Control system, inference device, and learning device

Abstract

To provide a control system, an inference device, and a learning device which can provide a comfortable space to a user.SOLUTION: The control system of the present disclosure includes: an illumination facility; an air-conditioning facility; and a management facility for inferring the set value of the illumination facility and the air-conditioning facility from weather information, the state of the illumination facility corresponding to the weather information, and the state of the air-conditioning facility corresponding to the weather information by using a learned control model for inferring the set value of the illumination facility and the air-conditioning facility from the weather information, the state of the illumination facility corresponding to the weather information, and the state of the air-conditioning facility corresponding to the weather information, and controlling the illumination facility and the air-conditioning facility by using the set value.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] This disclosure relates to a control system, an inference device, and a learning device.

Background Art

[0002] Patent Document 1 discloses a facility operation system including a facility information management server that creates an operation plan for facilities in a living room including air conditioning equipment based on weather information obtained from the outside, and controls the operation of the facilities based on the operation plan. In this facility operation system, the facility information management server corrects the operation plan based on personal data regarding the comfort index of the user. The facility information management server updates the personal data based on the operation input to the air conditioning equipment by the user.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] As conditions for spending comfortably indoors, there are appropriate room temperature settings and lighting effects. For example, in summer, a room temperature of 28 degrees and daylight white lighting are recommended so that a feeling of coolness can be felt. Also, for example, in winter, a room temperature of 20 degrees and bulb-colored lighting are recommended so that a feeling of warmth can be felt. Also, similar to calculating the discomfort index from the relationship between temperature and humidity, a discomfort index is defined for the relationship between illuminance and color temperature.

[0005] In Patent Document 1, personal data is updated based on the operation input to the air conditioning equipment by the user. However, updating of personal data in response to lighting operations is not considered.

[0006] This disclosure was made to solve the aforementioned problems and aims to provide a control system, inference device, and learning device that can provide a comfortable space. [Means for solving the problem]

[0007] The control system relating to this disclosure comprises lighting equipment, air conditioning equipment, weather information, the state of the lighting equipment corresponding to the weather information, and the state of the air conditioning equipment corresponding to the weather information, and a management system that uses a trained control model to infer the set values ​​of the lighting equipment and the air conditioning equipment from the weather information, the state of the lighting equipment corresponding to the weather information, and the state of the air conditioning equipment corresponding to the weather information to infer the set values ​​and control the lighting equipment and the air conditioning equipment using the set values. The management equipment has a mode in which the set value is used as is, and a mode in which it is used after making predetermined changes. ru.

[0008] The inference device according to this disclosure comprises: a data acquisition unit that acquires weather information, the state of lighting equipment corresponding to the weather information, and the state of air conditioning equipment corresponding to the weather information; and an inference unit that uses a trained control model for inferring setting values ​​for the lighting equipment and the air conditioning equipment from the weather information, the state of the lighting equipment corresponding to the weather information, and the state of the air conditioning equipment corresponding to the weather information to infer the setting values ​​and control the lighting equipment and the air conditioning equipment using the setting values. It has a mode in which the aforementioned settings are used as they are, and a mode in which predetermined changes are made before use. ru.

[0009] The learning device according to this disclosure includes a data acquisition unit that acquires weather information, the state of lighting equipment corresponding to the weather information, and the state of air conditioning equipment corresponding to the weather information, and a model generation unit that generates a trained control model for inferring the set values ​​of the lighting equipment and the air conditioning equipment from the weather information, the state of the lighting equipment corresponding to the weather information, and the state of the air conditioning equipment corresponding to the weather information. The model generation unit modifies the date or season control model corresponding to the weather information based on the weather information, and then further modifies the control model based on the state of the lighting equipment and the state of the air conditioning equipment corresponding to the weather information, and stores it as the learned control model. ru. [Effects of the Invention]

[0010] In the control system described herein, the setting values ​​for lighting and air conditioning equipment are inferred using a trained control model that infers the setting values ​​for lighting and air conditioning equipment from weather information, the status of lighting equipment corresponding to the weather information, and the status of air conditioning equipment corresponding to the weather information. By controlling the lighting and air conditioning equipment based on these setting values, a comfortable space can be provided. In the inference device described herein, the setting values ​​for lighting equipment and air conditioning equipment are inferred using a trained control model that infers the setting values ​​for lighting equipment and air conditioning equipment from weather information, the state of lighting equipment corresponding to the weather information, and the state of air conditioning equipment corresponding to the weather information. By controlling the lighting equipment and air conditioning equipment based on these setting values, a comfortable space can be provided. The learning device described herein generates a trained control model for inferring the set values ​​of lighting equipment and air conditioning equipment from weather information, the state of lighting equipment corresponding to the weather information, and the state of air conditioning equipment corresponding to the weather information. By using this trained control model to infer the set values ​​of lighting equipment and air conditioning equipment and controlling the lighting equipment and air conditioning equipment, a comfortable space can be provided. [Brief explanation of the drawing]

[0011] [Figure 1] This is a block diagram of the control system according to Embodiment 1. [Figure 2] This is a diagram illustrating a learning device according to Embodiment 1. [Figure 3] This is a diagram illustrating the inference device according to Embodiment 1. [Modes for carrying out the invention]

[0012] The control system, inference device, and learning device according to this embodiment will be described with reference to the drawings. The same or corresponding components are denoted by the same reference numerals, and repetition of the description may be omitted.

[0013] Embodiment 1. Figure 1 is a block diagram of a control system 100 according to Embodiment 1. The control system 100 comprises a management unit 10, an air conditioning unit 20, a lighting unit 30, and a server 40 that provides weather information. The management unit 10, the air conditioning unit 20, the lighting unit 30, and the server 40 are connected to each other via a wired or wireless network, which is a LAN (Local Area Network). The LAN is, for example, Ethernet®. The air conditioning unit 20 and the lighting unit 30 are installed in the same space. The management unit 10 is linked to the air conditioning unit 20 and the lighting unit 30.

[0014] The control equipment 10 is set to the current date and the location of the control system 100. The location may also be the location of the air conditioning equipment 20 or the lighting equipment 30. The location may be set by latitude and longitude, or it may be the capital city of a prefecture.

[0015] The communication unit 11 of the management equipment 10 uses the network to obtain weather information for its location from the server 40. Weather information includes weather conditions, temperature, humidity, wind speed, rainfall, and perceived temperature. By transmitting the location information of the control system 100 to the server 40, the server 40 may transmit weather information corresponding to the location information.

[0016] The communication unit 11 of the management equipment 10 uses the network to obtain the status of the air conditioning equipment 20. The status of the air conditioning equipment 20 includes the operating mode, set temperature, room temperature, and power consumption. Operating modes include cooling, heating, ventilation, and dehumidification. When the communication unit 21 of the air conditioning equipment 20 receives a request signal from the management equipment 10 to the air conditioning equipment 20, it transmits the status of the air conditioning equipment 20. The room temperature is obtained by the temperature acquisition unit 23 and transmitted from the communication unit 21.

[0017] The communication unit 11 of the management device 10 uses a network to obtain the status of the lighting device 30. The status of the lighting device 30 includes the lighting status, the number of people staying in the space, the power consumption, etc. The lighting status includes the dimming rate, the color temperature, etc. When the communication unit 31 of the lighting device 30 receives a request signal from the management device 10 to the lighting device 30, it transmits the status of the lighting device 30. The number of people staying in the space is obtained by the human presence sensor 34 and transmitted from the communication unit 31.

[0018] The information obtained by the management device 10 from the air conditioning device 20, the lighting device 30, and the server 40 is stored in the storage unit 13.

[0019] FIG. 2 is a diagram for explaining the learning device 50 according to Embodiment 1. The learning device 50 is provided, for example, in the management device 10. The learning device 50 includes a data acquisition unit 51 and a model generation unit 52. The data acquisition unit 51 acquires weather information, the status of the lighting device 30 corresponding to the weather information, and the status of the air conditioning device 20 corresponding to the weather information. The data acquisition unit 51 corresponds to, for example, the communication unit 11.

[0020] The model generation unit 52 generates a learned control model for inferring the set values of the lighting device 3以及空調設備20 from the weather information acquired by the data acquisition unit 51, the status of the lighting device 30 corresponding to the weather information, and the status of the air conditioning device 20 corresponding to the weather information. The model generation unit 52 corresponds to, for example, the control unit 12. The control unit 12 can be composed of, for example, a microcomputer, a processor, etc.

[0021] A method for generating a learned control model will be described. First, the model generation unit 52 generates a base control model. The control model is generated, for example, for each date or season. For example, if the season is summer based on the current date, the model generation unit 52 generates a control model such that the set value of the air conditioning device 20 is operation mode = cooling, set temperature = 28 degrees, the set value of the lighting device 30 is dimming rate = 70%, and color temperature = 4200K.

[0022] Next, the model generation unit 52 incorporates weather information into the control model. The model generation unit 52 modifies the control model for the date or season corresponding to the weather information acquired by the data acquisition unit 51 based on the weather information. For example, if the weather for that date or season is sunny, temperature is 35 degrees, humidity is 70%, wind speed is 1 m / s, rainfall is 0 mm, and perceived temperature is 37 degrees, the model generation unit 52 modifies the control model so that the set temperature is 27 degrees and the dimming rate is 50%. The model generation unit 52 may also modify the control model based on a time corresponding to the weather information, such as 14:00.

[0023] Next, the model generation unit 52 incorporates information obtained from the air conditioning equipment 20 and the lighting equipment 30 into the control model. Based on the state of the lighting equipment 30 corresponding to the weather information and the state of the air conditioning equipment 20 corresponding to the weather information, the model generation unit 52 further modifies the control model and stores it as a learned control model. For example, if the data acquisition unit 51 obtains from the air conditioning equipment 20 that the operating mode is fan-only, the set temperature is 27 degrees, and the room temperature is 26 degrees, the model generation unit 52 learns this information and reflects it in the control model. Also, if the data acquisition unit 51 obtains from the lighting equipment 30 that the dimming rate is 50%, the color temperature is 4500K, and the number of people in the space is 80, the model generation unit 52 learns this information and reflects it in the control model.

[0024] The data acquisition unit 51 acquires from the air conditioning equipment 20 and lighting equipment 30, indicating the state of air conditioning and lighting that can provide a comfortable space for the user under the weather conditions of the location. The model generation unit 52 stores the trained control model generated based on these states in the trained model storage unit 53. The trained model storage unit 53 corresponds to, for example, the storage unit 13.

[0025] The learned model memory unit 53 may be a non-volatile or volatile semiconductor memory such as RAM, ROM, flash memory, EPROM, EEPROM, magnetic disk, flexible disk, optical disk, compact disk, minidisc, DVD, etc. RAM is an abbreviation for Random Access Memory. ROM is an abbreviation for Read Only Memory. EPROM is an abbreviation for Erasable Programmable Read Only Memory. EEPROM is an abbreviation for Electrically Erasable Programmable Read-Only Memory.

[0026] Figure 3 is a diagram illustrating an inference device 60 according to Embodiment 1. The inference device 60 is installed, for example, in the management equipment 10. The inference device 60 comprises a data acquisition unit 61 and an inference unit 62. The data acquisition unit 61 acquires weather information, the status of the lighting equipment 30 corresponding to the weather information, and the status of the air conditioning equipment 20 corresponding to the weather information. The data acquisition unit 61 corresponds, for example, to a communication unit 11.

[0027] The inference unit 62 retrieves a trained control model from the trained model storage unit 53. The inference unit 62 infers the set values ​​for the lighting equipment 30 and the air conditioning equipment 20 from the trained control model, the weather information acquired by the data acquisition unit 61, the state of the lighting equipment 30 corresponding to the weather information, and the state of the air conditioning equipment 20 corresponding to the weather information. The inference unit 62 then controls the lighting equipment 30 and the air conditioning equipment 20 using these set values. The inference unit 62 corresponds to, for example, the control unit 12.

[0028] First, the inference unit 62 extracts a model from the trained control model that corresponds to the weather information acquired by the data acquisition unit 61. Then, using the extracted model, the inference unit 62 infers the set values ​​of the lighting equipment 30 and the air conditioning equipment 20 from the state of the lighting equipment 30 corresponding to the weather information and the state of the air conditioning equipment 20 corresponding to the weather information.

[0029] For example, if the data acquisition unit 61 obtains the indoor temperature = 26 degrees as the status of the air conditioning equipment 20, the inference unit 62 infers the setting values ​​of operating mode = fan and set temperature = 27 degrees based on the learned control model. Also, for example, if the data acquisition unit 61 obtains the number of people in the space = 80 as the status of the lighting equipment 30, the inference unit 62 infers the setting values ​​of dimming rate = 50% and color temperature = 4500K based on the learned control model.

[0030] Thus, the status of the air conditioning equipment 20 corresponding to weather information includes information on the indoor temperature, and the setting value of the air conditioning equipment 20 may include the operating mode or set temperature of the air conditioning equipment 20. Furthermore, the status of the lighting equipment 30 corresponding to weather information includes information on the number of people present in the space where the lighting equipment 30 is installed, and the setting value of the lighting equipment 30 may include the dimming rate or color temperature of the lighting equipment 30.

[0031] The control unit 12 of the management equipment 10 controls the air conditioning equipment 20 and the lighting equipment 30 based on the inferred set values. The set values ​​are transmitted from the communication unit 11 to the air conditioning equipment 20 and the lighting equipment 30. In the air conditioning equipment 20, the communication unit 21 receives the set values, and the control unit 22 controls the temperature of the space, etc., based on the received set values. In the lighting equipment 30, the communication unit 31 receives the set values, and the control unit 32 controls the lighting state of the light source unit 33 based on the received set values.

[0032] The control equipment 10 may perform control based on various models depending on the level of emphasis placed on the learned control model, as shown in the table below, for example. In other words, the control equipment 10 may have a mode in which it uses the setpoints inferred based on the learned control model as they are, and a mode in which it uses them with predetermined modifications.

[0033] [Table 1]

[0034] The trained control model may be generated taking into account sunrise time, sunset time, time of day, etc. Sunrise time and sunset time may be obtained from server 40 or the like based on the date. The training interval or inference interval of the training device 50 and inference device 60 may be changed to 1 hour, 2 hours, etc.

[0035] The learning device 50 and the inference device 60 are not limited to the management equipment 10, but may also be installed in the air conditioning equipment 20 or the lighting equipment 30. In other words, the air conditioning equipment 20 or the lighting equipment 30 may also serve as the management equipment 10. In addition to the learning function based on weather information, the status of the lighting equipment 30, and the status of the air conditioning equipment 20, learning functions specific to each piece of equipment may also be provided. The learning device 50 and the inference device 60 may also be cloud-based using a network.

[0036] The control equipment 10 may learn the times when people enter and exit the space where the lighting equipment 30 is installed, infer the time when people will enter the space, and start controlling the lighting equipment 30 and the air conditioning equipment 20 before the inferred time. The control equipment 10 may learn the times when people enter and exit the space where the lighting equipment 30 is installed, infer the time when people will leave the space, and start controlling the lighting equipment 30 and the air conditioning equipment 20 before the inferred time. In this case, the control equipment 10 may learn the time it takes for the indoor temperature to change and set the time to start controlling the air conditioning equipment 20.

[0037] The control equipment 10 may, for example, change the temperature and humidity of the space to near the boundary between values ​​that the person finds comfortable and uncomfortable, before the time inferred as the time when a person will enter the space. When the control equipment 10 detects a person, it controls the air conditioning equipment 20 and lighting equipment 30 to the optimal temperature, humidity, illuminance, and color temperature that the person will find comfortable. The control equipment 10 may also, for example, change the temperature and humidity of the space to near the boundary between values ​​that the person finds comfortable and uncomfortable, before the time inferred as the time when a person will leave the space. This makes it possible to quickly provide a comfortable indoor space while suppressing energy consumption.

[0038] As described above, in the control system 100 of this embodiment, a trained control model is generated for inferring the setting values ​​of the lighting equipment 30 and the air conditioning equipment 20 from weather information, the state of the lighting equipment 30 corresponding to the weather information, and the state of the air conditioning equipment 20 corresponding to the weather information. The setting values ​​of the lighting equipment 30 and the air conditioning equipment 20 are inferred using this trained control model. By controlling the lighting equipment 30 and the air conditioning equipment 20 according to these setting values, a comfortable space can be provided.

[0039] For example, by applying the control system 100 indoors, it is possible to reduce physical strain and discomfort for users when moving between the outdoors and indoors. In particular, it is possible to provide a comfortable space by considering discomfort indices based on illuminance and color temperature, in addition to discomfort indices based on temperature and humidity.

[0040] Furthermore, a comfortable space for a user varies depending on the location, season, climate, time of day, and state of the space. For example, the conditions for a comfortable space are expected to differ between extremely cold and warm regions, basement and above-ground floors, and altitude. The management equipment 10 in this embodiment uses weather information of the location of the lighting equipment 30 or air conditioning equipment 20 to generate a trained control model and infer the setting values ​​of the lighting equipment 30 and air conditioning equipment 20. Therefore, it can provide a comfortable space according to the location of the space. In addition, the trained control model is generated based on the time of day, date, or season. Therefore, it can provide a comfortable space according to the season, climate, and time of day. Furthermore, the trained control model is generated based on information about the number of people present in the space. Therefore, it can provide a comfortable space according to the state of the space.

[0041] The technical features described in this embodiment may be used in combination as appropriate.

[0042] The various aspects of this disclosure are summarized below as an appendix. (Note 1) Lighting equipment, Air conditioning equipment, A control system that uses a trained control model to infer the set values ​​of the lighting equipment and the air conditioning equipment from weather information, the state of the lighting equipment corresponding to the weather information, and the state of the air conditioning equipment corresponding to the weather information, infers the set values ​​from the weather information, the state of the lighting equipment corresponding to the weather information, and the state of the air conditioning equipment corresponding to the weather information, and controls the lighting equipment and the air conditioning equipment using the set values, A control system characterized by comprising the following features. (Note 2) The control system according to Appendix 1, characterized in that the management equipment infers the set value using the weather information of the location of the lighting equipment. (Note 3) The control system according to Appendix 1 or 2, characterized in that the management equipment extracts a model corresponding to the weather information from the learned control model, and then uses the extracted model to infer the set value from the state of the lighting equipment corresponding to the weather information and the state of the air conditioning equipment corresponding to the weather information. (Note 4) The status of the lighting equipment corresponding to the weather information includes information on the number of people present in the space where the lighting equipment is installed. The control system according to any one of the appendices 1 to 3, characterized in that the set value includes the dimming rate or color temperature of the lighting equipment. (Note 5) The status of the air conditioning equipment corresponding to the weather information includes information on the indoor temperature. The control system according to any one of the appendices 1 to 4, characterized in that the set value includes the operating mode or set temperature of the air conditioning equipment. (Note 6) The control system according to any one of the appendices 1 to 5, characterized in that the management equipment has a mode for using the set value as is and a mode for using it after making predetermined changes. (Note 7) The control system according to any one of the appendices 1 to 6, characterized in that the management equipment learns the times when people enter and exit the space in which the lighting equipment is installed, infers the time when people will come into the space, and starts controlling the lighting equipment and the air conditioning equipment before the inferred time. (Note 8) The control system according to any one of the appendices 1 to 7, characterized in that the management equipment learns the times when people enter and exit the space in which the lighting equipment is installed, infers the time when people leave the space, and starts controlling the lighting equipment and the air conditioning equipment before the inferred time. (Note 9) A data acquisition unit that acquires weather information, the status of lighting equipment corresponding to the weather information, and the status of air conditioning equipment corresponding to the weather information. An inference unit that uses a trained control model to infer the set values ​​of the lighting equipment and the air conditioning equipment from the weather information, the state of the lighting equipment corresponding to the weather information, and the state of the air conditioning equipment corresponding to the weather information, infers the set values ​​from the weather information, the state of the lighting equipment corresponding to the weather information, and the state of the air conditioning equipment corresponding to the weather information, and controls the lighting equipment and the air conditioning equipment using the set values, An inference device characterized by comprising: (Note 10) A data acquisition unit that acquires weather information, the status of lighting equipment corresponding to the weather information, and the status of air conditioning equipment corresponding to the weather information. A model generation unit generates a trained control model for inferring the set values ​​of the lighting equipment and the air conditioning equipment from the weather information, the state of the lighting equipment corresponding to the weather information, and the state of the air conditioning equipment corresponding to the weather information. A learning device characterized by being equipped with the following features. (Note 11) The learning device according to Appendix 10, characterized in that the model generation unit modifies a date or season control model corresponding to the weather information based on the weather information, and then further modifies the control model based on the state of the lighting equipment and the state of the air conditioning equipment corresponding to the weather information, and stores it as a learned control model. (Note 12) The learning device according to appendix 10 or 11, characterized in that the model generation unit changes the control model based on the time corresponding to the weather information. [Explanation of Symbols]

[0043] 10 Management equipment, 11 Communication unit, 12 Control unit, 13 Storage unit, 20 Air conditioning equipment, 21 Communication unit, 22 Control unit, 23 Temperature acquisition unit, 30 Lighting equipment, 31 Communication unit, 32 Control unit, 33 Light source unit, 34 Motion sensor, 40 Server, 50 Learning device, 51 Data acquisition unit, 52 Model generation unit, 53 Trained model storage unit, 60 Inference device, 61 Data acquisition unit, 62 Inference unit, 100 Control system

Claims

1. Lighting equipment, Air conditioning equipment, A control system that uses a trained control model to infer the set values ​​of the lighting equipment and the air conditioning equipment from weather information, the state of the lighting equipment corresponding to the weather information, and the state of the air conditioning equipment corresponding to the weather information, infers the set values ​​from the weather information, the state of the lighting equipment corresponding to the weather information, and the state of the air conditioning equipment corresponding to the weather information, and controls the lighting equipment and the air conditioning equipment using the set values, Equipped with, The control system is characterized by having a mode in which the set value is used as is and a mode in which it is used after making predetermined changes.

2. The control system according to claim 1, characterized in that the management equipment infers the set value using the weather information of the location of the lighting equipment.

3. The control system according to claim 1 or 2, characterized in that the management equipment extracts a model corresponding to the weather information from the learned control model, and then uses the extracted model to infer the set value from the state of the lighting equipment corresponding to the weather information and the state of the air conditioning equipment corresponding to the weather information.

4. The status of the lighting equipment corresponding to the weather information includes information on the number of people present in the space where the lighting equipment is installed. The control system according to claim 1 or 2, characterized in that the set value includes the dimming rate or color temperature of the lighting equipment.

5. The status of the air conditioning equipment corresponding to the weather information includes information on the indoor temperature. The control system according to claim 1 or 2, characterized in that the set value includes the operating mode or set temperature of the air conditioning equipment.

6. The control system according to claim 1 or 2, characterized in that the management equipment learns the times when people enter and exit the space in which the lighting equipment is installed, infers the time when people will come into the space, and starts controlling the lighting equipment and the air conditioning equipment before the inferred time.

7. The control system according to claim 1 or 2, characterized in that the management equipment learns the times when people enter and exit the space in which the lighting equipment is installed, infers the time when people leave the space, and starts controlling the lighting equipment and the air conditioning equipment before the inferred time.

8. A data acquisition unit that acquires weather information, the status of lighting equipment corresponding to the weather information, and the status of air conditioning equipment corresponding to the weather information. An inference unit that uses a trained control model to infer the set values ​​of the lighting equipment and the air conditioning equipment from the weather information, the state of the lighting equipment corresponding to the weather information, and the state of the air conditioning equipment corresponding to the weather information, infers the set values ​​from the weather information, the state of the lighting equipment corresponding to the weather information, and the state of the air conditioning equipment corresponding to the weather information, and controls the lighting equipment and the air conditioning equipment using the set values, Equipped with, An inference device characterized by having a mode in which the aforementioned setting values ​​are used as they are, and a mode in which they are used after being modified in a predetermined manner.

9. A data acquisition unit that acquires weather information, the status of lighting equipment corresponding to the weather information, and the status of air conditioning equipment corresponding to the weather information. A model generation unit generates a trained control model for inferring the set values ​​of the lighting equipment and the air conditioning equipment from the weather information, the state of the lighting equipment corresponding to the weather information, and the state of the air conditioning equipment corresponding to the weather information. Equipped with, The learning device is characterized in that the model generation unit modifies a date or season control model corresponding to the weather information based on the weather information, and then modifies the control model further based on the state of the lighting equipment and the state of the air conditioning equipment corresponding to the weather information, and stores it as the learned control model.

10. The learning device according to claim 9, characterized in that the model generation unit changes the control model based on the time corresponding to the weather information.

Images