss embodiments of the present disclosure with reference to the accompanying drawings. In each drawing, identical or corresponding parts are designated by the same reference numerals, and redundant descriptions are appropriately simplified or omitted. The present disclosure is not limited to the following embodiments, and any of the components of the embodiments may be modified, combined, or omitted without departing from the spirit of the present disclosure.

[0010] Embodiment 1 FIG. 1 is a diagram showing an example of the configuration of an air conditioning system 100 including an air conditioning control device 3 according to this embodiment. The air conditioning control device 3 and the air conditioning system 100 will be described with reference to FIG. 1. The air conditioning system 100 includes a control server 1, a management device 2 installed in a building 10, the air conditioning control device 3, an air conditioner 4 consisting of an outdoor unit 5 and multiple indoor units 6, and a handheld remote control 7. Multiple air conditioners 4 may be installed in the building 10. In this embodiment, the building 10 is assumed to be an office or commercial building, but it may also be a residence as long as an air conditioner 4 is installed therein. The control server 1 and the management device 2 are connected to each other via a wide area network 11 such as the Internet so that they can communicate with each other. In the example of FIG. 1, the management device 2 is connected to the air conditioning control device 3, which is further connected to the outdoor unit 5, which is further connected to the multiple indoor units 6 and the handheld remote control 7. For example, communication from the air conditioning control device 3 to the indoor units 6 is performed via the outdoor unit 5. In this way, each device performs routing, so that the management device 2, air conditioning control device 3, outdoor unit 5, indoor unit 6, and handheld remote control 7 can communicate with each other. Furthermore, the air conditioning control device 3, outdoor unit 5, indoor unit 6, and handheld remote control 7 communicate with the control server 1 via the management device 2. Note that the connections are not limited to the example in Fig. 1 as long as the management device 2, air conditioning control device 3, outdoor unit 5, indoor unit 6, and handheld remote control 7 can communicate with each other. Furthermore, communication may be performed wirelessly.

[0011] The control server 1 is a server computer and includes, for example, a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), and RTC (Real Time Clock). The CPU is also called a central processing unit, processor, microprocessor, microcomputer, or DSP (Digital Signal Processor), and functions as a central processing unit that executes various programs. The control server 1 also includes a communication unit such as a wired LAN (Local Area Network) or a wireless LAN. The control server 1 acquires information about the air conditioners 4 and transmits control signals via a wide area network 11.

[0012] The management device 2 manages the air conditioners 4 in the building 10. The management device 2 may be connected to equipment other than the air conditioners in the building 10, such as a lighting system (not shown), and manage them together with the air conditioners 4. The management device 2 communicates with the control server 1, sends information about the air conditioners 4 connected to the management device 2 to the control server 1, and receives control signals for the air conditioners 4 from the control server 1. Note that the air conditioning system 100 may not have a management device 2, and an air conditioning control device 3 (described later) may communicate with the control server 1.

[0013] The air conditioning control device 3 is a central controller that controls multiple air conditioners 4 installed in a building 10. The air conditioning control device 3 includes a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), RTC (Real Time Clock), etc. The CPU is also called a central processing unit, processor, microprocessor, microcomputer, or DSP (Digital Signal Processor), and functions as a central processing unit that executes various programs. The air conditioning control device 3 also includes non-volatile memory such as flash memory, EPROM (Erasable Programmable ROM), and EEPROM (Electrically Erasable Programmable ROM). The air conditioning control device 3 collects learning data from the outdoor unit 5 and the indoor unit 6 and, through learning, generates a trained model that infers the startup standby time from when the air conditioner 4 is started until the set temperature is reached. The detailed configuration of the air conditioning control device 3 will be described later.

[0014] The outdoor unit 5 is a piece of equipment that conditions indoor air and is installed outdoors. The outdoor unit 5 is equipped with an outdoor air temperature sensor 51 that detects the outdoor air temperature. The outdoor unit 5 also stores the heating and cooling capacity of the air conditioner 4 for each unit time based on the operating frequency of the compressor (not shown) equipped in the outdoor unit 5, etc. Conditioning indoor air means adjusting the temperature, humidity, air cleanliness, etc. of the indoor air. The indoor unit 6 is a piece of equipment that conditions indoor air and is installed indoors. The indoor unit 6 blows air into the room for heating, cooling, dehumidification, ventilation, etc. The indoor unit 6 is equipped with an indoor temperature sensor 61 that detects the indoor temperature. The outdoor unit 5 and the indoor unit 6 are connected by refrigerant piping (not shown) for circulating the refrigerant as well as communication lines to form the air conditioner 4. At least one indoor unit 6 is connected to one outdoor unit 5 by refrigerant piping and communication lines. The air conditioning control device 3 controls the outdoor unit 5 and the indoor unit 6, and controls the operation of the air conditioner 4.

[0015] The handheld remote control 7 is an operating device that is installed on the wall of the room where the indoor unit 6 is installed. By operating the handheld remote control 7, the user can turn the air conditioner 4 on / off, change the set temperature, etc. Note that the air conditioning system 100 may be configured so that the handheld remote control 7 is not installed and the air conditioner 4 is controlled only from the air conditioning control device 3.

[0016] Fig. 2 is a block diagram showing the functional configuration of the air conditioning control device 3 according to this embodiment. The configuration of the air conditioning control device 3 will be described with reference to Fig. 2. The air conditioning control device 3 includes a communication unit 31, a data collection unit 32, a data processing unit 33, a learning unit 34, a calculation unit 35, a control unit 36, a learning data storage unit 37, and a learned model storage unit 38.

[0017] The communication unit 31 communicates with the management device 2, the outdoor unit 5, and the indoor unit 6. For example, when the communication unit 31 receives a communication addressed to the outdoor unit 5 from the management device 2, the communication unit 31 manages the communication, such as forwarding the communication to the outdoor unit 5.

[0018] The data collection unit 32 collects, as data at the time of startup of the air conditioner 4, the startup conditions and the actual measured value of the startup standby time from when the air conditioner 4 is started until the set temperature is reached, via the communication unit 31 as learning data to be used for learning the startup standby time. The startup conditions include the outdoor air temperature detected by the outdoor air temperature sensor 51 of the outdoor unit 5, the room temperature detected by the indoor temperature sensor 61 of the indoor unit 6, and the operating state of the air conditioner 4 at the time of startup of the air conditioner 4. The operating state indicates the on / off status of the air conditioner 4, the operating mode such as cooling or heating, and the amount of capacity saved by the outdoor unit 5. Furthermore, the data collection unit 32 collects, as data at the time of shutdown of the air conditioner 4, the conditions at the time of shutdown and the time of room temperature change after shutdown as learning data. The shutdown conditions include the outdoor air temperature detected by the outdoor air temperature sensor 51 of the outdoor unit 5, the room temperature detected by the indoor temperature sensor 61 of the indoor unit 6, and the operating states of the outdoor unit 5 and the indoor unit 6 at the time of shutdown of the air conditioner 4. When the air conditioner 4 is stopped, the room temperature changes to approach the outside air temperature. The room temperature change time after stopping refers to the time it takes for the rate of change of the room temperature after the air conditioner 4 is stopped to fall below a predetermined threshold. The rate of change of the room temperature refers to the amount of change in the room temperature per unit time. Specifically, the data collection unit 32 periodically (for example, every minute) acquires the room temperature and calculates the difference from the previously acquired room temperature as the rate of change of the room temperature.

[0019] FIG. 4 is a graph showing the changes in room temperature and outdoor air temperature over time. Here, with reference to FIG. 4, the data collected by the data collection unit 32 will be described in detail. The start time t0 is the time when the air conditioner 4 is started. The set time tset is a time set in advance in the air conditioning control device 3 by the user. For example, if the building 10 is an office, the set time tset is set to the start time of work. The air conditioning control device 3 aims to control the air conditioner 4 so that the room temperature becomes the set temperature Tset at the set time tset. The set temperature Tset is set by the user in the air conditioning control device 3 or the handheld remote controller 7. If sufficient learning data has not been collected, the start time t0 is set to a time a certain time (e.g., one hour) before the set time tset. If sufficient learning data has been collected, the start time t0 is set to a time before the set time tset by the estimated start time ton_est. The data collection unit 32 collects start-up data from the start time t0 until the room temperature reaches the set temperature Tset. The startup data includes the startup conditions at startup time t0 and the actual measured value ton of the startup pre-time. The data collection unit 32 acquires the room temperature Ton_in at the startup time t0 of the air conditioner 4 from the indoor temperature sensor 61 as the startup condition. The data collection unit 32 acquires the outdoor air temperature Ton_out at the startup time t0 of the air conditioner 4 from the outdoor air temperature sensor 51 as the startup condition. The data collection unit 32 also acquires the set temperature Tset as the startup condition. The data collection unit 32 also stores the time from the startup time t0 when the air conditioner 4 is started to the time t1 when the room temperature reaches the set temperature Tset as the actual measured value ton of the startup pre-time. The data collection unit 32 periodically acquires the room temperature from the indoor temperature sensor 61 and compares it with the set temperature Tset to determine whether the room temperature has reached the set temperature Tset. Alternatively, the indoor unit 6 may notify the data collection unit 32 when the room temperature has reached the set temperature Tset.

[0020] Furthermore, because the startup spare time varies depending on the heating and cooling capacity of the air conditioner 4, the data collection unit 32 may acquire the amount of heat processed by the air conditioner 4 from the startup time t0 to the arrival time t1 as startup data. The amount of heat processed by the air conditioner 4 is determined by the amount of capacity saved by the outdoor unit 5 provided in the air conditioner 4 relative to the heating and cooling capacity of the air conditioner 4. Therefore, the data collection unit 32 may acquire the amount of capacity saved by the outdoor unit 5 from the startup time t0 to the arrival time t1 as startup data. By using the amount of heat processed by the air conditioner 4 or the amount of capacity saved as learning data, the startup spare time can be learned more accurately.

[0021] The data collection unit 32 may also acquire the number of active indoor units 6 as data at the time of startup. The startup spare time is learned for each indoor unit 6. If multiple indoor units 6 are installed in the same room as the indoor unit 6 being learned, the startup spare time will be affected by the operating status of adjacent indoor units 6. Therefore, by using the number of active indoor units 6 as learning data, the startup spare time can be learned more accurately.

[0022] The air conditioning control device 3 stops the air conditioner 4 at the stop time t2 set in advance in the air conditioning control device 3 by the user. For example, if the building 10 is an office, the stop time t2 is set to the end of business hours. Alternatively, the stop time t2 may not be set in the air conditioning control device 3, but may be the time when the user operates the handheld remote control 7 to stop the air conditioner 4. The data collection unit 32 collects data during the stop time from the stop time t2 until the rate of change in room temperature falls below a threshold. The data collection unit 32 acquires the room temperature Toff_in at the stop time t2 of the air conditioner 4 from the indoor temperature sensor 61 as a condition for stopping the air conditioner 4. The data collection unit 32 also acquires the outdoor air temperature Toff_out at the stop time t2 of the air conditioner 4 from the outdoor air temperature sensor 51 as a condition for stopping the air conditioner 4. When the air conditioner 4 is stopped, the room temperature changes to approach the outdoor air temperature. However, it is known that the change in room temperature becomes gradual after a sufficient amount of time has passed, as shown in FIG. 4. In particular, when the building 10 is a building, buildings are often more highly insulated than residential homes, and their building frames retain heat, so the room temperature does not drop to the outside temperature even when the air conditioner 4 is turned off. The data collection unit 32 stores the time from time t2 when the air conditioner 4 is turned off to time t3 when the room temperature stabilizes and the rate of change of the room temperature falls below a predetermined threshold as the room temperature change time after shutdown toff. The data collection unit 32 determines whether the rate of change of the room temperature has fallen below the threshold by periodically acquiring the room temperature from the indoor temperature sensor 61, calculating the rate of change, and comparing it with the threshold. Alternatively, the indoor unit 6 may notify the data collection unit 32 when the rate of change of the room temperature falls below the threshold. The data collection unit 32 stores the learning data collected as described above in the learning data storage unit 37.

[0023] The startup data and shutdown data collected by the data collection unit 32 may be data showing the relationship between the room temperature and the outside air temperature and the passage of time, as shown in Fig. 4. That is, the data collection unit 32 may collect, as startup data, the room temperature and the outside air temperature acquired periodically (for example, every minute) from the start-up time t0 until the room temperature reaches the set temperature Tset. Also, the data collection unit 32 may collect, as shutdown data, the room temperature and the outside air temperature acquired periodically (for example, every minute) from the stop time t2 until the rate of change of the room temperature from the stop time t2 becomes equal to or less than a threshold.

[0024] The data processing unit 33 processes the learning data stored in the learning data storage unit 37 into a data set suitable for learning the startup prep time. That is, the data processing unit 33 creates learning data by combining the startup conditions and actual measured values ​​of the startup prep time on the same day with the shutdown conditions and the room temperature change time after shutdown. The data processing unit 33 outputs the created learning data to the learning unit 34.

[0025] The learning unit 34 learns the standby start time using the learning data created by the data processing unit 33. That is, it generates a trained model that infers the standby start time from the room temperature, the outside temperature, and the set temperature. The learning unit 34 stores the generated trained model in the trained model holding unit 38. The room temperature change time after shutdown included in the learning data is affected by the conditions at the time of shutdown and the performance of the building 10, such as the size of the space in which the indoor unit 6 of the building 10 is installed and the thermal conductivity. Therefore, by including the conditions at the time of shutdown and the room temperature change time after shutdown in the learning data, the learning unit 34 can infer the standby start time taking into account the performance of the building 10 even when learning the standby start time using learning data for a small number of days.

[0026] Here, a method for learning the startup standby time in the learning unit 34 will be described. The learning algorithm used by the learning unit 34 can be a known algorithm such as supervised learning, unsupervised learning, or reinforcement learning. As an example, a case where a neural network is applied will be described.

[0027] The learning unit 34 learns the startup standby time by, for example, so-called supervised learning in accordance with a neural network model. Here, supervised learning refers to a technique in which a learning device is provided with pairs of input and result (label) data, and the learning device learns the features of the learning data and infers the result from the input.

[0028] A neural network consists of an input layer consisting of multiple neurons, an intermediate layer (hidden layer) consisting of multiple neurons, and an output layer consisting of multiple neurons. The intermediate layer may be one layer, or two or more layers.

[0029] Figure 3 is a diagram showing an example of a neural network used to infer the startup standby time of an air conditioning control device according to this embodiment. For example, in a three-layer neural network such as the one shown in Figure 3, when multiple inputs are input to the input layer (X1-X3), the values ​​are multiplied by a weight W1 (w11-w16) and input to the middle layer (Y1-Y2), and the result is further multiplied by a weight W2 (w21-w26) and output from the output layer (Z1-Z3). This output result varies depending on the values ​​of the weights W1 and W2.

[0030] In the present application, the neural network learns the pre-start time by so-called supervised learning in accordance with learning data created based on a combination of the start-up conditions and the actual measured value of the pre-start time acquired by the data collection unit 32, and the shutdown conditions and the room temperature change time after shutdown. That is, the neural network learns by inputting the start-up conditions into the input layer and adjusting the weights W1 and W2 so that the result output from the output layer approaches the actual measured value of the pre-start time.

[0031] The learning unit 34 performs the above-described learning to generate and output a trained model.

[0032] The calculation unit 35 acquires the room temperature, outside temperature, and set temperature from the data collection unit 32, and uses the learned model stored in the learned model storage unit 38 to infer the startup reserve time and output it to the control unit 36.

[0033] The control unit 36 ​​controls the air conditioner 4 to start up earlier than the scheduled start-up time by the estimated pre-start time, so that the room temperature will reach the set temperature at the scheduled start-up time that is set in advance.

[0034] 5 is a flowchart showing the flow of learning and collection of learning data in the air conditioning control device 3 according to this embodiment. Using FIG. 5, the collection and learning of learning data for estimating the startup spare time in the air conditioning control device 3 will be described.

[0035] First, step S101 shows that the flow of learning the startup reserve time is performed periodically. The cycle is one day, as it is assumed that the air conditioner 4 will be started in the morning when the building 10 is in use and stopped in the evening when use of the building 10 ends. However, the cycle is not limited to one day and can be set according to the usage schedule of the air conditioner 4. Next, the process proceeds to step S102.

[0036] In step S102, the air conditioning control device 3 determines whether the start-up time t0 of the air conditioner 4 has arrived. If sufficient learning data has not been collected, the start-up time t0 is a fixed time (e.g., one hour) before the set time tset, and if sufficient learning data has been collected, the start-up time t0 is the time an estimated standby start-up time ton_est before the set time tset. If the start-up time t0 has arrived, proceed to step S103 (S102: Yes). If the start-up time t0 has not arrived, proceed to step S104 (S102: No).

[0037] In step S103, the data collection unit 32 of the air conditioning control device 3 performs processing to acquire data at startup. Figure 6 is a flowchart showing the flow of data acquisition processing at startup of the air conditioning control device 3 according to this embodiment. Figure 6 corresponds to step S103 in Figure 5. The data acquisition processing at startup in the air conditioning control device 3 will be described with reference to Figure 6.

[0038] First, in step S10, the data collection unit 32 acquires the startup conditions from the air conditioner 4. The startup conditions include the room temperature Ton_in acquired from the room temperature sensor 61, the outside air temperature Ton_out acquired from the outside air temperature sensor 51, and the set temperature Tset. Next, the process proceeds to step S11.

[0039] In step S11, the air conditioning control device 3 determines whether the room temperature obtained from the indoor temperature sensor 61 has reached the set temperature Tset. The air conditioning control device 3 periodically obtains the room temperature from the indoor temperature sensor 61 and compares it with the set temperature Tset to determine whether the room temperature has reached the set temperature Tset. Alternatively, the indoor unit 6 notifies the air conditioning control device 3 when the value detected by the indoor temperature sensor 61 is equal to the set temperature Tset. The air conditioning control device 3 determines that the room temperature has reached the set temperature when it receives a notification from the indoor unit 6. Note that the air conditioning control device 3 or the indoor unit 6 may also determine that the room temperature has reached the set temperature when the difference between the room temperature obtained from the indoor temperature sensor 61 and the set temperature Tset is equal to or less than a threshold. If the air conditioning control device 3 determines that the room temperature has reached the set temperature, this time is set as the arrival time t1 and the process proceeds to step S12 (S11: Yes). If the air conditioning control device 3 determines that the room temperature is not the set temperature, the process returns to step S11 (S11: No).

[0040] In step S12, the data collection unit 32 stores the time from the startup time t0 to the arrival time t1 when the room temperature reaches the set temperature Tset as the actual startup standby time value ton in the learning data storage unit 37. The data collection unit 32 may also acquire the amount of heat processed by the air conditioner 4 during ton from the outdoor unit 5. The outdoor unit 5 knows the heating and cooling capacity from the operating frequency of the compressor, etc., and stores this for each unit time. Therefore, it is possible to determine the amount of heat processed by the air conditioner 4 during ton. When the data collection unit 32 acquires the amount of heat processed by the air conditioner 4, it also stores this in the learning data storage unit 37. This ends the startup data acquisition process, and the process proceeds to step S104 in FIG. 5.

[0041] Returning to FIG. 5, in step S104, the air conditioning control device 3 determines whether it is time t2 to stop the air conditioner 4. The stop time t2 is set in the air conditioning control device 3 in advance by the user. Alternatively, the stop time t2 may be the time when the user operates the handheld remote control 7 to stop the air conditioner 4. If it is time t2, proceed to step S105 (S104: Yes). If it is not time t2, proceed to step S106 (S104: No).

[0042] In step S105, the data collection unit 32 of the air conditioning control device 3 performs processing to acquire data when the device is stopped. Figure 7 is a flowchart showing the flow of data acquisition processing when the air conditioning control device 3 according to this embodiment is stopped. Figure 7 corresponds to step S105 in Figure 5. The data acquisition processing when the air conditioning control device 3 is stopped will be described with reference to Figure 7.

[0043] First, in step S20, the data collection unit 32 acquires the stop conditions from the air conditioner 4. The stop conditions include the room temperature Toff_in acquired from the room temperature sensor 61 and the outside air temperature Toff_out acquired from the outside air temperature sensor 51. Next, the process proceeds to step S21.

[0044] In step S21, the air conditioning control device 3 periodically calculates the rate of change using the room temperature acquired from the indoor temperature sensor 61, compares this with a predetermined threshold, and determines whether the rate of change of the room temperature has become equal to or less than the threshold. Alternatively, the indoor unit 6 calculates the rate of change of the room temperature from the value detected by the indoor temperature sensor 61, and notifies the air conditioning control device 3 when the rate of change of the room temperature has become equal to or less than the threshold. When the air conditioning control device 3 receives a notification from the indoor unit 6, it determines that the rate of change of the room temperature has become equal to or less than the threshold. If the air conditioning control device 3 determines that the rate of change of the room temperature has become equal to or less than the threshold, it sets this time as the room temperature stabilization time t3 and proceeds to step S22 (S21: Yes). If the air conditioning control device 3 determines that the rate of change of the room temperature is not equal to or less than the threshold, it returns to step S21 (S21: No).

[0045] In step S22, the data collection unit 32 stores the time from the stop time t2 to the room temperature stabilization time t3, at which the rate of change of the room temperature becomes equal to or less than a predetermined threshold, as the room temperature change time after stop toff in the learning data holding unit 37. This ends the data acquisition process during stop, and the process proceeds to step S106 in FIG.

[0046] Returning to FIG. 5, in step S106, the air conditioning control device 3 determines whether it is time to learn the startup reserve time. The learning timing is preferably set to the time from when the data acquisition process at the time of shutdown is completed until the startup time. For example, if the air conditioner 4 is to be started at the start of work and stopped at the end of work, late night hours are set in advance as the learning timing in the air conditioning control device 3. If it is time to learn, proceed to step S107 (S106: Yes). If it is not time to learn, proceed to step S108 (S106: No).

[0047] In step S107, the air conditioning control device 3 learns the preliminary startup time using the learning data collected by the data collection unit 32. Figure 8 is a flowchart showing the flow of learning the preliminary startup time in the air conditioning control device 3 according to this embodiment. The flow of learning the preliminary startup time will be described with reference to Figure 8.

[0048] First, in step S30, the data processing unit 33 reads out the learning data stored in the learning data storage unit 37, and creates learning data by combining the conditions at start-up on the same day and the actual measured value of the startup standby time ton with the conditions at shutdown and the room temperature change time after shutdown toff. The created learning data is output to the learning unit 34. Next, the process proceeds to step S31.

[0049] In step S31, the learning unit 34 learns the extra startup time using the learning data and generates a trained model that infers the extra startup time from the conditions at startup. The learning unit 34 stores the trained model that has been generated in the trained model holding unit 38. This completes the learning of the extra startup time, and the process proceeds to step S108 in FIG. 5.

[0050] 5, in step S108, the collection of learning data and one cycle of learning processing in the air conditioning control device 3 ends, and the process returns to S101. This completes the flow of collection of learning data and learning for estimating the startup spare time in the air conditioning control device 3.

[0051] In this manner, the air conditioning control device 3 collects learning data for learning the standby startup time and generates a learning model for inferring the standby startup time. When the learning unit 34 attempts to generate a trained model that infers the standby startup time with sufficient expected accuracy, the learning data can be generated in a shorter time than when only the startup conditions and the actual measured values ​​of the standby startup time are used. Furthermore, for example, if the control server 1 collects training data from air conditioners 4 installed in multiple buildings 10, the influence of each individual building 10 is not taken into account. In this embodiment, the training data is acquired from air conditioners 4 actually installed in the buildings 10, and therefore is data influenced by the buildings 10. This allows the learning unit 34 to generate a training model suitable for the air conditioners 4 installed in the buildings 10.

[0052] FIG. 9 is a flowchart showing the estimation of the spare startup time and the control of the air conditioner 4 in the air conditioning control device 3 according to this embodiment. The estimation of the spare startup time and the control of the air conditioner 4 by the air conditioning control device 3 will be described with reference to FIG. 9 . The estimation of the spare startup time and the control of the air conditioner 4 in FIG. 9 are performed at any timing within a day. However, because the room temperature and outdoor temperature at the time of performing the processing in FIG. 9 are input to the trained model, it is preferable to select a time close to the set time so that the difference between the room temperature and outdoor temperature and the room temperature and outdoor temperature at the actual start-up time is as small as possible, and a time before the set time and the spare startup time so that the set temperature Tset is reached at the set time tset. Therefore, the spare startup time is estimated, for example, at a time before the set time tset by the maximum value of the scheduled start-up time up to that point. This reduces the difference between the room temperature and outdoor temperature input to the trained model and the room temperature and outdoor temperature at the time the air conditioner 4 is actually started, enabling accurate estimation of the spare startup time. If there is no data on the past scheduled start-up time, the spare startup time is estimated a certain time (e.g., three hours) before the set time tset.

[0053] First, in S201, the calculation unit 35 of the air conditioning control device 3 acquires the set time tset and set temperature Tset set in the air conditioning control device 3 or the handheld remote controller. Next, the process proceeds to step S202.

[0054] In S202, the calculation unit 35 acquires the room temperature from the indoor unit 6 and the outdoor air temperature from the outdoor unit 5 via the data collection unit 32. Next, the process proceeds to step S203.

[0055] In S203, the calculation unit 35 inputs the room temperature, the outside temperature, and the set temperature and infers the start-up spare time using the learned model stored in the learned model holding unit 38. The calculation unit 35 outputs the inferred start-up spare time ton_est to the control unit 36. Next, the process proceeds to step S204.

[0056] In step S204, the control unit 36 ​​sets the time before the startup reserve time ton_est estimated from the set time tset as the startup time t0, and sends control signals to the outdoor unit 5 and the indoor unit 6 to start the air conditioner 4 at the startup time t0. Note that in step S202, the control unit 36 ​​may not send control signals to the outdoor unit 5 and the indoor unit 6, but may instead send control signals to the outdoor unit 5 and the indoor unit 6 to start them when the startup time t0 arrives. This completes the estimation of the startup reserve time and the control of the air conditioner 4.

[0057] In this way, the air conditioning control device 3 combines the conditions at startup on the same day, the actual measured values ​​of the start-up standby time, the conditions at shutdown, and the room temperature change time after shutdown to create learning data, infers the start-up standby time using the generated trained model, and controls the air conditioner 4 using the inferred start-up standby time. This allows the start-up standby time appropriate for the building 10 in which the air conditioner 4 is installed to be inferred in a shorter time than when only start-up data is used, and the air conditioner 4 can be started at an appropriate time to reach the set temperature at the set time. In particular, when the building 10 is used as an office, there has been an issue of reduced accuracy when inferring the start-up standby time after a long holiday. This is because there is a difference in outside temperature before and after a long holiday. In this embodiment, a trained model can be generated that can infer the start-up standby time more accurately and in a shorter time than when only start-up data is used after a long holiday.

[0058] As described above, the air conditioning control device 3 of this embodiment is an air conditioning control device 3 that controls the operation of the air conditioner 4, and is equipped with a data collection unit 32 that acquires learning data including data when the air conditioner 4 is started and data when it is stopped, a learning unit 34 that uses the learning data to generate a trained model for inferring the startup standby time from when the air conditioner 4 is started until it reaches the set temperature, a calculation unit 35 that uses the trained model to output the startup standby time from the startup data acquired by the data collection unit 32, and a control unit 36 ​​that starts operation of the air conditioner 4 by the startup standby time from a predetermined set time.

[0059] This allows the start-up reserve time appropriate for the building 10 in which the air conditioner 4 is installed to be estimated in a shorter time than when only data at the time of start-up is used, and the air conditioner 4 can be started at a time appropriate for reaching the set temperature at the set time.

[0060] The startup data is the conditions when the air conditioner 4 is started and the startup standby time from start-up until the set temperature is reached, while the shutdown data is the conditions when the air conditioner 4 is stopped and the room temperature change time after stopping until the rate of change in room temperature after stopping falls below a threshold. By using the startup standby time as learning data, it is possible to obtain a trained model that can accurately infer the startup standby time.

[0061] The conditions for startup include the room temperature and outdoor temperature when the air conditioner 4 is started, and the conditions for shutdown include the room temperature and outdoor temperature when the air conditioner 4 is stopped. Because the startup preparation time and the room temperature change time after shutdown are affected by the room temperature and outdoor temperature, the room temperature and outdoor temperature are used as learning data.

[0062] Furthermore, the startup conditions include at least one of the number of indoor units 6 included in the air conditioner 4 and the capacity saving amount of the outdoor unit 5 included in the air conditioner 4. When multiple indoor units 6 are installed in the same room, the startup standby time is affected by the operating status of adjacent indoor units 6. Therefore, by using the number of indoor units 6 that are running as learning data, the startup standby time can be learned more accurately. Furthermore, the amount of heat processed by the air conditioner 4 is determined by the capacity saving amount of the outdoor unit 5 included in the air conditioner 4 relative to the heating and cooling capacity of the air conditioner 4. The startup standby time is affected by the amount of heat processed by the air conditioner 4. Therefore, by using the number of indoor units 6 included in the air conditioner 4 and the capacity saving amount of the outdoor unit 5 included in the air conditioner 4 as learning data, a trained model that infers the startup standby time with higher accuracy can be generated.

[0063] Embodiment 2 Next, a second embodiment will be described. In this embodiment, the configurations of the air conditioning system 100 and the air conditioning control device 3 are the same as those in the first embodiment, and therefore a description thereof will be omitted. In the first embodiment, the air conditioner 4 was stopped at the stop time, and data acquisition processing was performed at the time of stopping. In this embodiment, when the data at the time of stopping is combined with the data at the time of starting to use as learning data, the air conditioning control device 3 performs a temperature difference control processing to control the air conditioner 4 so that the difference between the room temperature and the outside temperature at the time of stopping approaches the difference between the room temperature and the outside temperature at the time of starting, and then stops the air conditioner 4. The start-up spare time varies mainly depending on the difference between the room temperature and the outside temperature, the set temperature, the amount of heat processed by the air conditioner 4, the heat storage capacity of the building 10's building frame, and the thermal insulation performance of the building 10. On the other hand, the room temperature change time after stopping is mainly determined by the difference between the room temperature and the outside temperature and the thermal insulation performance of the building 10. Therefore, by making the difference between the room temperature and the outside temperature the same when the air conditioner is started and when it is stopped, the air conditioning control device 3 can estimate the impact of the thermal storage capacity of the building 10 by comparing the data when the air conditioner is started and the data when it is stopped. As a result, the air conditioning control device 3 can generate a trained model that can infer the startup reserve time with sufficient accuracy as expected using less training data.

[0064] FIG. 10 is a graph showing the time changes in room temperature and outdoor air temperature when temperature difference control processing is performed. Referring to FIG. 10, the data collected by the data collection unit 32 when temperature difference control processing is performed will be described. The data acquisition processing at startup is the same as in Embodiment 1, and therefore will not be described here. As shown in FIG. 10, the difference between the room temperature and outdoor air temperature at startup time t0 is defined as the startup temperature difference Tdiff. In this embodiment, the time when the user has previously set the air conditioning control device 3 to stop the air conditioner 4 is defined as the scheduled shutdown time t4'. When the scheduled shutdown time t4' arrives, the air conditioning control device 3 controls the air conditioner 4 so that the difference between the room temperature and outdoor air temperature becomes the startup temperature difference Tdiff. The air conditioning control device 3 stops the air conditioner 4 at the shutdown control time t4, which is defined as the shutdown control time t4. The data collection unit 32 acquires the room temperature Toff_in at the shutdown control time t4 of the air conditioner 4 from the indoor temperature sensor 61 as a shutdown condition. The data collection unit 32 also acquires the outdoor air temperature Toff_out at the time t4 when the air conditioner 4 is controlled to stop from the outdoor air temperature sensor 51 as a condition for stopping the air conditioner 4. Furthermore, the data collection unit 32 stores the time from the time t4 when the air conditioner 4 is stopped to the room temperature stabilization time t3 when the room temperature change rate falls below a predetermined threshold as the room temperature change time after shutdown toff. The data collection unit 32 periodically (e.g., every minute) acquires the room temperature from the indoor temperature sensor 61, calculates the difference from the previously acquired room temperature as the change rate, and compares it with the threshold to determine whether the room temperature change rate has fallen below the threshold. Alternatively, the indoor unit 6 may notify the data collection unit 32 when the room temperature change rate falls below the threshold. The data collection unit 32 stores the learning data collected as described above in the learning data storage unit 37.

[0065] Fig. 11 is a flowchart showing the flow of collection and learning of learning data in the air conditioning control device 3 according to this embodiment. Using Fig. 11, we will explain the collection and learning of learning data for inferring the startup spare time in the air conditioning control device 3. In Fig. 11, the same processes as in Fig. 5 of embodiment 1 are assigned the same reference numerals, and the explanation will be simplified.

[0066] First, step S101 indicates that the flow of learning the startup reserve time is periodically executed, and then the process proceeds to step S102.

[0067] In step S102, the air conditioning control device 3 determines whether it is start-up time t0 of the air conditioner 4. If it is start-up time t0, the process proceeds to step S103 (S102: Yes). If it is not start-up time t0, the process proceeds to step S110 (S102: No).

[0068] In step S103, the data collection unit 32 of the air conditioning control device 3 performs a process to acquire data at startup. The process of acquiring data at startup is the same as in embodiment 1, so a description thereof will be omitted. Next, the process proceeds to step S110.

[0069] In step S110, the air conditioning control device 3 determines whether the scheduled stop time t4' for the air conditioner 4 has arrived. The scheduled stop time t4' is set in the air conditioning control device 3 in advance by the user. Alternatively, the scheduled stop time t4' may be the time when the user operates the local remote control 7 to stop the air conditioner 4. If the scheduled stop time t4' has arrived, proceed to step S111 (S110: Yes). If it is not the scheduled stop time t4', proceed to step S106 (S110: No).

[0070] In step S111, the control unit 36 ​​of the air conditioning control device 3 performs temperature difference control processing to control the air conditioner 4 so that the difference between the room temperature and the outside air temperature becomes the same as the startup temperature difference Tdiff, which is the difference between the room temperature and the outside air temperature at startup time t0. Figure 12 is a flowchart showing the flow of the temperature difference control processing in the air conditioning control device 3 according to this embodiment. Figure 12 corresponds to step S111 in Figure 11. The temperature difference control processing in the air conditioning control device 3 will be described with reference to Figure 12.

[0071] First, in step S40, the control unit 36 ​​controls the air conditioner 4 so that the difference between the room temperature and the outside air temperature is the same as the startup temperature difference Tdiff. Specifically, when the operation mode of the air conditioner 4 is heating, the control unit 36 ​​sends a control signal to the air conditioner 4 to reduce the operating capacity of the air conditioner 4 if the difference between the room temperature and the outside air temperature is greater than the startup temperature difference Tdiff. When the difference between the room temperature and the outside air temperature is smaller than the startup temperature difference Tdiff, the control unit 36 ​​sends a control signal to the air conditioner 4 to increase the operating capacity of the air conditioner 4. Furthermore, when the operation mode of the air conditioner 4 is cooling, the control unit 36 ​​sends a control signal to the air conditioner 4 to reduce the operating capacity of the air conditioner 4 if the difference between the room temperature and the outside air temperature is greater than the startup temperature difference Tdiff. When the difference between the room temperature and the outside air temperature is smaller than the startup temperature difference Tdiff, the control unit 36 ​​sends a control signal to the air conditioner 4 to increase the operating capacity of the air conditioner 4. Next, proceed to step S41.

[0072] In step S41, the control unit 36 ​​determines whether the difference between the room temperature obtained from the indoor unit 6 and the outdoor temperature obtained from the outdoor unit 5 has become the same as the startup temperature difference Tdiff by calculating the difference between the room temperature and the outdoor temperature and comparing it with the startup temperature difference Tdiff. The control unit 36 ​​may also determine that the difference between the room temperature and the outdoor temperature has become the same as the startup temperature difference Tdiff if the difference between the room temperature and the outdoor temperature and the startup temperature difference Tdiff is equal to or less than a threshold. If the control unit 36 ​​determines that the difference between the room temperature and the outdoor temperature has become the same as the startup temperature difference Tdiff, it sets this time as the stop control time t4 and proceeds to step S42 (S41: Yes). If the control unit 36 ​​determines that the difference between the room temperature and the outdoor temperature is not the same as the startup temperature difference Tdiff, it returns to step S40 (S41: No) and controls the air conditioner 4 again.

[0073] In step S42, the control unit 36 ​​stops the air conditioner 4. This ends the temperature difference control process in the air conditioning control device 3, and the process proceeds to step S105 in FIG.

[0074] Returning to Fig. 11, in step S105, the data collection unit 32 of the air conditioning control device 3 performs processing to acquire data at the time of shutdown. As with embodiment 1, the data at the time of shutdown includes the conditions at the time of shutdown and the room temperature change time toff after shutdown. The conditions at the time of shutdown include the room temperature Toff_in acquired from the room temperature sensor 61 and the outside air temperature Toff_out acquired from the outside air temperature sensor 51. Next, the process proceeds to step S106.

[0075] In step S106, the air conditioning control device 3 determines whether it is time to learn the startup reserve time. If it is time to learn, the process proceeds to step S107 (S106: Yes). If it is not time to learn, the process proceeds to step S108 (S106: No).

[0076] In step S107, the air conditioning control device 3 learns the preliminary startup time using the learning data collected by the data collection unit 32. The preliminary startup time is learned in the same manner as in embodiment 1. Next, the process proceeds to step S108.

[0077] In step S108, the collection of learning data and one cycle of learning processing in the air conditioning control device 3 ends, and the process returns to S101. This completes the flow of collection of learning data and learning for estimating the startup spare time in the air conditioning control device 3.

[0078] In this manner, the air conditioning control device 3 collects learning data for learning the standby start time and generates a learning model for inferring the standby start time. In this embodiment, before stopping the air conditioner 4, the air conditioning control device 3 controls the air conditioner 4 so that the difference between the room temperature and the outside air temperature is the same as the startup temperature difference Tdiff, which is the temperature difference at startup time t0. In this manner, the air conditioning control device 3 can generate a learning model for inferring the standby start time that takes into account the thermal storage capacity of the building 10's building structure by learning the startup conditions and actual measured values ​​of the standby start time, and the shutdown conditions and the room temperature change time after shutdown.

[0079] The estimation of the spare startup time by the air conditioning control device 3 using the trained model and the control of the air conditioner 4 using the estimated spare startup time are the same as in the first embodiment, and therefore will not be described again.

[0080] As described above, the control unit 36 ​​of the air conditioning control device 3 of this embodiment calculates the startup temperature difference, which is the difference between the room temperature and the outside temperature when the air conditioner 4 is started, and when the scheduled time for the air conditioner 4 to stop arrives, performs temperature difference control to control the air conditioner 4 so that the difference between the room temperature and the outside temperature approaches the startup temperature difference, and stops operation of the air conditioner 4 when the difference between the room temperature and the outside temperature and the startup temperature difference becomes smaller than a threshold value. By using temperature difference control to stop the air conditioner 4 when the difference between the room temperature and the outside temperature and the startup temperature difference becomes smaller than a threshold value, it is possible to match the difference between the room temperature and the outside temperature under the startup conditions and the shutdown conditions, and it is possible to estimate the startup reserve time taking into account the performance of the building 10.

[0081] The temperature difference control by the control unit 36 ​​controls the operating capacity of the air conditioner 4 to be lower than before the scheduled shutdown time when the difference between the room temperature and the outside temperature is larger than the temperature difference at startup, and controls the operating capacity of the air conditioner to be higher than before the scheduled shutdown time when the difference between the room temperature and the outside temperature is smaller than the temperature difference at startup. By controlling the air conditioner 4 in this way by the control unit 36, it is possible to control the difference between the room temperature and the outside temperature to approach the temperature difference at startup.

[0082] Embodiment 3 Next, a third embodiment will be described. In this embodiment, the same components as those in the first embodiment are assigned the same reference numerals, and their description will be omitted where appropriate. FIG. 13 is a diagram showing an example of the configuration of an air conditioning system 100 including an air conditioning control device 3 according to this embodiment. In this embodiment, it is assumed that a second indoor unit 6b is installed in the same room 8 as a first indoor unit 6a that is the target of learning. The number of indoor units 6 installed in the room 8 is not limited to two, and multiple indoor units 6 may be installed. Furthermore, hereinafter, the term "indoor unit 6" includes the first indoor unit 6a and the second indoor unit 6b. When multiple indoor units 6 are installed in the room 8, the startup reserve time is affected by the operating status of adjacent indoor units 6. In this embodiment, the air conditioning control device 3 performs stop time difference control for the air conditioners 4 so that the difference in start time between the first indoor unit 6a and the second indoor unit 6b is the same as the difference in stop time between the first indoor unit 6a and the second indoor unit 6b. This allows the influence of the second indoor unit 6b adjacent to the first indoor unit 6a to be inferred by combining data at startup and data at shutdown, and the air conditioning control device 3 can generate a trained model that can infer the startup reserve time with sufficient accuracy as expected using less training data.

[0083] The first indoor unit 6a and the second indoor unit 6b are configured similarly to the indoor unit 6 in embodiment 1. The first indoor unit 6a and the second indoor unit 6b are connected to the outdoor unit 5 by communication lines and refrigerant piping (not shown) to form the air conditioner 4. The first indoor unit 6a is equipped with a first indoor temperature sensor 61a that detects the indoor temperature. The second indoor unit 6b is equipped with a second indoor temperature sensor 61b that detects the indoor temperature.

[0084] FIG. 14 is a graph showing the change in room temperature over time when stop time difference processing is performed. The room temperature is represented by a first room temperature detected by the first room temperature sensor 61a equipped in the first indoor unit 6a and a second room temperature detected by the second room temperature sensor 61b equipped in the second indoor unit 6b. The outdoor temperature is not shown. In this embodiment, the time when the user has previously set in the air conditioning control device 3 to stop the air conditioner 4 is referred to as the scheduled stop time t5'. The startup reserve time is learned for each indoor unit 6. In FIG. 14, the learning target is the first indoor unit 6a, and values ​​related to the learning data for the first indoor unit 6a are listed. The learning data for the first indoor unit 6a when stop time difference processing is performed will be described with reference to FIG. 14. It is assumed that the set time tset, set temperature Tset, and scheduled stop time t5' are set individually for multiple indoor units 6 installed in the same room 8.

[0085] The first start-up time t0_1 is the time when the first indoor unit 6a is started. The second start-up time t0_2 is the time when the second indoor unit 6b is started. Similar to the start-up time t0 in the first embodiment, the first start-up time t0_1 and the second start-up time t0_2 are set to a time a certain time (for example, one hour) before the set time tset when sufficient learning data has not been collected. That is, the air conditioning control device 3 aims to control the air conditioner 4 so that the first room temperature and the second room temperature become the set temperature Tset at the set time tset. Because the first indoor unit 6a and the second indoor unit 6b differ in distance from a window and distance from a heat source machine installed in the room 8, the start-up standby times are different even if the set time tset and the set temperature Tset are the same. The start-up standby time estimated for the first indoor unit 6a is designated ton_est1, and the start-up standby time estimated for the second indoor unit 6b is designated ton_est2 (not shown). If sufficient learning data has been collected, the first start-up time t0_1 is set to a time that precedes the set time tset by the inferred standby start-up time ton_est1. If sufficient learning data has been collected, the second start-up time t0_2 is set to a time that precedes the set time tset by the inferred standby start-up time ton_est2. The air conditioning control device 3 calculates the start-up time difference tdiff, which is the difference between the first start-up time t0_1 and the second start-up time t0_2. In Figure 14, the first start-up time t0_1 is earlier than the second start-up time t0_2. In other words, the first indoor unit 6a is started up before the second indoor unit 6b.

[0086] The data collection unit 32 acquires the room temperature Ton_in_1 at the first start-up time t0_1 from the first indoor temperature sensor 61a as a start-up condition. The data collection unit 32 acquires the outdoor air temperature Ton_out_1 (not shown) at the first start-up time t0_1 of the air conditioner 4 from the outdoor air temperature sensor 51 as a start-up condition. The data collection unit 32 acquires the set temperature Tset as a start-up condition. The data collection unit 32 also stores the time from the first start-up time t0_1, when the first indoor unit 6a is started, to the time t1_1, when the room temperature reaches the set temperature Tset, as the actual value ton_1 of the start-up reserve time of the first indoor unit 6a. The data collection unit 32 periodically acquires the room temperature from the first indoor temperature sensor 61a and compares it with the set temperature Tset to determine whether the room temperature has reached the set temperature Tset. Alternatively, the first indoor unit 6a may notify the data collection unit 32 when the room temperature has reached the set temperature Tset.

[0087] The air conditioning control device 3 stops the first indoor unit 6a at the scheduled stop time t5' set in advance by the user in the air conditioning control device 3. The first stop time t5_1, the time when the first indoor unit 6a is stopped, becomes the scheduled stop time t5'. Next, after the start time difference tdiff has elapsed, the air conditioning control device 3 stops the second indoor unit 6b. The second stop time t5_2, the time when the second indoor unit 6b is stopped, becomes the time when the start time difference tdiff has elapsed from the scheduled stop time t5'. In this way, the control performed by the air conditioning control device 3, in which the time difference between when the first indoor unit 6a and the second indoor unit 6b are stopped is the start time difference tdiff, in order to ensure that the operating states indicating the start or stop of the first indoor unit 6a and the second indoor unit 6b during the start prep time and the room temperature change time after stop are the same, is called stop time difference control. The data collection unit 32 acquires the room temperature Toff_in_1 at the first stop time t5_1 from the first indoor temperature sensor 61a as a stop condition. The data collection unit 32 also acquires, as a stop condition, the outdoor air temperature Toff_out_1 (not shown) at the first stop time t5_1 when the first indoor unit 6a is stopped from the outdoor air temperature sensor 51. Furthermore, the data collection unit 32 stores the time from the first stop time t5_1 when the first indoor unit 6a is stopped to the first room temperature stabilization time t3_1 when the temperature change rate of the room temperature becomes equal to or less than a predetermined threshold as the room temperature change time toff_1 after stopping the first indoor unit 6a.

[0088] As shown in Figure 14, by stopping the second indoor unit 6b after the start time difference tdiff has elapsed from the first stop time t5, it is possible to make the operating states indicating start or stop during the start spare time and the room temperature change time after stop of the first indoor unit 6a and the second indoor unit 6b the same. In other words, the influence of the second indoor unit 6b on the start spare time of the first indoor unit 6a is equivalent to the influence of the second indoor unit 6b on the room temperature change time after stop of the first indoor unit 6a. Therefore, by combining data at start and data at stop and using it as learning data, it is possible to infer the start spare time taking into account the influence of adjacent indoor units 6.

[0089] As described above, the learning data for the first indoor unit 6a has been described, but the data collection unit 32 also stores the room temperature Ton_in_2, outdoor temperature Ton_out_2, and actual measured value ton_2 of the startup standby time at the second start-up time t0_2 for the second indoor unit 6b as data at the time of startup. The data collection unit 32 also stores the room temperature Toff_in_2, outdoor temperature Toff_out_2, and room temperature change time after shutdown toff_2 at the second stop time t5_2 for the second indoor unit 6b as data at the time of shutdown. The data collection unit 32 stores the learning data collected as above in the learning data holding unit 37.

[0090] Fig. 15 is a flowchart showing the flow of collection and learning of learning data in the air conditioning control device 3 according to this embodiment. Using Fig. 15, we will explain the collection and learning of learning data for inferring the startup spare time in the air conditioning control device 3. In Fig. 15, processes that are the same as those in Fig. 5 of embodiment 1 are assigned the same reference numerals, and the explanation will be simplified.

[0091] First, step S101 indicates that learning of the startup standby time is periodically executed. Next, the process proceeds to steps S301 and S301′. Note that steps S301 and S301′ are processed in parallel by the air conditioning control device 3.

[0092] In step S301, the air conditioning control device 3 determines whether the first start-up time t0_1 of the first indoor unit 6a has arrived. If the first start-up time t0_1 has arrived, the process proceeds to step S302 (S301: Yes). If the first start-up time t0_1 has not arrived, the process proceeds to step S304 (S301: No).

[0093] In step S302, the data collection unit 32 of the air conditioning control device 3 performs processing to acquire data at startup of the first indoor unit 6a. The processing to acquire data at startup is the same as in embodiment 1, so a description thereof will be omitted. Next, the process proceeds to step S303.

[0094] In step S301', the same process as in step S301 is performed on the second indoor unit 6b. That is, the air conditioning control device 3 determines whether the second start-up time t0_2 of the second indoor unit 6b has arrived. If the second start-up time t0_2 has arrived, the process proceeds to step S302' (S301': Yes). If it is not the second start-up time t0_2, the process proceeds to step S304 (S301': No). Note that the first start-up time t0_1 is assumed to be earlier than the second start-up time t0_2. That is, the indoor unit 6 that started up first is assumed to be the first indoor unit 6a.

[0095] In step S302', the same process as in step S302 is performed on the second indoor unit 6b. That is, the data collection unit 32 of the air conditioning control device 3 performs a process to acquire data at startup of the second indoor unit 6b. Since the process of acquiring data at startup is the same as in embodiment 1, a description thereof will be omitted. Next, proceed to step S303.

[0096] In step S303, the air conditioning control device 3 calculates the difference between the first start-up time t0_1 and the second start-up time t0_2 as the start-up time difference tdiff. Next, the process proceeds to step S304.

[0097] In step S304, the air conditioning control device 3 determines whether it is time t5' to stop the air conditioner 4. If it is time t5', the process proceeds to step S305 (S304: Yes). If it is not time t5', the process proceeds to step S106 (S304: No).

[0098] In step S305, the control unit 36 ​​of the air conditioning control device 3 stops the first indoor unit 6a. Next, the process proceeds to steps S306 and S308. Note that steps S306 and S308 are processed in parallel by the air conditioning control device 3.

[0099] In step S306, the air conditioning control device 3 determines whether the start time difference tdiff has elapsed since the scheduled stop time t5'. If the start time difference tdiff has elapsed, the process proceeds to step S307 (S306: Yes). If the start time difference tdiff has not elapsed, the process returns to step S306 (S306: No).

[0100] In step S307, the control unit 36 ​​stops the second indoor unit 6b. Next, the process proceeds to step S308'. Note that the process of stopping the first indoor unit 6a at the scheduled stop time t5' and stopping the second indoor unit 6b after the start time difference tdiff has elapsed (corresponding to S304, S305, S306, and S307) is referred to as stop time difference control.

[0101] In step S308, the data collection unit 32 of the air conditioning control device 3 performs processing to acquire data when the first indoor unit 6a is stopped. The processing to acquire data when the first indoor unit 6a is stopped is the same as in embodiment 1, so a description thereof will be omitted. Next, the process proceeds to step S106.

[0102] In step S308', the data collection unit 32 of the air conditioning control device 3 performs processing to acquire data when the second indoor unit 6b is stopped. Since the processing to acquire data when the second indoor unit 6b is stopped is the same as in embodiment 1, a description thereof will be omitted. Next, the process proceeds to step S106.

[0103] In step S106, the air conditioning control device 3 determines whether it is time to learn the startup reserve time. If it is time to learn, the process proceeds to step S107 (S106: Yes). If it is not time to learn, the process proceeds to step S108 (S106: No).

[0104] In step S107, the air conditioning control device 3 learns the spare startup time using the learning data collected by the data collection unit 32. The air conditioning control device 3 learns the spare startup time for each of the first indoor unit 6a and the second indoor unit 6b using the collected learning data, and generates a learned model. Learning of the spare startup time is performed in the same way as in embodiment 1. Next, proceed to step S108.

[0105] In step S108, the collection of learning data and one cycle of learning processing in the air conditioning control device 3 ends, and the process returns to S101. This completes the flow of collection of learning data and learning for estimating the startup spare time in the air conditioning control device 3.

[0106] In this manner, the air conditioning control device 3 collects learning data for learning the spare startup time and generates a learning model for inferring the spare startup time. In this embodiment, the air conditioning control device 3 controls the first indoor unit 6a and the second indoor unit 6b so that the time difference between when the first indoor unit 6a and the second indoor unit 6b are stopped is equal to the start time difference tdiff. This results in the operating states indicating start or stop during the spare startup time and the room temperature change time after shutdown of the first indoor unit 6a and the second indoor unit 6b being equal. Therefore, by combining data at startup and data at shutdown and using this as learning data, a learning model can be generated that infers the spare startup time while taking into account the influence of adjacent indoor units 6.

[0107] The estimation of the spare startup time by the air conditioning control device 3 using the trained model and the control of the air conditioner 4 using the estimated spare startup time are the same as in the first embodiment, and therefore will not be described again.

[0108] As described above, the air conditioner 4 controlled by the air conditioning control device 3 of this embodiment has a first indoor unit 6a and a second indoor unit 6b, and the control unit 36 ​​stores the time from when the first indoor unit 6a starts until when the second indoor unit 6b starts as the start-up time difference, and stops the second indoor unit 6b when the start-up time difference has elapsed since the first indoor unit 6a stopped operating. This makes it possible to match the start-up conditions with the stop-down conditions. Therefore, by combining start-up data and stop-down data and using them as learning data, it is possible to take into account the influence of adjacent indoor units 6 and generate a trained model that infers the start-up standby time with higher accuracy.

[0109] Embodiment 4 Next, a fourth embodiment will be described. In this embodiment, the temperature difference control process described in the second embodiment is performed, and the acquired learning data is used to estimate the amount of heat stored in the building structure, which is then used to infer the startup reserve time. Note that, in this embodiment, the configurations of the air conditioning system 100 and the air conditioning control device 3 are the same as those in the second embodiment, and therefore their explanation will be omitted.

[0110] Fig. 16 is a flowchart showing the flow of learning and data collection in the air conditioning control device 3 according to this embodiment. In this embodiment, the operations of the data acquisition process at startup, the temperature difference control process, and the data acquisition process at shutdown are the same as those shown in Fig. 11 in embodiment 2, and therefore descriptions thereof will be omitted. In this embodiment, after the data acquisition process at shutdown (step S105), a process of estimating the building heat storage amount in step S401 is added.

[0111] In step S401, the air conditioning control device 3 uses data at the time of startup and data at the time of shutdown to estimate the amount of heat stored in the building 10. An example of a method for estimating the amount of heat stored in the building will be described below.

[0112] The temperature change rate after the air conditioner 4 is started is expressed, for example, by equation (1) using a thermal characteristic model with representative influence factors. In equation (1), a' and b' are coefficients, and C is the indoor heat capacity [kWh / K] targeted by the air conditioner 4. R is the window thermal conductivity [kW / K], and α is the amount of heat due to other heat load influence factors. W(t) is the amount of heat [kW] processed by the air conditioner 4 at time t. The amount of heat W(t) is the amount of heat removed in cooling operation and the amount of heat supplied in heating operation. b'Q(t) is the amount of heat [kW] released from the building's building frame at time t. Q(t) is the amount of heat stored in the building's building frame by the time the air conditioner 4 is started, and indicates the amount released into the room at time t.

[0113]

number

[0114] Using equation (1), we calculate the startup standby time ton, which is the time it takes for the room temperature to reach the set temperature Tset after the air conditioner 4 is started. Assuming that the outdoor temperature Tout and the amount of heat Q(t) are constant during the startup standby time ton, this can be expressed as equation (2). In equation (2), a and b are coefficients. W is the average air conditioning heat [kW] processed by the air conditioner 4 during the startup standby time ton, and Q is the amount of heat stored in the building 10's building structure by the time of startup [kWh]. bQ represents the amount of heat released per unit time from the building structure thermal storage into the room. Note that while the air conditioner 4 is running, the amount of heat released per unit time from the building structure thermal storage into the room, bQ, can be considered constant regardless of time t. R is the average amount of heat flowing into the room per unit time [kW] during the startup standby time ton, and is determined by the window thermal conductivity Rwin and the temperature difference between the room temperature and the outdoor temperature (Tset - Tin). Tin is the room temperature at the time the air conditioner 4 is started. The amount of heat W for air conditioning is a negative value during cooling. The amount of heat R flowing into the room is a negative value when the outside temperature is lower than the room temperature.

[0115]

number

[0116] Furthermore, the room temperature change time after shutdown toff is calculated using equation (1). While the air conditioner 4 is running, the heat storage amount of the building structure can be considered to be 0. The outdoor air temperature Tout is assumed to be constant during the room temperature change time after shutdown toff. Furthermore, because the temperature difference control process results in the temperature difference between the room temperature and the outdoor air temperature when the air conditioner is stopped being the same as the temperature difference at startup (Tset - Tin), the average heat quantity per unit time flowing into the room during the room temperature change time after shutdown toff can be considered to be equivalent to the average heat quantity R per unit time flowing into the room during the startup standby time ton. Furthermore, because the temperature difference control process results in the difference between the room temperature and the outdoor air temperature when the air conditioner is stopped being the same as the temperature difference at startup (Tset - Tin), the temperature change during the room temperature change time after shutdown toff can be considered to be equivalent to the difference between Tset and Tin. Therefore, the room temperature change time after shutdown toff can be expressed as in equation (3).

[0117]

number

[0118] The amount of heat W for air conditioning processed by the air conditioner 4 during the startup standby time ton can be obtained from the air conditioner 4. The indoor heat capacity C is a value determined by the material of the building 10 and the size of the space covered by the air conditioner 4. By obtaining the amount of heat processed by the air conditioner 4 and the change in room temperature obtained from the indoor temperature sensor 61 over the long term, the indoor heat capacity C and the coefficients a, b, and α can be estimated. Therefore, using equations (2) and (3), the amount of heat stored in the building structure Q can be estimated from the startup standby time ton and the time of room temperature change after shutdown toff.

[0119] The air conditioning control device 3 stores the estimated building heat storage amount Q, together with the data at startup and shutdown, in the learning data storage unit 37 as learning data for inferring the startup standby time. Note that the model formulas used to estimate the building heat storage amount Q are not limited to formulas (2) and (3). A different thermal characteristic model may be used to estimate the building heat storage amount Q using the startup standby time ton and the room temperature change time after shutdown toff when temperature difference control processing is performed. Next, the air conditioning control device 3 proceeds to step S106.

[0120] In step S106, the air conditioning control device 3 determines whether it is time to learn the startup reserve time. If it is time to learn, the process proceeds to step S402 (S106: Yes). If it is not time to learn, the process proceeds to step S108 (S106: No).

[0121] In step S402, the air conditioning control device 3 learns the preliminary startup time using learning data including the amount of heat stored in the building structure collected by the data collection unit 32. Figure 17 is a flowchart showing the flow of learning the preliminary startup time in the air conditioning control device 3 according to this embodiment. The flow of learning the preliminary startup time will be described with reference to Figure 17.

[0122] First, in step S50, the data processing unit 33 reads out the learning data stored in the learning data storage unit 37, and creates learning data by combining the conditions at startup on the same day, the actual measured values ​​of the startup standby time, the conditions at shutdown, the room temperature change time after shutdown, and the building heat storage amount estimated in step S401. The created learning data is output to the learning unit 34. Next, the process proceeds to step S51.

[0123] In step S51, the learning unit 34 learns the extra startup time using the learning data and generates a trained model that infers the extra startup time from the conditions at startup. The learning unit 34 stores the generated trained model in the trained model holding unit 38. This completes the learning of the extra startup time, and the process proceeds to step S108 in FIG. 16.

[0124] 16, in step S108, the collection of learning data and one cycle of learning processing in the air conditioning control device 3 ends, and the process returns to step S101. This completes the flow of collection of learning data and learning for inferring the startup spare time in the air conditioning control device 3.

[0125] As described above, in this embodiment, the estimated building thermal storage amount Q is used as learning data for learning the startup spare time. The startup spare time is affected by the building thermal storage amount Q in addition to the outside air temperature, room temperature, and set temperature. By estimating the building thermal storage amount Q in advance and using it as learning data, the learning unit 34 can generate a learned model that infers a startup spare time appropriate for the building 10 in which the air conditioner 4 is installed.

[0126] The estimation of the spare startup time by the air conditioning control device 3 using the trained model and the control of the air conditioner 4 using the estimated spare startup time are the same as in the first embodiment, and therefore will not be described again.

[0127] As described above, the learning unit 34 of the air conditioning control device 3 of this embodiment estimates the building's thermal storage amount using the startup reserve time of the air conditioner 4 and the room temperature change time after shutdown, and generates a trained model using the estimated building's thermal storage amount as a feature. This allows the learning unit 34 to generate a trained model that infers the startup reserve time appropriate for the building 10 in which the air conditioner 4 is installed.

[0128] Furthermore, the learning unit 34 estimates the building's heat storage capacity using the room temperature acquired from the indoor temperature sensor 61 installed in the air conditioner 4 and the air conditioning heat quantity, which is the quantity of heat processed by the air conditioner 4. By estimating the building's heat storage capacity using values ​​acquired by actually operating the air conditioner 4, it is possible to estimate the building's heat storage capacity suitable for the building 10 in which the air conditioner 4 is installed.

[0129] The configurations shown in the above embodiments are examples of the content of the present invention, and may be combined with other known technologies, and parts of the configurations may be omitted or modified within the scope of the gist of the present invention. [Industrial Applicability]

[0130] According to the present disclosure, an air conditioning control device can be obtained that collects learning data for accurately estimating the startup standby time of an air conditioner taking into account the performance of the building in a shorter time than when only startup data is used. [Explanation of symbols]

[0131] 1 control server, 2 management device, 3 air conditioning control device, 4 air conditioner, 5 outdoor unit, 6 indoor unit, 6a first indoor unit, 6b second indoor unit, 7 handheld remote control, 8 room, 10 building, 11 wide area network, 31 communication unit, 32 data collection unit, 33 data processing unit, 34 learning unit, 35 calculation unit, 36 control unit, 37 learning data storage unit, 38 learned model storage unit, 51 outdoor temperature sensor, 61 indoor temperature sensor, 61a first indoor temperature sensor, 61b second indoor temperature sensor.

Claims

1. An air conditioning control device that controls the operation of an air conditioner, a data collection unit that acquires learning data including data when the air conditioner is started and data when the air conditioner is stopped; a learning unit that generates a trained model using the training data to infer a startup standby time from when the air conditioner is started until the indoor temperature reaches a set temperature; and a calculation unit that uses the trained model to output the spare startup time from the startup conditions acquired by the data collection unit; and a control unit that starts operation of the air conditioner a predetermined set time before the startup standby time, calculates a startup temperature difference which is the difference between the room temperature and the outside air temperature when the air conditioner is started, performs temperature difference control to control the air conditioner so that the difference between the room temperature and the outside air temperature approaches the startup temperature difference when the scheduled stop time of the air conditioner arrives, and stops operation of the air conditioner when the difference between the room temperature and the outside air temperature and the startup temperature difference becomes smaller than a threshold value; An air conditioning control device comprising:

2. The temperature difference control by the control unit is The air conditioning control device according to claim 1, characterized in that when the difference between the room temperature and the outside air temperature is larger than the temperature difference at startup, the operating capacity of the air conditioner is controlled to be lower than that before the scheduled shutdown time, and when the difference between the room temperature and the outside air temperature is smaller than the temperature difference at startup, the operating capacity of the air conditioner is controlled to be higher than that before the scheduled shutdown time.

3. The air conditioning control device described in Claim 1, characterized in that the learning unit estimates the heat storage amount of the building using the startup reserve time of the air conditioner and the room temperature change time after shutdown until the rate of change of the room temperature after shutdown becomes below a threshold, and generates the learned model using the estimated room temperature heat storage amount as a feature.

4. The air conditioning control device described in Claim 3, characterized in that the learning unit estimates the heat storage amount of the structure using the room temperature obtained from an indoor temperature sensor installed in the air conditioner and the air conditioning heat amount, which is the amount of heat processed by the air conditioner.

5. The air conditioning control device described in Claim 1, characterized in that the data at startup are the conditions at startup of the air conditioner and the startup preparatory time from startup until the set temperature is reached, and the data at shutdown are the conditions at shutdown of the air conditioner and the room temperature change time after shutdown until the rate of change of room temperature after shutdown becomes below a threshold value.

6. An air conditioning control device as described in Claim 5, characterized in that the conditions at startup include the room temperature and outside temperature when the air conditioner is started, and the conditions at shutdown include the room temperature and outside temperature when the air conditioner is stopped.

7. An air conditioning control device as described in Claim 5 or 6, characterized in that the startup conditions include at least one of the number of indoor units equipped in the air conditioner and the capacity saving amount of the outdoor units equipped in the air conditioner.

8. The air conditioner controlled by the air conditioning control device has a first indoor unit and a second indoor unit, The air conditioning control device according to claim 1, characterized in that the control unit stores the time from when the first indoor unit starts up to when the second indoor unit starts up as a start-up time difference, and stops the second indoor unit when the start-up time difference has elapsed since the first indoor unit stopped operating.

Images