Air conditioning control device and air conditioning system

Abstract

This air conditioning control device for controlling an air conditioner comprises an acquisition unit, an indoor model construction unit, a coupled analysis unit, a control target determination unit, and a command unit. The acquisition unit acquires room shape information indicating the shape of an air-conditioning target space accommodating a user and air state information relating to the state of air in the air-conditioning target space. The indoor model construction unit constructs an indoor model for CFD simulation on the basis of the room shape information and the air state information. The coupled analysis unit performs CFD simulation on the basis of the indoor model, and derives a state quantity indicating the state of air at each time point within a predetermined first time range. The coupled analysis unit derives a deviation of the state quantity at each time point from a preset target state quantity, integrates the deviation at each time point over the first time range, and derives an optimal solution for control parameters of the air conditioner, the optimal solution minimizing an objective function containing the obtained integral value. The control target determination unit determines control target values that are target values of the control parameters on the basis of the optimal solution. The command unit issues a command to the air conditioner on the basis of the control target values.

Description

[Technical Field]

[0001] The present disclosure relates to an air conditioning control device that controls an air conditioner and an air conditioning system. [Background technology]

[0002] Conventionally, a technology has been proposed for controlling the thermal environment in a space to be air-conditioned based on thermal fluid analysis (see, for example, Patent Document 1). This technology executes a simulation based on thermal fluid analysis and optimizes air-conditioning control based on the simulation results. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2014-31899 Summary of the Invention [Problem to be solved by the invention]

[0004] However, simulations based on thermal fluid dynamics often take a long time to obtain an optimal solution. Furthermore, the technology described in Patent Document 1 is based on the premise of transitioning from a solution obtained by prior optimization to the next optimal solution, so there is a possibility that user comfort may be impaired from an arbitrary state, such as at startup, until control based on the optimal solution is executed.

[0005] The present disclosure has been made to solve the above-mentioned problems, and aims to provide an air conditioning control device and an air conditioning system that enable rapid improvement in user comfort. [Means for solving the problem]

[0006] The air conditioning control device of the present disclosure is an air conditioning control device that controls an air conditioner that conditions a space to be air-conditioned, and includes: an acquisition unit that acquires room shape information that indicates the shape of the space to be air-conditioned and air condition information related to the state of the air in the space to be air-conditioned; an indoor model construction unit that constructs an indoor model for CFD simulation based on the room shape information and the air condition information; a coupled analysis unit that executes the CFD simulation based on the indoor model, derives state quantities that indicate the state of the air at each time point in a predetermined first time range, derives the deviation of the state quantities at each time point from a predetermined target state quantity, integrates the deviation at each time point in the first time range, and derives an optimal solution for the control parameters of the air conditioner that minimizes an objective function including the integrated value obtained by the integration; a control target determination unit that determines a control target value that is a target value of the control parameter based on the optimal solution; and a command unit that issues commands to the air conditioner based on the control target value.

[0007] The air conditioning system according to the present disclosure is an air conditioning system having an air conditioning control device that controls an air conditioner that conditions an air conditioner in an air-conditioned space, and a server that communicates with the air conditioning control device, wherein the air conditioning control device comprises an acquisition unit that acquires room shape information that indicates the shape of the air-conditioned space and air condition information related to the state of the air in the air-conditioned space, an indoor model construction unit that constructs an indoor model for a CFD simulation based on the room shape information and the air condition information, and a first communication unit that transmits the indoor model to the server, and the server executes the CFD simulation based on the indoor model and transmits the indoor model to the server at a predetermined first time. the air conditioning control device further comprises a coupled analysis unit that derives a state quantity indicating the state of the air at each time point within a range, derives the deviation of the state quantity at each time point from a predetermined target state quantity, integrates the deviation at each time point within the first time range, and derives an optimal solution for the control parameters of the air conditioner that minimizes an objective function including the integrated value obtained by the integration; and a second communication unit that transmits the optimal solution to the air conditioning control device, wherein the air conditioning control device further comprises a control target determination unit that determines a control target value that is a target value for the control parameter based on the optimal solution obtained from the server, and a command unit that issues commands to the air conditioner based on the control target value. [Effects of the Invention]

[0008] In the air conditioning control device and air conditioning system according to the present disclosure, the acquisition unit acquires room shape information and air condition information, and the indoor model construction unit constructs an indoor model based on the room shape information and air condition information. This enables the indoor model construction unit to construct an indoor model according to the air condition of the air-conditioned space, and the coupled analysis unit to derive an optimal solution according to the indoor model. Therefore, the air conditioning control device can perform air conditioning control based on the optimal solution of the indoor model according to the air condition of the air-conditioned space. This allows the air conditioning control device to efficiently change the current air condition of the air-conditioned space to the air condition desired by the user. This enables a rapid improvement in user comfort. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a diagram schematically illustrating an example of the configuration of an air conditioning system including an air conditioning control device according to a first embodiment. [Figure 2] 1 is a block diagram showing an example of the configuration of an air conditioning control device according to a first embodiment. [Figure 3] 4 is a flowchart illustrating a process of determining a target region by a target region determining unit according to the first embodiment. [Figure 4] 3 is a schematic diagram illustrating a target region determined by a target region determining unit according to the first embodiment. FIG. [Figure 5] 4 is a flowchart illustrating an analysis process performed by a coupled analysis unit according to the first embodiment. [Figure 6] 10 is a flowchart illustrating a sensitivity derivation process performed by a coupled analysis unit according to the first embodiment. [Figure 7] FIG. 2 is a schematic diagram for explaining the direction on the time axis of the process of deriving each of the state quantities and the adjoint variables in the first embodiment. [Figure 8] 4 is a flowchart illustrating a process for determining a control target value at a specific timing performed by the air conditioning control device according to the first embodiment. [Figure 9] 1 is a diagram illustrating an example of a hardware configuration of an air conditioning control device according to a first embodiment. [Figure 10] FIG. 10 is a block diagram showing an example of the configuration of a target region determining unit according to the second embodiment. [Figure 11] FIG. 11 is a schematic diagram illustrating a user's stay area based on location information in the second embodiment. [Figure 12] FIG. 10 is a schematic diagram showing an example of a neural network according to the second embodiment. [Figure 13] 10 is a flowchart illustrating a process for acquiring radio wave information by an air conditioning control device according to a second embodiment. [Figure 14] 10 is a flowchart illustrating a learning process by a learning model generation unit in embodiment 2. [Figure 15]10 is a flowchart illustrating a target area determination process performed by an air conditioning control device according to a second embodiment. [Figure 16] FIG. 11 is a diagram for explaining the process of deriving adjoint variables and sensitivities by the coupled analysis unit in the third embodiment. [Figure 17] 11 is a flowchart illustrating a sensitivity derivation process performed by a coupled analysis unit in the third embodiment. [Figure 18] FIG. 10 is a block diagram illustrating the configuration of an air conditioning system according to a fourth embodiment. [Figure 19] FIG. 10 is a diagram illustrating an example of a hardware configuration of an air conditioning control device according to a fourth embodiment. [Figure 20] FIG. 10 is a diagram illustrating an example of a hardware configuration of a server according to a fourth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, an air conditioning control device according to an embodiment will be described in detail with reference to the drawings.

[0011] Embodiment 1 1 is a diagram schematically illustrating an example of the configuration of an air conditioning system including an air conditioning control device according to Embodiment 1. The air conditioning system 100 according to Embodiment 1 has an air conditioner 1, a detection unit 2, and an air conditioning control device 3. The air conditioning control device 3 is connected to be able to communicate with the air conditioner 1 and the detection unit 2 via an electrical communication line 5. Note that the air conditioning control device 3 may also communicate wirelessly with the air conditioner 1 and the detection unit 2.

[0012] The air conditioner 1 includes an outdoor unit 10, an indoor unit 11, and a remote controller 12. The outdoor unit 10 and the indoor unit 11 are connected by heat medium piping (not shown), with the outdoor unit 10 cooling or heating the heat medium, and the indoor unit 11 exchanging heat between the air in the space to be air-conditioned and the heat medium, thereby adjusting the temperature of the space to be air-conditioned. Examples of the heat medium include water, brine, and a refrigerant. Examples of the refrigerant include HFC refrigerants, which are widely available, such as R32, R410A, or R448A, and natural refrigerants, such as R290 or R717, which are environmentally friendly.

[0013] The remote controller 12 is used to receive instructions from the user to the air conditioner 1 and cause the outdoor unit 10 and the indoor unit 11 to perform operations in accordance with the instructions. Examples of such instructions include instructions to start or stop operation, instructions regarding the set temperature, instructions regarding the air volume, instructions regarding the air direction, etc. Hereinafter, information indicating instructions input by the user to the remote controller 12 may also be referred to as instruction information.

[0014] The detection unit 2 includes a plurality of sensors 20 that acquire various types of information about the air-conditioned space. At least one of the plurality of sensors 20 is, for example, a thermograph, and acquires information indicating the temperature distribution in the air-conditioned space. The information indicating the temperature distribution is, for example, information on a thermal image. Hereinafter, the information indicating the temperature distribution may also be referred to as temperature distribution information. The temperature distribution information is an example of stay information that indicates the area in which a user stays within the air-conditioned space.

[0015] The multiple sensors 20 include one or more temperature sensors that detect the air temperature in the air-conditioned space. When the detection unit 2 includes two or more temperature sensors, each temperature sensor is installed at a different position in the air-conditioned space and detects the air temperature at each installation position. Hereinafter, information indicating the air temperature in the air-conditioned space may also be referred to as temperature information. Temperature information is an example of air condition information that indicates the state of the air in the air-conditioned space.

[0016] The multiple sensors 20 may include one or more flow meters that detect the air flow velocity within the air-conditioned space. When the detection unit 2 includes two or more flow meters, each flow meter is installed at a different position within the air-conditioned space and detects the air flow velocity at each installation position. Hereinafter, information indicating the air flow velocity within the air-conditioned space may also be referred to as flow velocity information. Flow velocity information is an example of air condition information.

[0017] The multiple sensors 20 may include one or more air pressure sensors that detect the air pressure in the air-conditioned space. When the detection unit 2 includes two or more air pressure sensors, each air pressure sensor is installed at a different position in the air-conditioned space and detects the air pressure at each installation position. Hereinafter, information indicating the air pressure in the air-conditioned space may also be referred to as air pressure information. Air pressure information is an example of air condition information.

[0018] The multiple sensors 20 may include at least one of a photoelectric sensor, a laser displacement sensor with a built-in camera, an ultrasonic sensor, and an image recognition sensor. This allows the detection unit 2 to acquire information indicating the shape and dimensions of the air-conditioned space, i.e., the width, depth, and height of the room. Hereinafter, information indicating the shape and dimensions of the air-conditioned space may also be referred to as room shape information.

[0019] The air conditioning control device 3 controls the air conditioner 1 based on the above-mentioned room shape information, air state information, instruction information, etc. Figure 2 is a block diagram showing an example configuration of the air conditioning control device according to Embodiment 1. The air conditioning control device 3 includes an acquisition unit 30, a storage unit 31, a current state estimation unit 32, an indoor model construction unit 33, an equipment model construction unit 34, a target area determination unit 35, a coupled analysis unit 36, a control target determination unit 37, and a command unit 38.

[0020] The acquisition unit 30 acquires instruction information and device information from the air conditioner 1. The device information is information indicating the performance of the air conditioner 1, and specifically, information including values ​​that can be set as control parameter values ​​for the air conditioner 1. The device information includes at least one of information indicating the rated capacity and operating range of devices such as compressors that constitute the refrigerant circuit of the air conditioner 1, information indicating the operating range of fans that send air to heat exchangers in the refrigerant circuit, and information indicating the operating range of air direction indicators that adjust the airflow direction into the air-conditioned space. The operating range of a compressor refers to the range of possible compressor frequencies. The operating range of a fan refers to the range of possible fan frequencies. Fans are provided in both the indoor unit 11 and the outdoor unit 10, and information indicating the operating range of the fan in the indoor unit 11 corresponds to information indicating the airflow volume from the indoor unit 11 to the air-conditioned space. Information indicating the operating range of the air direction indicator corresponds to information indicating the airflow direction from the indoor unit 11 to the air-conditioned space. The acquisition unit 30 may acquire device information from an external server or the like based on information that identifies the air conditioner 1, such as the serial number of the air conditioner 1.

[0021] The acquisition unit 30 acquires room shape information from the detection unit 2 or an external device. The room shape information from the external device may be created based on, for example, BIM (Building Information Modeling). The acquisition unit 30 acquires temperature distribution information and air condition information from the detection unit 2. The acquisition unit 30 may include all or some of the multiple sensors 20. In other words, all or some of the multiple sensors 20 may be included in the air conditioning control device 3. The memory unit 31 stores various information such as the room shape information and device information acquired by the acquisition unit 30.

[0022] The current state estimation unit 32 estimates the current state of the air in the air-conditioned space based on the air condition information acquired by the acquisition unit 30. For example, if multiple temperature sensors are installed in the air-conditioned space, the current state estimation unit 32 acquires the average temperature of the air-conditioned space at the current time based on the temperature information acquired from each temperature sensor. The current state estimation unit 32 then generates information that associates the average temperature with information indicating the current time. Note that the information indicating the current time is, for example, the current time. Hereinafter, information indicating the current time may also be referred to as current information. If one temperature sensor is installed in the air-conditioned space, the current state estimation unit 32 generates information that associates the temperature information acquired from that one temperature sensor with the current information.

[0023] When multiple flow meters are installed in the air-conditioned space, the current state estimation unit 32 acquires the average flow velocity of the air in the air-conditioned space at the current time based on flow velocity information acquired from each flow meter.The current state estimation unit 32 then generates information that associates the average flow velocity with the current information.When a single flow meter is installed in the air-conditioned space, the current state estimation unit 32 generates information that associates the flow velocity information acquired from that single flow meter with the current information.

[0024] When multiple air pressure sensors are installed in the air-conditioned space, the current state estimation unit 32 acquires the average air pressure in the air-conditioned space at the current time based on the air pressure information acquired from each air pressure sensor.The current state estimation unit 32 then generates information that associates the average air pressure with the current information.When a single air pressure sensor is installed in the air-conditioned space, the current state estimation unit 32 generates information that associates the air pressure information acquired from that single air pressure sensor with the current information.

[0025] The indoor model construction unit 33 constructs an indoor model based on the room shape information acquired by the acquisition unit 30 and the information generated by the current state estimation unit 32. The indoor model construction unit 33 stores the constructed indoor model in the storage unit 31. Here, the indoor model includes information for a CFD (Computational Fluid Dynamic) simulation executed by the coupled analysis unit 36 ​​(described later) regarding airflow in the air-conditioned space. Hereinafter, this simulation will be referred to as a CFD simulation. In the CFD simulation, the air-conditioned space is treated as a collection of multiple micro-regions divided into a grid pattern, and simulation processing is performed.

[0026] More specifically, the room model is a model for solving the governing equations of fluids in a CFD simulation (described later), and is a model related to airflow that reflects the geometric shape of the air-conditioned space. The model includes information on state quantities that indicate the state of the airflow and information on boundary conditions of the state field. The state quantities are the temperature, flow velocity, and pressure of the air. The state field refers to the field in the air-conditioned space, obtained by the state quantities at each position within the air-conditioned space. The boundary conditions are conditions related to the influence of boundaries such as walls, floors, and ceilings on the state field. The room model includes information on the state quantities and boundary conditions at each time point within a predetermined first time range, enabling unsteady simulations.

[0027] The equipment model construction unit 34 constructs an equipment model that associates the COP (Coefficient of performance) of the air conditioner 1 with the control parameters based on the equipment information, i.e., an equipment model that expresses the COP as a function of the control parameters. The equipment model construction unit 34 stores the constructed equipment model in the storage unit 31. Here, the equipment model is expressed, for example, by the following equation 1.

[0028]

number

[0029] V in Eq. inlet is the blowing speed, T inlet is the outlet temperature, f RAC indicates a function. The blowing speed is the speed of air blown out from the air outlet of the air conditioner 1. The blowing temperature is the temperature of the air blown out from the air outlet. The blowing speed and the blowing temperature are each an example of a control parameter.

[0030] The equipment model includes constraint conditions based on the equipment information. The constraint conditions refer to conditions on the values ​​that the control parameters of the air conditioner 1 can take. For example, the constraint conditions are conditions that indicate both or either the upper and lower limits of the values ​​that the control parameters can take. The constraint conditions are expressed, for example, by the following equation 2.

[0031]

number

[0032] V in Equation 2 min indicates the lower limit of the blowing speed, and V max indicates the upper limit of the blowing speed. min indicates the lower limit of the outlet temperature, and T max indicates the upper limit of the blown-out temperature. Note that the equipment model may include the constraint condition exemplified by Equation 2, but may not include the function relating to COP exemplified by Equation 1.

[0033] The target area determination unit 35 determines a target area to be subjected to air conditioning control based on the temperature distribution information. FIG. 3 is a flowchart illustrating the process of determining a target area by the target area determination unit according to the first embodiment. In step S1, the target area determination unit 35 refers to the temperature distribution information and identifies a heat source in the air-conditioning target area. That is, the target area determination unit 35 identifies the position, size, shape, etc. of the heat source. In step S2, the target area determination unit 35 determines the presence or absence of a person in the air-conditioned space based on the size, shape, etc. of the identified heat source and any changes over time in the position, size, shape, etc. If no person is present (step S2: no), the target area determination unit 35 returns the process to step S1. If a person is present (step S2: yes), in step S3, the target area determination unit 35 extracts the area where the person is present. Note that the target area determination unit 35 may also extract the surrounding area along with the area where the person is present. The surrounding area refers to an area within a predetermined distance from an area where a person is present, and the predetermined distance is, for example, 50 cm to 1 m. In step S4, the target area determination unit 35 stores information indicating the area extracted in step S3 in the storage unit 31. Hereinafter, the area including the position where a person is present, extracted by the target area determination unit 35 in step S3, may also be referred to as a candidate area, and the information indicating the candidate area may also be referred to as candidate area information.

[0034] In step S5, the target area determination unit 35 determines whether a predetermined determination time has elapsed. If the determination time has not elapsed (step S5: NO), the target area determination unit 35 returns the process to step S1. Note that if the process returns from step S5 to step S1 and step S4 is performed again, in step S4 the target area determination unit 35 stores candidate area information indicating the candidate area extracted in the current step S3 together with the candidate area information stored in the previous or previous step S4. That is, candidate area information is cumulatively stored in the storage unit 31.

[0035] If the determination time has elapsed (step S5: YES), in step S6 the target area determination unit 35 acquires information indicating the frequency of people present in each area within the air-conditioned space, based on the candidate area information stored in the storage unit 31. In step S7, the target area determination unit 35 determines whether or not there is a candidate area where the frequency of people present is equal to or greater than a predetermined threshold frequency.

[0036] If there is no candidate area where the human presence frequency is equal to or greater than the threshold frequency (step S7: NO), the target area determination unit 35 returns the process to step S1. In this case, the target area determination unit 35 may restart counting the determination time from the beginning.

[0037] If there is a candidate area where the human presence frequency is equal to or greater than the threshold frequency (step S7: YES), in step S8 the target area determination unit 35 determines the candidate area where the human presence frequency is equal to or greater than the threshold frequency as the target area. Note that the target area is an area in the air-conditioned space that is subject to air conditioning control by the air conditioner 1.

[0038] In step S9, the target area determination unit 35 stores information indicating the determined target area in the storage unit 31. At this time, the target area determination unit 35 may delete the stored candidate area information from the storage unit 31.

[0039] The target area may be determined based on input by the user to the air conditioning control device 3, instead of or in addition to the temperature distribution information. Specifically, the air conditioning control device 3 may receive settings from the user indicating the area in the air-conditioned space where the user is staying or the area where the user desires air conditioning, and determine the target area based on the received settings. Input to the air conditioning control device 3 may be made via both or either the air conditioner 1 and the user's terminal device. Information indicating the user's staying area, which is set in the air conditioning control device 3, is an example of stay information.

[0040] FIG. 4 is a schematic diagram illustrating a target area determined by the target area determination unit according to the first embodiment. In the example shown in FIG. 4, the determination time period is three days. Note that the outline arrow in FIG. 4 indicates the direction of time. As shown in FIG. 4, among the multiple sensors 20, the sensor 20 that acquires temperature distribution information is provided in the indoor unit 11. The target area determination unit 35 extracts a candidate area CA including the location of the user H based on temperature distribution information indicating the temperature distribution in the air-conditioned space on each of the first to third days, which is acquired from the sensor 20 via the acquisition unit 30. In FIG. 4, each of the candidate areas CA on the first to third days is represented by a cone with the position of the sensor 20 that acquires the temperature distribution information as its apex and the hatched surface as its base. The target area determination unit 35 determines the target area Ω based on the candidate area information indicating these candidate areas CA. In FIG. 4, the target area Ω is represented by an ellipse drawn with a dashed line, and is represented by a cone with the hatched surface inside as its base and the position of the sensor 20 as its apex. Note that the target area determination unit 35 may determine the height of the target area Ω from the floor based on the user's height or sitting height, rather than only the horizontal area. In Fig. 4, the height of the target area Ω from the floor is indicated by the hatched area outside the dashed ellipse.

[0041] The coupled analysis unit 36 ​​performs processing to optimize the control parameters of the air conditioner 1 based on the indoor model constructed by the indoor model construction unit 33, the target area determined by the target area determination unit 35, and the equipment model constructed by the equipment model construction unit 34. The optimal control parameter values ​​are values ​​that minimize an objective function, which will be described later. Hereinafter, the optimal control parameter values ​​may also be referred to as an optimal solution. The coupled analysis unit 36 ​​derives the optimal solution based on equation 3.

[0042]

number

[0043] In Equation 3, J is the objective function, and τ indicates the time in the first time range. W is a state variable vector indicating the air flow velocity, temperature, etc. in each minute region of the air-conditioned space. The components in the state variable vector W correspond to the above-mentioned state quantities. U is a control variable vector such as the blowout velocity and blowout temperature, and the components in the control variable vector U correspond to the control parameters. u in (τ) is the time series condition of the blowing velocity vector, and θ in (τ) is the time series condition of the outlet temperature. in (τ) and θ in (τ) is included in U. Also, u in (τ) and θ in Each of (τ) satisfies Equation 2. The expression "stR(W,U)=0" in Equation 3 indicates that the condition is to satisfy the governing equation, and R(W,U) is a function of the state variable vector W and the control variable vector U that satisfy the governing equation.

[0044] The governing equations are expressed by the following formulas 4 to 6.

[0045]

number

[0046]

number

[0047]

number

[0048] Equation 4 is the continuity equation that represents the conservation of mass of a fluid. Equation 5 is the incompressible Navier-Stokes equation that represents the conservation of momentum. And Equation 6 is the energy equation. In Equations 4 to 6, u represents the air flow velocity in each infinitesimal region. In Equations 5 to 6, ρ represents the air density, and t represents time. In Equation 5, p represents the air pressure vector in each infinitesimal region, and μ represents the air viscosity in each infinitesimal region. ρ0 is the reference air density. The third term on the right-hand side of Equation 5 represents buoyancy, and g is a value that represents the magnitude of an acceleration vector, such as a gravity vector. C in Equation 6 p represents the specific heat at constant pressure, T represents the temperature of the air in each micro-region, k represents the thermal conductivity, and Q represents the amount of heat given to each micro-region. Any of the above values ​​may be a predetermined value as needed.

[0049] J in Equation 3 is expressed by Equation 7.

[0050]

number

[0051] J in Equation 7 opt corresponds to J in the above-mentioned formula 3. J1 in formula 7 is shown by formula 8, and J2 is shown by formula 9.

[0052]

number

[0053]

number

[0054] In Equation 7, ω is a preset coefficient. ω may be set based on settings made by the user and the operating status of the air conditioner 1. ω may also be a vector or matrix including multiple coefficients.

[0055] In Equation 8, x, y, and z are the x-, y-, and z-coordinates in the air-conditioned space, respectively. τ indicates the time in the first time range. θ(x, y, z, τ) is the air temperature at time τ at the position in the air-conditioned space whose coordinates are (x, y, z). θ d is the target air temperature, which is set to improve the user's comfort level. u(x,y,z,τ) is the air flow velocity at time τ at a position in the air-conditioned space indicated by coordinates (x,y,z). u d is the target air flow rate, which is set to improve the user's comfort level. d and u d Hereinafter, these may be referred to as target state quantities. The target state quantities are based on instruction information input by the user to the remote controller 12 and acquired by the air conditioning control device 3. The target state quantities are stored in the storage unit 31.

[0056] In Equation 8, Ω indicates the target region, and T indicates the length of the first time range. In Equation 8, the start point of the first time range is set to 0, and the end point is set to T. The length of the first time range may be a fixed value set in advance, or may be changeable by the user. γ T is a weighting coefficient for the term related to the air temperature. v is a weighting coefficient for the term related to the air flow velocity. T and γ v Each of γ may be a preset value. T and γ v may be set based on at least one of the settings made by the user and the operating status of the air conditioner 1, or may be a vector or matrix including multiple coefficients.

[0057] As shown in Equation 8, J1 is represented by the deviation of the state quantity in the target region at each time within the first time range from the target state quantity. RAC indicates the air conditioning capacity. Air conditioning capacity Q RAC is shown by equation 10.

[0058]

number

[0059] The T in the "∫" that indicates the integral in Equation 10, i.e., the T that indicates the upper limit of the integral, indicates the length of the first time range. In Equation 10, ρ indicates the density of air, and C indicates the specific heat at constant pressure. V i indicates the blowing speed of the i-th air conditioner 1. In equation (10), it is assumed that n air conditioners 1 are installed in the space to be air-conditioned. A i indicates the area of ​​the air outlet of the i-th air conditioner 1. T i,inlet indicates the outlet temperature of the i-th air conditioner 1, and T i,outlet indicates the temperature of the air drawn into the i-th air conditioner 1.

[0060] The coupled analysis unit 36 ​​calculates the value of J in Equation 8 so as to satisfy Equations 4 to 6. opt The control variable vector U in equation 3 is determined so that the objective function expressed by the following equation is minimized. When the objective function is minimized, both or one of the following equations 11 and 12 holds true.

[0061]

number

[0062]

number

[0063] Equation 11 and Equation 12 are equations that indicate the convergence of the objective function. In Equation 11 and Equation 12, k indicates the number of times the objective function is updated by the coupled analysis unit 36. ε1 and ε2 are arbitrary small quantities. Note that the left side of Equation 12 corresponds to the sensitivity, which will be described later. The coupled analysis unit 36 ​​updates U in Equation 3 until either or both of Equation 11 and Equation 12 are satisfied.

[0064] The analysis processing by the coupled analysis unit 36 ​​will be described in detail below with reference to Fig. 5. Fig. 5 is a flowchart illustrating the analysis processing by the coupled analysis unit in embodiment 1. The coupled analysis unit 36 ​​repeats the processing of steps S11 to S15 until the value of the objective function is minimized.

[0065] In step S11, the coupled analysis unit 36 ​​executes a CFD simulation based on the indoor model. At this time, the coupled analysis unit 36 ​​performs a direct analysis. A direct analysis is an analysis that obtains state quantities in each infinitesimal region in the air-conditioned space from boundary conditions, governing equations, etc. In other words, the coupled analysis unit 36 ​​solves the governing equations shown in equations 4 to 6 based on the indoor model, and derives the state quantities in each infinitesimal region. At this time, the coupled analysis unit 36 ​​derives a state field that changes over time depending on boundary conditions, etc., so in the direct analysis, the state quantities are derived along the direction of time progression.

[0066] In this indoor model, the boundary condition at the air outlet of the air conditioner 1 is u in Equation 3. in (τ) and θ in (τ). In the following, the boundary condition indicates the u at each time point within the first time range. in (τ) and θ in A component of the control variable vector U including (τ) may be referred to as a first value. The first value is set to a predetermined initial value in the first step S11, i.e., in a step S11 before which step S15 has not been executed. The first value is determined by the coupled analysis unit 36 ​​for each time point within the first time range based on the equipment model. The coupled analysis unit 36 ​​may determine the first value based on settings such as a set temperature or a set wind speed set by the user.

[0067] In step S12, the coupled analysis unit 36 ​​calculates the state quantities in each microscopic region derived in step S11 and u in (τ) and θ in An objective function is derived based on the control variable vector U including (τ) and the target region Ω determined by the target region determination unit 35.

[0068] In step S13, the coupled analysis unit 36 ​​derives the sensitivity. The sensitivity corresponds to the degree of influence on the objective function due to a change in the value of the control parameter, and is expressed by equation (13).

[0069]

number

[0070] Equation 13 shows the sensitivity expressed in a non-dimensional manner. L is a Lagrangian, and the sensitivity is expressed as the first variation of L. Note that L corresponds to the optimization problem expressed by Equation 3, which is made into an unconstrained problem based on the Lagrangian relaxation method, and is expressed as shown in Equation 14 below.

[0071]

number

[0072] The first term J on the right-hand side of Equation 14 is the objective function, and the second term is the dot product of P and R. Here, P is the adjoint variable vector, and R is R in Equation 3. When R in Equation 3 is 0, the minimized J can be obtained by minimizing L, which is obtained by adding the dot product of R and P to J.

[0073] x in Eq. 13 i The subscript i in the formula (13) indicates either 1, 2, or 3, x1 indicates the x coordinate in the air-conditioned space, x2 indicates the y coordinate in the air-conditioned space, and x3 indicates the z coordinate in the air-conditioned space. a,in is the adjoint variable related to the air pressure at the outlet. T a,in is an adjoint variable related to the temperature of the air at the outlet. in is an adjoint variable related to the air flow velocity at the air outlet. Here, the adjoint variable is a variable introduced as a variable corresponding to an actual physical quantity for the purpose of deriving sensitivity. The adjoint variable will be described in detail later.

[0074] n in Equation 13 i is a component of the normal vector of the air outlet. In Equation 13, the direction of air blown out from the air conditioner 1 is the y direction. in,y is the y component of the outlet velocity. in is the outlet temperature, and u in is a component of the blowing velocity. In equation 13, θ in , u in Each of these is assumed to be non-dimensional.

[0075] λ in Equation 13 is expressed by Equation 15.

[0076]

number

[0077] p in Eq. 15 a,in and n i and x i and v in and θ in Each of these is the same as in Equation 13. Re in Equation 13 and Equation 15 is a dimensionless number and is shown by Equation 16.

[0078]

number

[0079] In equation 16, μ is the dynamic viscosity coefficient, and V ref is the characteristic speed, and L ref is the characteristic length. The characteristic velocity and the characteristic length are arbitrary values ​​that depend on the state of the target flow field, and the characteristic velocity is, for example, the blowing velocity, and the characteristic length is, for example, the width of the blowing outlet. Here, the flow field refers to a vector field in which the flow velocity is defined at an arbitrary point in space.

[0080] Pe in Equation 13 is a dimensionless number and is expressed by Equation 17.

[0081]

number

[0082] V in Equation 17 ref and L ref Each of these is the same as in equation 16. In equation 17, κ is the thermal diffusivity.

[0083] Fig. 6 is a flowchart illustrating the sensitivity derivation process performed by the coupled analysis unit in embodiment 1. The processes of steps S21 to S22 shown in Fig. 6 are the processes of step S13 in Fig. 5. In step S21, the coupled analysis unit 36 ​​derives the values ​​of the adjoint variables from the state quantities derived in step S11, based on the following equations (18) to (20).

[0084]

number

[0085]

number

[0086]

number

[0087] The subscripts i and j in formulas 18 to 20 indicate the x-coordinate, y-coordinate, and z-coordinate of the air-conditioned space, respectively. That is, i and j each indicate 1, 2, or 3, x1 indicates the x-coordinate in the air-conditioned space, x2 indicates the y-coordinate in the air-conditioned space, and x3 indicates the z-coordinate in the air-conditioned space. p in formula 19 a is p in Eq. a,in T in Eq. a is T in Eq. a,in v in equations 18 to 20 i is v in Eq. in is the i component of v jis v in Eq. in The j component of Equation 19 to Equation 20 is the j component of Equation 13. in In equations 19 to 20, u i is the u in Eq. in is the i component of u j is the u in Eq. in The j component of the equation. Re and Pe are the same as above. δ i,2 is 1 when the subscript i is 2, and is 0 when the subscript i is other than 2. As above, the direction of i=2 is the normal direction of the air outlet, i.e., the air outlet direction, which is the y direction.

[0088] In the first embodiment, α and β in equations 19 to 20 are coefficients, which are greater than 0 within the target region Ω and 0 outside the target region Ω. Ri in equation 20 is expressed by the following equation 21.

[0089]

number

[0090] g in Equation 21 is the same as g in Equation 5. V in Equation 21 ref and L ref is the same as above. β 00 is the volume expansion coefficient, and T ref is the representative temperature. The representative temperature is an arbitrary value that depends on the state of the target flow field, and is, for example, the outlet temperature.

[0091] The coupled analysis unit 36 ​​performs an inverse analysis in step S21 to derive adjoint variables. Here, the inverse analysis reverses the causal relationship, i.e., input and output, of the direct analysis, and is a method of deriving boundary conditions, etc. for obtaining state quantities from state quantities that are the output results of the direct analysis. The coupled analysis unit 36 ​​derives the boundary conditions, etc. from a state field that has changed over time due to the boundary conditions, etc., in the direction opposite to the direction of time progression. That is, in the first embodiment, the adjoint variables corresponding to the boundary conditions at the air outlet are derived in the direction opposite to the direction of time progression.

[0092] 7 is a schematic diagram for explaining the direction on the time axis of the derivation process of each of the state quantities and the adjoint variables in the first embodiment. As shown in FIG. 7, in step S11 of FIG. 5, the coupled analysis unit 36 ​​derives the state quantities in order from t0 to (t0+T), where t is the start time point and (t0+T) is the end time point of the first time range. T is the length of the first time range. The coupled analysis unit 36 ​​stores the derived state quantities at each time point t from t0 to (t0+T) in the storage unit 31.

[0093] 7, in step S21 of Fig. 6, the coupled analysis unit 36 ​​derives adjoint variables at each time point t from the state quantities at that time point t stored in the storage unit 31, based on equations 18 to 20. At this time, the coupled analysis unit 36 ​​sets the start time point as (t0+T) and the end time point as t0, and derives the adjoint variables by going back in time in order from (t0+T) to t0.

[0094] In step S22 of FIG. 6, the coupled analysis unit 36 ​​derives the sensitivity based on Equation 13 from the state quantities derived in step S11 and the adjoint variables derived in step S21.

[0095] In step S14 of FIG. 5, the coupled analysis unit 36 ​​updates the control variable vector based on the following equation (22).

[0096]

number

[0097] In Equation 22, k indicates the number of updates of the control variable vector, and x(t) k is the control variable vector before updating, and x(t) k+1 is the updated control variable vector, i.e., x(t) k is the control variable vector obtained by the kth update, and x(t) k+1 is the control variable vector obtained by the (k+1)th update. α(t) k is a sensitivity vector when the number of updates is k, and includes components corresponding to the sensitivity of each control parameter such as the outlet temperature and outlet speed. k is the update width of each component of the control variable vector. Note that, although the equation (22) may be an update method based on the steepest descent method, it may also be an update method such as the quasi-Newton method using information indicating sensitivity.

[0098] In step S15, the coupled analysis unit 36 ​​determines whether the objective function converges. That is, the coupled analysis unit 36 ​​determines whether or not Equation 11 holds true using the objective function obtained from the control variable vector before the update and the objective function obtained from the control variable vector after the update. Alternatively, the coupled analysis unit 36 ​​may determine whether or not the sensitivity derived in step S13 satisfies Equation 12, thereby determining whether or not the objective function converges. In this case, the processing of step S15 may be performed after the processing of step S13, but before the processing of step S14, or in parallel with the processing of step S14. Note that Equation 12 can be rewritten, for example, as shown in Equation 23 below. L and v in Equation 23 in,y , θ in is the same as in the case of equation 13. δ is an arbitrary small quantity.

[0099]

number

[0100] If it is determined in step S15 that the objective function does not converge (step S15: NO), the coupled analysis unit 36 ​​returns the process to step S11. In this case, the coupled analysis unit 36 ​​performs the processes from step S15 to step S11 onwards based on the updated control variable vector. If it is determined in step S15 that the objective function does converge (step S15: YES), the coupled analysis unit 36 ​​ends the analysis process.

[0101] Before or after step S15, or in parallel with step S15, the coupled analysis unit 36 ​​stores the control variable vector obtained in step S14 in the storage unit 31. When it is determined in step S15 that the objective function has converged, the control variable vector stored in the storage unit 31 has the optimal solution for the control parameters as its components. The coupled analysis unit 36 ​​stores the control variable vector obtained in step S14 in association with the indoor model and the equipment model in the storage unit 31. At this time, the coupled analysis unit 36 ​​sets the boundary condition for the air outlet of the air conditioner 1, among the boundary conditions of the indoor model, as the condition indicated by the control variable vector obtained in step S14. When re-executing the processing from step S11 onwards, the coupled analysis unit 36 ​​updates the first value based on the equipment model with the values ​​of the components of the control variable vector obtained in step S14.

[0102] Returning to FIG. 2, the control target determination unit 37 in the first embodiment determines the temperature at a first position as the control target temperature based on the temperature distribution in the air-conditioned space realized by the optimal solution obtained by the coupled analysis unit 36. Examples of the first position include the installation position of the temperature sensor described above or a position in the target area. The control target determination unit 37 stores the determined control target temperature in the storage unit 31 in association with the indoor model, the equipment model, and the optimal solution. Note that the control target determination unit 37 may determine the air flow velocity at a second position as the control target velocity based on the air flow velocity distribution in the air-conditioned space realized by the optimal solution obtained by the coupled analysis unit 36, and store the control target velocity in the storage unit 31. Examples of the second position include the installation position of the flow meter described above or a position in the target area. The control target determination unit 37 may determine the air pressure at a third position as the control target air pressure based on the air pressure distribution in the air-conditioned space realized by the optimal solution obtained by the coupled analysis unit 36, and store this in the storage unit 31. Examples of the third position include the installation position of the barometer described above, or a position within the target area. Hereinafter, the respective values ​​of the control target temperature, control target speed, and control target air pressure may also be referred to as control target values.

[0103] The command unit 38 controls the air conditioner 1 based on the control target value derived by the control target determination unit 37.

[0104] The air conditioning control device 3 may control the air conditioner 1 based on the control target values ​​determined by the control target determination unit 37 and stored in the storage unit 31. However, the indoor model, the equipment model, or the above-mentioned target state quantities may also change based on changes in the furniture arrangement in the air-conditioned space, seasonal changes, or changes in user settings. Therefore, the air conditioning control device 3 may reconstruct both or either the indoor model and the equipment model at a specific timing, derive an optimal solution based on the reconstructed model, and re-determine the control target values. Examples of the specific timing include a specific time of day, a specific date and time within one to four weeks, a specific date and time within one to three months, or when the air conditioner 1 or the air conditioning control device 3 is started. This specific timing may be set by the user. Below, the processing by the air conditioning control device 3 at the specific timing is described with reference to FIG. 8.

[0105] FIG. 8 is a flowchart illustrating a process for determining a control target value at a specific timing by the air conditioning control device according to the first embodiment. It is assumed that, prior to step S31, the indoor model construction unit 33 constructs an indoor model, and the equipment model construction unit 34 constructs an equipment model. In step S31, the control target determination unit 37 determines whether a first condition is satisfied. The first condition includes a condition that the indoor model constructed by the indoor model construction unit 33 is identical to the indoor model stored in the storage unit 31, and that the equipment model constructed by the equipment model construction unit 34 is identical to the equipment model stored in the storage unit 31. The first condition also includes a condition that, among the boundary conditions in the indoor model, the values ​​of control parameters such as the discharge temperature and discharge speed indicated by the boundary conditions related to the air outlet of the air conditioner 1 are equal to the values ​​of control parameters already stored as an optimal solution. The first condition also includes a condition that target state quantities such as the target temperature and target flow rate indicated by newly obtained instruction information are equal to target state quantities already set and stored. The first condition may include at least one of the following conditions: the indoor model constructed by the indoor model construction unit 33 is identical to the indoor model stored in the memory unit 31; the equipment model constructed by the equipment model construction unit 34 is identical to the equipment model stored in the memory unit 31; and the newly obtained target state quantity is identical to the target state quantity stored in the memory unit 31.

[0106] If the first condition is satisfied in step S31 (step S31: YES), the air conditioning control device 3 proceeds to step S33. If the first condition is not satisfied in step S31 (step S31: NO), the coupled analysis unit 36 ​​executes the analysis process shown in FIGS. 5 and 6 described above in step S32. At this time, the coupled analysis unit 36 ​​stores the obtained optimal solution. After the process of step S32, the air conditioning control device 3 proceeds to step S33. In step S33, the control target determination unit 37 determines a control target value based on the optimal solution stored in the memory unit 31. In step S34, the command unit 38 controls the air conditioner 1 based on the control target value determined in step S33.

[0107] This allows optimization of air conditioning in the air conditioned space at an appropriate timing. Note that prior to the processing of step S31 described above, the target area determination unit 35 may re-determine the target area.

[0108] The hardware configuration of the air conditioning control device 3 will be described below with reference to FIG. 9. FIG. 9 is a diagram illustrating an example of the hardware configuration of an air conditioning control device according to the first embodiment. The air conditioning control device 3 can be configured, for example, with a first processor 41, a first memory 42, a storage device 43, an input interface circuit 44, an input / output interface circuit 45, and the like, all connected to one another via a first bus 40. The first processor 41 is, for example, a central processing unit (CPU) or a micro processing unit (MPU). The first memory 42 is, for example, a read-only memory (ROM) or a random access memory (RAM). The storage device 43 may be, for example, a magnetic disk such as a hard disk drive (HDD) or an optical disk such as a compact disc (CD). Alternatively, the storage device 43 may be a flash memory such as a universal serial bus (USB) memory or an SD memory card.

[0109] The functions of the acquisition unit 30 can be realized by an input interface circuit 44 connected to the multiple sensors 20 and an input / output interface circuit 45 connected to the air conditioner 1. The functions of the acquisition unit 30 may be realized by the input interface circuit 44, the input / output interface circuit 45, and the first processor 41. The functions of the memory unit 31 can be realized by the storage device 43. The functions of the memory unit 31 may be realized by the first memory 42. In this case, the storage device 43 does not need to be included in the air conditioning control device 3. The functions of the current state estimation unit 32, the indoor model construction unit 33, the equipment model construction unit 34, the target area determination unit 35, the coupled analysis unit 36, and the control target determination unit 37 can be realized by the first processor 41 reading and executing various programs stored in the first memory 42. The functions of the command unit 38 can be realized by the input / output interface circuit 45. The functions of the command unit 38 may be realized by the input / output interface circuit 45 and the first processor 41. All or part of the functions of the air conditioning control device 3 described above may be realized by dedicated hardware.

[0110] The effects of the air conditioning control device 3 according to the first embodiment are described below. The air conditioning control device 3 according to the first embodiment controls an air conditioner 1 that conditions the air in a space to be air-conditioned. The air conditioning control device 3 includes an acquisition unit 30, an indoor model construction unit 33, a coupled analysis unit 36, a control target determination unit 37, and a command unit 38. The acquisition unit 30 acquires room shape information indicating the shape of the space to be air-conditioned and air state information related to the state of the air in the space to be air-conditioned. The indoor model construction unit 33 constructs an indoor model for a CFD simulation based on the room shape information and the air state information. The coupled analysis unit 36 ​​executes a CFD simulation based on the indoor model. That is, the coupled analysis unit 36 ​​derives state quantities indicating the state of the air at each time point within a predetermined first time range. The coupled analysis unit 36 ​​then derives the deviation of the state quantity at each time point from a preset target state quantity, integrates the deviation at each time point over a first time range, and derives an optimal solution for the control parameters of the air conditioner 1 that minimizes an objective function including the integral value obtained by the integration. The control target determination unit 37 determines control target values, which are target values ​​for the control parameters, based on the optimal solution. The command unit 38 issues commands to the air conditioner 1 based on the control target value.

[0111] According to the above configuration, the acquisition unit 30 acquires room shape information and air condition information, and the indoor model construction unit 33 constructs an indoor model based on the room shape information and air condition information. This makes it possible to construct an indoor model that corresponds to the current air condition of the air-conditioned space. The coupled analysis unit 36 ​​obtains an optimal solution from this indoor model, and the air conditioning control device 3 controls the air conditioner 1 based on this optimal solution. This enables the air conditioner 1 to change the current air condition of the air-conditioned space to the air condition desired by the user. Therefore, even if an optimal solution has not been obtained, the air conditioner 1 can perform air conditioning as desired by the user, enabling a rapid improvement in user comfort.

[0112] The acquisition unit 30 in the first embodiment acquires stay information indicating the area where people stay within the air-conditioned space. The air conditioning control device 3 further includes a target area determination unit 35 that determines a target area, which is an area in the air-conditioned space that is subject to air conditioning control, based on the stay information. The coupled analysis unit 36 ​​derives an objective function by integrating the deviation at each time point within the first time range and the target area. This eliminates the need for the coupled analysis unit 36 ​​to perform integration processing across the entire air-conditioned space when deriving the objective function, thereby reducing the amount of processing. This shortens the time it takes to achieve the air conditioning desired by the user. The air-conditioning control device 3 can therefore quickly improve user comfort.

[0113] The occupancy information in the first embodiment is temperature distribution information that indicates the temperature distribution in the air-conditioned space. The target area determination unit 35 identifies areas in the air-conditioned space where people are present based on the temperature distribution information and obtains the frequency with which people are present in the identified areas. The target area determination unit 35 then determines the target area based on the obtained frequency. This allows the air conditioning control device 3 to target areas where people are frequently present, thereby improving user comfort and saving energy.

[0114] The control target determination unit 37 in the first embodiment determines a control target value based on the air temperature at a predetermined first position on the temperature distribution of the air-conditioned space realized by the optimal solution. This speeds up and simplifies the process of determining the control target value. Therefore, the air conditioning desired by the user can be realized more quickly.

[0115] The acquisition unit 30 in the first embodiment acquires equipment information related to the performance of the air conditioner 1 from the air conditioner 1. The air conditioning control device 3 further includes an equipment model construction unit 34. The equipment model construction unit 34 constructs an equipment model that specifies the conditions for the values ​​of the control parameters based on the equipment information. The coupled analysis unit 36 ​​derives an objective function based on the equipment model. This allows an optimal solution for the control parameters according to the performance of the air conditioner 1 to be obtained. Therefore, the air conditioning control device 3 can issue appropriate commands to the air conditioner 1 according to the performance of the air conditioner 1.

[0116] The indoor model in the first embodiment includes state quantities at the air outlet from the air conditioner 1, which are based on the equipment model. This allows the air outlet speed and temperature from the actually installed air conditioner 1, etc., to be reflected in the boundary conditions of the indoor model, thereby improving the accuracy of the indoor model.

[0117] The equipment model in the first embodiment includes information that associates the coefficient of performance of the air conditioner 1 with the values ​​of the control parameters, thereby making it possible to derive an optimal solution that improves the coefficient of performance.

[0118] The acquisition unit 30 in the first embodiment acquires instruction information indicating the settings input by a person to the air conditioner 1. The target state quantities are determined based on the instruction information. This allows the coupled analysis unit 36 ​​to obtain an optimal solution for achieving the air conditioning desired by the user.

[0119] The air conditioning control device 3 further includes a storage unit 31. The storage unit 31 stores an indoor model, a target state quantity, an equipment model, and an optimal solution in association with each other. The control target determination unit 37 derives a control target value based on the optimal solution stored in the storage unit 31 when the target state quantity based on the instruction information reacquired by the acquisition unit 30 at a specific timing is equal to the target state quantity stored in the storage unit 31, the indoor model based on the air condition information reacquired by the acquisition unit 30 at a specific timing is equal to the indoor model stored in the storage unit 31, and the equipment model based on the equipment information reacquired by the acquisition unit 30 at a specific timing is equal to the equipment model stored in the storage unit 31. As a result, when there are no changes in the air condition of the air-conditioned space and the instruction information and no changes to the air conditioner 1, the air conditioning control device 3 performs control based on the stored optimal solution, thereby reducing processing, such as the need to derive an optimal solution, and allowing the air conditioner 1 to perform air conditioning as desired by the user. Therefore, the air conditioning control device 3 can quickly execute the control process, and the user's comfort can be improved even more quickly.

[0120] Embodiment 2 The air conditioning control device 3 according to the second embodiment will be described in detail below. In the second embodiment, the same components as those in the first embodiment will be denoted by the same reference numerals. Furthermore, in the second embodiment, the same configurations as those in the first embodiment and the same functions as those in the first embodiment will not be described unless there are special circumstances.

[0121] The configuration of an air conditioning system 100 according to the second embodiment is illustrated in Fig. 1, as in the first embodiment, and the configuration of an air conditioning control device 3 according to the second embodiment is illustrated in Fig. 2, as in the first embodiment. Furthermore, the hardware configuration of the air conditioning control device 3 according to the second embodiment is illustrated in Fig. 9, as in the first embodiment.

[0122] The stay information in the second embodiment is temperature distribution information. The acquisition unit 30 in the second embodiment acquires radio wave information indicating the radio wave strength and radio wave reception direction of a signal indicating an instruction input by a user to the remote controller 12 or the terminal device. Note that the radio wave strength refers to the strength of the radio waves received by the air conditioning control device 3 or the indoor unit 11 from the remote controller 12 or the terminal device. The radio wave reception direction refers to the direction in which the air conditioning control device 3 or the indoor unit 11 receives radio waves from the remote controller 12 or the terminal device.

[0123] When acquiring radio wave information, the acquiring unit 30 associates the temperature distribution information acquired within a predetermined time period before or after the acquisition of the radio wave information with the radio wave information and stores the temperature distribution information acquired within the predetermined time period in the storage unit 31. The predetermined time period may be, for example, 10 seconds to 3 minutes. The acquiring unit 30 may also store the first temperature distribution information acquired after the acquisition of the radio wave information, or the last temperature distribution information acquired before the acquisition of the radio wave information, in the storage unit 31 in association with the radio wave information.

[0124] The acquisition unit 30 may constantly acquire temperature distribution information from the sensor 20 that detects the temperature distribution in the air-conditioned space. Alternatively, the acquisition unit 30 may transmit a request signal to the sensor 20 to request that the sensor 20 transmit temperature distribution information to the air conditioning control device 3, triggered by the acquisition of radio wave information, and acquire the temperature distribution information from the sensor 20 in response to the request signal. Note that if the acquisition unit 30 includes the sensor 20, the acquisition unit 30 may acquire the temperature distribution information triggered by the acquisition of radio wave information. Alternatively, the acquisition unit 30 may constantly acquire temperature distribution information.

[0125] The acquisition unit 30 may acquire radio wave information and temperature distribution information multiple times during the above-mentioned determination time, and may associate the radio wave information acquired at each time point with the temperature distribution information acquired within a specified time before and after the time point at which the radio wave information was acquired, and store these in the storage unit 31. Note that the length of the determination time in the second embodiment may be the same as or different from the length of the determination time in the first embodiment.

[0126] The target area determination unit 35 in the second embodiment is equipped with an AI (Artificial Intelligence) function. Fig. 10 is a block diagram showing a configuration example of the target area determination unit in the second embodiment. The target area determination unit 35 in the second embodiment has a learning model generation unit 350 and an estimation unit 351.

[0127] The learning model generation unit 350 acquires the temperature distribution information and radio wave information, which are associated with each other, from the storage unit 31. The learning model generation unit 350 acquires position information indicating the position of the remote controller 12 or the terminal device based on the radio wave information. Note that the position of the remote controller 12 or the terminal device is estimated to coincide with the position of the user operating the remote controller 12 or the terminal device, or to be within, for example, 1 m from the user's position. Therefore, the position information corresponds to information indicating the user's position at the time the acquisition unit 30 acquires the radio wave information. The learning model generation unit 350 may acquire position information based on room shape information together with the radio wave information. Note that the spatial coordinates of the position information, room shape information, and temperature distribution information are associated with each other.

[0128] The learning model generation unit 350 performs machine learning based on the location information and temperature distribution information, or the location information, temperature distribution information, and room shape information, to generate a trained model. Hereinafter, the combination of location information and temperature distribution information, or the combination plus room shape information, may be referred to as training data. The trained model may also be referred to as a training model. More specifically, the learning model generation unit 350 regards the location information in the training data as the correct answer and generates a learning model for estimating the user's stay area from the temperature distribution information. The learning model generation unit 350 stores the generated learning model in the storage unit 31.

[0129] Fig. 11 is a schematic diagram illustrating a user's stay area based on position information in embodiment 2. In Fig. 11, the hatched area around user H operating remote controller 12 is obtained as the user's stay area BA. Note that Fig. 11 shows remote controller 12 in user H's hand, and stay area BA is obtained based on position information indicating the position of remote controller 12, but stay area BA may be obtained based on position information indicating the position of user H's terminal device instead of or in addition to the position information of remote controller 12.

[0130] The learning model generation unit 350 generates the learning model based on a known learning algorithm such as supervised learning, unsupervised learning, or reinforcement learning. As an example, the following describes a case where the learning model generation unit 350 generates a learning model based on a supervised learning algorithm using a neural network.

[0131] Fig. 12 is a schematic diagram showing an example of a neural network in embodiment 2. The neural network is composed of an input layer of multiple neurons, a middle layer of one or more neurons, and an output layer of multiple neurons. Fig. 12 shows three input layers X1-X3 each consisting of three neurons, two middle layers Y1-Y2 each consisting of two neurons, and three output layers Z1-Z3 each consisting of three neurons.

[0132] 12, when multiple input values ​​are input to input layers X1 to X3, intermediate values, which are weighted by w11 to w16, are input to intermediate layers Y1 to Y2. Then, output values, which are weighted by w21 to w26, are obtained from output layers Z1 to Z3. Note that the output values ​​from output layers Z1 to Z3 may change depending on the values ​​of weights w11 to w16 and weights w21 to w26, even if the input values ​​are the same.

[0133] The learning model generation unit 350 inputs temperature distribution information and room shape information into the input layer, and performs learning by adjusting the weights exemplified by w11 to w16 and w21 to w26 in Figure 12 so that the output result from the output layer becomes position information or approaches position information, thereby generating a learning model.

[0134] The estimation unit 351 estimates the user's position from the temperature distribution information acquired by the acquisition unit 30 based on the learning model stored in the storage unit 31, and determines the target area.

[0135] Note that both or one of the learning model generation unit 350 and the estimation unit 351 may be provided outside the air conditioning control device 3. Specifically, both or one of the learning model generation unit 350 and the estimation unit 351 may be provided in another device, such as a cloud server, that communicates with the air conditioning control device 3. Specifically, when the learning model generation unit 350 is provided outside the air conditioning control device 3, the learning model generation unit 350 receives the radio wave information, temperature distribution information, and room shape information acquired by the acquisition unit 30 from the air conditioning control device 3. The learning model generation unit 350 then acquires location information from the received radio wave information and generates a learning model from the location information, temperature distribution information, and room shape information. The learning model generation unit 350 then transmits the generated learning model to the air conditioning control device 3, and the memory unit 31 stores the learning model from the learning model generation unit 350.

[0136] FIG. 13 is a flowchart illustrating a process for acquiring radio wave information by the air conditioning control device according to the second embodiment. In step S41, the acquisition unit 30 acquires radio wave information. In step S42, the acquisition unit 30 associates the radio wave information acquired in step S41 with the following temperature distribution information and stores the information in the storage unit 31. The temperature distribution information is temperature distribution information acquired by the acquisition unit 30 within a specified time after the acquisition of the radio wave information in step S41. Alternatively, the temperature distribution information is temperature distribution information acquired by the acquisition unit 30 within a specified time before the acquisition of the radio wave information in step S41. Alternatively, the temperature distribution information is temperature distribution information last acquired by the acquisition unit 30 before the acquisition of the radio wave information in step S41, or temperature distribution information first acquired by the acquisition unit 30 after the acquisition of the radio wave information in step S41. The acquisition unit 30 may also acquire room shape information along with the temperature distribution information, and store the room shape information in the storage unit 31 in association with the radio wave information and the temperature distribution information. This makes it possible to obtain learning data that corresponds to the changed room shape even if the shape of the space to be air-conditioned changes due to changes in furniture arrangement or renovations, etc.

[0137] In step S43, the acquisition unit 30 or the target area determination unit 35 determines whether the determination time has elapsed since the acquisition unit 30 first acquired radio wave information. If the determination time has elapsed (step S43: YES), the air conditioning control device 3 ends the radio wave information acquisition process. If the determination time has not elapsed (step S43: NO), the air conditioning control device 3 returns the process to step S41. In the process of step S42, which is re-executed after the process of step S43, the acquisition unit 30 cumulatively stores the radio wave information, temperature distribution information, etc., without updating the radio wave information, temperature distribution information, etc., stored in the storage unit 31 with the newly acquired radio wave information, temperature distribution information, etc. Note that the learning data may include position information based on radio wave information at a given point in time, in which case the process of step S43 may be omitted.

[0138] 14 is a flowchart illustrating a learning process by the learning model generation unit in embodiment 2. In step S51, the learning model generation unit 350 acquires radio wave information, temperature distribution information, and room shape information from the storage unit 31. The room shape information in the storage unit 31 may be acquired in conjunction with the acquisition of radio wave information, or may be acquired in advance.

[0139] In step S52, the learning model generation unit 350 acquires location information based on the radio wave information. In step S53, the learning model generation unit 350 generates a learning model based on learning data including location information, temperature distribution information, and room shape information. In step S54, the learning model generation unit 350 stores the generated learning model in the memory unit 31. After processing in step S54, the learning model generation unit 350 ends the learning process.

[0140] FIG. 15 is a flowchart illustrating a target area determination process performed by the air conditioning control device according to the second embodiment. In step S61, the acquisition unit 30 acquires temperature distribution information. In this case, the acquisition unit 30 may also acquire room shape information. In step S62, the estimation unit 351 estimates the user's stay area based on a learning model from the temperature distribution information acquired in step S61, and determines the target area. At this time, the estimation unit 351 may determine the target area from the room shape information together with the temperature distribution information. The room shape information may be the room shape information acquired in step S61, or may be room shape information acquired in advance by the acquisition unit 30 and stored in the storage unit 31. After the process of step S62, the target area determination process performed by the air conditioning control device 3 ends.

[0141] In the second embodiment, the acquisition unit 30 acquires radio wave information indicating radio wave intensity and radio wave reception direction. However, both or one of the remote controller 12 and the user's terminal device may have a function such as a global positioning system (GPS), and the acquisition unit 30 may acquire location information indicating the location of the device from the device. Alternatively, an application program for identifying the location of the device in the air-conditioned space may be installed in the device, and the acquisition unit 30 may acquire location information from the device. In these cases, the memory unit 31 stores learning data including location information, and the learning model generation unit 350 generates a learning model from the learning data from the memory unit 31 without performing a process to acquire location information based on the radio wave information. In this case, the radio wave information in the processes of steps S41 to S43 is replaced with location information. Furthermore, the radio wave information in step S51 is replaced with location information, and the process of step S52 is omitted.

[0142] In the second embodiment, the learning model generation unit 350 generates a learning model using temperature distribution information from one sensor 20 that detects the temperature distribution in the air-conditioned space. However, the number of sensors 20 that detect the temperature distribution in the air-conditioned space may be changeable. The learning model generation unit 350 may create a learning model based on temperature distribution information from each of multiple sensors 20 that detect the temperature distribution in the air-conditioned space. Note that the multiple sensors 20 are each installed at a different position in the air-conditioned space. This allows the learning model generation unit 350 to obtain more detailed information about the temperature distribution in the air-conditioned space. This enables the learning model generation unit 350 to generate a more accurate learning model, thereby improving the accuracy of the estimation process related to the user's position by the estimation unit 351.

[0143] In the second embodiment, the learning model generation unit 350 generates a learning model using room shape information from one sensor 20 that detects the room shape in the air-conditioned space. However, the number of sensors 20 that detect the room shape in the air-conditioned space may be changeable. The learning model generation unit 350 may create a learning model based on room shape information from each of multiple sensors 20 that detects room shape information of the air-conditioned space. Note that the multiple sensors 20 are each installed at a different position in the air-conditioned space. This allows the learning model generation unit 350 to obtain more detailed information about the room shape of the air-conditioned space. This enables the learning model generation unit 350 to generate a more accurate learning model, thereby improving the accuracy of the estimation process related to the user's position by the estimation unit 351.

[0144] In the second embodiment, the learning model generation unit 350 generates a learning model based on radio wave information or position information from one remote controller 12. However, the number of remote controllers 12 may be changeable. The learning model generation unit 350 may create a learning model based on radio wave information or position information from each of multiple remote controllers 12. This enables the learning model generation unit 350 to associate the positions of each user obtained from the signals from each remote controller 12 with the positions of each heat source indicated by the temperature distribution information when multiple users are present in the air-conditioned space. Therefore, the learning model generation unit 350 can generate a learning model from the learning data that enables the estimation unit 351 to more accurately estimate the position of each user.

[0145] In the second embodiment, the learning model generation unit 350 generates a learning model based on radio wave information or location information from one terminal device. However, the number of terminal devices may be changeable. The learning model generation unit 350 may create a learning model based on radio wave information or location information from each of multiple terminal devices. This enables the learning model generation unit 350 to associate the location of each user obtained from the signal from each terminal device with the location of each heat source indicated by the temperature distribution information when multiple users are present in the air-conditioned space. Therefore, the learning model generation unit 350 can generate a learning model from the learning data that enables the estimation unit 351 to more accurately estimate the location of each user.

[0146] In the second embodiment, the air conditioning system 100 includes one air conditioning control device 3. However, the number of air conditioning control devices 3 in the air conditioning system 100 may be changeable. The air conditioning system 100 may include multiple air conditioning control devices 3. In this case, the learning model generation unit 350 in one of the multiple air conditioning control devices 3 may generate a learning model based on temperature distribution information, etc. acquired by all of the air conditioning control devices 3. The learning model generated by the learning model generation unit 350 in the one air conditioning control device 3 may then be stored in another air conditioning control device 3. In this case, the other air conditioning control device 3 may estimate the user's position based on the learning model, or may update the learning model by re-learning. In addition to the above, a learning model generation unit 350 provided external to the multiple air conditioning control devices 3 may generate a learning model based on temperature distribution information, etc. acquired by all of the air conditioning control devices 3. The learning model generated by the external learning model generation unit 350 may then be stored in the multiple air conditioning control devices 3. In this case, each air conditioning control device 3 may estimate the user's position based on the learning model, or may update the learning model by re-learning.

[0147] In the second embodiment, the learning model generation unit 350 generates a learning model using a neural network with an input layer, an intermediate layer, and an output layer. However, the learning model generation unit 350 may generate a learning model based on deep learning. Alternatively, the learning model generation unit 350 may perform machine learning using, for example, genetic programming, functional logic programming, or a support vector machine.

[0148] The effects of the air conditioning control device 3 according to the second embodiment are described below. The stay information in the second embodiment is temperature distribution information indicating the temperature distribution in the air-conditioned space. The acquisition unit 30 receives radio waves from the remote controller 12 or a terminal device for operating the air conditioner 1, and acquires radio wave information indicating the strength and reception direction of the radio waves. The target area determination unit 35 has an estimation unit 351 that determines the target area based on a learning model for estimating the area in the air-conditioned space where a person is present, obtained from the radio wave information and temperature distribution information. The remote controller 12 or the terminal device at the time of radio wave transmission is associated with the user's position. Therefore, the radio wave information makes it possible to identify a person from among the heat sources indicated by the temperature distribution information. The air conditioning control device 3 can accurately determine the area including the person's position as the target area from the stay information based on the learning model obtained from the radio wave information and temperature distribution information.

[0149] The target area determination unit 35 in the second embodiment further includes a learning model generation unit 350. The learning model generation unit 350 acquires location information indicating the location of the remote controller 12 or the terminal device based on radio wave information, and generates a learning model for estimating the area where a person is present within the air-conditioned space based on the location information and temperature distribution information. This enables the estimation unit 351 to estimate the location of a person from the stay information with high accuracy using the learning model. This allows the target area determination unit 35 to accurately determine the target area where a person is present. This also improves the accuracy of the objective function obtained by integrating the deviation over the target area. This allows the air conditioning control device 3 to efficiently optimize air conditioning.

[0150] The stay information in the second embodiment is temperature distribution information indicating the temperature distribution in the air-conditioned space. The acquisition unit 30 acquires location information indicating the location of the remote controller 12 or terminal device for operating the air conditioner 1 from the remote controller 12 or terminal device. The target area determination unit 35 has an estimation unit 351. The estimation unit 351 determines the target area based on a learning model for estimating the area in the air-conditioned space where people are present, which is obtained from the location information and temperature distribution information. The remote controller 12 or terminal device at the time of radio wave transmission is associated with the user's position. Therefore, the position of the remote controller 12 or terminal device makes it possible to identify people from among the heat sources indicated by the temperature distribution information. The air conditioning control device 3 can accurately determine the area including the location of people as the target area from the stay information, based on the learning model obtained from the radio wave information and temperature distribution information.

[0151] The target area determination unit 35 in the second embodiment further includes a learning model generation unit 350. The learning model generation unit 350 generates a learning model for estimating an area in the air-conditioned space where a person is present, based on the position information and temperature distribution information. This enables the estimation unit 351 to estimate the position of a person from the stay information with high accuracy using the learning model. This allows the target area determination unit 35 to accurately determine the target area in which a person is present. This also improves the accuracy of the objective function obtained by integrating the deviation over the target area. This allows the air conditioning control device 3 to efficiently optimize air conditioning.

[0152] Embodiment 3 The air conditioning control device 3 according to the third embodiment will be described in detail below. In the third embodiment, the same components as those in the first and second embodiments are denoted by the same reference numerals. In the third embodiment, the same configurations as those in the first and second embodiments and the same functions as those in the first and second embodiments will not be described unless there are special circumstances.

[0153] The configuration of an air conditioning system 100 according to the third embodiment is illustrated in Fig. 1, as in the first and second embodiments, and the configuration of an air conditioning control device 3 according to the third embodiment is illustrated in Fig. 2, as in the first and second embodiments. Furthermore, the hardware configuration of the air conditioning control device 3 according to the third embodiment is illustrated in Fig. 9, as in the first and second embodiments.

[0154] In the first embodiment, the coupled analysis unit 36 ​​derives the state variable vector at each time point in the first time range, and derives the adjoint variable vector at each time point from the state variable vector at each time point. At this time, the coupled analysis unit 36 ​​derives the adjoint variable vector by inverse analysis, so it is necessary to read out the state variable vector at each time point from the storage unit 31 or the first memory 42 of the coupled analysis unit 36. However, in this case, the amount of data in the first memory 42 increases, which may slow down processing or cause the capacity of the first memory 42 to become insufficient. In order to solve such problems, the coupled analysis unit 36 ​​in the third embodiment performs the following processing.

[0155] FIG. 16 is a diagram for explaining the process of deriving adjoint variables and sensitivities by the coupled analysis unit in the third embodiment. In FIG. 16, the linear white arrows indicate the direction of the process flow by the coupled analysis unit 36. The coupled analysis unit 36 ​​first derives a state variable vector along the time progression direction within a first time range using the CFD simulation described above. Thereafter, the coupled analysis unit 36 ​​selects multiple time points within the first time range and stores the state variable vectors at the multiple time points in the first memory 42. A predetermined time interval is provided between each of the multiple time points. Hereinafter, each of the multiple time points may also be referred to as a check time point.

[0156] The coupled analysis unit 36 ​​calculates the state variable vectors at the check time t among the state variable vectors at each time t in the first time range obtained by the CFD simulation. mThe state variable vector at (n+1) check points t in the first time range from the start point t0 to the end point (t0+T) of the analysis is stored in the first memory 42. Note that m is an integer between 0 and n, and n is an integer equal to or greater than 1. In FIG. 16, the state variable vector at (n+1) check points t in the first time range from the start point t0 to the end point (t0+T) of the analysis is stored in the first memory 42. m is selected, and at each check time t m The state variable vector is stored in the first memory 42.

[0157] The coupled analysis unit 36 ​​checks the m By tracing back the data, forward and backward analysis is performed to check the time t m ~Check time t m+1 The sensitivity at each time point t in the equation is derived. This will be explained in detail below.

[0158] As a first direct analysis, the coupled analysis unit 36 ​​performs the first direct analysis at the check time t n-1 From the check time t n At this time, the coupled analysis unit 36 ​​derives the state variable vectors at each time point up to the check time t n-1 and check time t n The coupled analysis unit 36 ​​performs a CFD simulation based on the indoor model including the respective state quantities of the above. n-1 From the check time t n Based on the state variable vector at each time point t up to the check time point t n From the check time t n-1 Then, the coupled analysis unit 36 ​​derives the adjoint variable vectors at each time point t up to the check time point t as the first sensitivity derivation process. n-1 From the check time t n The state variable vector at each time point t up to the check time t n From the check time t n-1 Based on the adjoint variable vectors at each time point t up to the check time point t n-1 ~Check time t n The sensitivity at

[0159] As a second direct analysis, the coupled analysis unit 36 ​​performs the second direct analysis at the check time t n-2 From the check time tn-1 At this time, the coupled analysis unit 36 ​​derives the state variable vectors at each time point t up to the check time point t n-2 and check time t n-1 The coupled analysis unit 36 ​​performs a second inverse analysis by performing a CFD simulation based on the indoor model including the state quantities of the above. n-2 From the check time t n-1 Based on the state variable vector at each time point t up to the check time point t n-1 From the check time t n-2 Then, the coupled analysis unit 36 ​​derives the adjoint variable vectors at each time point t up to the check time point t as the second sensitivity derivation process. n-2 From the check time t n-1 The state variable vector at each time point t up to the check time t n-1 From the check time t n-2 Based on the adjoint variable vectors at each time point t up to the check time point t n-2 ~Check time t n-1 The sensitivity at

[0160] As the final nth forward analysis, the coupled analysis unit 36 ​​derives state variable vectors for each time point from check time t0 to check time t1, and as the nth inverse analysis, it derives adjoint variable vectors for each time point from check time t1 to check time t0. Then, as the nth sensitivity derivation process, the coupled analysis unit 36 ​​derives sensitivity from check time t0 to check time t1 based on the state variable vectors for each time point from check time t0 to check time t1 and the adjoint variable vectors for each time point from check time t1 to check time t0.

[0161] 17 is a flowchart illustrating a process of deriving sensitivity by the coupled analysis unit in the third embodiment. The coupled analysis unit 36 ​​executes the process shown in FIG. 17 as the process of step S13 shown in FIG. 5, instead of the process shown in FIG. 6. The process of FIG. 17 may be executed in parallel with step S12, or may be executed after step S11 and before step S12. For ease of understanding, the check time point is set as t in FIG. 17 as in FIG. 16.m The number of check points is (n+1), and the check point t m t0~t n Let's say.

[0162] In step S71, the coupled analysis unit 36 ​​calculates (n+1) check points t0 to t n In step S72, the coupled analysis unit 36 ​​stores the state quantities at each check time point, among the state quantities derived in the above-mentioned step S11, in the first memory 42. In step S73, the coupled analysis unit 36 ​​stores (n-1) in m. In step S74, the coupled analysis unit 36 ​​selects the state quantities at the check time point t m From the check time t m+1 The state quantities at each point in time are derived.

[0163] In step S75, the coupled analysis unit 36 ​​performs inverse analysis based on the state quantities obtained in step S74 to determine the check time t m+1 From the check time t m In step S76, the coupled analysis unit 36 ​​derives the adjoint variables at each time point from the state quantity obtained in step S74 and the adjoint variables obtained in step S75. m ~Check time t m+1 The sensitivity at each time point is derived.

[0164] In step S77, the coupled analysis unit 36 ​​determines whether m is 0. If m is not 0 (step S77: NO), in step S78 the coupled analysis unit 36 ​​resets m to (m-1). That is, the coupled analysis unit 36 ​​decrements the value of m by 1. After processing step S78, the coupled analysis unit 36 ​​proceeds to step S74. In step S77, if m is 0 (step S77: YES), the coupled analysis unit 36 ​​ends the sensitivity derivation process.

[0165] The effects of the air conditioning control device 3 according to the third embodiment will be described below. The coupled analysis unit 36 ​​in the third embodiment selects multiple check times within the first time range, and performs forward analysis and inverse analysis between the check times while going back in time from the check times based on the state quantities at the multiple check times obtained by the forward analysis. The coupled analysis unit 36 ​​derives the state quantities at each time between the check times by the forward analysis between the check times. Then, the coupled analysis unit 36 ​​derives the adjoint variables of the state quantities at each time between the check times by the inverse analysis between the check times. The coupled analysis unit 36 ​​derives the sensitivity at each time between the check times based on the state quantities and the adjoint variables at each time between the check times. The sensitivity is a quantity corresponding to the degree of influence on the objective function due to a change in the value of the control parameter. The coupled analysis unit 36 ​​derives an optimal solution based on the sensitivity. As a result, the coupled analysis unit 36 ​​stores the state quantities at the check times in the first memory 42 instead of all of the state quantities over the first time range, and is able to derive the sensitivities at each time point between the check times based on the stored state quantities at the check times. The coupled analysis unit 36 ​​then derives the sensitivities at each time point between the check times while tracing back the check times on the time axis, thereby obtaining the sensitivities at each time point in the first time range. This makes it possible to ensure sufficient storage capacity in the first memory 42 when deriving the sensitivities. This makes it possible to perform the calculations necessary to derive the desired control even in devices with limited computational resources.

[0166] Embodiment 4 The air conditioning control device 3 according to embodiment 4 will be described in detail below. In embodiment 4, the same components as those in embodiments 1 to 3 will be assigned the same reference numerals. Furthermore, in embodiment 4, explanations of configurations similar to those in embodiments 1 to 3 and functions similar to those in embodiments 1 to 3 will be omitted unless there are special circumstances.

[0167] 18 is a block diagram illustrating the configuration of an air conditioning system according to embodiment 4. The air conditioning system 100 according to embodiment 4 includes an air conditioner 1, a detection unit 2, an air conditioning control device 3, and a server 6. The air conditioning control device 3 in embodiment 4 is the air conditioning control device 3 according to embodiments 1 to 3, with the coupled analysis unit 36 ​​omitted, and with a first communication unit 39 added to the air conditioning control device 3 according to embodiments 1 to 3. The first communication unit 39 communicates with the server 6 via wired or wireless communication.

[0168] The server 6 includes a second communication unit 60 that performs wired or wireless communication with the air conditioning control device 3. The server 6 in the fourth embodiment also includes, in place of the air conditioning control device 3, the above-mentioned coupled analysis unit 36 ​​that performs the processing exemplified in Figures 5 to 6 and 17.

[0169] The first communication unit 39 transmits the indoor model constructed by the indoor model construction unit 33, the equipment model constructed by the equipment model construction unit 34, and information indicating the target area determined by the target area determination unit 35 to the server 6. The second communication unit 60 of the server 6 receives the indoor model, the equipment model, and the information indicating the target area. Similar to the first to third embodiments, the coupled analysis unit 36 ​​of the server 6 performs the process shown in FIG. 5 and the process shown in any of FIG. 6 and FIG. 17 based on the indoor model, the equipment model, and the information indicating the target area received by the second communication unit 60, and derives an optimal solution for the control variable vector. The second communication unit 60 transmits the optimal solution derived by the coupled analysis unit 36 ​​to the air conditioning control device 3. The first communication unit 39 of the air conditioning control device 3 receives the optimal solution from the server 6.

[0170] The control target determination unit 37 of the air conditioning control device 3 derives a control target value in the same manner as in the first embodiment, based on the optimal solution received by the first communication unit 39 from the server 6. Specifically, the control target determination unit 37 determines the air temperature at a first position or the like on the temperature distribution of the air-conditioned space achieved by the optimal solution as the control target value. The command unit 38 controls the air conditioner 1 based on the control target value determined by the control target determination unit 37.

[0171] Fig. 19 is a diagram illustrating an example of the hardware configuration of an air conditioning control device according to embodiment 4. The air conditioning control device 3 according to embodiment 4 further includes a first communication interface circuit 46 in addition to the hardware configuration shown in Fig. 9. The functions of the first communication unit 39 can be realized by the first communication interface circuit 46.

[0172] 20 is a diagram illustrating a hardware configuration of a server in the fourth embodiment. The server 6 can be configured, for example, by a second processor 62, a second memory 63, and a second communication interface circuit 64, which are connected to each other by a second bus 61. The second processor 62 is, for example, a CPU or an MPU. The second memory 63 is, for example, a ROM or a RAM.

[0173] The functions of the coupled analysis unit 36 ​​in the fourth embodiment can be realized by the second processor 62 reading and executing various programs stored in the second memory 63. The functions of the second communication unit 60 can be realized by the second communication interface circuit 64. Note that all or part of the functions of the server 6 may be realized by dedicated hardware.

[0174] The effects of the air conditioning system 100 and air conditioning control device 3 according to the fourth embodiment will be described below. The air conditioning system 100 according to the fourth embodiment includes an air conditioning control device 3 and a server 6. The air conditioning control device 3 controls the air conditioners 1 that condition the air in the air-conditioned space. The server 6 communicates with the air conditioning control device 3. The air conditioning control device 3 includes an acquisition unit 30, an indoor model construction unit 33, a first communication unit 39, a control target determination unit 37, and a command unit 38. The acquisition unit 30 acquires room shape information indicating the shape of the air-conditioned space and air state information regarding the state of the air in the air-conditioned space. The indoor model construction unit 33 constructs an indoor model for CFD simulation based on the room shape information and the air state information. The first communication unit 39 transmits the indoor model to the server 6. The server 6 includes a coupled analysis unit 36 ​​and a second communication unit 60. The coupled analysis unit 36 ​​executes a CFD simulation based on the indoor model and derives state quantities indicating the state of the air at each time point within a predetermined first time range. The coupled analysis unit 36 ​​then derives the deviation of the state quantity at each time point from a preset target state quantity, integrates the deviation at each time point over a first time range, and derives an optimal solution for the control parameters of the air conditioner 1 that minimizes an objective function including the integrated value obtained by the integration. The second communication unit 60 transmits the optimal solution to the air conditioning control device 3. The control target determination unit 37 of the air conditioning control device 3 determines a control target value, which is a target value for the control parameter, based on the optimal solution obtained from the server 6. The command unit 38 issues a command to the air conditioner 1 based on the control target value.

[0175] According to the above configuration, the analytical process for deriving the optimal solution is executed by the server 6, so even if the calculation performance of the air conditioning control device 3 is limited, the optimal solution can be obtained and appropriate air conditioning control becomes possible. Furthermore, because the optimal solution can be obtained quickly depending on the calculation performance of the server 6, the user's analytical ability is quickly improved as a result.

[0176] Although the embodiments have been described above, the contents of the present disclosure are not limited to the embodiments and include conceivable equivalents. Furthermore, the configurations described in the first to fourth embodiments and their modifications can be combined with each other as long as the functions and operations are not impaired. [Explanation of symbols]

[0177] 1 air conditioner, 2 detection unit, 3 air conditioning control device, 5 telecommunication line, 6 server, 10 outdoor unit, 11 indoor unit, 12 remote controller, 20 sensor, 30 acquisition unit, 31 memory unit, 32 current state estimation unit, 33 indoor model construction unit, 34 equipment model construction unit, 35 target area determination unit, 36 coupled analysis unit, 37 control target determination unit, 38 command unit, 39 first communication unit, 40 first bus, 41 first processor, 42 first memory, 43 storage device, 44 input interface circuit, 45 input / output interface circuit, 46 first communication interface circuit, 60 second communication unit, 61 second bus, 62 second processor, 63 second memory, 64 second communication interface circuit, 100 air conditioning system, 350 learning model generation unit, 351 estimation unit, BA stay area, CA candidate area, H user, Q RAC Air conditioning capacity, X1, X2, X3 input layer, Y1, Y2 hidden layer, Z1, Z2, Z3 output layer, w11~w16, w21~w26 weights, Ω target area.

Claims

1. An air conditioning control device that controls an air conditioner that conditions an air conditioning target space, an acquisition unit that acquires room shape information indicating the shape of the air conditioned space and air condition information regarding the state of air in the air conditioned space; an indoor model construction unit that constructs an indoor model for CFD simulation based on the room shape information and the air condition information; a coupled analysis unit that executes the CFD simulation based on the indoor model, derives a state quantity that indicates the state of the air at each time point within a predetermined first time range, derives a deviation of the state quantity at each time point from a predetermined target state quantity, integrates the deviation at each time point within the first time range, and derives an optimal solution for control parameters of the air conditioner that minimizes an objective function including an integral value obtained by the integration; and a control target determination unit that determines a control target value, which is a target value of the control parameter, based on the optimal solution; a command unit that issues a command to the air conditioner based on the control target value; An air conditioning control device comprising:

2. The acquisition unit Acquire stay information indicating a stay area of ​​a person within the air-conditioned space; The air conditioning control device a target area determination unit that determines a target area that is an area to be air-conditioned in the air-conditioned space based on the stay information, The coupled analysis unit The air conditioning control device according to claim 1 , wherein the objective function is derived by integrating the deviation at each time point in the first time range and the target region.

3. The stay information is Temperature distribution information indicating a temperature distribution in the air-conditioned space, The target region determination unit The air conditioning control device according to claim 2, further comprising: identifying an area in the air-conditioned space where people are present based on the temperature distribution information; obtaining a frequency with which people are present in the identified area; and determining the target area based on the frequency.

4. The stay information is Temperature distribution information indicating a temperature distribution in the air-conditioned space, The acquisition unit receiving radio waves from a remote controller or a terminal device for operating the air conditioner, and acquiring radio wave information indicating the strength and receiving direction of the radio waves; The target region determination unit The air conditioning control device according to claim 2, further comprising an estimation unit that determines the target area based on a learning model for estimating an area in which people are present within the air-conditioned space, the learning model being obtained from the radio wave information and the temperature distribution information.

5. The target region determination unit The air conditioning control device according to claim 4, further comprising a learning model generation unit that acquires location information indicating the location of the remote controller or the terminal device based on the radio wave information, and generates the learning model for estimating an area in which people are present within the air-conditioned space based on the location information and the temperature distribution information.

6. The stay information is Temperature distribution information indicating a temperature distribution in the air-conditioned space, The acquisition unit acquiring, from the remote controller or the terminal device, location information indicating the location of a remote controller or a terminal device for operating the air conditioner; The target region determination unit The air conditioning control device according to claim 2, further comprising an estimation unit that determines the target area based on a learning model for estimating an area in which a person is present within the air-conditioned space, the learning model being obtained from the position information and the temperature distribution information.

7. The target region determination unit The air conditioning control device according to claim 6, further comprising a learning model generation unit that generates the learning model for estimating an area in which a person is present within the air-conditioned space based on the position information and the temperature distribution information.

8. The coupled analysis unit selecting a plurality of check time points within the first time range; 2. The air conditioning control device according to claim 1, wherein a forward analysis is performed between each of the plurality of check times based on the state quantities at the plurality of check times to derive the state quantities at each time point between the plurality of check times, an inverse analysis is performed between each of the plurality of check times to derive an adjoint variable based on the state quantities at each time point between the plurality of check times, a sensitivity at each time point between the plurality of check times is derived based on the state quantities at each time point between the plurality of check times and the adjoint variable, the sensitivity corresponding to a degree of influence on the objective function due to a change in the value of the control parameter, and the optimal solution is derived based on the sensitivity.

9. The control target determination unit The air conditioning control device according to claim 1 , wherein the control target value is determined based on an air temperature at a predetermined first position on a temperature distribution in the air conditioned space realized by the optimal solution.

10. The acquisition unit Acquiring device information relating to the performance of the air conditioner from the air conditioner; The air conditioning control device further comprising an equipment model construction unit that constructs an equipment model that defines conditions for values ​​of the control parameters based on the equipment information; The coupled analysis unit The air conditioning control device according to claim 1 , wherein the objective function is derived based on the equipment model.

11. The indoor model is The air conditioning control device according to claim 10 , further comprising the state quantity at an air outlet from the air conditioner, based on the equipment model.

12. The equipment model is The air conditioning control device according to claim 10, further comprising information associating a coefficient of performance of the air conditioner with values ​​of the control parameters.

13. The acquisition unit acquire instruction information indicating settings input by a person to the air conditioner; The target state quantity is The air conditioning control device according to claim 10 , wherein the temperature is determined based on the instruction information.

14. The air conditioning control device a storage unit that stores the indoor model, the target state quantity, the equipment model, and the optimal solution in association with each other; The control target determination unit 14. The air conditioning control device according to claim 13, wherein, when the target state quantity based on the instruction information reacquired by the acquisition unit at a specific timing is equal to the target state quantity stored in the memory unit, the indoor model based on the air condition information reacquired by the acquisition unit at the specific timing is equal to the indoor model stored in the memory unit, and the equipment model based on the equipment information reacquired by the acquisition unit at the specific timing is equal to the equipment model stored in the memory unit, the control target value is derived based on the optimal solution stored in the memory unit.

15. An air conditioning control device that controls an air conditioner that conditions an air conditioning target space, an acquisition unit that acquires room shape information indicating the shape of the air conditioned space and air condition information regarding the state of air in the air conditioned space; an indoor model construction unit that constructs an indoor model for CFD simulation based on the room shape information and the air condition information; a first communication unit that transmits the indoor model to a server; Equipped with The server executes the CFD simulation based on the indoor model, derives a state quantity indicating the state of the air at each time point within a predetermined first time range, derives a deviation of the state quantity at each time point from a predetermined target state quantity, integrates the deviation at each time point within the first time range, derives an optimal solution for control parameters of the air conditioner that minimizes an objective function including the integral value obtained by the integration, and transmits the optimal solution to the air conditioning control device; The air conditioning control device further includes: a control target determination unit that determines a control target value, which is a target value of the control parameter, based on the optimal solution obtained from the server; a command unit that issues a command to the air conditioner based on the control target value; An air conditioning control device comprising:

16. an air conditioning control device that controls an air conditioner that conditions the air in the space to be air-conditioned; a server that communicates with the air conditioning control device; An air conditioning system having: The air conditioning control device an acquisition unit that acquires room shape information indicating the shape of the air conditioned space and air condition information regarding the state of air in the air conditioned space; an indoor model construction unit that constructs an indoor model for CFD simulation based on the room shape information and the air condition information; a first communication unit that transmits the indoor model to the server; Equipped with The server a coupled analysis unit that executes the CFD simulation based on the indoor model, derives a state quantity that indicates the state of the air at each time point within a predetermined first time range, derives a deviation of the state quantity at each time point from a predetermined target state quantity, integrates the deviation at each time point within the first time range, and derives an optimal solution for control parameters of the air conditioner that minimizes an objective function including an integral value obtained by the integration; and a second communication unit that transmits the optimal solution to the air conditioning control device; Equipped with The air conditioning control device further includes: a control target determination unit that determines a control target value, which is a target value of the control parameter, based on the optimal solution obtained from the server; a command unit that issues a command to the air conditioner based on the control target value; Equipped with an air conditioning system.

Images