Air conditioning system

Abstract

This air conditioning system comprises: an air conditioner that is indoor air conditioning equipment; an air conditioning controller that controls the air conditioner; a CO2 sensor provided in each of a plurality of target areas and acquiring CO2 concentration information; and a BLE beacon that transmits location information indicating the location of the CO2 sensor. The air conditioning controller has a learning model that infers future CO2 concentration information for each target area from the CO2 concentration information acquired by the CO2 sensor, and when the future CO2 concentration information of the target area inferred by the learning model exceeds a threshold, the air conditioning controller operates the air conditioner to perform air-conditioning of the target area corresponding to the location indicated by the location information of the CO2 sensor transmitted from the BLE beacon.

Description

Technical Field

[0001] The present disclosure relates to an air conditioning system that performs air conditioning in a target area.

Background Art

[0002] Conventionally, there is known a technique of controlling an air conditioner if the concentration of a pollutant is equal to or higher than a first concentration and lower than a second concentration (see Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the measurement of the pollutant concentration only determines based on the value at that time, and it is not ventilation control suitable for the characteristics of each area. Such a method is a post - event response after the occurrence of the condition of "exceeding the reference value", and is not a method of ventilating the indoor space so as not to exceed the reference value.

[0005] The present disclosure has been made in view of the above circumstances, and an object thereof is to provide an air conditioning system capable of performing ventilation control suitable for the characteristics of each target area.

Means for Solving the Problems

[0006] The air conditioning system according to the present disclosure includes an air conditioner which is indoor air conditioning equipment, an air conditioning controller that controls the air conditioner, a CO2 sensor provided in each of a plurality of target areas to acquire CO2 concentration information, a BLE beacon that transmits position information indicating the position of the CO2 sensor, a human presence sensor provided for each of the target areas to detect human presence information indicating the number and position of people in the target area, and for each of the target areas, the current and past CO2 concentration information acquired by the CO2 sensor and, for each of the target areas, the human presence information detected by the human presence sensor The foregoing a storage unit that stores the human presence information, and includes The air conditioner includes a ventilation device that performs ventilation and an indoor unit that supplies conditioned air with its temperature or humidity adjusted indoors. The air conditioning controller includes a learning model that infers future CO2 concentration information for each of the target areas from the CO2 concentration information acquired by the CO2 sensor. When the future CO2 concentration information of the target area inferred by the learning model exceeds a threshold value, the air conditioner is operated to perform air conditioning of the target area corresponding to the position indicated by the position information of the CO2 sensor transmitted from the BLE beacon, and learning of the learning model is performed based on the past human presence information and CO2 concentration information stored in the storage unit.

Effect of the Invention

[0007] According to the present disclosure, when the inferred CO2 concentration information of the target area exceeds a threshold value using a learning model, the air conditioner is operated to perform air conditioning of the target area corresponding to the position indicated by the position information of the CO2 sensor transmitted from the BLE beacon. Thereby, it is possible to maintain an appropriate ventilation state along each area so that the CO2 concentration state of the target area becomes less than the reference value.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Mode for Carrying Out the Invention

[0009] Hereinafter, with reference to the drawings, the air conditioning system 100 according to the embodiment will be described. In the drawings, the same reference numerals are given to the same components for description, and duplicate description will be made only when necessary.

[0010] Embodiment 1. FIG. 1 is a diagram showing the configuration of the air conditioning system 100 in Embodiment 1. In FIG. 1, the air conditioning system 100 includes an outdoor unit 110, a ventilation device 120, an indoor unit 130, an IoT gateway 140, a human sensor 150, an air conditioner controller 160, an external memory 170, a cloud 180, a CO2 sensor 190, and a BLE (Bluetooth (registered trademark) Low Energy) beacon 200.

[0011] The outdoor unit 110 is installed outdoors and is connected to the ventilation device 120 and the indoor unit 130. The outdoor unit 110 is connected to the indoor unit 130 by a refrigerant pipe and supplies the refrigerant heat-exchanged with the outside air to the indoor unit 130. The outdoor unit 110 is connected to the ventilation device 120 by an air pipe, sucks in the outside air and supplies it to the ventilation device 120, and exhausts the indoor air sent from the ventilation device 120 outdoors.

[0012] The ventilation device 120 and the indoor unit 130 are air-conditioning devices that are indoor air-conditioning facilities. The ventilation device 120 discharges the indoor air outdoors and introduces the outdoor air indoors to perform ventilation. The indoor unit 130 generates conditioned air with its temperature or humidity adjusted by heat-exchanging the refrigerant sent from the outdoor unit 110 with the indoor air, and supplies this conditioned air indoors. The ventilation device 120 and the indoor unit 130 are operationally controlled by the air-conditioning controller 160.

[0013] The IoT (Internet of Things) gateway 140 is provided in the ventilation device 120 and exchanges data with the air-conditioning controller 160. Also, the IoT gateway 140 is provided in the indoor unit 130 and exchanges data with the air-conditioning controller 160.

[0014] The human presence sensor 150 is provided in the ventilation device 120 and detects human information indicating the number and position of people in the target area. Also, the human presence sensor 150 is provided in the indoor unit 130 and detects human information indicating the number and position of people in the target area. As this human presence sensor 150, for example, an image-type human presence sensor is used. The factors causing the increase in CO2 concentration are due to the number and position of people, and this information is used in the AI control described later.

[0015] The air-conditioning controller 160 is a device for monitoring and controlling a plurality of ventilation devices 120, outdoor units 110, and indoor units 130. Also, the air-conditioning controller 160 transmits and receives data to and from the IoT gateways 140 installed in the indoor unit 130 and the ventilation device 120.

[0016] The external memory 170 is a storage medium that accumulates the data of the air conditioner controller 160. The external memory 170 mentioned here refers to media such as a USB memory and an SD card. This medium may be replaceable by the user with one having a larger data capacity.

[0017] The cloud 180 is a data storage area accessible via the Internet. This storage area is utilized to hold various data of the air conditioner controller 160.

[0018] The CO2 sensor 190 transmits the CO2 concentration information of the target area via wireless communication. The wireless communication here assumes Wi-Fi, but it may also be wireless communication such as BLE communication, ZigBee (registered trademark), and EnOcean.

[0019] The BLE beacon 200 transmits the location information of the CO2 sensor 190 via BLE communication. Here, by arranging the BLE beacon 200 integrally with the CO2 sensor 190, it is used to grasp the location of the CO2 sensor 190. The BLE beacon 200 is accompanied by a UUID (Universally Unique Identifier) and a unique identifier.

[0020] FIG. 2 is a diagram showing the functional blocks of the air conditioning system 100 according to Embodiment 1.

[0021] The IoT gateway 140 has a BLE sensor information acquisition unit 300, a CO2 data measurement unit 310, and a data transmission / reception unit 320. Here, it is described as the IoT gateway 140, but the functions of the IoT gateway 140 may be added to the indoor unit 130 or the ventilation device 120.

[0022] The BLE sensor information acquisition unit 300 receives the location information from the BLE beacon 200. At this time, the BLE sensor information acquisition unit 300 also receives the UUID and the unique identifier attached to the BLE beacon 200.

[0023] The CO2 data measurement unit 310 acquires the CO2 concentration information of the target area transmitted from the CO2 sensor 190.

[0024] The data transmission / reception unit 320 transmits the UUID and location information received by the BLE sensor information acquisition unit 300 and the CO2 concentration information of the target area acquired by the CO2 data measurement unit 310 to the air conditioner controller 160.

[0025] The air conditioner controller 160 periodically acquires the UUID and location information and the CO2 concentration information from the IoT gateway 140. The air conditioner controller 160 includes a CO2 information acquisition unit 210, a data processing unit 220, a data non-volatile unit 230, and an internal non-volatile area 240.

[0026] The CO2 information acquisition unit 210 acquires data from the IoT gateway 140. It acquires the data from the BLE sensor information acquisition unit 300 and the CO2 data measurement unit 310 installed in the IoT gateway 140 via the data transmission / reception unit 320.

[0027] The data processing unit 220 performs data processing based on the information stored in the data non-volatile unit 230. The data processing includes a process of comparing the acquired CO2 concentration with the CO2 concentration information threshold value for judgment, and a process of calculating the forced time by AI control (inference and learning).

[0028] When saving data, the data processing unit 220 determines whether the CO2 concentration information exceeds the reference value. The reference value is, for example, 1000 ppm. This reference value can be set in advance in the system. The setting can be a common value for the entire system, or the reference value of the CO2 concentration information can be set individually for each CO2 sensor 190.

[0029] When the data processing unit 220 detects that the reference value of the CO2 concentration has been exceeded, the ventilation device 120 is forced to operate in the target area of the CO2 sensor 190. The forced operation means that if the ventilation device 120 is in the OFF state, it is turned on, and if the ventilation device 120 is in the operating ON state, it means an increase in the air volume.

[0030] The process of calculating the forced operation time by AI control (inference and learning) will be described later with reference to FIG. 4.

[0031] The data non-volatile unit 230 stores the data processed by the data processing unit 220 in a non-volatile manner in the internal non-volatile area 240. The internal non-volatile area 240 accumulates CO2 concentration information and human information indicating the number of people and their positions for each target area.

[0032] The non-volatile storage destination of the data may be, in addition to the internal non-volatile area 240, an external non-volatile area 250 or a cloud non-volatile area 260. The external non-volatile area 250 corresponds to external media such as an SD card and a USB memory. The cloud non-volatile area 260 may be a drive on a network such as a LAN DISK in addition to cloud services such as AWS (Amazon Web Services).

[0033] FIG. 3 is a diagram for explaining the control of the air conditioner controller 160 according to Embodiment 1.

[0034] As shown in FIG. 3, when the air conditioner controller 160 determines that forced operation of the ventilation device 120 and the indoor unit 130 is necessary, an operation command for ventilating the target area is given to the ventilation device 120 and the indoor unit 130 adjacent to the target area where the CO2 concentration information has increased.

[0035] FIG. 3 shows an example in which only the direction of the CO2 concentration increase area, which is the target area, is set to the "strong wind" operation for the purpose of ventilating only the CO2 concentration increase area, but it may also be controlled to have "strong wind" in all directions for ventilation of the entire room.

[0036] FIG. 4 is a diagram for explaining the calculation of the forced operation time in the data processing unit 220 according to Embodiment 1.

[0037] As shown in FIG. 4, for the calculation of the forced operation time, as input parameters, the CO2 concentration information of the target area, the CO2 concentration information threshold value, and the number of people in the room are input. Then, based on these input parameters, an inference is made to calculate the forced operation time. Note that, as an input parameter, the human information indicating the position of a person, which is the occupancy information of the target area, may be included.

[0038] For the CO2 concentration information, the time-series data stored in the internal non-volatile area 240 is used. The CO2 concentration information threshold value may be the same value as the above-mentioned reference value used for determining whether to forcibly operate the ventilation device 120 and the indoor unit 130, or may be a different value. The CO2 concentration information threshold value is set in the data processing unit 220. In the inference process, the learning model md is utilized.

[0039] The learning model md is provided for each target area and infers the future CO2 concentration information of the target area from the CO2 concentration information measured by the CO2 sensor 190. Specifically, an inference process is performed using the accumulated data of the past CO2 concentration information measured by the CO2 sensor 190, the number of people in the room, the CO2 concentration information threshold value, and the learning model md, and in the target area, the time until the CO2 concentration information reaches the threshold value in the future is calculated. Then, from the arrival time until the CO2 concentration reaches the threshold value, the time to forcibly operate either or both of the ventilation device 120 and the indoor unit 130 so that the CO2 concentration does not exceed the threshold value is calculated. The calculated time is output as the forced operation time.

[0040] The learning of the learning model md for each target area starts at a fixed time every day and is performed from the past accumulated data of the input data and the arrival time.

[0041] FIG. 5 is a learning and inference model used in both the inference process and the learning process in the data processing unit 220 according to Embodiment 1.

[0042] As shown in FIG. 5, the learning and inference model is a Deep Neural Network composed of an input layer I to which input parameters are input, an output layer O from which output parameters are output, an intermediate layer M_1, an intermediate layer M_2, and an intermediate layer M_3.

[0043] In the inference process, it starts from the input layer I and calculates the arrival time at the output layer O. In the learning process, parameters, weights, and bias values in the intermediate layer M are updated from the input data and the past accumulated data of the arrival time.

[0044] Next, the details of the operation of the air conditioning system 100 will be described with a flowchart. FIG. 6 is a flowchart of CO2 concentration information acquisition in the air conditioning system 100 according to Embodiment 1.

[0045] In FIG. 6, the UUID and location information are periodically acquired from the BLE beacon 200 (step S101). The UUID is an identifier of the BLE beacon 200 and is used for association with the CO2 sensor 190.

[0046] Next, the CO2 concentration information at the location of the BLE beacon 200 is acquired by the CO2 sensor 190. Also, the human information of the number of people and the location is acquired by the human presence sensor 150 (step S102).

[0047] Next, the CO2 concentration information and the human information are transmitted to the air conditioning controller 160 (step S103).

[0048] FIG. 7 is a flowchart of the accumulation of CO2 concentration information in the air conditioning controller 160 according to Embodiment 1.

[0049] The air conditioning controller 160 acquires the BLE location information, UUID, CO2 concentration information, and human information indicating the number of people and the location (step S201). Note that the acquisition is performed at regular intervals.

[0050] The air conditioner controller 160 collates the acquired UUID with a database that associates the pre-stored UUID with the CO2 sensor 190, and identifies the CO2 sensor 190 (step S202). One CO2 sensor 190 can be specified by the UUID.

[0051] The air conditioner controller 160 stores the obtained CO2 concentration information together with the time in units of the identified CO2 sensor 190 (step S203).

[0052] Next, the air conditioner controller 160 determines whether the CO2 concentration information received in step S201 exceeds a reference value (step S204).

[0053] In step S204, if it is determined that the CO2 concentration information exceeds the reference value (YES in step S204), the process proceeds to the CO2 concentration excess process in FIG. 8 (step S205).

[0054] On the other hand, in step S204, if it is determined that the received CO2 concentration information does not exceed the reference value (NO in step S204), the accumulation process of the CO2 concentration information in FIG. 7 is terminated.

[0055] FIG. 8 is a flowchart of the CO2 concentration excess process of the air conditioner controller 160 according to Embodiment 1.

[0056] As shown in FIG. 8, in the CO2 concentration excess process, the air conditioner controller 160 identifies the ventilation device 120 and the indoor unit 130 near the target area based on the BLE position information (step S301).

[0057] Next, the air conditioner controller 160 determines whether the operating states of the ventilation device 120 and the indoor unit 130 near the target area are in the operating state (step S302).

[0058] In step S302, when it is determined that the operating states of the ventilation device 120 and the indoor unit 130 are not in the operating state (NO in step S302), the operations of the ventilation device 120 and the indoor unit 130 are turned on, and forced ventilation operation is performed (step S303).

[0059] In step S302, when it is determined that the operating states of the ventilation device 120 and the indoor unit 130 are in the operating state (YES in step S302), the air volume in the target area direction of the ventilation device 120 and the indoor unit 130 is increased (step S304).

[0060] FIG. 9 is a flowchart of the inference process of the air conditioner controller 160 according to Embodiment 1.

[0061] The air conditioner controller 160 determines whether inference start is necessary (step S401). Specifically, the air conditioner controller 160 determines that inference start is necessary when the CO2 concentration information exceeds, for example, an internal lower limit value of 500 ppm. This is because in a low concentration state, there is no need for ventilation, so a certain lower limit value is set, and the inference process is started at the timing when the CO2 concentration information has risen to a certain extent. The internal lower limit value is a value lower than the reference value and the CO2 concentration information threshold value. As input parameters, CO2 concentration information, a CO2 concentration information threshold value, and the number of people in the room are input.

[0062] In step S401, when it is determined that inference start of the CO2 concentration information is not necessary (NO in step S401), the process of FIG. 9 ends.

[0063] In step S401, when it is determined that inference start of the CO2 concentration information is necessary (YES in step S401), the inference process of the CO2 concentration information is performed (step S402). In step S402, the inference process from the input layer I to the output layer O shown in FIG. 5 is performed. Then, the time until the CO2 concentration information exceeds the CO2 concentration information threshold value, that is, the arrival time shown in FIG. 4, is calculated.

[0064] Next, it is determined whether the inference result is expected to exceed the CO2 concentration information threshold (step S403). Here, when the arrival time obtained in step S402 is shorter than the time until the processing of step S401 is next performed, it is determined that it is expected to exceed. That is, it is determined whether the CO2 concentration exceeds the CO2 concentration information threshold earlier than the next timing of the inference process that is periodically performed.

[0065] In step S403, when the inference result is not expected to exceed the CO2 concentration information threshold (NO in step S403), the process of the flowchart of the inference process in FIG. 9 ends.

[0066] In step S403, when the inference result is expected to exceed the CO2 concentration information threshold (YES in step S403), when the forced operation time described in FIG. 4 is reached, the ventilation device 120 and the indoor unit 130 in the target area are forcibly operated (step S404), and the process ends. Specifically, in step S404, when the CO2 concentration information of the target area inferred by the learning model md exceeds the CO2 concentration information threshold, the air conditioner in the target area corresponding to the position indicated by the position information of the CO2 sensor 190 transmitted from the BLE beacon is ventilated. When the ventilation device 120 and the indoor unit 130 are already in the operating state, the air volume of the ventilation device 120 and the indoor unit 130 is increased.

[0067] FIG. 10 is a flowchart of the learning process of the air conditioner controller 160 according to Embodiment 1.

[0068] As shown in FIG. 10, the air conditioner controller 160 periodically determines whether it is the learning start time (step S501). Since the CPU load increases during learning, the air conditioner controller 160 starts at a predetermined time once or twice a day.

[0069] Next, the air conditioner controller 160 performs the learning process from the output layer O to the input layer I described in FIG. 5 for each area (step S502).

[0070] Next, the air conditioner controller 160 updates the parameters, weights, and bias values in the intermediate layers M_1, M_2, and M_3 according to the learning results (step S503). The air conditioner controller 160 performs learning of the learning model md based on the human information and CO2 concentration information stored in the internal non-volatile area 240 which is a storage unit.

[0071] Therefore, according to the air conditioning system 100 of Embodiment 1, when the inferred CO2 concentration information of the target area exceeds the CO2 concentration information threshold value using the learning model md, the air conditioner is operated to perform air conditioning of the target area corresponding to the position indicated by the position information of the CO2 sensor 190 transmitted from the BLE beacon. Thereby, an appropriate air conditioning state along each area can be maintained so that the CO2 concentration state of the target area becomes less than the reference value.

[0072] The embodiments are presented as examples and are not intended to limit the scope of the claims. The embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the embodiments. These embodiments and their modifications are included in the scope and gist of the embodiments.

Description of Reference Numerals

[0073] 100 Air conditioning system, 110 Outdoor unit, 120 Ventilator, 130 Indoor unit, 140 IoT gateway, 150 Human sensor, 160 Air conditioner controller, 170 External memory, 180 Cloud, 190 CO2 sensor, 200 BLE beacon, 210 CO2 information acquisition unit, 220 Data processing unit, 230 Data non-volatile unit, 240 Internal non-volatile area, 250 External non-volatile area, 260 Cloud non-volatile area, 300 BLE sensor information acquisition unit, 310 CO2 data measurement unit, 320 Data transmission / reception unit, I Input phase, O Output layer, M_1, M_2, M_3 Intermediate layers, md Learning model.

Claims

【Claim 1】 An air conditioner which is an indoor air conditioning facility, an air conditioning controller for controlling the air conditioner, a CO2 sensor provided in each of a plurality of target areas for acquiring CO2 concentration information, a BLE beacon for transmitting position information indicating the position of the CO2 sensor, a human presence sensor provided for each of the target areas for detecting human presence information indicating the number and position of people in the target area, a storage unit for storing the current and past CO2 concentration information acquired by the CO2 sensor for each of the target areas and the human presence information detected by the human presence sensor for each of the target areas, comprising, the air conditioner includes a ventilation device for performing ventilation and an indoor unit for supplying conditioned air with temperature or humidity adjusted indoors, the air conditioning controller, comprises a learning model for inferring future CO2 concentration information for each of the target areas from the CO2 concentration information acquired by the CO2 sensor, when the future CO2 concentration information of the target area inferred by the learning model exceeds a threshold value, the air conditioner is operated to perform air conditioning of the target area corresponding to the position indicated by the position information of the CO2 sensor transmitted from the BLE beacon, and learning of the learning model is performed based on the past human presence information and CO2 concentration information stored in the storage unit air conditioning system.

Images