JP7387010B2 - Air conditioning system and air conditioner control method - Google Patents

Description

The present disclosure relates to an air conditioning system that air-conditions a space to be air-conditioned, and a method of controlling an air conditioner.

In recent years, there has been an increasing need to improve the comfort of living environments. The role of air conditioners in maintaining a comfortable thermal sensation for residents is becoming increasingly important. In order to realize comfort, a comfort index called PMV (Predicted Mean Vote) has been proposed. An air conditioning control system that monitors the PMV of a user in an air-conditioned space and controls an air conditioner has been disclosed (for example, see Patent Document 1).

Furthermore, an air conditioner has been proposed that recognizes the shape and size of a living room in which an indoor unit is installed and performs air conditioning according to the condition of the person in the living room (for example, see Patent Document 2). The air conditioner disclosed in Patent Document 2 includes an imaging unit that captures image information of a living room, and an image processing unit that detects the shape and size of the living room based on the image information captured by the imaging unit. In Patent Document 2, even if the image data captured by the imaging unit includes furniture or a partition wall, the image processing unit detects the furniture by the ridge line formed between the furniture or partition wall and the ceiling and wall. It is described that it is possible to identify partition walls.

International Publication No. 2008/087959 Japanese Patent Application Publication No. 2015-161425

The air conditioning control system disclosed in Patent Document 1 performs air conditioning to improve the comfort of users in the room. However, when the layout of the room is changed, such as by moving furniture, the air conditioning system does not maintain the same air condition as before the layout change. If harmonization is performed, user comfort may be reduced. Improving comfort for multiple people becomes even more difficult when there are multiple people in the room.

On the other hand, the air conditioner disclosed in Patent Document 2 recognizes the shape and size of the living room by detecting physical objects such as furniture and partition plates when the layout of the room is changed. The impact on air conditioning cannot be determined. Therefore, if the air conditioner disclosed in Patent Document 2 recognizes physical objects such as furniture and partition plates as obstacles and changes the air conditioning control content, the comfort of the people in the room may be affected. It may be damaged.

The present disclosure has been made to solve the above-mentioned problems, and provides an air conditioning system that can improve the comfort of users in an air-conditioned space even if the layout of the air-conditioned space is changed; A method for controlling an air conditioner is provided.

An air conditioning system according to the present disclosure includes an air conditioner that air-conditions an air conditioned space, a detection unit that detects a heat radiation state and a human condition in the air conditioned space, and a plurality of air conditioners representing different layouts of the air conditioned space. a layout model, a plurality of air conditioning control patterns for each layout model, an application model that is the layout model applied to the air conditioning target space, and an operating state of the air conditioner and the operating state for the application model. a storage device that stores a plurality of learning data in which the heat radiation state corresponding to the above is combined; and combination data of the operating state acquired from the air conditioner and the heat radiation state detected by the detection means; It is determined whether the layout of the air-conditioned space has been changed by comparing the plurality of learning data, and if it is determined that the layout of the air-conditioned space has been changed, the new data corresponding to the combination data is determined. a control device that selects a layout model from the plurality of layout models and obtains an air conditioning control pattern from the plurality of air conditioning control patterns of the new layout model based on the state of the person detected by the detection means; It is something.

A method for controlling an air conditioner according to the present disclosure is a method for controlling an air conditioner using a control device connected to each of a storage device and a detection means for detecting a heat radiation state and a person's state in an air-conditioned space, the method comprising: a plurality of layout models representing different layouts of the air-conditioned space, a plurality of air-conditioning control patterns for each of the layout models, an application model that is the layout model applied to the air-conditioning space, and the application model described above regarding the application model. storing in the storage device a plurality of learning data in which the operating state of the air conditioner and the heat radiation state corresponding to the operating state are combined; and the operating state and the detection acquired from the air conditioner. determining whether the layout of the air-conditioned space has been changed by comparing the combination data of the heat radiation state detected by the means with the plurality of learning data; and the layout of the air-conditioned space has been changed. If it is determined that a new layout model corresponding to the combination data is selected from the plurality of layout models, the person detected by the detection means is selected from the plurality of air conditioning control patterns of the new layout model. and determining an air conditioning control pattern based on the state of the air conditioner.

According to the present disclosure, even if the layout of the air-conditioned space is changed, a layout model that best matches the layout of the air-conditioned space is selected from a plurality of layout models. Then, from the plurality of air conditioning control patterns of the selected layout model, an air conditioning control pattern corresponding to the state of the person in the air conditioning target space is applied to the air conditioner. Therefore, the comfort of the user in the air-conditioned space is improved.

1 is a diagram showing a configuration example of an air conditioning system according to Embodiment 1. FIG. FIG. 2 is a refrigerant circuit diagram showing a configuration example of the air conditioner shown in FIG. 1. FIG. FIG. 3 is a schematic side view showing a configuration example of the load-side unit shown in FIG. 2. FIG. FIG. 4 is a schematic diagram showing the relationship between the angle of the first flap shown in FIG. 3 and the blowing direction of air. FIG. 4 is a schematic diagram showing the relationship between the angle of the second flap shown in FIG. 3 and the blowing direction of air. 3 is a diagram showing an example of a range of inclination angles based on the direction of gravity of the temperature distribution detected by the infrared sensor shown in FIG. 2. FIG. 3 is a diagram showing an example of a horizontal range of temperature distribution detected by the infrared sensor shown in FIG. 2. FIG. FIG. 3 is an image diagram showing an example of a case where the temperature distribution detected by the infrared sensor shown in FIG. 2 is displayed in a two-dimensional thermal image. 3 is a functional block diagram showing an example of the configuration of the control device shown in FIG. 2. FIG. 10 is a hardware configuration diagram showing an example of the configuration of the control device shown in FIG. 9. FIG. 10 is a hardware configuration diagram showing another configuration example of the control device shown in FIG. 9. FIG. 2 is a block diagram showing an example of the configuration of the information processing terminal shown in FIG. 1. FIG. 2 is a functional block diagram showing an example of a configuration of a control device of the information processing device shown in FIG. 1. FIG. FIG. 14 is a functional block diagram showing an example of a configuration of a layout determining section shown in FIG. 13; FIG. 3 is a schematic diagram for explaining the association between a layout model and air conditioning data. 9 is an image diagram showing an example of an analysis result of the thermal image shown in FIG. 8 by a determining means. FIG. 15 is an image diagram showing an example of a reference thermal image used by the determining means shown in FIG. 14 to determine a layout model. FIG. 17 is an image diagram showing an example of a case where the determination means shown in FIG. 14 extracts feature points from the thermal image shown in FIG. 16. FIG. FIG. 15 is a schematic diagram for explaining an example of a case where the shape of the air-conditioned space is detected by the determining means shown in FIG. 14; FIG. 14 is a functional block diagram showing an example of a configuration of a control determining section shown in FIG. 13; It is a table showing an example of a combination describing the type of activity and the energy metabolic rate representing the amount of activity. 14 is a hardware configuration diagram showing an example of the configuration of the arithmetic device shown in FIG. 13. FIG. 2 is a layout diagram showing an example of an air-conditioned space air-conditioned by the air conditioner shown in FIG. 1. FIG. It is a table showing an example of the amount of activity and location of each user. 3 is a flowchart showing an operation procedure of the information processing apparatus according to the first embodiment. 3 is a flowchart showing an operation procedure of the information processing apparatus according to the first embodiment. 24 is an image diagram showing an example of the indoor thermal image shown in FIG. 23. FIG. 28 is an image diagram showing an example of an analysis result of the thermal image shown in FIG. 27 by a determining means. FIG. 29 is an image diagram showing an example of a case where the determining means shown in FIG. 14 extracts feature points from the thermal image shown in FIG. 28. FIG. FIG. 27 is a schematic diagram showing the operation procedure after step S111 shown in FIG. 26 of the information processing apparatus according to the first embodiment. It is a table showing an example of calculation results of comfort efficiency. It is an image diagram showing an example of IPMV distribution in the case of the air conditioning control pattern determined in step S113. FIG. 7 is an image diagram showing another example of the IPMV distribution in the case of the air conditioning control pattern determined in step S113. 7 is a diagram illustrating a configuration example of an air conditioning system according to modification 1. FIG.

Embodiments of the present disclosure will be described in detail using the drawings. The various specific setting examples described in this embodiment are merely examples, and the present invention is not limited to the described setting examples. Furthermore, in the embodiments of the present disclosure, communication means either or both of wireless communication and wired communication. In this embodiment, the communication may be a communication method that includes a mixture of wireless communication and wired communication. The communication method may be, for example, one in which wireless communication is performed in a certain section and wired communication is performed in another space. Further, communication from one device to another device may be performed by wired communication, and communication from another device to a certain device may be performed by wireless communication.

Embodiment 1.
The configuration of the air conditioning system 1 according to the first embodiment will be explained. FIG. 1 is a diagram illustrating a configuration example of an air conditioning system according to a first embodiment. As shown in FIG. 1, the air conditioning system includes an air conditioner 10 that conditions the air in a room that is a space to be air-conditioned, a detection means 30 that detects the state of heat radiation in the room and the state of people in the room, and It has an information processing device 2 that is communicatively connected to the harmonization device 10 and the detection means 30. The detection means 30 detects the amount of activity and position of a user in the room as the state of the person in the room. The detection means 30 shown in FIG. 1 includes a heat detection means 31 that detects the position and amount of activity of a user indoors, and the state of heat radiation in the room.

The air conditioner 10 and the detection means 30 are communicatively connected to the information processing device 2 via the network 50. Further, an information processing terminal 40 of a user of the air conditioner 10 is connected to the network 50. Network 50 is, for example, the Internet.

The configuration of the air conditioner 10 shown in FIG. 1 will be explained. FIG. 2 is a refrigerant circuit diagram showing an example of the configuration of the air conditioner shown in FIG. The air conditioner 10 includes a heat source side unit 104 that generates a heat source, and a load side unit 103 that adjusts indoor air using the heat source generated by the heat source side unit 104. The heat source side unit 104 includes a compressor 119, a heat source side heat exchanger 116, an expansion valve 117, an air blower 114, and a four-way valve 118. The load side unit 103 includes a load side heat exchanger 115, an air blower 113, an air direction adjustment section 105, and a control device 130.

The air direction adjustment section 105 has a first flap 4 and a second flap 5 that adjust the direction of air blown out from the load side unit 103. The load side unit 103 is provided with an environment detection section 120. The environment detection unit 120 includes a room temperature sensor 121 that detects the temperature of the indoor air, a humidity sensor 122 that detects the humidity of the indoor air, and a temperature sensor that detects the temperature Tb of the air blown into the room from the load side unit 103. It has a sensor 123. Further, the load side unit 103 is provided with an infrared sensor 140 that detects the temperature distribution in the indoor space. The infrared sensor 140 functions as the detection means 30 shown in FIG.

A compressor 119, a heat source side heat exchanger 116, an expansion valve 117, and a load side heat exchanger 115 are connected by a refrigerant pipe 110, and a refrigerant circuit 102 in which refrigerant circulates is configured. The compressor 119, the expansion valve 117, the blower 114, the four-way valve 118, and the air direction adjustment section 105 are communicatively connected to the control device 130. The environment detection unit 120 and the infrared sensor 140 are communicatively connected to the control device 130.

The compressor 119 compresses the refrigerant it takes in and discharges it. The compressor 119 is, for example, an inverter type compressor whose capacity can be changed. The four-way valve 118 changes the flow direction of the refrigerant flowing through the refrigerant circuit 102. The expansion valve 117 reduces the pressure of the refrigerant and expands it. The expansion valve 117 is, for example, an electronic expansion valve. The heat source side heat exchanger 116 is a heat exchanger that exchanges heat between the refrigerant and the outside air. The load-side heat exchanger 115 is a heat exchanger that exchanges heat between the refrigerant and indoor air. The heat source side heat exchanger 116 and the load side heat exchanger 115 are, for example, fin tube type heat exchangers.

A heat pump is formed by circulating the refrigerant through the refrigerant circuit 102 while repeating compression and expansion. The load-side unit 103 adjusts the indoor air by performing operations such as cooling, heating, dehumidification, humidification, moisturizing, and blowing air. Although FIG. 2 shows a case where the control device 130 is provided in the load-side unit 103, the installation position of the control device 130 is not limited to the load-side unit 103. The control device 130 may be provided in the heat source side unit 104 or may be provided in a position other than both the load side unit 103 and the heat source side unit 104. Furthermore, the air conditioner 10 may be provided with a temperature sensor (not shown) that detects the condensation temperature and the evaporation temperature.

FIG. 3 is a schematic side view showing a configuration example of the load-side unit shown in FIG. 2. FIG. The load side unit 103 is embedded in the ceiling 75. When the blower 113 rotates, an air current is formed in the load side unit 103 in which air flows in the direction indicated by the broken line arrow, and the air is blown into the room through the air outlet 6. The air outlet 6 is provided with a first flap 4 and a second flap 5. The second flap 5 has a front blade 5a and a rear blade 5b.

FIG. 4 is a schematic diagram showing the relationship between the angle of the first flap shown in FIG. 3 and the blowing direction of air. As shown in FIG. 4, the first flap 4 has blades 4a to 4d. For the sake of explanation, FIG. 4 shows the blades 4a to 4d that are seen through when the load side unit 103 is looked down from above. The angle of the blades 4a to 4d of the first flap 4 is expressed as θh, and the front direction of the load side unit 103 (opposite direction to the X-axis arrow) is set to a horizontal reference θh0=0°. In FIG. 4, the air blowing direction ad1 when the horizontal direction angle θh1 is shown by a broken line arrow, and the air blowing direction ad2 when the horizontal direction angle θh2 is shown by a solid line arrow.

FIG. 5 is a schematic diagram showing the relationship between the angle of the second flap shown in FIG. 3 and the air blowing direction. In FIG. 5, for the sake of explanation, the front blade 5a of the second flap 5 shown in FIG. 3 is shown in an enlarged manner, and the rear blade 5b is not shown. The angle of the front blade 5a is expressed as θv, with the direction of gravity of the load side unit 103 (opposite direction of the Z-axis arrow) being a vertical reference Vax. In FIG. 5, a solid line arrow indicates the air blowing direction ad3 when the angle is θv1 with respect to the direction of gravity, and a broken line arrow indicates the air blowing direction ad4 when the angle is θv2 in the gravity direction.

In the first embodiment, the case where the load-side unit 103 is a type embedded in the ceiling has been described, but it is not limited to the type embedded in the ceiling. , may be of other types. Further, the configuration of the load side unit 103 shown in FIG. 3 is an example, and the configuration is not limited to that shown in FIG. 3. The arrangement of the load-side heat exchanger 115 and the blower 113 is not limited to the configuration shown in FIG. 3.

Furthermore, the configuration for adjusting the direction of air blown out from the load-side unit 103 is not limited to the wind direction adjustment section 105 described with reference to FIGS. 3 to 5. The wind direction adjustment unit 105 has two types of vanes: a first flap 4 that adjusts the angle in the horizontal direction and a second flap 5 that adjusts the angle of inclination with respect to the direction of gravity. A configuration may be adopted in which one type of vane is provided that can adjust the angle in any direction among the directions in which the angle is combined. Further, the means for adjusting the blowing direction of the air blown out from the load-side unit 103 is not limited to means such as the wind direction adjustment section 105, but may be a means for changing the direction of the air outlet itself. For example, it is possible to consider means for changing the horizontal angle of the air outlet and the inclination angle with respect to the direction of gravity.

FIG. 6 is a diagram showing an example of the range of inclination angles of the temperature distribution detected by the infrared sensor shown in FIG. 2 with respect to the direction of gravity. Similarly to FIG. 5, the inclination angle with respect to the vertical reference Vax is assumed to be θv. FIG. 7 is a diagram showing an example of a horizontal range of temperature distribution detected by the infrared sensor shown in FIG. Similarly to FIG. 4, the horizontal angle with respect to the horizontal reference θh0 is assumed to be θh. As shown in FIGS. 6 and 7, the infrared sensor 140 has a certain range of inclination angle θv with respect to the direction of gravity and a horizontal The indoor temperature distribution within a certain range of the direction angle θh is measured.

FIG. 8 is an image diagram showing an example of a case where the temperature distribution detected by the infrared sensor shown in FIG. 2 is displayed in a two-dimensional thermal image. For the sake of explanation, in FIG. 8, the boundaries between each of the walls, floor, and ceiling and other parts are shown with broken lines. In general, the materials of walls, floors, and ceilings have different thermal conductivities, so in a two-dimensional thermal image showing temperature distribution, the temperatures of walls, floors, and ceilings are different from each other, making it difficult to detect each boundary. can.

In the thermal image Img1 shown in FIG. 8, the higher the density of the pattern, the higher the temperature. Warm air tends to stay on the side closer to the ceiling than on the floor FL, so the density of the pattern is higher on the ceiling side than on the floor FL. Since the temperature of the floor surface FL is low, no pattern is displayed. Referring to the thermal image Img1 shown in FIG. 8, when there is a person in the room, the surface temperature of the human body is different from the temperature of the floor surface FL and the wall, so the thermal image shown in FIG. 8 is analyzed to detect the position of the human body. I know what I can do. Moreover, by analyzing the thermal image shown in FIG. 8 and comparing the surface temperatures of user MA and user MB, the amount of activity of each user can be estimated.

Further, the thermal image Img1 shown in FIG. 8 shows that not only the window 302 but also furniture such as the display cabinet 301, the sofas 303 and 304, and the piano 305 can be detected from the relative value of thermal radiation.

FIG. 9 is a functional block diagram showing an example of the configuration of the control device shown in FIG. 2. As shown in FIG. Control device 130 is, for example, a microcomputer. The control device 130 includes a refrigeration cycle control means 131 and a communication means 132. Various functions of the control device 130 are realized by a calculation device such as a microcomputer executing software. Further, the control device 130 may be configured with hardware such as a circuit device that implements various functions.

The refrigeration cycle control means 131 controls the four-way valve 118 in response to the cooling, heating, dehumidifying, humidifying, moisturizing, and ventilation operations of the load-side unit 103. The refrigeration cycle control means 131 controls the refrigeration cycle of the refrigerant circuit 102 based on the room temperature and the set temperature, and the humidity and the set humidity. For example, the refrigeration cycle control means 131 controls the operating frequency of the compressor 119 and the opening of the expansion valve 117 so that the room temperature matches the set temperature within a certain range and the indoor humidity matches the set humidity within a certain range. The rotational speed of blowers 113 and 114 is controlled. The wind speed W of the airflow generated by the blower 113 can be selected from, for example, three levels: high, medium, and low. The set temperature and set humidity are set by the user in the control device 130 via a remote controller (not shown).

Furthermore, the refrigeration cycle control means 131 transmits environmental information, which is information indicating the environment such as indoor heat, and operating information, which is information indicating the operating state of the air conditioner 10, to the communication means 132. The environmental information includes room temperature detected by room temperature sensor 121, humidity detected by humidity sensor 122, and two-dimensional thermal image data indicating indoor temperature distribution detected by infrared sensor 140. The operation information includes, for example, information on the frequency of the compressor 119, the condensing temperature, the evaporation temperature, and the opening degree of the expansion valve 117. The operation information may include airflow information including the temperature Tb detected by the temperature sensor 123, the horizontal angle θh of the first flap 4, the inclination angle θv of the second flap 5, and the wind speed W. . The operating information may include information on the operating mode that the air conditioner 10 is currently executing. The types of operation modes are heating operation, cooling operation, ventilation operation, and defrosting operation.

Furthermore, upon receiving the information on the air conditioning control pattern from the communication means 132, the refrigeration cycle control means 131 controls the wind direction adjustment unit 105 and the blower 113 in accordance with the air conditioning control pattern. Specifically, the refrigeration cycle control means 131 adjusts the blowing temperature, wind speed, and wind direction in accordance with the air conditioning control pattern.

The air conditioning control pattern is based on, for example, the temperature Tb that is the detected value of the temperature sensor 123, the horizontal angle θh of the first flap 4, the inclination angle θv of the second flap 5, and the air blown out from the load side unit 103. This is a combination of wind speed W and four control parameters. The plurality of air conditioning control patterns are patterns in which at least one control parameter among these four control parameters is combined to be different from each other. Specific examples of the plurality of air conditioning control patterns will be explained later.

The communication means 132 transmits the environmental information and operation information received from the refrigeration cycle control means 131 to the information processing device 2 . Upon receiving the information on the air conditioning control pattern from the information processing device 2, the communication means 132 transmits the received information on the air conditioning control pattern to the refrigeration cycle control means 131. The communication means 132 transmits and receives information to and from the information processing device 2 according to, for example, TCP/IP (Transmission Control Protocol/Internet Protocol).

Here, an example of the hardware of the control device 130 shown in FIG. 9 will be explained. FIG. 10 is a hardware configuration diagram showing an example of the configuration of the control device shown in FIG. When various functions of the control device 130 are executed by hardware, the control device 130 shown in FIG. 9 is configured with a processing circuit 80, as shown in FIG. Each function of the refrigeration cycle control means 131 and the communication means 132 shown in FIG. 9 is realized by the processing circuit 80.

When each function is executed by hardware, the processing circuit 80 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), or an FPGA (Field-Programmable Gate). Array) or a combination of these. Each of the functions of the refrigeration cycle control means 131 and the communication means 132 may be realized by the processing circuit 80. Furthermore, the functions of the refrigeration cycle control means 131 and the communication means 132 may be realized by one processing circuit 80.

Further, another example of hardware of the control device 130 shown in FIG. 9 will be explained. FIG. 11 is a hardware configuration diagram showing another example of the configuration of the control device shown in FIG. 9. When various functions of the control device 130 are executed by software, the control device 130 shown in FIG. 9 is configured with a processor 81 such as a CPU (Central Processing Unit) and a memory 82, as shown in FIG. 11. Each function of the refrigeration cycle control means 131 and the communication means 132 is realized by the processor 81 and the memory 82. FIG. 11 shows that processor 81 and memory 82 are communicably connected to each other via bus 83.

When each function is executed by software, the functions of the refrigeration cycle control means 131 and the communication means 132 are realized by software, firmware, or a combination of software and firmware. Software and firmware are written as programs and stored in memory 82. The processor 81 realizes the functions of each means by reading and executing programs stored in the memory 82.

Examples of the memory 82 include ROM (Read Only Memory), flash memory, EPROM (Erasable and Programmable ROM), and EEPROM (Electrically Erasable and Programmable ROM). Non-volatile semiconductor memory is used. Further, as the memory 82, a volatile semiconductor memory such as RAM (Random Access Memory) may be used. Further, as the memory 82, a removable recording medium such as a magnetic disk, a flexible disk, an optical disk, a CD (Compact Disc), an MD (Mini Disc), and a DVD (Digital Versatile Disc) may be used.

Next, the configuration of the information processing terminal 40 used by the user of the air conditioner 10 will be described. FIG. 12 is a block diagram showing an example of the configuration of the information processing terminal shown in FIG. The information processing terminal 40 is, for example, a mobile terminal such as a smartphone and a PDA (Personal Digital Assistant). The information processing terminal 40 includes a terminal control section 41 , a storage section 42 , an input section 43 , a display section 44 , and a wireless communication section 45 .

The storage unit 42 is, for example, a nonvolatile memory such as a flash memory. The input unit 43 is, for example, a touch panel. The display unit 44 is, for example, a liquid crystal display device. The wireless communication unit 45 is connected to the network 50 via a wireless base station (not shown). The terminal control unit 41 includes a memory 412 that stores programs, and a CPU 411 that executes processing according to the programs.

Next, before explaining the configuration of the information processing device 2 shown in FIG. 1, a comfort index used by the information processing device 2 when determining an air conditioning control pattern to be executed by the air conditioner 10 will be explained. First, PMV, which is a type of comfort index, will be explained.

For people, fatigue during work and the feeling of ease of work are comprised of physical environmental factors such as the thermal environment, visual environment, and sound environment surrounding the person. The thermal environment is, for example, temperature, humidity, airflow, and radiation. The visual environment is, for example, illuminance. The sound environment is, for example, sound pressure. A complex environment, which is a combination of these environmental factors, affects the sense of suitability for work and the feeling of fatigue of people working in that environment.

PMV is a value proposed by Professor Fanger of the Technical University of Denmark as an index for numerically evaluating a person's comfort level and thermal sensation in a thermal environment. PMV was standardized internationally as ISO-7730 in 1984. PMV is a combination of heat load on the human body and human thermal sensation. Specifically, in PMV, a heat balance equation for the human body is established by elements on the air environment side and the human body side, and in that heat balance equation, the amount of heat dissipated by skin temperature and sweat when a person feels comfortable is calculated. It is calculated by substituting the formula. Elements on the air environment side include not only air temperature, but also elements such as radiant temperature, radiant temperature, humidity, and airflow. The factors on the human body side include factors such as the amount of human activity, amount of clothing, and average skin temperature.

The amount of activity is an example of a person's biological information, and is expressed in a unit indicating exercise intensity called MET (Metabolic Equivalent). Various movements have been quantified using MET. For example, the exercise intensity when a person is sitting quietly and watching television is defined as 1 MET.

In the first embodiment, a case will be described in which the comfort index is IPMV (Individual PMV), which is an individual comfort index. The IPMV value is a value based on PMV, but it is not the average value of the thermal sensation of the entire air-conditioned space, but indicates the local thermal sensation that is the thermal sensation of the specified position by specifying the position where a person is present. It is a value. Local thermal sensation is sometimes referred to as local comfort level.

The eight variables in equation (1) will be explained. M is metabolic rate [W/m ² ], and W is mechanical work rate [W/m ² ]. Ed is the amount of insensible evaporation [W/m ² ], and Es is the amount of heat loss due to sweat evaporation from the skin surface [W/m ² ]. Ere is the amount of latent heat loss due to respiration [W/m ² ], and Cre is the amount of sensible heat loss due to respiration [W/m ² ]. R is the amount of radiant heat loss [W/m ² ], and C is the amount of convective heat loss [W/m ² ].

As shown in equation (1), IPMV is a numerical representation of a person's thermal sensation based on temperature, humidity, radiant temperature, and the like. The range of IPMV is -3 to +3. When IPMV=0, it is considered neutral. When IPMV=0, it is defined as comfortable. It is defined as hot when IPMV=3, warm when IPMV value=2, and slightly warm when IPMV=1. It is defined as cold when IPMV=-3, cool when IPMV=-2, and slightly cool when IPMV=-1. In other words, it is defined that the closer IPMV is to 0, the more comfortable a person is.

Next, the configuration of the information processing device 2 shown in FIG. 1 will be explained. FIG. 13 is a functional block diagram showing a configuration example of a control device of the information processing apparatus shown in FIG. 1. As shown in FIG. The information processing device 2 is, for example, a server device. The information processing device 2 determines an optimal air conditioning control pattern based on the storage device 21 that stores the IPMV database 212, the layout of the room, and the amount of activity, position, and comfort index of multiple users in the room. and a control device 22 provided to the harmonization device 10.

The storage device 21 is, for example, an HDD (Hard Disk Drive). The control device 22 is, for example, a microcomputer. Various functions of the control device 22 are realized by an arithmetic circuit such as a microcomputer executing software. This software has written procedures shown in flowcharts (FIGS. 25 and 26) that will be explained later.

The storage device 21 stores a layout model database 211 in which data related to a plurality of indoor layout models is stored, and an IPMV database 212 in which data related to IPMV is stored. The layout model is a virtual model showing the layout of the room shape, furniture arrangement, etc. that affects the air conditioning performed by the air conditioner 10. In the first embodiment, a plurality of layout models are assumed based on a combination of a plurality of shapes of a room that is a space to be air-conditioned by the air conditioner 10 and a plurality of arrangements of one or more pieces of furniture in the room. has been done. The layout model database 211 stores, for each layout model, air conditioning data indicating feature points of the layout model and relational information that associates the layout model with the air conditioning data. The air conditioning data is learning data or teacher data. Each of the learning data and the teacher data has combination data of information on the operating state of the air conditioner 10 and data on a thermal image indicating the heat radiation state of the room.

The IPMV database 212 stores an IPMV (comfort index) model for each layout model. In the IPMV model, a group including a comfort index distribution, which is a distribution of comfort indexes indicating a user's comfort level indoors, corresponding to each of a plurality of air conditioning control patterns of the air conditioner 10, is divided into groups for each of a plurality of activity levels. It is classified and stored. The storage device 21 also stores a standard three-dimensional fluid model (not shown) for generating the IPMV database 212.

The control device 22 includes a data acquisition means 11 , a layout determination section 12 , and a control determination section 13 . The data acquisition means 11 causes the storage device 21 to store environmental information and operating information received from the air conditioner 10 at regular intervals. The data acquisition means 11 stores information received from the air conditioner 10 at regular intervals in a chronological order in the storage device 21, and monitors the operating state of the air conditioner 10.

FIG. 14 is a functional block diagram showing an example of the configuration of the layout determining section shown in FIG. 13. The layout determining section 12 includes a determining means 251, a layout selecting means 252, and a learning means 253.

The determining means 251 acquires driving state information from the driving information stored in the storage device 21. Further, the determining means 251 reads data of a two-dimensional thermal image from the environmental information stored in the storage device 21, and generates an indoor thermal image showing a heat radiation state by removing the human part from the thermal image. Then, the determining means 251 compares the combined data of the operating state and the heat radiation state based on the indoor thermal image with a plurality of learning data of the applied model, and determines whether there is learning data that matches the combined data. . The applied model is a layout model that has been applied as a layout model that best matches the current room layout among a plurality of layout models. The determining means 251 determines that the layout of the room has not been changed when there is learning data that matches the combination data, and determines that the layout of the room has been changed when there is no learning data that matches the combination data.

For example, the determining means 251 extracts feature points from the indoor thermal image, and determines whether the amount of coincidence between the extracted feature points and the feature points indicated by the learning data corresponding to the current driving state is greater than or equal to a predetermined threshold. Determine whether or not. As a result of the determination, if the matching amount is equal to or greater than the threshold, the determining means 251 determines that the current room layout is compatible with the applied model. On the other hand, if the matching amount is smaller than the threshold, the determining means 251 determines that the current room layout does not conform to the applied model and that the room layout has been changed. The threshold value is stored in the storage device 21.

In the first embodiment, the determining means 251 determines whether the layout model is determined to have been changed. For example, even if one chair among a plurality of chairs placed at the dining table is moved, the flow of air blown out from the air conditioner 10 is not significantly affected. Therefore, the determining means 251 does not determine that the layout model has been changed in such a movement of furniture.

Further, the determining means 251 may inquire of the user whether the layout has been changed. Specifically, the determination means 251 compares the combination data with a plurality of learning data of the applied model, and if there is no learning data that matches the combination data, the determination means 251 determines whether the layout of the room has been changed in the information processing terminal 40. Send an inquiry message containing information about the inquiry. Then, when receiving a reply message including information indicating that the layout of the room has been changed from the information processing terminal 40, the determining means 251 determines that the layout of the room has been changed. On the other hand, when receiving a reply message from the information processing terminal 40 that includes information indicating that the layout of the room has not been changed, the determining means 251 determines that the layout of the room has not been changed.

When the determination means 251 determines that the layout of the room has been changed, the layout selection means 252 selects a new layout model corresponding to the combination data from among the plurality of layout models, and updates the new layout model to the next applied model. . Specifically, the layout selection means 252 selects, as the new layout model, the layout model that maximizes the amount of coincidence between the feature points extracted from the thermal image by the determination means 251 and the feature points indicated by the air conditioning data. Moreover, when the determining means 251 determines that the layout of the room has not been changed, the layout selecting means 252 maintains the selected layout model as the current applied model.

The learning means 253 combines thermal image data indicating the heat radiation state of the applied model selected by the layout selection means 252 and information on the operating state of the air conditioner 10, and stores the combined data in the storage device 21 as learning data. The thermal image data stored as learning data in the storage device 21 may be image data processed by the determining means 251. A specific example of this case will be explained later.

FIG. 15 is a schematic diagram for explaining the association between a layout model and air conditioning data. As shown in FIG. 15, different identifiers are assigned to the relationship information for each layout model. LMD1 to LMD3 are layout model identifiers. In the related information, in correspondence with the layout model identifier, information as to whether the model is an applicable model, an air conditioning data identifier, and an IPMV model identifier are registered. ACD1 to ACD3 are identifiers of air conditioning data. A plurality of learning data or teacher data is stored in the layout model database 211 shown in FIG. 14 in association with the identifier of the air conditioning data. Teacher data is associated with layout models that are not adopted as applied models.

FIG. 15 shows that the layout model with the layout model identifier LMD1 is the applied model. For the layout model with the layout model identifier LMD1, a plurality of pieces of learning data identified by the air conditioning data identifier ACD1 are stored in the layout model database 211 shown in FIG. The plurality of learning data are, for example, thermal image data during cooling operation and thermal image data during heating operation. Each learning data includes thermal image data and driving state information.

For example, when the layout model of the layout model identifier LMD2 is a rectangular room with no furniture, the training data of the identifier ACD2 is thermal image data when heating is performed at a predetermined set temperature, air volume, and direction. It is. Here, a case is shown in which there is one training data for a layout model that is not adopted as an applied model, but there may be a plurality of training data. When the layout model with the layout model identifier LMD2 becomes the applied model, learning data is accumulated as the air conditioning data specified by the identifier ACD2.

Here, a method for extracting feature points from a thermal image by the determining means 251 will be specifically explained with reference to FIGS. 8, 16, and 17. FIG. 16 is an image diagram showing an example of an analysis result by the determination means for the thermal image shown in FIG. 8.

The determining means 251 specifies the position and shape of the person from the relative value of thermal radiation in the room by analyzing the data of the two-dimensional thermal image shown in FIG. Then, as shown in FIG. 16, the determining means 251 generates an indoor thermal image Img1a showing a heat radiation state by removing the human part from the two-dimensional thermal image shown in FIG. FIG. 16 shows a state in which users MA and MB have been removed from the thermal image Img1 shown in FIG.

FIG. 17 is an image diagram showing an example of a reference thermal image used by the determining means shown in FIG. 14 to determine the layout model. The storage device 21 stores data of a reference thermal image Img0 shown in FIG. 17. The reference thermal image Img0 shown in FIG. 17 is a thermal image of a layout model in which no furniture is placed in a rectangular room.

FIG. 18 is an image diagram showing an example in which the determination means shown in FIG. 14 extracts feature points from the thermal image shown in FIG. 16. The determining means 251 compares the indoor thermal image Img1a shown in FIG. 16 with the reference thermal image Img0 shown in FIG. 17, and generates the feature extraction image Img1b shown in FIG. 18. The determining means 251 detects the edges of the window 302 and the decorative shelf 301 from the indoor thermal image Img1a as causes of disturbing the heat radiation state in the room, and extracts the detected edges as feature points. Since the temperature of the window 302 is closer to the outside air temperature than the room temperature, the edge of the window 302 is easily detected, and the temperature around the window 302 is lower than that of the wall. Since the display shelf 301 obstructs the flow of air blown out from the air conditioner 10, the temperature around the display shelf 301 is lower than that of the wall, so the edge of the display shelf 301 is also easily detected. Further, the determining means 251 detects the edges of the sofas 303 and 304 installed in the room and the edge of the piano 305 from the indoor thermal image Img1a, and extracts the detected edges as feature points.

The window 302 and the display shelf 301 have a greater influence on the air conditioning by the air conditioner 10 than the piano 305 and the sofas 303 and 304. Therefore, the determining means 251 adds information in which the feature amounts of the feature points of the window 302 and the display shelf 301 are larger than the feature amounts of the feature points of the piano 305, sofas 303, and 304 to the feature extraction image Img1b. The determining means 251 may leave information indicating a disturbance in the heat radiation state in the feature extraction image 1mg1b. FIG. 18 shows a case where information that the heat radiation state is disturbed by the window 302 and the display shelf 301 is left.

The learning means 253 stores the feature extraction image Img1b shown in FIG. 18 in the storage device 21 as learning data, but may also store the indoor thermal image Img1a shown in FIG. 16 in the storage device 21.

Further, a case where the determining means 251 specifies the shape of a room will be described with reference to FIG. 19. FIG. 19 is a schematic diagram for explaining an example in which the shape of the air-conditioned space is detected by the determining means shown in FIG. 14. The determination means 251 uses thermal image data obtained when hot air is blown at the same air volume both in the diagonal right direction and in the diagonal left direction with respect to the load side unit 103 installed on the wall WAL 4 as environmental information, and uses the air conditioner as environmental information. 10, the thermal image is analyzed. As a result of the analysis, if the determination means 251 determines that the temperature of the wall WAL2 is higher than the wall WAL1 and that there is no furniture that obstructs the airflow between the load side unit 103 and the wall WAL1, the shape of the room is changed. It is determined to be L-shaped. In other words, the determining means 251 determines that the room in the air-conditioned space is a room in which the distance L1 from the wall WAL4 to the wall WAL2 is shorter than the distance L2 from the wall WAL4 to the wall WAL1, with the detected wall WAL3 as the boundary. . In this way, the determining means 251 can determine not only the furniture installed in the room of the air-conditioned space but also the shape of the room.

Next, the configuration of the control determining section 13 shown in FIG. 13 will be explained. FIG. 20 is a functional block diagram showing a configuration example of the control determining section shown in FIG. 13. The control determining unit 13 includes a model generating means 201 , an activity amount determining means 202 , a position determining means 203 , an efficiency calculating means 204 , and a control determining means 205 .

The model generating means 201 reads environmental information and driving information from the storage device 21, reflects the read information on a standard three-dimensional fluid model, and generates an IPMV database 212. The activity amount determining means 202 estimates the amount of activity from the surface temperature of each user indoors by analyzing the two-dimensional thermal image stored in the storage device 21. Then, the activity amount determination unit 202 refers to the IPMV model selected by the layout determination unit 12 from the IPMV database 212 and identifies, for each user, a group corresponding to the amount of activity detected by the infrared sensor 140.

The position determining means 203 estimates the position of each user in the room by analyzing the latest two-dimensional thermal image stored in the storage device 21. The user's position is a position expressed by the horizontal angle θh of the thermal image and the inclination angle θv with respect to the direction of gravity with respect to the load-side unit 103. The position determining means 203 extracts, for each user, a plurality of comfort indexes corresponding to the position estimated from the thermal image from the plurality of comfort index distributions within the group specified by the activity amount determining means 202. The efficiency calculating means 204 calculates comfort efficiency ζ indicating the overall comfort level of the plurality of users for each of the plurality of air conditioning control patterns, using the plurality of comfort indices extracted corresponding to the positions of each user. . The control determining means 205 determines an air conditioning control pattern that maximizes the calculated comfort efficiency ζ from among the plurality of air conditioning control patterns. The control determining means 205 transmits the obtained air conditioning control pattern to the air conditioner 10.

The control determining unit 13 transmits to the air conditioner 10 an air conditioning control pattern that changes the wind direction, air volume, etc. so that the IPMV at the user's location approaches neutrality. The control determining unit 13 does not attempt to neutralize the PMV in all areas of the room, but instead determines an air conditioning control pattern so that the IPMV in the position where the user is present approaches neutrality, and air-conditions the IPMV in the position where the user is not present. Do not include it as a determining element of the control pattern. Among the various means of the control determining section 13 shown in FIG. 20, the configurations of the model generating means 201 and the efficiency calculating means 204 will be described in detail.

The configuration of the model generation means 201 shown in FIG. 20 will be explained. The values of the eight variables in Equation (1) can be derived from six values: room temperature, wind speed, radiant temperature, and humidity, and the amount of clothing and activity of the user. In IPMV, room temperature, wind speed, and radiant temperature are values that correspond to the user's position. Therefore, here, room temperature is defined as local temperature, wind speed is defined as local wind speed, and radiant temperature is defined as local radiant temperature. The method by which the model generation means 201 obtains these six values will be explained below.

As the local temperature, the model generation means 201 uses CFD (Computational Fluid Dynamics), which is an example of computational fluid analysis, to simulate the temperature distribution of the air conditioning target space in accordance with the air conditioning control pattern, and calculates a specific position from the temperature distribution. Estimate the temperature of Humidity is detected by humidity sensor 122. The model generating means 201 acquires humidity information from the operating information stored in the storage device 21. As the local wind speed, the model generation means 201 estimates the wind speed at a specific position from the wind speed of the entire air in the air-conditioned space in the CFD analysis result. It is assumed that the local radiation temperature is equivalent to room temperature. Therefore, the model generating means 201 acquires the detected value of the room temperature sensor 121 from the operating information stored in the storage device 21.

As the amount of clothing, the model generating means 201 estimates a clo value representing the thermal resistance of clothing using data of a two-dimensional thermal image received from the air conditioner 10. Specifically, the model generation unit 201 estimates the skin temperature, the amount of skin exposure, and the surface temperature of clothing for each detected user from the two-dimensional thermal image data. Then, the model generating means 201 refers to a claw value table that associates skin temperature, amount of skin exposure, and clothing surface temperature with clo values, and obtains the clo value of each user. The storage device 21 stores a claw value table. As the amount of activity, the model generation means 201 estimates the MET of each user from the two-dimensional thermal image data received from the air conditioner 10. For example, the storage device 21 stores in advance a MET table in which infrared detection values of two-dimensional thermal image data are associated with METs. The model generation means 201 refers to the MET table and reads out the MET corresponding to the infrared detection value of each user.

The model generation means 201 uses CFD as computational fluid analysis to generate an IPMV model for each layout model for the air-conditioned space for each amount of activity independent of the position of the person, corresponding to a plurality of air conditioning control patterns. The created IPMV database 212 is stored in the storage device 21. For a layout model without learning data, the model generation unit 201 applies CFD to the teacher data, simulates the temperature distribution of the air-conditioned space in accordance with the air-conditioning control pattern, and generates an IPMV model. When a layout model without learning data becomes an applied model, the model generation unit 201 updates the IPMV model using the learning data accumulated in the layout model database 211.

FIG. 21 is a table showing an example of a combination of the type of activity and the energy metabolic rate representing the amount of activity. The energy metabolic rate is calculated using equation (2). Referring to FIG. 21, for example, the amount of activity of a sleeping person is 0.7 MET, and the amount of activity of a person sitting at rest is 1 MET.

An example of CFD calculation processing by the model generation means 201 will be explained. First, the model generation unit 201 creates a three-dimensional model of an air-conditioned space to be simulated using a standard three-dimensional fluid model. Subsequently, the model generating means 201 divides the modeled air-conditioned space into, for example, a grid pattern. Then, the model generation means 201 applies boundary conditions to the results of thermal calculation corresponding to the pressure, temperature, velocity of the fluid, heating elements existing in the space, and heat intrusion from the walls for each rectangular region between the grids. Give the necessary initial conditions as . Furthermore, the model generation means 201 analyzes the pressure, air volume, temperature, etc. in each rectangular area based on boundary conditions such as heat intrusion from the wall and internal heat generation using a predetermined turbulence model and difference scheme. .

In the first embodiment, IPMV is calculated corresponding to each of the plurality of air conditioning control patterns. The plurality of air conditioning control patterns include, for example, three patterns regarding the angle θh of the first flap 4, three patterns regarding the angle θv of the second flap 5, three patterns regarding the wind speed W, and three patterns regarding the temperature Tb. There are 81 combinations. That is, in the first embodiment, there are 3×3×3×3=81 air conditioning control patterns.

The horizontal angle θh of the first flap 4 has three patterns: 30° leftward (in the direction of the X-axis arrow in FIG. 4), 0°, and 30° rightward (in the direction opposite to the X-axis arrow in FIG. 4). The inclination angle θv of the second flap 5 has three patterns: θv=20°, 45°, and 60°. The wind speed W has three patterns: high, medium, and low. The temperature Tb of the air blown out from the load-side unit 103 has three patterns: high, medium, and low.

The model generating means 201 performs CFD analysis on 81 air conditioning control patterns for each activity level such as 1MET and 2MET for the entire air-conditioned space, regardless of the position of the air-conditioned space, and calculates the IPMV in the air-conditioned space. An IPMV distribution is generated. In the IPMV distribution, the air-conditioned space is divided into a plurality of rectangular areas by CFD analysis, and the IPMV is stored in the storage device 21 corresponding to each rectangular area. For example, the model generating means 201 generates 81 IPMV distributions for the activity amount of 1 MET and forms one group, and generates 81 IPMV distributions for the activity amount of 2 METs and forms another group. In this way, the model generation means 201 generates groups corresponding to each of the plurality of activity amounts, and stores the plurality of groups in the storage device 21 as an IPMV database. In the first embodiment, a case will be described in which the amount of activity is changed at intervals of 1 MET, 2 MET, etc., but the interval of the amount of activity is not limited to 1.0. The interval between activity amounts may be 0.1 or 0.5.

The efficiency calculating means 204 calculates the comfort efficiency ζ of each of the plurality of air conditioning control patterns using equation (3) using information on the position and activity amount of the user in the room.

In equation (3), k is an identification number that differs for each user, and K is the number of users in the room. In the first embodiment, K≧2. The target value is that the personal comfort index IPMV is within ±0.5, and when |IPMVk|>0.5, |IPMVk| is set to 0.5.

The comfort efficiency ζ is a value that evaluates how close the thermal sensations of a plurality of users are to neutral (individual IPMV=0). The comfort efficiency ζ is a value indicating the overall comfort level of multiple users in the room. It is considered that the higher the comfort efficiency ζ (maximum 100%), the more comfortable the multiple users in the room can be satisfied. That is, comfort efficiency ζ=100% means that a plurality of users are comfortable, and comfort efficiency ζ=0% means that a plurality of users are uncomfortable. The control determining means 205 determines an air conditioning control pattern that maximizes the comfort efficiency ζ among the 81 types of air conditioning control patterns corresponding to the comfort efficiency ζ.

An example of the hardware of the control device 22 shown in FIG. 13 will be explained. FIG. 22 is a hardware configuration diagram showing an example of the configuration of the arithmetic device shown in FIG. 13. When the various functions of the control device 22 are executed by software, the control device 22 shown in FIG. 13 is configured with a processor 91 such as a CPU and a memory 92, as shown in FIG. The functions of the data acquisition means 11, the layout determination section 12, and the control determination section 13 are realized by the processor 91 and the memory 92. FIG. 22 shows that processor 91 and memory 92 are communicatively connected to each other via bus 93. Processor 91 and memory 92 are connected to storage device 21 shown in FIG. 13 via bus 93. The memory 92 serves as a primary storage device, and the storage device 21 serves as a secondary storage device.

When each function is executed by software, the functions of the data acquisition means 11, the layout determination section 12, and the control determination section 13 are realized by software, firmware, or a combination of software and firmware. Software and firmware are written as programs and stored in memory 92. The processor 91 realizes the functions of each means by reading and executing programs stored in the memory 92. The memory 92 has, for example, a similar configuration to the memory 82, and detailed description thereof will be omitted.

Note that the model generation unit 201 may learn a method of calculating IPMV in advance using a neural network, and estimate the IPMV of the air-conditioned space from input conditions such as building load, region, and user preference.

Furthermore, the temperature Tb of the air blown out from the load side unit 103 varies linearly depending on the load of the building and the operating frequency of the compressor 119. Therefore, the model generation means 201 learns the optimal combination of the temperature Tb of the air blown out from the load side unit 103, the angles θh and θv, and the wind speed W from input conditions such as building load, region, and user preferences. However, the number of air conditioning control patterns to be selected may be narrowed down using a neural network. In this case, since the control determining means 205 selects the optimal air conditioning control pattern from the narrowed number of air conditioning control patterns, the process of determining the air conditioning control pattern is performed smoothly. The user's preference is, for example, the tendency of the user's thermal sensation.

Specifically, the storage device 21 stores in chronological order load data that is a combination of input conditions including the heat load of the building in which the air conditioner 10 is installed and an air conditioning control pattern that maximizes the comfort efficiency ζ. do. Then, the control determining means 205 narrows down the number of air conditioning control patterns to be selected from among the plurality of air conditioning control patterns based on the plurality of load data stored in time series. In this case, the input conditions include, in addition to the heat load of the building, the area where the air conditioner 10 is installed and regional weather data, the amount of solar radiation in the building, and information indicating trends in thermal sensation of multiple users. May contain.

Furthermore, the model generating means 201 may update the IPMV distribution in the IPMV database as follows. The model generation means 201 estimates the refrigerating capacity of the air conditioner 10 from operating information including the frequency of the compressor 119, the condensing temperature, the evaporation temperature, and the opening degree of the expansion valve 117. Then, the model generating means 201 generates the estimated refrigeration capacity and the airflow state estimated from the temperature Tb, the horizontal angle θh, the inclination angle θv, and the wind speed W into a plurality of groups stored for each of the plurality of activity amounts. reflected in each IPMV distribution. In this case, the IPMV database is updated to the latest state according to changes in the operating state of the air conditioner 10.

Next, a method of controlling the air conditioner 10 by the information processing device 2 of the first embodiment will be described. FIG. 23 is a layout diagram showing an example of an air-conditioned space that is air-conditioned by the air conditioner shown in FIG. FIG. 23 shows the positions of furniture placed in the room and the positions of two users in the room. FIG. 23 shows a case where the layout of the room has been changed from the layout shown in the thermal image of FIG. 8. Specifically, the layout of the room shown in FIG. 23 shows a case where the display case shown in FIG. 8 is removed from the room and the sofa is moved to the position of the display case.

Here, as shown in FIG. 23, a case will be described in which two people, user MA and user MB, are in the room. The vertical axis in FIG. 23 is the Y-axis coordinate, and the horizontal axis is the X-axis coordinate. FIG. 24 is a table showing an example of the amount of activity and location of each user. The amount of activity of user MA is 1 MET, and the amount of activity of user MB is 2 MET. 25 and 26 are flowcharts showing the operation procedure of the information processing apparatus according to the first embodiment. FIG. 27 is an image diagram showing an example of a thermal image of the room shown in FIG. 23.

In step S101 shown in FIG. 25, the data acquisition means 11 acquires environmental information from the air conditioner 10. The data acquisition means 11 causes the storage device 21 to store the acquired environmental information. In step S101, the data acquisition means 11 acquires data of a two-dimensional thermal image detected by the infrared sensor 140 from the air conditioner 10 as information indicating the heat radiation state and the state of the person, and stores it in the storage device 21. .

In step S102, the data acquisition means 11 acquires operating information from the air conditioner 10. The data acquisition means 11 causes the storage device 21 to store the acquired driving information. The operating information is information indicating the operating state, and includes, for example, information on the frequency of the compressor 119, the condensing temperature, the evaporation temperature, and the opening degree of the expansion valve 117. Further, the operation information includes airflow information including the temperature Tb detected by the temperature sensor 123, the horizontal angle θh of the first flap 4, the inclination angle θv of the second flap 5, and the wind speed W.

In step S103, the activity amount determining means 202 refers to the data of the thermal image Img2 shown in FIG. 27 to obtain information on the amount of activity of each user. Here, the activity amount determining means 202 estimates the amount of activity of user MA to be 1 MET, and estimates the amount of activity of user MB to be 2 METs.

In step S104, the position determining means 203 refers to the data of the thermal image Img2 shown in FIG. 27 to obtain information on the position of each user. Here, the position determining means 203 determines the position of user MA to be at coordinates (2, 7), and determines the position of user MB to be at coordinates (7, 9).

In step S105, the determining means 251 determines whether the current room layout matches the applied model. Here, the applied model is the layout model shown in the thermal image Img1 shown in FIG. 8. FIG. 28 is an image diagram showing an example of an analysis result of the thermal image shown in FIG. 27 by the determination means.

The determining means 251 specifies the position and shape of the person from the relative value of thermal radiation in the room by analyzing the data of the thermal image Img2 shown in FIG. Then, as shown in FIG. 28, the determining means 251 generates an indoor thermal image Img2a showing the heat radiation state by removing the portions of users MA and MB from the thermal image Img2. The determining means 251 extracts feature points of the room layout from the indoor thermal image Img2a.

FIG. 29 is an image diagram showing an example when the determination means shown in FIG. 14 extracts feature points from the thermal image shown in FIG. 28. The determining means 251 detects the edge of the window 302 as a feature point from the indoor thermal image Img2a shown in FIG. 28 as a cause of disturbing the indoor heat radiation state. Further, the determining means 251 detects the edges of the sofas 303 and 304 and the edge of the piano 305 as feature points from the indoor thermal image Img2a shown in FIG. Then, the determining means 251 generates a feature extraction image Img2b shown in FIG. 29.

Specifically, in step S105, the determining means 251 refers to a plurality of learning data of the currently applied model in the layout model database 211, and reads learning data corresponding to the current operating state of the air conditioner 10. Then, the determining means 251 determines whether the amount of coincidence between the feature points extracted in the feature extraction image Img2b and the feature points indicated by the read learning data is greater than or equal to a threshold value. As a result of the determination, if the matching amount is equal to or greater than the threshold, the determining means 251 determines that the current room layout is compatible with the applied model. Then, the determining means 251 transmits information to the effect that the layout of the room has not been changed to the layout selecting means 252. On the other hand, if the matching amount is smaller than the threshold, the determining means 251 determines that the current room layout does not conform to the applied model, and proceeds to step S106.

In step S106, the determining means 251 inquires of the user whether the layout of the room has been changed. Specifically, the determining means 251 transmits an inquiry message including information inquiring whether the layout of the room has been changed to the information processing terminal 40 via the network 50. Upon receiving the inquiry message from the information processing device 2, the terminal control unit 41 of the information processing terminal 40 causes the display unit 44 to display the inquiry message. When the user inputs an answer to the inquiry message displayed on the display section 44 via the input section 43, the terminal control section 41 sends the answer message to the information processing device 2 via the wireless communication section 45 and the network 50. Send to.

Upon receiving the reply message from the information processing terminal 40, the determining means 251 checks the contents of the reply message. If the response message is information indicating that the layout of the room has been changed, the determining means 251 transmits information indicating that the layout of the room has been changed to the layout selecting means 252. Thereby, the layout selection means 252 proceeds to step S108. On the other hand, if the response message is information indicating that the layout of the room has not been changed, the determining means 251 transmits information indicating that the layout of the room has not been changed to the layout selecting means 252. Thereby, the layout selection means 252 proceeds to step S107.

Note that although FIG. 25 shows a case where the determining means 251 inquires of the user when determining that the layout of the room has not been changed as a result of the determination in step S105, it is possible to good. That is, in the flow shown in FIG. 25, if the result of the determination in step S105 is No, the process proceeds to step S108, and if the result is Yes, the process proceeds to step S107.

When the layout selection means 252 receives information indicating that the layout of the room has not been changed from the determination means 251, the layout selection means 252 maintains the current applied model (step S107). On the other hand, when the layout selection means 252 receives the information that the layout of the room has been changed from the determination means 251, it selects a new layout model that matches the current layout of the room from the plurality of layout models (step S108). . Specifically, the layout selection means 252 refers to the layout model database 211, reads air conditioning data corresponding to the current operating state of the air conditioner 10, and uses the feature points of the read air conditioning data and the determination means 251 to determine whether the indoor Compare the feature points extracted from the thermal image. In this case, there may be one piece of air conditioning data or a plurality of pieces of air conditioning data. Further, the air conditioning data may be learning data or teacher data. Then, the layout selection means 252 selects a layout model that maximizes the amount of coincidence between the feature points extracted from the indoor thermal image and the feature points indicated by the read air conditioning data as a new layout model from the plurality of layout models. . The layout selection means 252 updates the applied model to the selected new layout model (step S109).

Comparing the feature extraction image Img2b shown in FIG. 29 with the feature extraction image Img1b shown in FIG. do not have. Therefore, in this case, the determining means 251 determines that the layout of the room needs to be changed.

In step S110, the layout selection means 252 selects an IPMV model corresponding to the applied model maintained in step S107 or the applied model updated in step S109. Then, the layout selection unit 252 transmits information on the selected applied model to the control determination unit 13. For example, the layout selection means 252 reads out the identifier of the IPMV model from the relational information shown in FIG.

FIG. 30 is a schematic diagram showing the operation procedure after step S111 shown in FIG. 26 of the information processing apparatus according to the first embodiment. n of nMET is a positive integer of 2 or more. Here, a case will be explained in which the model generation means 201 generates the IPMV database 212 in advance using information stored in the storage device 21. The model generation means 201 stores the generated IPMV database 212 in the storage device 21. FIG. 30 shows an IPMV model in which 81 IPMV distributions are provided for each activity amount. The IPMV database 212 stores the IPMV model shown in FIG. 30 corresponding to the applied model maintained in step S107 or updated in step S109.

In step S111, the efficiency calculation means 204 reads out the 1MET group and the 2MET group from the IPMV model selected in step S110 from the estimation result of the activity amount determination means 202 in step S103. Subsequently, the efficiency calculation means 204 reads out 81 IPMVs located at the coordinates (2, 7) of the 1MET group from the determination result of the position determination means 203 in step S104. Furthermore, the efficiency calculation means 204 reads out 81 IPMVs located at the coordinates (7, 9) of the 2MET group from the determination result of the position determination means 203. At this time, the efficiency calculation means 204 reads out the IPMV at a predetermined height (for example, 1.3 m above the floor) of the air-conditioned space in each IPMV distribution. Then, the efficiency calculation means 204 calculates 81 types of comfort efficiency ζ by substituting the 81 IPMVs of user MA and the 81 IPMVs of user MB into equation (3) (step S112).

In step S113, the control determining means 205 determines the air conditioning control pattern with the largest comfort efficiency ζ among the 81 air conditioning control patterns. In this case, the conditions for selecting the air conditioning control pattern may include not only the condition that the comfort efficiency ζ is maximum, but also the condition that the IPMV of each user is within ±0.5.

In step S114, the control determining means 205 transmits information on the air conditioning control pattern determined in step S113 to the air conditioner 10. When the control device 130 of the air conditioner 10 receives the information on the air conditioning control pattern from the information processing device 2, it controls at least one of the compressor 119, the blower 113, and the wind direction adjustment unit 105 according to the air conditioning control pattern. . For example, when changing the blowing temperature of air from the load side unit 103, the refrigeration cycle control means 131 changes the operating frequency of the compressor 119. When changing the wind speed W, the refrigeration cycle control means 131 changes the rotation speed of the blower 113. When changing the angle θh, the refrigeration cycle control means 131 changes the angle θh of the first flap 4. When changing the angle θv, the refrigeration cycle control means 131 changes the angle θv of the second flap 5.

In step S115, the data acquisition means 11 determines whether a certain period of time has elapsed. If a certain period of time has not elapsed, the control device 22 enters a standby state. As a result of the determination in step S115, if a certain period of time has elapsed, the control device 22 returns to the process in step S101.

FIG. 31 is a table showing an example of the calculation results of comfort efficiency. FIG. 31 shows IPMV when the amount of activity is 1 MET, IPMV when the amount of activity is 2 MET, and comfort efficiency ζ corresponding to each air conditioning control pattern. The numbers in the left column of the table shown in FIG. 31 are the identification numbers of the air conditioning control patterns. Referring to the table shown in FIG. 31, it can be seen that the air conditioning control pattern with the maximum comfort efficiency ζ is the 16th air conditioning control pattern.

FIG. 32 is an image diagram showing an example of the IPMV distribution in the case of the air conditioning control pattern determined in step S113. FIG. 32 shows the IPMV distribution when the amount of activity is 1 MET in the 16th air conditioning control pattern. FIG. 33 is an image diagram showing another example of the IPMV distribution in the case of the air conditioning control pattern determined in step S113. FIG. 33 shows the IPMV distribution when the amount of activity is 2MET in the 16th air conditioning control pattern.

As shown in FIGS. 32 and 33, in the air conditioning control pattern No. 16, the IPMV of user MA whose activity amount is 1 MET and the IPMV of user MB whose activity amount is 2 MET are visualized. FIGS. 32 and 33 show that the higher the density of the pattern, the more negative the IPMV is than neutral, and the lower the density of the pattern, the more negative the IPMV is from neutral. In FIG. 32, the IPMV at the user MA's position has a value close to 0. In Figure 33, the IPMV has a value larger than 0 over a wide range in the room, but the IPMV around the coordinates (7, 7) near the user MB's position has a value close to 0. I know that there is. This is because air is blown out from the load-side unit 103 in the direction of coordinates (7, 7), and the value of IPMV decreases. In this way, the IPMVs of the plurality of users MA and MB can be quickly brought to a comfortable range and stabilized so that the IPMVs of the users MA and MB become close to neutral.

Note that in the flowcharts shown in FIGS. 25 and 26, the processes in steps S103 and S104 only need to be executed before step S111, and are not limited to the positions of the steps shown in FIG.

Furthermore, although a case has been described in which the process returns to step S101 after a certain period of time has elapsed in step S115 shown in FIG. 26, the process may return to step S103. In this case, in step S103, the data acquisition means 11 acquires data of the two-dimensional thermal image detected by the infrared sensor 140 from the air conditioner 10 as information indicating the heat radiation state and the state of the person. If the IPMV database 212 constructed in the storage device 21 is compatible with the application model of the air conditioner 10 and the air-conditioned space, it does not need to be updated frequently. In this case, the computational processing load on the model generation means 201 is reduced.

Furthermore, in step S115 shown in FIG. 26, the activity amount determining means 202 and the position determining means 203 may monitor the two-dimensional thermal image data received from the air conditioner 10. If the activity amount determination means 202 determines that the user's activity amount is not constant within a certain period of time, or if the position determination means 203 cannot determine the presence or absence of the user in the room, in one or both cases, the load side unit The direction of the air blown out from 103 may be changed. Specifically, the control determining means 205 generates control information that causes a swing operation to change one or both of the horizontal angle of the first flap 4 and the inclination angle of the second flap 5 at a constant cycle. It is transmitted to the air conditioner 10. For example, the swinging motion of the first flap 4 is a motion in which the first flap 4 swings left and right at a cycle of 20 seconds with respect to the horizontal reference θh0. In this case, the environmental information and driving information that the information processing device 2 receives from the air conditioner 10 change, making it easier for the control device 22 to recognize the amount of activity and location of the user.

Furthermore, in the first embodiment, when the control determining means 205 determines the air conditioning control pattern in step S113 shown in FIG. 26, the efficiency calculating means 204 calculates the comfort efficiency of each air conditioning control pattern using equation (3). Although ζ was calculated, the evaluation method is not limited to this. The efficiency calculation unit 204 may use TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution) to find an air conditioning control pattern that maximizes the overall comfort level of a plurality of users. In the first embodiment, since the evaluation method using equation (3) requires less calculation than TOPSIS, the computational processing load on the control device 22 is reduced.

The air conditioning system 1 according to the first embodiment includes an air conditioner 10, a detection means 30 that detects a heat radiation state and a person's state in an air-conditioned space, a storage device 21, and a control device 22. The storage device 21 stores a plurality of layout models representing different layouts of the air-conditioned space, a plurality of air-conditioning control patterns for each layout model, an applied model that is a layout model applied to the air-conditioned space, and an air conditioner for the applied model. A plurality of learning data in which the operating state of the harmonizing device and the heat radiation state corresponding to the operating state are combined are stored. The control device 22 includes a determining means 251, a layout selecting means 252, and a control determining section 13. The determining means 251 determines whether the layout of the air-conditioned space has been changed by comparing the combination data of the operating state acquired from the air conditioner 10 and the heat radiation state detected by the detecting means 30 with a plurality of learning data. Determine. When the determining means 251 determines that the layout of the air-conditioned space has been changed, the layout selecting means 252 selects a new layout model corresponding to the combination data from among the plurality of layout models. The control determining unit 13 determines an air conditioning control pattern based on the state of the person detected by the detection means 30 from among the plurality of air conditioning control patterns of the new layout model.

According to the first embodiment, even if the layout of the air-conditioned space is changed, a layout model that best matches the layout of the air-conditioned space is selected from a plurality of layout models. Then, from the plurality of air conditioning control patterns of the selected layout model, an air conditioning control pattern corresponding to the state of the person in the air conditioning target space is applied to the air conditioner. Therefore, the comfort of the user in the air-conditioned space is improved.

Specifically, the determining means 251 detects feature points of the shape of the air-conditioned space and the layout of the installed furniture, etc., and the layout selection means 252 selects the layout model most suitable for the current layout of the air-conditioned space. . Then, the control determining unit 13 determines, based on the plurality of air conditioning control patterns of the selected layout model, the user's comfort efficiency is maximized according to the state of the user in the air-conditioned space, for example, the user's position and activity level. Find the air conditioning control pattern. The air conditioner 10 performs air conditioning according to the determined air conditioning control pattern, thereby improving comfort for users of the air-conditioned space.

Furthermore, in the first embodiment, the detection means 30 may detect the amount of activity of each user and the position of each user in the air-conditioned space for a plurality of users in the air-conditioned space as the state of the person. The storage device 21 stores, for each layout model, an IPMV model in which groups including comfort index distributions in the air-conditioned space corresponding to each of the plurality of air conditioning control patterns of the air conditioner 10 are classified according to a plurality of activity amounts. Remember. The control determining unit 13 includes an activity amount determining means 202, a position determining means 203, an efficiency calculating means 204, and a control determining means 205. The activity amount determination means 202 identifies, for each user, a group corresponding to the amount of activity detected by the detection means 30. The position determination means 203 extracts a plurality of comfort indicators corresponding to the position detected by the detection means 30 from the plurality of comfort index distributions within the specified group. The efficiency calculating means 204 calculates comfort efficiency ζ indicating the overall comfort level of the plurality of users for each of the plurality of air conditioning control patterns, using the plurality of comfort indices extracted corresponding to the positions of each user. . The control determining means 205 determines an air conditioning control pattern that maximizes the calculated comfort efficiency ζ from among the plurality of air conditioning control patterns.

According to the first embodiment, the comfort index distribution in the air-conditioned space corresponding to each of the plurality of air-conditioning control patterns corresponds to the activity amount of each user in the air-conditioned space whose layout is adapted to the applied model. Find the group that includes. Further, a plurality of comfort indices are extracted from a plurality of comfort index distributions within the group, corresponding to the position of each user in the air-conditioned space. Then, based on the plurality of comfort indexes for each user, an air conditioning control pattern that maximizes the comfort efficiency for the plurality of users is determined from the plurality of air conditioning control patterns. Even if the layout of the room is changed, the air conditioner 10 performs air conditioning according to the air conditioning control pattern that maximizes the comfort efficiency for a plurality of users, thereby improving comfort for a plurality of users.

Furthermore, in the first embodiment, the learning means 253 accumulates thermal image data indicating the heat radiation state in the storage device 21 for each layout model as learning data. Therefore, a large amount of learning data indicating the feature points of the layout model is accumulated, and the accuracy of the determination by the determining means 251 between the actual layout of the air-conditioned space and the layout model is improved.

Note that in the first embodiment described above, a case has been described in which the infrared sensor 140 functions as a means for detecting the amount of activity of the user, but the means for detecting the amount of activity of the user is not limited to the infrared sensor 140. For example, the means for detecting the amount of activity may be a wearable sensor. Below, a case where the means for detecting the amount of activity is a wearable sensor will be explained.

(Modification 1)
FIG. 34 is a diagram illustrating a configuration example of an air conditioning system according to modification 1. In the configuration shown in FIG. 34, the same components as those explained with reference to FIG.

The air conditioning system 1a includes an air conditioner 10 having a heat detection means 31, an information processing device 2, an access point (AP) 60, and a wearable terminal 70 provided for each user. The AP 60 is provided in a room that is a space to be air-conditioned by the air conditioner 10. The AP 60 includes a short-range wireless communication means (not shown) such as Bluetooth (registered trademark), and a network communication means (not shown) compatible with the communication protocol of the network 50. The communication protocol is, for example, TCP/IP. The heat detection means 31 is, for example, the infrared sensor 140 shown in FIG. 2.

Wearable terminal 70 is provided for each user. Wearable terminal 70 is, for example, in the form of a wristwatch or a bracelet. The wearable terminal 70 includes an activity amount detection means 32 that detects a pulse as the user's activity amount at regular intervals. The amount of activity may be the user's skin temperature. The wearable terminal 70 also includes a memory (not shown) that stores a terminal identifier that is a different identifier for each terminal and a program, and a CPU (not shown) that executes processing according to the program. The heat detection means 31 and the activity amount detection means 32 constitute a detection means 30a.

When the activity amount detection means 32 detects the user's activity amount, the CPU (not shown) of the wearable terminal 70 sends the user information including the activity amount information and the terminal identifier to the information processing device 2 via the AP 60 and the network 50. Send. A memory (not shown) of the wearable terminal 70 may store the coordinates of the installation position of the AP 60. The CPU (not shown) of the wearable terminal 70 refers to the strength of radio waves with the AP 60 and estimates the distance from the installation position of the AP 60. Then, the CPU (not shown) of the wearable terminal 70 includes the estimated position information in the user information as the user's position information. For example, when multiple APs 60 are installed indoors, the CPU (not shown) of the wearable terminal 70 estimates the user's position in the room more accurately by comparing the strength of the wireless radio waves of the multiple APs 60. can do. The information processing device 2 associates the user information received from the wearable terminal 70 with the user's position detected by the heat detection means 31.

Also in Modification 1, the information processing device 2 can determine the optimal air conditioning control pattern from a plurality of air conditioning control patterns in accordance with the applied model according to the procedures shown in FIGS. 25 and 26. In the case of the present modification 1, the wearable terminal 70 worn by each user detects the amount of activity of the user, so the amount of activity is detected with higher accuracy. As a result, air conditioning can be performed that is more suitable for the amount of activity of each of the plurality of users.

In addition, in Embodiment 1 mentioned above, the case where the number of people in the air-conditioned space is plural was explained, but the number of people in the air-conditioned space may be one.

Reference Signs List 1, 1a air conditioning system, 2 information processing device, 4 first flap, 4a to 4d blade, 5 second flap, 5a front blade, 5b rear blade, 6 outlet, 10 air conditioner, 11 data acquisition means, 12 Layout determination section, 13 Control determination section, 21 Storage device, 22 Control device, 30, 30a Detection means, 31 Heat detection means, 32 Activity amount detection means, 40 Information processing terminal, 41 Terminal control section, 42 Storage section, 43 Input part, 44 display part, 45 wireless communication part, 50 network, 60 access point, 70 wearable terminal, 75 ceiling, 80 processing circuit, 81 processor, 82 memory, 83 bus, 91 processor, 92 memory, 93 bus, 102 refrigerant circuit , 103 load side unit, 104 heat source side unit, 105 air direction adjustment section, 110 refrigerant piping, 113, 114 blower, 115 load side heat exchanger, 116 heat source side heat exchanger, 117 expansion valve, 118 four-way valve, 119 compressor , 120 environment detection section, 121 room temperature sensor, 122 humidity sensor, 123 temperature sensor, 130 control device, 131 refrigeration cycle control means, 132 communication means, 140 infrared sensor, 201 model generation means, 202 activity amount determination means, 203 position determination means, 204 efficiency calculation means, 205 control determination means, 211 layout model database, 212 IPMV database, 251 determination means, 252 layout selection means, 253 learning means, 301 display cabinet, 302 window, 303, 304 sofa, 305 piano, 411 CPU , 412 Memory, FL floor, WAL1 to WAL4 wall, ad1 to ad4 balloon direction.

Claims (10)

an air conditioning device that air-conditions a space to be air-conditioned;
Detection means for detecting a heat radiation state and a person's state in the air-conditioned space;
a plurality of layout models representing different layouts of the air-conditioned space, a plurality of air-conditioning control patterns for each of the layout models, an application model that is the layout model applied to the air-conditioning space, and the application model described above regarding the application model. a storage device that stores a plurality of learning data in which an operating state of the air conditioner and the heat radiation state corresponding to the operating state are combined;
Whether or not the layout of the air-conditioned space has been changed is determined by comparing the combination data of the operating state acquired from the air conditioner and the heat radiation state detected by the detection means with the plurality of learning data. If it is determined that the layout of the air-conditioned space has been changed, a new layout model corresponding to the combination data is selected from the plurality of layout models, and a new layout model is selected from the plurality of air-conditioning control patterns of the new layout model. , a control device that determines an air conditioning control pattern based on the state of the person detected by the detection means;
Air conditioning system with. The control device includes:
The combination data and the plurality of learning data are compared, and if there is no learning data that matches the combination data, an information processing terminal of the user of the air conditioner determines whether the layout of the air-conditioned space has been changed. When an inquiry message including information to inquire is transmitted and a reply message including information to the effect that the layout of the air-conditioned space has been changed is received, it is determined that the layout of the air-conditioned space has been changed;
The air conditioning system according to claim 1. The storage device is
storing, for each of the layout models, a layout model database including the learning data or teacher data as air conditioning data indicating feature points of the layout model, and relational information that associates the layout model with the air conditioning data;
The control device includes:
Extracting feature points of the layout of the air-conditioned space from information on the heat radiation state detected by the detection means, and a predetermined amount of coincidence between the extracted feature points and the feature points indicated by the air conditioning data of the applied model. If it is smaller than the set threshold, it is determined that the layout of the air-conditioned space has been changed;
The air conditioning system according to claim 1. The storage device is
storing, for each of the layout models, a layout model database including the learning data or teacher data as air conditioning data indicating feature points of the layout model, and relational information that associates the layout model with the air conditioning data;
The control device includes:
If it is determined that the layout of the air-conditioned space has been changed, feature points of the layout of the air-conditioned space are extracted from information on the heat radiation state detected by the detection means, and the extracted feature points and the air-conditioned data are selecting the layout model that maximizes the amount of coincidence with the feature points indicated by as the new layout model;
The air conditioning system according to any one of claims 1 to 3. The detection means includes:
As the state of the person, detecting the amount of activity of each user and the position of each user in the air-conditioning space for a plurality of users in the air-conditioning space;
The storage device is
For each of the layout models, there are a plurality of groups including comfort index distributions that are distributions of comfort indexes indicating the user's comfort level in the air conditioning target space corresponding to each of the plurality of air conditioning control patterns of the air conditioner. Memorizes comfort index models classified by activity level,
The control device includes:
With reference to the comfort index model corresponding to the new layout model, for each user, the group corresponding to the amount of activity detected by the detection means is identified, and a plurality of the comfort indexes in the identified group are identified. The plurality of comfort indicators corresponding to the positions detected by the detection means are extracted from the distribution, and the plurality of air conditioners are calculating a comfort efficiency indicating the overall comfort level of the plurality of users for each control pattern, and finding an air conditioning control pattern that maximizes the calculated comfort efficiency among the plurality of air conditioning control patterns;
The air conditioning system according to any one of claims 1 to 4. The control device includes:
Load data that is a combination of input conditions including the heat load of the building in which the air conditioner is installed and the air conditioning control pattern that maximizes the comfort efficiency of the plurality of users is stored in a time series, and the load data is stored in a time series. Narrowing down the number of air conditioning control patterns to be selected from among the plurality of air conditioning control patterns based on the plurality of load data stored in
The air conditioning system according to claim 5. Let k be the different identification number for each of the plurality of users, let IPMVk be the comfort index of the user with the identification number k, let K be an integer of 2 or more, and let the comfort efficiency be ζ, then each of the plurality of air conditioning control patterns The comfort efficiency ζ of
ζ = (1-2 | IPMV ₁ |) x (1-2 | IPMV ₂ |) x... x (1-2 | IPMV _k |) x... (1-2 | IPMV _K |) x 100 %
Calculated using the formula,
The air conditioning system according to claim 5 or 6. The detection means is an infrared sensor.
The air conditioning system according to any one of claims 1 to 7. The detection means includes:
a wearable terminal provided to each of the users and detecting the amount of activity of each of the users;
an infrared sensor that detects the position of each user in the air-conditioned space and the heat radiation state;
The air conditioning system according to any one of claims 5 to 7. A method for controlling an air conditioner using a control device connected to a detection means for detecting a heat radiation state and a person's state in an air-conditioned space and a storage device, the method comprising:
a plurality of layout models representing different layouts of the air-conditioned space, a plurality of air-conditioning control patterns for each of the layout models, an application model that is the layout model applied to the air-conditioning space, and the application model described above regarding the application model. storing in the storage device a plurality of learning data in which the operating state of the air conditioner and the heat radiation state corresponding to the operating state are combined;
Whether or not the layout of the air-conditioned space has been changed is determined by comparing the combination data of the operating state acquired from the air conditioner and the heat radiation state detected by the detection means with the plurality of learning data. a step of determining;
If it is determined that the layout of the air-conditioned space has been changed, selecting a new layout model corresponding to the combination data from the plurality of layout models;
determining an air conditioning control pattern from the plurality of air conditioning control patterns of the new layout model based on the state of the person detected by the detection means;
A method for controlling an air conditioner having:

Images